Few-shot fine-grained image classification (FSFGIC) methods refer to machine learning methods which aim to classify images (e.g., bird species, flowers, and airplanes) belonging to subordinate object categories of the same entry-level category with only a few samples. It is worth to note that feature representation learning is used not only to represent training samples, but also to construct classifiers for performing various FSFGIC tasks. In this paper, starting from the definition of FSFGIC, a taxonomy of feature representation learning for FSFGIC is proposed. According to this taxonomy, we discuss key issues on FSFGIC (including data augmentation, local or/and global deep feature representation learning, class representation learning, and task specific feature representation learning). The existing popular datasets and evaluation standards are introduced. Furthermore, a novel classification performance evaluation mechanism is designed with a 0.95 confidence interval for judging whether the classification accuracy obtained by a certain specified method is good or bad. Moreover, current challenges and future trends of feature representation learning on FSFGIC are elaborated.

Object detection is important in many applications, such as autonomous driving. While 2D images are lack of depth information and are sensitive to environmental conditions, 3D point cloud can provide accurate depth information and a more descriptive environment. However, sparsity is always a challenge in single-frame point cloud object detection. This paper introduces a two-stage proposal-based feature fusion method for object detection using multiple frames. The proposed method, called proposal features fusion (PFF), utilizes a cosine-similarity approach to associate proposals from multiple frames and employs an attention weighted fusion module to merge features from these proposals. It allows for feature fusion specific to individual objects and offers lower computational complexity while achieving higher precision. The experimental results on the nuScenes dataset demonstrate the effectiveness of our approach, achieving a mAP of 46.7%, which is 1.3% higher than the state-of-the-art 3D object detection method.

This paper first introduces the main classification of brain diseases and the main causes of these diseases. It is followed by wavelet analysis, which is a mathematical function or wave-like pattern used to transform data, which can decompose the signal into different wavelet functions, each of which is related to a specific scale or frequency. Wavelet analysis has been applied in many fields such as image processing, data analysis and engineering. In addition, wavelet is also used in the analysis of biological signals. Wavelet analysis breaks down brain signals, such as EEG or fMRI data, into various frequency components at different scales. Wavelet analysis provides time-frequency localization. Pattern recognition can be enhanced by isolating salient features in the data. Wavelet denoising can effectively separate noise from underlying brain signals. Wavelet denoising usually adopts threshold method. Wavelet analysis can enhance pattern recognition by isolating salient features in the data. Researchers can train machine learning models based on these wavelet-derived features to recognize specific patterns associated with different neurological disorders. Wavelet analysis can track these changes by continuously evaluating the frequency content of the neuroimage data over time. Through continuous efforts, wavelet theory and technology have become valuable tools in the field of neuroscience and brain disease research.

The healthy function of the vestibular system (VS) is of vital importance for individuals to carry out their daily activities independently and safely. This study carries out Tsallis entropy (TE)-based analysis on insole force sensor data in order to extract features to differentiate between healthy and VS-diseased individuals. Using a specifically developed algorithm, we detrend the acquired data to examine the fluctuation around the trend curve in order to consider the individual’s walking habit and thus increase the accuracy in diagnosis. It is observed that the TE-value increases for diseased people as an indicator of the problem of maintaining balance. As one of the main contributions of this study, in contrast to studies in the literature that focus on gait dynamics requiring extensive walking time, we directly process the instantaneous pressure values, enabling to reduce the data acquisition period significantly. The extracted feature set is then inputted into fundamental classification algorithms, with the Support-Vector-Machine (SVM) demonstrating the highest performance, achieving an average accuracy of 95%. This study constitutes a significant step of a large project aiming to identify specific VS disease together with its stage. The performance achieved in this study provides a strong motivation to further explore this topic.

Currently, software development is more associated with families of configurable software rather than the single implementation of a product. Due to the numerous possible combinations in a software product line, testing these families of software product lines (SPLs) is a difficult undertaking (SPL). Moreover, the presence of optional features makes the testing of SPLs impractical. Several features are presented in SPLs, but due to the environment's time and financial constraints, these features are rendered unfeasible. Testing subsets of configured products is thus one approach to solving this issue. In order to reduce testing effort and get better results, alternative methods of testing SPLs are required, such as the combinatorial interaction testing (CIT) technique. Unfortunately CIT method produces unscalable solutions for large size SPLs with excessive constraints. The CIT method costs more because of feature combinations. The optimization of the various conflicting testing objectives, such as reducing the cost and configuration number, have also been considered. In this article, we have proposed a search-based software engineering solution using multi-objective optimization algorithms (MOEAs). In particular, the research is applied to different types of MOEA methods; Indicator-Based Evolutionary Algorithm (IBEA), Multi-objective Evolutionary Algorithm based on Decomposition (MOEA/D), Non-Dominated Sorting Genetic Algorithm II (NSGAII), NSGAIII, and Strength Pareto Evolutionary Algorithm 2 (SPEA2). The results of the algorithms are examined in the context of distinct objectives and two quality indicators. The results revealed how feature model attributes, implementation context and the number of objectives affect the performance of the algorithms.

The used car market has a high global economic importance, with more than 35 million cars sold yearly. Accurately predicting prices is a crucial task for both buyers and sellers to facilitate informed decisions in terms of opportunities or potential problems. Although various Machine Learning techniques have been applied to create robust prediction models, a comprehensive approach has yet to be studied. This research introduces two datasets from different markets, one with over 300,000 entries from Germany to serve as a training base for deep prediction models and a second dataset from Romania containing more than 15,000 car quotes used mainly to observe local traits. As such, we include extensive cross-market analyses by comparing the emerging Romanian market versus one of the world’s largest and most developed car markets, Germany. Our study uses several neural network architectures that capture complex relationships between car model features, individual add-ons, and visual features to predict used car prices accurately. Our models achieved a high R2 score exceeding 0.95 on both datasets, indicating their effectiveness in estimating used car prices. Moreover, we experimented with advanced convolutional architectures to predict car prices based solely on visual features extracted from car images. This approach exhibited transfer-learning capabilities, leading to improved prediction accuracy, especially since the Romanian training dataset is limited. Our experiments highlight the most important factors influencing the price, while our findings have practical implications for buyers and sellers in assessing the value of vehicles. At the same time, the insights gained from this study enable informed decision-making and provide valuable guidance in the used car market.

Industrial nameplates serve as a means of conveying critical information and parameters. In this work, we propose a novel approach for rectifying industrial nameplate pictures utilizing a probabilistic Hough transform. Our method effectively corrects for distortions and clipping, and features a collection of challenging nameplate pictures for analysis. To determine the corners of the nameplate, we employ a progressive probability Hough transform, which not only enhances detection accuracy but also possesses the ability to handle complex industrial scenarios. The results of our approach are clear and readable nameplate text, as demonstrated through experiments that show improved accuracy in model identification compared to other methods.

Automatic target detection of remote sensing images (RSI) plays an important role in military reconnaissance, disaster monitoring, and target rescue. The core task of remote sensing target detection is to judge the target categories and complete precise location. However, the existing target detection algorithms have limited accuracy and weak generalization capability for remote sensing images with complex backgrounds. To achieve accurate detection of different categories targets in remote sensing images, this study presents a novel feature enhancement single shot multibox detector (FESSD) algorithm for remote sensing target detection. The FESSD introduces feature enhancement module and attention mechanism into the convolution neural networks (CNN) model, which can effectively enhance the feature extraction ability and nonlinear relationship between different convolution features. Specifically, the feature enhancement module is used to extract the multi-scale feature information, and enhance the model nonlinear learning ability; the self-learning attention mechanism (SAM) is used to expand the convolution kernel local receptive field, which makes the model extract more valuable features. In addition, the nonlinear relationship between different convolution features is enhanced using the feature pyramid attention mechanism (PAM). The advantage of FESSD over other state-of-the-art target detection methods is validated by experiments on the presented seven-class target detection dataset (SD-RSI) and the public DIOR dataset.

Photovoltaic power generation has high variability and uncertainty because it is affected by uncertain factors such as weather conditions. Therefore, probabilistic forecasting is useful for optimal operation and risk hedging in power systems with large amounts of photovoltaic power generation. However, deterministic forecasting is the mainstay of photovoltaic generation forecasting; there are few studies on probabilistic forecasting and feature selection from weather or time-oriented features in such forecasting. In this study, prediction intervals were generated by the lower upper bound estimation using neural networks with two outputs to make probabilistic predictions. The objective was to improve prediction interval coverage probability (PICP), mean prediction interval width (MPIW), and loss, which is the integration of these two metrics, by removing unnecessary features through feature selection. When features with high gain were selected by random forests (RF), in the forecast of 14.7-kW PV systems, loss improved by 1.57 kW, PICP by 0.057, and MPIW by 0.12 kW on average over two weeks compared to the case where all features were used without feature selection. Therefore, the low gain features from RF act as noise in LUBE and reduce the prediction accuracy.

Nutrient regulation in aquaponic environments has been the topic of research for many years. Most have focused on appropriate control of nutrients in an aquaponic set-up, but very little research has been done on commercial scale applications. In our model, the input data was sourced on a weekly basis from three commercial aquaponic farms in South-East Texas over the course of a year. Due to limited number of data points, dimensionality reduction techniques like pair-wise correlation matrix was used to remove the highly correlated predictors. Feature selection techniques like the XGBoost classifier and Recursive Feature Elimination with ExtraTreesClassifier were used to rank the features in order of their relative importance. Ammonium and calcium were found to be the top two nutrient predictors and based on the months in which lettuce was cultivated, the median of these nutrient values from the historical dataset served as the optimal concentrations to be maintained in the aquaponic solution. To accomplish this, Vernier sensors were used to measure the nutrient values and actuator systems were built to dispense the appropriate nutrient into the ecosystem via a closed loop.

Cytosine (C) to uracil (U) RNA editing is one of the most important post-transcriptional processes, however exploring C-to-U editing events efficiently within the crop mitochondrial genome remains a challenge. An improving predictive RNA editor for crop mitochondrial genomes, iPReditor-CMG, was proposed, which was based on SVM, three common crop mitochondrial genomes and self-sequenced tobacco mitochondrial ATPase. After multi-combination feature extracting, high-dimension feature screening and multi-test independent predicting, the results showed that the average accuracy of intraspecific prediction was 0.85, and the highest value even up to 0.91, which outperformed the previous reference models. While the prediction accuracies were 0.78 between dicotyledons and no more than 0.56 between dicotyledons and monocotyledons, implying a possible similarity in C-to-U editing mechanisms among close relatives. The best model was finally identified with an independent test accuracy of 0.91 and an area under the curve of 0.88, and further suggested that five unreported feature sequences TGACA, ACAAC, GTAGA, CCGTT and TAACA were closely associated with the editing phenomenon. Multiple evaluation findings supported that the iPReditor-CMG could be effectively applied to predict crop mitochondrial editing sites, which may contribute to insight into their recognition mechanisms and even other post-transcriptional events in crop mitochondria.

High costs for the repair of concrete structures can be prevented if damage at an early stage of degradation is detected and precautionary maintenance measures are applied. To this end, we use numerical wave propagation simulations to identify simulated damage in concrete using convolutional neural networks (CNN). Damage in concrete subjected to compression is modeled at the mesoscale using the discrete element method. Ultrasonic wave propagation simulation on the damaged concrete specimens are performed using the rotated staggered finite-difference grid method. The simulated ultrasonic signals are used to train a CNN based classifier capable of classifying three different damage stages (microcrack initiation, microcrack growth and microcrack coalescence leading to macrocracks). The performance of the classifier is improved by refining the dataset via an analysis of the averaged envelope of the signal. The classifier using the refined dataset has an overall accuracy of 90%.

This work proposes a systematic topology optimization approach to simultaneously design the morphing functionality and actuation in three-dimensional wing structures. The actuation is assumed to be a linear strain-based expansion in the actuation material and a three-phase material model is employed to represent structural and actuating materials, and void. To ensure both structural stiffness with respect to aerodynamic loading and morphing capabilities, the optimization problem is formulated to minimize structural compliance while morphing functionality is enforced by constraining a morphing error between actual and target wing shape. Moreover, a feature mapping approach is utilized to constrain and simplify actuator geometries. A trailing edge wing section is designed to validate the proposed optimization approach. Numerical results demonstrate that three-dimensional optimized wing sections utilize a more advanced structural layout to enhance structural performance while keeping morphing functionality than two-dimensional wing ribs. The work presents the first step towards systematic design of three-dimensional morphing wing sections.

In order to design efficient and sustainable office spaces and to automate lighting, heating and air circulation in these facilities, solving the challenge of occupancy prediction is crucial. In office spaces where large areas need to be observed, multiple sensors must be used for full coverage. In these cases, it is normally important to keep the costs low, but also to make sure that the privacy of the people who use such environments are preserved. Low-cost and low-resolution heat (thermal) sensors can be very useful to build solutions that address these concerns. However, they are extremely sensitive to noise artifacts which might be caused by heat prints of the people who left the space or by other objects which are either using electricity or exposed to sunlight. There are some earlier solutions for occupancy prediction that employ low-resolution heat sensors, however, they have not addressed nor compensate for such heat artifacts. Therefore, in this paper, we present a low-cost and low-energy consuming smart space implementation to predict the number of people in the environment based on whether their activity is static or dynamic in time. We use a low-resolution (8×8) and non-intrusive heat sensor to collect data from an actual meeting room. We propose two novel workflows to predict the occupancy; one based on computer vision and one based on machine learning. Besides comparing the advantages and disadvantages of these different workflows, we use several state-of-the-art explainability methods in order to provide a detailed analysis of the algorithm parameters and how the image properties influence the resulting performance. Furthermore, we analyze noise resources which affect the heat sensor data. We hope that our analysis brings light into understanding how to handle very low-resolution heat images in these environments. The presented workflows could be used in various domains and applications other than smart offices, where occupancy prediction is essential, e.g., for elderly care.

The presented research faces the problem of early detection of sepsis for patients in the Intensive Care Unit. The PhysioNet/Computing in Cardiology Challenge 2019 facilitated the development of automated, open-source algorithms for the early detection of sepsis from clinical data. A labeled clinical records dataset for training and verification of the algorithms was provided by the challenge organizers. However, a relatively small number of records with sepsis, supported by Sepsis-3 clinical criteria, led to highly unbalanced dataset (only 2% records with sepsis label). A high number of unbalanced data records is a great challenge for machine learning model training and is not suitable for training classical classifiers. To address these issues, a number of various models were investigated. A solution including feature selection and data balancing techniques was proposed in this paper. In addition, several performance metrics were investigated. Results show, that for successful prediction, a particular model having few or more predictors based on the length of stay in the Intensive Care Unit should be applied.

In recent years, more and more researchers have gradually paid attention to Hyperspectral Image (HSI) classification. It is significant to implement researches on how to use HSI's sufficient spectral and spatial information to its fullest potential. To capture spectral and spatial features, we propose a Double-Branch Dual-Attention mechanism network (DBDA) for HSI classification in this paper, Two branches aer designed to extract spectral and spatial features separately to reduce the interferences between these two kinds of features. What is more, because distinguishing characteristics exist in the two branches, two types of attention mechanisms are applied in two branches above separately, ensuring to exploit spectral and spatial features more discriminatively. Finally, the extracted features are fused for classification. A series of empirical studies have been conducted on four hyperspectral datasets, and the results show that the proposed method performs better than the state-of-the-art method.

In pattern recognition domain, deep architectures are widely used nowadays and they have achieved fine grades. However, these deep architectures need special demands, especially big datasets and GPU. Aiming to gain better grades without deep networks, we propose a simplified algorithm framework using fusion features extracted from the salient areas of faces. Furthermore, the proposed algorithm has achieved a better result than some deep architectures. For extracting more effective features, this paper firstly defines the salient areas on the faces. This paper normalizes the salient areas of the same location in the faces to the same size, therefore it can gain more similar features from different subjects. LBP and HOG features are extracted from the salient areas, fusion features’ dimensions are reduced by Principal Component Analysis( PCA) and we apply softmax to classify the six basic expressions at once. This paper proposes a salient areas definitude method which uses peak expressions frames to compare with their neutral faces. This paper also proposes and applies the idea of normalizing the salient areas to align the specific areas which express the different expressions. This makes the salient areas found from different subjects have the same size. Besides, gamma correction method is firstly applied on LBP features in our algorithm framework which improves our recognition rates significantly. By applying this algorithm framework, our research has gained state-of-the-art performances on CK+ database and JAFFE database.

Due to the intermittency and fluctuation of photovoltaic (PV) output power, a high proportion of grid-connected PV power generation systems has a significant impact on power systems. Accurate PV power forecasting can alleviate the uncertainty of the PV power and is of great significance for the stable operation and scheduling of the power systems. Therefore, in this study, a feature rise-dimensional (FRD) two-layer ensemble learning (TLEL) model for short-term PV power deterministic forecasting and probability forecasting is proposed. First， based on the eXtreme Gradient Boosting (XGBoost), Random Forest (RF), CatBoost, and Long-short-term memory (LSTM) models, a TLEL model is constructed utilizing the ensemble learning algorithm. Meanwhile, the FRD method is introduced to construct the FRD-XGBoost-LSTM (R-XGBL), FRD-RF-LSTM(R-RFL), and FRD- CatBoost - LSTM (R-CatBL) models. Subsequently, the above models are combined to construct the FRD-TLEL model for deterministic forecasting, and perform probability interval forecasting based on quantile regression(QR). Finally, the performance of the proposed model is demonstrated with a real-world dataset. By comparing with other models, the proposed model displays better forecasting accuracy for deterministic forecasting and reliable forecasting intervals for probability forecasting, and good generalization ability in the datasets of different seasons and weather types.

Some recent studies show that filters in convolutional neural networks (CNNs) have low color selectivity in datasets of natural scenes such as Imagenet. CNNs, bio-inspired in the visual cortex, are characterized by their hierarchical learning structure, which appears to gradually transform the representation space. Inspired by the direct connection between the LGN and V4, which allows V4 to handle low-level information closer to the trichromatic input in addition to processed information that comes from V2/V3, we propose the addition of a long skip connection (LSC) between the first and last blocks of the feature extraction stage to allow deeper parts of the network to receive information from shallower layers. This type of connection improves classification accuracy by combining simple-visual and complex-abstract features to create more color-selective ones. We have applied this strategy to classic CNN architectures and quantitatively and qualitatively analyzed the improvement in accuracy while focusing on color selectivity. The results show that, in general, skip connections improve accuracy, but LSC improves it even more and enhances the color selectivity of the original CNN architectures. As a side result, we propose a new color representation procedure for organizing and filtering feature maps, making their visualization more manageable.

Accurate evaluation of health status of lithium-ion batteries must be deemed as of great significance, insofar as utility and safety of batteries are of concern. Lithium plating, in particular, is notoriously known to be a chemical reaction that can cause deterioration in, or even fatal hazards to, the health of lithium-ion batteries. Electrochemical impedance spectroscopy (EIS), which has distinct advantages such as fast or non-destructive over its competitors, suffices in detecting lithium plating and thus has been attracting increasing attention in the field of battery management, but its ability of assessing quantitatively the degree of lithium plating remains largely unexplored hitherto. On this point, this work seeks to narrow that gap, by proposing an EIS-based method that can quantify the degree of lithium plating. The core conception is to eventually circumvent the reliance on state-of-health measurement, and use instead the impedance spectrum, to acquire an estimate on battery capacity loss. To do so, the effects of solid electrolyte interphase formation and lithium plating on battery capacity must be first decoupled, so that the mass of lithium plating can be quantified. Then, based on an impedance spectrum measurement, the parameters of the fractional equivalent circuit model (ECM) of the battery can be identified. These fractional ECM parameters are received as inputs by an artificial neural network, which is tasked to establish a correspondence between the model parameters and the mass of lithium plating. The empirical part of the work revolves around the data collected from an aging experiment, and the validity of the proposed method is truthfully attested by dismantling the batteries, which is otherwise not needed during the actual uptake of the method.

To address the problems of poor recognition, low detection accuracy, a large number of model parameters and computation, complex network structure, and unfavorable portability to embedded devices in traditional tennis ball detection algorithms, this study proposes a lightweight tennis ball detection algorithm YOLOv5s-Z based on Robomater EP. The main work is as follows: Firstly, constructing lightweight G-Backbone and G-Neck network layers to reduce the number of parameters and computation of the network structure. Secondly, the convolutional coordinate attention is incorporated in G-Backbnone to embed the location information into the channel attention, which makes the network obtain the location information in a larger area through multiple convolutions and enhances the expression ability of the mobile network learning features. In addition, the Concat module in the original feature fusion is modified into a weighted bi-directional feature pyramid W-BiFPN with settable learning weights to improve the feature fusion capability and achieve efficient weighted feature fusion and bi-directional cross-scale connectivity. The EIOU loss is introduced to split the influence factor of aspect ratio and calculate the length and width of the target frame and anchor frame respectively, combined with Focal-EIOU Loss to solve the problem of imbalance between difficult and easy samples. The activation function Meta-ACON is introduced to achieve an adaptive selection of whether to activate the neurons and improve the detection accuracy. Finally, the experimental results show that compared with the original algorithm, the YOLOv5s-Z algorithm reduces the number of parameters and computation by 42$\%$ and 44$\%$, the model size by 39$\%$, and 2$\%$ improvement in average accuracy mean value, which verifies the effectiveness of the improved algorithm and the light weight of the model to meet the deployment requirements of embedded devices, and adapts Robomaster EP for accurate detection and real-time recognition of tennis balls.

Surface defect detection is one of the most widely used research areas in the field of image processing and machine vision. Detection of surface defects is used in visual inspection systems and medical image analysis. In this manuscript, an innovative method for detecting surface defects based on energy changes in co-occurrence matrices is presented in several directions. The method presented in this manuscript includes two stages of learning and testing. In the learning phase, to extract texture features, the gray level co-occurrence matrix operator is applied on the healthy image of the desired level. Then the energy value of the output matrix is ​​calculated. In the following, changes in the amount of energy are considered as statistical characteristics that are a good representative of the image of a healthy surface. Finally, with its help, a suitable threshold for the health of the images is obtained. Then, in the test phase, with the help of the calculated quorum, the defective windows that have suffered from non-normality are distinguished from the healthy surface sections. In the results section, the efficiency of the mentioned method has been measured on medical images and stone and ceramic images, and its detection accuracy has been compared with some previous effective methods. The advantages of the presented method include high accuracy, low calculations and compatibility with all types of levels due to the use of the learning stage. The proposed approach can be used in medical applications to diagnose abnormalities such as diseases. All extracted features are statistical, so its detection speed is higher than deep neural networks.

The Industrial Internet of things (IIoT) enabled smart system has entered into a golden era of rapid technology growth. IIoT is a concept to make every system interrelated such that they are able to collect and transfer data over a wireless network without human intervention. In this paper, we discuss the development of an IoT enabled system to monitor the vibration signature of equipment as part of prognosis and availability management system (P&AM) that serves to prevent unplanned operation downtime and catastrophic failure of a whole system. In order to simply the complexity of processing video content and performing inference, the Intel OpenVINO platform was selected because of it’s simplicity, portability across Intel AI processors, performance and comprehensiveness of it’s analytical and diagnostics capabilities that can be tested in Intel’s DevCloud. The IIoT system consists of a High Performance Computing (HPC) platform based on Intel’s Xeon processors and Movidius AI accelerator, Intel’s OpenVINO toolkit for AI, a Regul high performance programmable controller capturing vibration data through sensors and a low-latency network connection. Notifications of anomalies are sent to a smartphone. This paper reveals an approach for the features extraction and selection, known as feature engineering, of the equipment component we want to protect. Feature engineering is the first step for the P&AM of these components and extends to the whole system. The broader aim of this paper is to help technical leaders at the exploring or experimenting stages of their AI framework to learn the concepts of implementing algorithms using datasets that have real value to their companies. Datasets generated and referred to in this paper were generated by simulation under various material failure scenarios.

This paper proposes a linear eddy-current feature to determine the radius of a metallic ball in a non-contact manner. An electromagnetic eddy-current sensor with two coils is placed co-axially to the metal ball during measurement. It is well known that the distance between the sensor and test piece (i.e. lift-off) affects eddy-current signals. In this paper, it is found that the peak frequency feature of inductance spectrum is linear to the lift-off spacing between the centre of coil and ball. Besides, the slope of peak frequencies versus lift-offs is linked to the radius of ball. The radius of metallic balls is retrieved from the experimental and embedded analytical result of the slope. Measurements have been carried out on 6 metallic balls with different radii. The radius of the metallic ball can be retrieved with an error of less than 2 %.

The Coronavirus disease (COVID-19) caused by a novel coronavirus, SARS-CoV-2, has been declared as a global pandemic. Due to its infection rate and severity, it has emerged as one of the major global threats of the current generation. To support the current combat against the disease, this research aims to propose a Machine Learning based pipeline to detect the COVID-19 infection using the lung Computed Tomography scan images (CTI). This implemented pipeline consists of a number of sub-procedures ranging from segmenting the COVID-19 infection to classifying the segmented regions. The initial part of the pipeline implements the segmentation of the COVID-19 affected CTI using Social-Group-Optimization and Kapur’s Entropy thresholding, followed by k-means clustering and morphology-based segmentation. The next part of the pipeline implements feature extraction, selection and fusion to classify the infection. PCA based serial fusion technique is used in fusing the features and the fused feature vector is then employed to train, test and validate four different classifiers namely Random Forest, k-Nearest Neighbors (KNN), Support Vector Machine with Radial Basis Function, and Decision Tree. Experimental results using benchmark datasets show a high accuracy (> 91%) for the morphology-based segmentation task and for the classification task the KNN offers the highest accuracy among the compared classifiers (> 87%). However, this should be noted that this method still awaits clinical validation, and therefore should not be used to clinically diagnose the ongoing COVID-19 infection.

In the field of pavement engineering, the determination of the mechanical characteristics is one of the essential process for reliable material design and highway sustainability. Early determination of mechanical characteristics of pavement is highly essential for road and highway construction and maintenance. Tensile strength (TS), compressive strength (CS) and flexural strength (FS) of roller compacted concrete pavement (RCCP) are very crucial characteristics as they are necessitated for many data from mixture proportions as input variables. In this research, the classification-based regression models named Random Forest (RF), M5rule model tree (M5rule), M5prime model tree (M5p) and Chi-square Automatic Interaction Detection (CHAID) are developed for simulation of the mechanical characteristics of RCCP. A comprehensive and reliable dataset comprising 621, 326 and 290 data records for CS, TS and FS experimental cases extracted from several open sources over the literature. The mechanical properties are developed based on influential inputs combination that processed using Principle Component Analysis (PCA). The applied PCA method as feature selection is specified that volumetric/weighted content forms of experimental variables (e.g., coarse aggregate, fine aggregate, supplementary cementitious materials, water and binder) and specimens’ age are the most effective inputs to generate the better performances. Several statistical metrics are measured to evaluate proposed classification-based regression models. RF model revealed an optimistic classification capacity of the CS, TS and FS prediction of the RCCP in comparison with the CHAID, M5rule, and M5p models. The research is extended for the results verification using Monte-carlo model for the uncertainty and sensitivity of variables importance analysis. Overall, the proposed methodology indicated a reliable soft computing model that can be implemented for the material engineering construction and design.

We propose an iterative scheme for feature-based positioning using a new weighted dissimilarity measure with the goal of reducing the impact of large errors among the measured or modeled features. The weights are computed from the location-dependent standard deviations of the features and stored as part of the reference fingerprint map (RFM). Spatial filtering and kernel smoothing of the kinematically collected raw data allow efficiently estimating the standard deviations during RFM generation. In the positioning stage, the weights control the contribution of each feature to the dissimilarity measure, which in turn quantifies the difference between the set of online measured features and the fingerprints stored in the RFM. Features with little variability contribute more to the estimated position than features with high variability. Iterations are necessary because the variability depends on the location, and the location is initially unknown when estimating the position. Using real WiFi signal strength data from extended test measurements with ground truth in an office building, we show that the standard deviations of these features vary considerably within the region of interest and are neither simple functions of the signal strength nor of the distances from the corresponding access points. This is the motivation to include the empirical standard deviations in the RFM. We then analyze the deviations of the estimated positions with and without the location-dependent weighting. In the present example the maximum radial positioning error from ground truth are reduced by 40% comparing to kNN without the weighted dissimilarity measure.

This paper offers a comprehensive examination of the process involved in developing and automating supervised end-to-end machine learning workflows for forecasting and classification purposes. It offers a complete overview of the components (i.e. feature engineering, model selection, etc), principles (i.e. bias-variance decomposition, model complexity, overfitting, model sensitivity to feature assumptions and scaling, output interpretability, etc), models (i.e. neural networks, regression models, etc), methods (i.e. Cross-Validation, data augmentation, etc), metrics (i.e. Mean Squared Error, F1-score, etc) and tools that rule most supervised learning applications with numerical and categorical data, as well as their integration, automation, and deployment. The end goal and contribution of this paper is the education and guidance of the non-AI expert academic community over complete and rigorous machine learning pipelines and data science practices, from problem scoping to design and state-of-the-art automation tools, including basic principles and reasoning in the choice of methods. The paper delves into the critical stages of supervised machine learning workflow development, many of which are often omitted by researchers due to brevity, and covers foundational concepts essential for understanding and optimizing a functional machine learning workflow, thereby offering a holistic view of task-specific application development for applied researchers who are not AI experts.

Abstract In order to solve the problem that it is difficult to obtain the accurate trigger signal moment when using the time difference of UAV flight acoustic signals collected by acoustic sensors arranged in advance to locate the position of UAVs when they cannot be tracked by radar and are difficult to be observed by the human eye, an acoustic source localisation method with improved empirical modal decomposition (REMD) under an adaptive frequency window is proposed. Firstly, the collected UAV flight signals are smoothed and filtered, then the robust empirical modal decomposition (REMD) is used for IMF modal decomposition and spectral analysis of the collected signals, and a panning frequency window with variable bandwidth is introduced for corresponding frequency locking and extracting the IMFs; the GWO optimisation is used and the sliding metrics are set to determine the position of the panning frequency window automatically; finally, the extracted Finally, the extracted IMF components are reconstructed according to the criterion, and the trigger signal moments in the reconstructed IMF components are resolved and recorded, and the algorithm is used to calculate the difference between the reception moments of different sensors; for the traditional sound source localisation algorithms with a small detection range, which are prone to fall into the no-solution or false-solution, i.e., unable to achieve the localisation, a weighted least-squares-based Chan-Taylor algorithm is proposed for the localisation computation, and a weighted least-squares algorithm is proposed for the localisation computation, through the Inputting the sensor delay parameter and solving the linear equation system to get the target position information; finally, this paper verifies the robustness and performance of the design method with simulated and actual signals. The results show that the maximum positioning error is no more than 5% in an area with a side length of 15m in the measurement area. With the improved accuracy of time delay estimation, the positioning simulation results meet the positioning requirements even though the positioning error is further expanded when the measurement area is further expanded.

Cervical cancer is one of the ailments that endangers the health of women all over the world and causes infertility. Fortunately, this disease can be avoided. Both the results and participation rates of the current preventative strategy remain poor. Hence, preventative or early detection methods remain challenging and open. In gynecology and computer science fields, few studies on identifying cervical cancer are based on behavior risk factor and machine learning. Moreover, various social and behavioral aspects might often make it more difficult to detect cervical cancer especially in low‑ and middle‑income countries (LMICs). Accordingly, focus on predicting the presence of cervical cancer through behavioral risk factors is the basic structure of this research. We proposed an approach to classify cervical cancer from a social-behavioral perspective using logistic regression to predict cervical cancer. We got significantly improved outcomes than the existing methods. Moreover, we used feature engineering to formulate less dimensionality as a pre-processing step and optimized parameters to be prepared for classification phase. The results proved that using the logistic regression with regularization type L1 had a promising performance. The accuracy of Logistic Regression (LR) L1 was 97.2%. Such results support the proposed work as a reliable classification predictive tool.

The energy-intensive sector of the cement industry needs to find technologically advanced methods to produce cement with as little energy as possible, without polluting the environment and without sacrificing the quality (fineness) of the cement. In addition, the stress on the machines changes the behavior of the data. By combining the k-means method, two (2) feature selection methods, nine (9) machine learning methods, and the differential evolution (DE) method, a dynamic system is created where the user determines the key performance indicators (KPIs) each time. The user has the potential to control the distribution of the data, the input of machine learning models, and the ability to switch the system to the suggested values without damage. The selection of the best-performing models is based on the normalized root mean squared error (NRMSE). The DE method optimizes the dynamic objective function. The optimal values of the manipulated variables are evaluated compared to the value of the objective function from the actual values of the variables. In all experiments, the recommendations are acceptable. The final results show an improvement in the operation of both the cement mill and kiln compared to the current operating condition.

In order to realize the performance degradation trend prediction accurately, a prediction method based on multi-domain features and temporal convolutional network (TCN) is proposed. Firstly, construct a high-dimensional feature set in the multi-domain of vibration signals, and use comprehensive evaluation indicators to preliminarily screen performance degradation indexes with good sensitivity and strong trend. Secondly, the kernel principal component analysis (KPCA) method is adopted to eliminate redundant information between multi-domain features, and construct a health index (HI) based on convolutional auto-encoder (CAE) network. Thirdly, a TCN-based performance degradation trend prediction model is constructed, and direct multi-step prediction is used to predict the performance degradation trend of the monitored object. On this basis, the validity of the proposed method is verified using the bearing public data, and it is successfully applied to performance degradation trend prediction of rolling contact fatigue specimen. The results show that the feature set can be reduced from 14 dimensions to 4 dimensions by using KPCA, while 98.33% of the information of the original feature set is retained. Furthermore, the method of constructing HI based on CAE network is effective. The change process of the HI constructed truly reflects the performance degradation process of the rolling contact fatigue specimen. Compared with the two commonly used HI construction methods, auto-encoding (AE) network and gaussian mixture model (GMM), this method has obvious advantages. At the same time, the prediction model based on TCN can accurately predict the performance degradation of the rolling contact fatigue specimen with the root mean square error 0.0146 and the mean absolute error 0.0105, which has better performance and higher prediction accuracy than the prediction model based on the long short-term memory (LSTM) network and the gated recurrent unit (GRU). This method has general significance and may be extended to the performance degradation prediction of other mechanical equipment/parts.

Visual signals are the upmost important source for robots, vehicles or machines to achieve human-like intelligence. Human beings heavily depend on binocular vision to understand the dynamically changing world. Similarly, intelligent robots or machines must also have the innate capabilities of perceiving knowledge from visual signals. Until today, one of the biggest challenges faced by intelligent robots or machines is the matching in stereovision. In this paper, we present the details of a new principle toward achieving a robust matching solution which leverages on the use and integration of top-down image sampling strategy, hybrid feature extraction, and RCE neural network for incremental learning (i.e., cognition) as well as robust match-maker (i.e., recognition). A preliminary version of the proposed solution has been implemented and tested with data from Maritime RobotX Challenge (www.robotx.org). The contribution of this paper is to attract more research interest and effort toward this new direction which may eventually lead to the development of robust solutions expected by future stereovision systems in intelligent robots, vehicles and machines.

In response to reducing the energy cost of unmanned surface vehicles (USVs) while overcoming the low accuracy problem in surface target detection, a lightweight detection algorithm with multi-scale feature fusion is proposed. Based on the popular one-stage lightweight Yolov7-tiny target detection model, a lightweight extraction module is designed first by introducing the multiscale residual module to reduce the number of parameters and computational complexity while improving accuracy. The Mish and SiLU activation functions are used to enhance network feature extraction. Second, the path aggregation network employs coordinate convolution to strengthen spatial information perception. Finally, the dynamic head, which is based on the at-tention mechanism, improves the representation ability of object detection heads without any computational overhead. According to the experimental findings, the proposed model has 22.1% fewer parameters than the original model, 15% fewer GFLOPs, a 6.2% improvement in mAP@0.5, a 4.3% rise in mAP@0.5:0.95, and it satisfies the real-time criteria. According to the research, the suggested lightweight water surface detection approach includes a lighter model, a simpler computational architecture, more accuracy, and a wide range of generalizability. It performs bet-ter in a variety of difficult water surface circumstances.

This paper proposes a high-performance and low-cost in-flight collision avoidance system based on background subtraction for unmanned aerial vehicles (UAVs). The pipeline of proposed in-flight collision avoidance system is as follows: (i) dynamic background subtraction to remove the background and to detect moving objects, (ii) denoise using morphology and binarization methods, (iii) Euclidean clustering to cluster the moving object and to remove noise blobs, (iv) distinguish independent objects and track the movement using Kalman filter, and (v) collision avoidance using proposed decision-making techniques. This work focuses on the design and the demonstration of a vision-based fast moving object detection and tracking system with decision-making capabilities to perform evasive maneuvers to replace high vision system such as event camera. The development of high-performance, low-cost unmanned aerial vehicles paired with rapid progress in vision-based perception systems herald a new era of autonomous flight systems with mission-ready capabilities. One of the key features of an autonomous UAV is a robust mid-air collision avoidance strategy. The novelty of our method lies in the motion-compensating moving object detection framework, which accomplishes the task with background subtraction via 2-D transformation approximation. Clustering and tracking algorithms process detection data to track independent objects, and stereo-camera-based distance estimation is conducted to estimate the 3-D trajectory, which is then used during decision-making procedures. The examination of the system is conducted with a quadrotor UAV test vehicle, and appropriate algorithm parameters for various requirements are deduced.

Sleep deficiency impacts the quality of life and may have serious health consequences in the long run. Questionnaire-based subjective assessment of sleep deficiency has many limitations. On the other hand, objective assessment of sleep deficiency is challenging. In this study, we propose a polysomnography-based mathematical model for computing baseline sleep deficiency severity score and then investigated the estimation of sleep deficiency severity using features available only from wearable sensor data including heart rate variability and single-channel electroen-cephalography for a dataset of 500 subjects. We used Monte-Carlo Feature Selection (MCFS) and inter-dependency discovery for selecting the best features and removing multi-collinearity. For developing the Regression model we investigated both the frequentist and the Bayesian ap-proaches. An Artificial Neural Network achieved the best performance of RMSE = 5.47 and an R-squared value of 0.67 for sleep deficiency severity estimation. The developed method is com-parable to conventional methods of Functional Outcome of Sleep Questionnaire and Epworth Sleepiness Scale for assessing the impact of sleep apnea on sleep deficiency. Moreover, the results pave the way for reliable and interpretable sleep deficiency severity estimation using a wearable device in Smart Health.

Deep convolutional neural network (CNN) has shown their great advantages in the single image deraining task. However, most existing CNN-based single image deraining methods still suffer from residual rain streaks and details lost. In this paper, we propose a deep neural network including the Multi-scale feature extraction module and the channel attention module, which are embed in the feature extraction sub-network and the rain removal sub-network respectively. In the feature extraction sub-network, the Multi-scale feature extraction module is constructed by a Multi-layer Laplacian pyramid, and is then integrated multi-scale feature maps by a feature fusion module. In the rain removal sub-network, the channel attention module, which assigns different weights to the different channels, is introduced for preserving image details. Experimental results on visually and quantitatively comparison demonstrate that the proposed method performs favorably against other state-of-the-art approaches

Cloud computing is an emerging area which provide on demand computing resources and services through internet. It is faster and efficient technique but prone to severe security attacks. In this paper author have proposed a Network Intrusion Detection System (NIDS) to detect attacks at front end and backend when bulky flow of data packets flowing in a cloud environment. In our framework we used Signature based detection system for identifying the intruder and the Anomaly based detection system for detecting network attacks. The NIDS sensors were placed in a collaborative manner to prevent the attacks and to update the knowledge bases. Author have used supervised learning model to detect abnormal behavior of packets from network traffic. The dataset were trained and tested in terms of precision, recall, accuracy and model build time to select the best machine-learning model for detection of intruder and to improve the computational time and performance.

Autonomous driving systems are increasingly becoming a necessary trend towards building smart cities of the future. Numerous proposals have been presented in recent years to tackle particular aspects of the working pipeline towards creating a functional end-to-end system, such as object detection, tracking, path planning, sentiment or intent detection. Nevertheless, few efforts have been made to systematically compile all of these systems into a single proposal that effectively considers the real challenges these systems will have on the road, such as real-time computation, hardware capabilities, etc. This paper has reviewed various techniques towards proposing our own end-to-end autonomous vehicle system, considering the latest state on the art on computer vision, DSs, path planning, and parallelization.

Genetic Programming (GP) is a powerful Machine Learning (ML) algorithm that can produce readable white-box models. Although successfully used for solving an array of problems in different scientific areas, GP is still not well known in Remote Sensing. The M3GP algorithm, a variant of the standard GP algorithm, performs Feature Construction by evolving hyper-features from the original ones. In this work, we use the M3GP algorithm on several sets of satellite images over different countries to create hyper-feature from satellite bands to improve the classification of land cover types. We add the evolved hyper-features to the reference datasets and observe a significant improvement of the performance of three state-of-the-art ML algorithms (Decision Trees, Random Forests and XGBoost) on multiclass classifications and no significant effect on the binary classifications. We show that adding the M3GP hyper-features to the reference datasets brings better results than adding the well-known spectral indices NDVI, NDWI and NBR. We also compare the performance of the M3GP hyper-features in the binary classification problems with those created by other Feature Construction methods like FFX and EFS.

The importance of antibodies in health care and the biotechnology research and development demands not only knowledge of their experimental structures at high resolution, but also practical implementation of this knowledge for both effective and efficient design and production of antibody for its use in both medical and research applications. While the experimental wet-lab approach is usually costly, laborious and time-consuming, computational (dry-lab) approaches, in spite of their intrinsic limitations in comparison with its experimental (wet-lab) counterpart, provide a cheaper and faster alternative option. For the first time, this article reports a comprehensive set of structural electrostatic features extracted from experimentally determined antigen-antibody-related structures, including especially those structural electrostatic features at the interfaces of all experimentally determined antigen-antibody complex structures as of February 29, 2020, to facilitate effective and efficient machine learning-based computational antibody design using currently available experimental structures inside Protein Data Bank.

Early detection of cancer increases the probability of recovery. This paper presents an intelligent decision support system (IDSS) for the early diagnosis of cancer based on gene expression profiles collected using DNA microarrays. Such datasets pose a challenge because of the small number of samples (no more than a few hundred) relative to the large number of genes (on the order of thousands). Therefore, a method of reducing the number of features (genes) that are not relevant to the disease of interest is necessary to avoid overfitting. The proposed methodology uses the information gain (IG) to select the most important features from the input patterns. Then, the selected features (genes) are reduced by applying the grey wolf optimization (GWO) algorithm. Finally, the methodology employs a support vector machine (SVM) classifier for cancer type classification. The proposed methodology was applied to two datasets (Breast and Colon) and was evaluated based on its classification accuracy, which is the most important performance measure in disease diagnosis. The experimental results indicate that the proposed methodology is able to enhance the stability of the classification accuracy as well as the feature selection

Electricity demand forecasting has been a real challenge for power system scheduling in the different levels of the energy sectors. Various computational intelligence techniques and methodologies have been employed in the electricity market for load forecasting; although, scant evidence is available about the feasibility of each of these methods considering the type of data and other potential factors. This work introduces several scientific, technical rationale behind intelligent forecasting methods, based on the work of previous researchers in the field of energy. The fundamental benefits and main drawbacks of the aforementioned methods are discussed in order to depict the efficiency of each approach in various situations. In the end, a proposed hybrid strategy is represented.

Classification of electromyographic signals has a wide range of applications, from clinical diagnosis of different muscular diseases to biomedical engineering, where their use as input control of prosthetic devices has become a hot topic of research. Challenge of classifying this signals relies on the accuracy of the proposed algorithm and the possibility of its implementation on hardware. This paper consider the problem of electromyography signal classification, solved with the proposed signal processing and feature extraction stages, with focus lying on the signal model and time domain characteristics for better classification accuracy. The proposal considers a simple preprocessing technique that produces signals suitable for feature extraction, and the Burg reflection coefficients to form learning and classification patterns. These coefficients yield a competitive classification rate compared to used time domain features. Sometimes, the feature extraction from electromyographic signals showed that procedure can omit less useful traits for machine learning models. Using feature selection algorithms provides a higher classification performance with as fewer traits as possible. Algorithms achieved a high classification rate up to 100% with low pattern dimensionality, with other kinds of uncorrelated attributes for hand movement identification.

Although the water absorption feature (WAF) at 970 nm is not very well-defined, it may be used alongside other indices to estimate the canopy water content. The individual performance of a number of existing vegetation water content (VWC) indices against the WAF is assessed using linear regression model. We developed a new Combined Vegetation Water Index (CVWI) by merging indices to boost the weak absorption feature. CVWI showed a promise in assessing the vegetation water status derived from the 970 nm absorption wavelength. CVWI was able to differentiate two groups of dataset when regressed against the absorption feature. CVWI could be seen as an easy and robust method for vegetation water content studies using hyperspectral field data.

In recent years, the rapid development of computer-aided planning and design technology has provided a new perspective for the study of complex problems such as the generation of architectural complex forms. This study focuses on how to apply parameterization technology to analyze and articulate traditional spatial form composition rules, aiming to minimize reliance on subjective human judgment in the protection and renewal design of the historical style of traditional villages. It aims to establish digital generative design tools to address the challenges of accurately inheriting and innovatively utilizing historical and cultural information in traditional settlements. It introduces how to rely on parameterization technology to analyze the spatial form composition rules, parameter extraction rules, and spatial reconstruction rules of traditional villages, facilitating the complete process from spatial features to parameterization rules, and then to the application of computational methods to deduce spatial features. It also includes case studies demonstrating the application of parameterization technology tools for village protection and explores the role of generative design tools in preserving the spatial style of these settlements.

In this paper, we use a machine learning method, known as Nonnegative Matrix Factorization, to extract from a given image some new information obtained from a number of color space representations. Such kind of information, termed ``metacolor'', can be considered as a particular color space representation of the image, which can be used to obtain a binary segmentation of the investigated image by distinguishing foreground and background pixels. Some numerical experiments prove that the proposed method shows improved results when compared with common simpler thresholding algorithms.

Deep learning is based on matrix computing with a large amount of hidden parameters that is not visible outside the computing module. Deep learning is a non-linear system and a linear approach is not possible. It is natural for people to visualize the algorithm and to follow some hidden parameters. In this paper, we propose a simple graphical programming of a nonlinear system based on drawing the simplest unit, such as a single neuron model. A more complex scheme of a classical neural network is obtained by commands copy-move-place of one neuron. The number of neurons and layers can be chosen arbitrarily. Once the scheme is complete, the implementation code is evaluated with symbolic parameters and nonlinear activation functions. This cannot be done manually. With the symbolic expression of outputs in terms of inputs and symbolic parameters, including symbolic activation pure functions, some other properties can be derived in closed form. This unique original approach can help scientists and developers and design numerical algorithms for machine learning and to understand how deep learning algorithms work.

In industrial settings, gears play a crucial role by assisting various machinery functions such as speed control, torque manipulation, and altering motion direction.The malfunction or failure of these gear components can have serious repercussions, resulting in production halts and financial losses. As a result, there is an increasing requirement to monitor the state of these components in order to avoid such issues from occurring. To address this need, research efforts have focused on early defect detection in gears in order to reduce the impact of possible failures. This study focused on analyzing vibration and thermal datasets from two extruder machine gearboxes using an autoencoder Long Short-Term Memory (LSTM) model. The major goal is to implement an outlier detection approach to detect and classify defects. The results of this study highlighted the extraordinary performance of the Autoencoder LSTM model, which achieved an impressive accuracy rate of 94.42% in recognizing malfunctioning gearboxes within the extruder machine system. Furthermore, the study used a thorough global metrics evaluation methodology to further test the model’s dependability and efficacy, consequently substantiating the proposed approach’s validity.

. Identifying students who might have difficulty in their course of studies ahead of time is crucial. There can be many reasons for performance issues, such as personality, family, social, and/or economic. We advocate that educational systems should use machine learning to predict students’ performance based on performance factors. This would allow educational professionals and institutions to put in place a preventive plan to help students towards achievements of their educational goals and success. In this chapter, we propose a student performance prediction method and evaluate its performance. We provide a taxonomy of performance factors that help to gauge students performance from different perspectives and give insights on the categories and features that have more significant impact on students’ performance. The results of this work can be used by education institutions to put in place a student-centric approach to tackle performance issues before they create long-term effects on student’s life. In addition, it will help education policymakers to introduce a tailored approach for the population in specific areas.

As a consequence of applying advanced maintenance practices, the theoretical probability of failures is relatively low. However, observation of low market intelligence and maintenance management has been reported. The experimental investigation is supported by findings from a survey targeting asset-intensive companies applying hydraulic power systems. Next, the study incorporates multidimensional data analysis using CA-AHC (Correspondance Analysis with Agglomerative Hierarchical Clustering) approach. The non-parametric machine learning models are used from generated feature subspace to extract features affecting maintenance performance indicators. The results support empirical evidence that equipment age increases the probability of failures. However, the novel findings show that number of maintenance personnel, equipment size measured by nominal working energy consumption, and activities dedicated to maintaining fluid cleanliness impact regression results of companies utilising hydraulic applications.

Deepfakes are manipulated or altered images, or video, that are created using deep learning models with high levels of photorealism. The two popular methods of producing a deepfake are based on either convolutional neural networks (CNN), or autoencoders. Deepfakes created using CNN comparatively show higher qualities of realism, yet oftentimes leave artifacts and distortions in the generated media that can be detected using machine learning and deep learning algorithms. In recent years, there has been an influx of periocular image and video data because of the increase usage of face masks. By wearing masks, much of what is used for facial recognition is hidden, leaving only the periocular region visible to an observer. This loss of vital information leads to easier misidentification of media, allowing deepfakes to less likely be identified as fake. In this work, feature extraction methods, such as Scale-Invariant Feature Transform (SIFT), Histogram of Oriented Gradients (HOG), and CNN, are used to train an ensemble deep learning model to detect deepfakes in videos on a frame-by-frame level based on the periocular region. Our proposed model is able to distinguish original and manipulated images with accuracies around 98.9 percent, which is an improvement to previous works by combining SIFT and HOG for deepfake detection in convolutional neural networks.

With the increasing availability of large digitized fine art collections, automated analysis and classification of paintings is becoming an interesting area of research. However, due to domain specificity, implicit subjectivity, and pervasive nuances that vaguely separate art movements, analyzing art using machine learning techniques poses significant challenges. Residual networks, or variants thereof, are one the most popular tools for image classification tasks, which can extract relevant features for well-defined classes. In this case study, we focus on the classification of a selected painting 'Portrait of the Painter Charles Bruni' by Johann Kupetzky and the analysis of the performance of the proposed classifier. We show that the features extracted during residual network training can be useful for image retrieval within search systems in online art collections.

The central goal of few-shot scene classification is to learn a model that can generalize well to a novel scene category (UNSEEN) from only one or a few labeled examples. Recent works in the remote sensing (RS) community tackle this challenge by developing algorithms in a meta-learning manner. However, most prior approaches have either focused on rapidly optimizing a meta-learner or aimed at finding good similarity metrics while overlooking the embedding power. Here we propose a novel Task-Adaptive Embedding Learning (TAEL) framework that complements the existing methods by giving full play to feature embedding’s dual roles in few-shot scene classification - representing images and constructing classifiers in the embedding space. First, we design a lightweight network that enriches the diversity and expressive capacity of embeddings by dynamically fusing information from multiple kernels. Second, we present a task-adaptive strategy that helps to generate more discriminative representations by transforming the universal embeddings into task-specific embeddings via a self-attention mechanism. We evaluate our model in the standard few-shot learning setting on two challenging datasets: NWPU-RESISC4 and RSD46-WHU. Experimental results demonstrate that, on all tasks, our method achieves state-of-the-art performance by a significant margin.

Bayesian formulations of learning imply that whenever the evidence for a correlation between events in an animal’s habitat is sufficient, the correlation is learned. This implies that regularities can be learnt rapidly, from small numbers of learning examples. This speed of learning gives maximum possible fitness, and no faster learning is possible. There is evidence in many domains that animals and people can learn at nearly Bayesian optimal speeds. These domains include associative conditioning, and the more complex domains of navigation and language. There are computational models of learning which learn at near-Bayesian speeds in complex domains, and which can scale well – to learn thousands of pieces of knowledge (i.e., relations and associations). These are not neural net models. They can be defined in computational terms, as algorithms and data structures at David Marr’s [1] Level Two. Their key data structures are composite feature structures, which are graphs of multiple linked nodes. This leads to the hypothesis that animal learning results not from deep neural nets (which typically require thousands of training exam-ples), but from neural implementations of the Level Two models of fast learning; and that neu-rons provide the facilities needed to implement those models at Marr’s Level Three. The required facilities include feature structures, dynamic binding, one-shot memory for many feature struc-tures, pattern-based associative retrieval, unification and generalization of feature structures. These may be supported by multiplexing of data and metadata in the same neural fibres.

To better understand the genes with altered expression caused by infection with the novel coronavirus strain SARS-CoV-2 causing COVID-19 infectious disease, a tensor decomposition (TD)-based unsupervised feature extraction (FE) approach was applied to a gene expression profile dataset of the mouse liver and spleen with experimental infection of mouse hepatitis virus, which is regarded as a suitable model of human coronavirus infection. TD-based unsupervised FE selected 134 altered genes, which were enriched in protein-protein interactions with orf1ab, polyprotein, and 3C-like protease that are well known to play critical roles in coronavirus infection, suggesting that these 134 genes can represent the coronavirus infectious process. We then selected compounds targeting the expression of the 134 selected genes based on a public domain database. The identified drug compounds were mainly related to known antiviral drugs, several of which were also included in those previously screened with an in silico method to identify candidate drugs for treating COVID-19.

The use of smartphones, coupled with different sensors, makes it an attractive solution for measuring different physical and physiological features, allowing for the monitoring of various parameters and even identifying some diseases. The BITalino device allows the use of different sensors, including Electroencephalography (EEG) and Electrocardiography (ECG) sensors, to study different health parameters. With these devices, the acquisition of signals is straightforward, and it is possible to connect them using a Bluetooth connection. With the acquired data, it is possible to measure parameters such as calculating the QRS complex and its variation with ECG data to control the individual's heartbeat. Similarly, by using the EEG sensor one could analyze the individual's brain activity and frequency. The purpose of this paper is to present a method for recognition of the diseases related to ECG and EEG data, with sensors available in off-the-shelf mobile devices and sensors connected to a BITalino device. The data were collected during the elderly's experiences, performing the Timed-Up and Go test, and the different diseases found in the sample in the study. The data were analyzed, and the following features were extracted from the ECG, including heart rate, heart rate variability, the average QRS interval, the average R-R interval, and the average R-S interval, and the EEG, including frequency and variability. Finally, the diseases are correlated with different parameters, proving that there are relations between the individuals and the different health conditions.

One of the most common and important destructive attacks on the victim system is Advanced Persistent Threats (APT)-attack. The APT attacker can achieve his hostile goals by obtaining information and gaining financial benefits regarding the infrastructure of a network. One of the solutions to detect a secret APT attack is using network traffic. Due to the nature of the APT attack in terms of being on the network for a long time and the fact that the network may crash because of high traffic, it is difficult to detect this type of attack. Hence, in this study, machine learning methods such as C5.0 decision tree, Bayesian network and deep neural network are used for timely detection and classification of APT-attacks on the NSL-KDD data set. Moreover, 10-fold cross validation method is used to experiment these models. As a result, the accuracy (ACC) of the C5.0 decision tree, Bayesian network and 6-layer deep learning models is obtained as 95.64%, 88.37% and 98.85%, respectively, and also, in terms of the important criterion of the false positive rate (FPR), the FPR value for the C5.0 decision tree, Bayesian network and 6-layer deep learning models is obtained as 2.56, 10.47 and 1.13, respectively. Other criterions such as sensitivity, specificity, accuracy, false negative rate and F-measure are also investigated for the models, and the experimental results show that the deep learning model with automatic multi-layered extraction of features has the best performance for timely detection of an APT-attack comparing to other classification models.

A significant attention has been made to the accurate detection of diabetes which is a big challenge for the research community to develop a diagnosis system to detect diabetes in a successful way in the IoT e-healthcare environment. Internet of Things (IOT) has emerging role in healthcare services which delivers a system to analyze the medical data for diagnosis of diseases applied data mining methods. The existing diagnosis systems have some drawbacks, such as high computation time, and low prediction accuracy. To handle these issues, we have proposed a IOT based diagnosis system using machine learning methods, such as preprocessing of data, feature selection, and classification for the detection of diabetes disease in e- healthcare environment. Model validation and performance evaluation metrics have been used to check the validity of the proposed system. We have proposed a filter method based on the Decision Tree (Iterative Dichotomiser 3) algorithm for highly important feature selection. Two ensemble learning Decision Tree algorithms, such as Ada Boost and Random Forest are also used for feature selection and compared the classifier performance with wrapper based feature selection algorithms also. Machine learning classifier Decision Tree has been used for the classification of healthy and diabetic subjects. The experimental results show that the Decision Tree algorithm based on selected features improves the classification performance of the predictive model and achieved optimal accuracy. Additionally, the proposed system performance is high as compared to the previous state-of-the-art methods. High performance of the proposed method is due to the different combinations of selected features set and GL, DPF, and BMI are more significantly important features in the dataset for prediction of diabetes disease. Furthermore, the experimental results statistical analysis demonstrated that the proposed method would be effectively detected diabetes disease and can easily be deployed in IOT wireless sensor technologies based e-healthcare environment.

With the increasing adoption of building integrated photovoltaics (BIPV), concerns arise about potential glare. While recommended criteria to assess glare exist, it is challenging to apply these in the spatial and temporal domains and communicate the complex data to planning authorities and clients. This paper presents a new computational workflow using annual daylight simulation, material modelling using bi-directional scattering distribution functions (BSDFs) and image-based postprocessing to obtain 3-dimensional renderings of cumulative annual irradiance and glare duration on the built environment. The annual daylight simulation considers relevant sun positions in high temporal resolution (15-minute timesteps) and measured BSDFs to model different PV materials. The postprocessing includes a relative irradiance visualisation comparing the impact of a proposed PV proportional to a reference material. It also includes a new spatio-temporal workflow to assess the glare duration based on recommended thresholds. This workflow is demonstrated with a case study of a proposed PV roof for a church, assessing the glare potential of two different PV materials. The visualisations indicate glare durations well below the thresholds with satinated PVs, and in noncritical zones outside observer positions with standard PVs. Thus the proposed PV roof does not cause any disturbing glare.

Software fault prediction is the very consequent research topic for software quality assurance. Data driven approaches provide robust mechanisms to deal with software fault prediction. However, the prediction performance of the model highly depends on the quality of dataset. Many software datasets suffers from the problem of class imbalance. In this regard, under-sampling is a popular data pre-processing method in dealing with class imbalance problem, Easy Ensemble (EE) present a robust approach to achieve a high classification rate and address the biasness towards majority class samples. However, imbalance class is not the only issue that harms performance of classifiers. Some noisy examples and irrelevant features may additionally reduce the rate of predictive accuracy of the classifier. In this paper, we proposed two-stage data pre-processing which incorporates feature selection and a new Rough set Easy Ensemble scheme. In feature selection stage, we eliminate the irrelevant features by feature ranking algorithm. In the second stage of a new Rough set Easy Ensemble by incorporating Rough K nearest neighbor rule filter (RK) afore executing Easy Ensemble (EE), named RKEE for short. RK can remove noisy examples from both minority and majority class. Experimental evaluation on real-world software projects, such as NASA and Eclipse dataset, is performed in order to demonstrate the effectiveness of our proposed approach. Furthermore, this paper comprehensively investigates the influencing factor in our approach. Such as, the impact of Rough set theory on noise-filter, the relationship between model performance and imbalance ratio etc. comprehensive experiments indicate that the proposed approach shows outstanding performance with significance in terms of area-under-the-curve (AUC).

The growth rate in academic and scientific publications increased very fast. Researchers must choose a good representative and significant literature in publications, which has become challenging worldwide. Usually, the paper citation number indicates this paper's potential influence and importance. However, this standard metric of citation numbers cannot be used as a measurement to judge the popularity and significance of the recently published papers. To address this challenge, this paper presents an effective prediction method called FutureCite to predict the future citation level of research articles. FutureCite combines machine learning with text and graph mining techniques, leveraging their abilities in classification, datasets in-depth analysis, and feature extraction. FutureCite aims to predict future citation levels of research articles applying a multilabel classification approach. FutureCite can extract significant semantic features and capture the interconnection relationships found in scientific articles during feature extraction using textual content, citation networks, and metadata as feature resources. Our goal is to contribute to the advancement of substantial effective approaches impacting the citation counts in scientific publications by enhancing the precision of future citations. We conducted several experiments using a comprehensive publication dataset to evaluate our method and determine the impact of using a variety of machine learning algorithms. FutureCite demonstrated its robustness and efficiency and showed promising results based on different evaluation metrics. Using the FutureCite model has significant implications in improving the researchers' ability to determine targeted literature for their research and better understand the potential impact of research publications.

ABSTRACT Purpose: Tongue image analysis for disease diagnosis is an ancient traditional non-invasive diagnosis technique widely used by traditional medicine practitioners. Deep Learning based multi-label disease detection models offer tremendous potential to clinical decision support systems, by facilitating preliminary diagnosis. Methods: In this work, we propose a multi-label disease detection pipeline, where in observation and analysis of tongue images captured and received via smartphones assist in predicting the health status of an individual. All images are voluntarily given by subjects consulting collaborating physicians. Images thus acquired are first and foremost classified either into a diseased or a normal category by a 5-fold cross-validation algorithm using a convolution neural network (MobileNetV2) model for binary classification. Once the diseased label is predicted, the image is used to diagnose multiple diseases using the prediction algorithm based on DenseNet121. Results: Average accuracy of 93 % was achieved in classifying diseased from normal healthy tongue by detection model with MobileNetV2 architecture. Multilabel disease classification produced more than 90% accurate results for the seven class labels considered. Conclusion: AI based image analysis shows promising results and an extensive dataset could provide further improvements to this approach. Rather than employing high-cost sophisticated image capturing setup, experimenting with smartphone images opens opportunity to provide preliminary health status to individuals on smartphone prior to further line of treatment and diagnosis.

With the development of artificial intelligence, the ability of capturing the background characteristics of hyperspectral imagery (HSI) is improved and promising performance in hyperspectral anomaly detection (HAD) tasks is yielded. However, existing methods proposed in recent years still suffer from certain limitations: 1) constraints are lacking in the deep feature learning process in terms of the issue for absence of prior background and anomaly information. 2) hyperspectral anomaly detectors with traditional self-supervised deep learning methods fail to ensure prioritized reconstruction of the background. 3) architectures of fully connected deep network in hyperspectral anomaly detectors lead to low utilization of spatial information and destruction for original spatial relationship of hyperspectral imagery, and disregard spectral correlation between adjacent pixels. 4) hypotheses or assumptions for background and anomaly distributions restrict the performance of many hyperspectral anomaly detectors because the distributions of background land covers are usually complex and not assumable in real-world hyperspectral imagery. With the consideration of above problems, in this paper, we propose a novel fully convolutional auto-encoder based on dual clustering and latent feature adversarial consistency (FCAE-DCAC) for HAD which is carried out in a self-supervised learning-based processing. Firstly, the density-based spatial clustering of applications with noise algorithm and connected component analysis are utilized for successive spectral and spatial clustering to obtain more precise prior background and anomaly information, which facilitates the separation between background and anomaly samples during the training of our method. Subsequently, a novel fully convolutional auto-encoder (FCAE) integrated with spatial-spectral joint attention (SSJA) is proposed to enhance the utilization of spatial information and augment feature expression. In addition, a latent feature adversarial consistency network is proposed to achieve pure background reconstruction with the ability of learning actual background distribution in hyperspectral imagery. Finally, a triplet loss is introduced to enhance the separability between background and anomaly, and the reconstruction residual serves as the anomaly detection result. We evaluate the proposed method on seven groups of real-world hyperspectral datasets, and the experimental results confirmed the effectiveness and superior performance of the proposed method versus nine state-of-the-art methods.

The 70/30 copper–nickel alloy is mainly used in critical parts with more demanding conditions in marine settings. There is a need for innovative methods that offer fast production and cost-effectiveness to supplement current copper–nickel alloy manufacturing processes. In this study, we employ wire-arc additive manufacturing (WAAM) to fabricate the 70/30 copper–nickel alloy. The as-built microstructure is characterized by columnar grains with prominent dendrites and chemical segregation in the inter-dendritic area. The aspect ratio of the columnar grain increases with increasing travel speed (TS) at the same wire feed speed (WFS). This is in contrast to an equiaxed grain structure with a more random orientation of conventional sample. The sample built with a WFS of 8 m/min, TS of 1000 mm/min, and a track distance of 3.85 mm exhibits superior corrosion properties in the 3.5 wt% NaCl solution compared to the conventional one, as evidenced by a higher film resistance and breakdown potential, along with a lower passive current density of the WAAM sample. The corrosion morphology reveals the critical roles played by the nickel element unevenly distributed between the dendrite core and inter-dendritic area.

Interferometric synthetic aperture radar (InSAR) and tomographic SAR measurement techniques are commonly used for the three-dimensional (3D) reconstruction of complex areas, while the effectiveness of these methods relies on the interferometric coherence among SAR images with minimal angular disparities. Radargrammetry exploits stereo image matching to determine the spatial coordinates of corresponding points in two SAR images, and acquire their 3D properties. The performance of the image matching process directly impacts the quality of the resulting digital surface model (DSM). However, the presence of speckle noise, along with dissimilar geometric and radiometric distortions, poses considerable challenges to achieve accurate stereo SAR image matching. To address the aforementioned challenges, this paper proposes a radargrammetric method based on composite registration of multi-aspect SAR images. The proposed method combines coarse registration using scale invariant feature transform (SIFT) with precise registration using normalized cross-correlation (NCC) to achieve accurate registration between multi-aspect SAR images with large disparities. Furthermore, the multi-aspect 3D point clouds are merged by the proposed radargrammetric 3D imaging method, resulting in 3D imaging of target scenes based on multi-aspect SAR images. For validation purpose, this paper presents a comprehensive 3D reconstruction of the Five-hundred-meter Aperture Spherical radio Telescope (FAST) by using Ka-band airborne SAR images. It does not necessitate prior knowledge of the target and is applicable to the detailed 3D imaging of large-scale areas with complex structures. In comparison to other SAR 3D imaging techniques, it reduces the requirements for orbit control and radar system parameters. To sum up, the proposed 3D imaging method with composite registration guarantees imaging efficiency while enhances the imaging accuracy of crucial areas with limited data.

Heart disease is a global health concern of paramount importance, causing a significant number of fatalities and disabilities. Precise and timely diagnosis of heart disease is pivotal in pre-venting adverse outcomes and improving patient well-being, thereby creating a growing demand for intelligent approaches to predict heart disease effectively. This paper introduces an Ensemble Heuristic-Metaheuristic Feature Fusion Learning (EHMFFL) algorithm for heart disease diagnosis. Within the EHMFFL algorithm, a diverse ensemble learning model is crafted, featuring different feature subsets for each heterogeneous base learner, including support vector machine, K-nearest neighbors, logistic regression, random forest, naive bayes, decision tree, and XGBoost. The primary objective is to identify the most pertinent features for each base learner, leveraging a combined heuristic-metaheuristic approach that integrates the heuristic knowledge of Pearson correlation coefficient with the metaheuristic-driven grey wolf optimizer. The second objective is to aggregate the decision outcomes of the various base learners through ensemble learning, aimed at constructing a robust prediction model. The performance of the EHMFFL algorithm is rigorously assessed using the Cleveland and Statlog datasets yielding remarkable results with an accuracy of 91.8% and 88.9%, respectively, surpassing state-of-the-art machine learning, ensemble learning, and feature selection techniques in heart disease diagnosis. These findings underscore the potential of the EHMFFL algorithm in enhancing diagnostic accuracy for heart disease and providing valuable support to clinicians in making more informed decisions regarding patient care.

Abstract: In recent years, the construction engineering sector has undergone a transformative shift towards the integration of machine learning (ML) techniques, particularly in predicting the properties of steel fiber-reinforced concrete (SFRC). Despite the theoretical sophistication of existing models, a persistent challenge remains – their opacity, lacking transparency and real-world relevance for practi-tioners. To address this gap and advance our current understanding, this study employs the extra gradient (XG) Boosting algorithm, crafting a comprehensive ap-proach. Grounded in a meticulously curated database drawn from 43 seminal pub-lications, encompassing 420 distinct records, this research focuses predominantly on three primary fiber types: crimped, hooked, and mil-cut. Complemented by hands-on experimentation involving 20 diverse SFRC mixtures, this empirical campaign is further illuminated through the strategic use of Partial Dependence Plots (PDPs), revealing intricate relationships between input parameters and con-sequent compressive strength. A pivotal revelation of this research lies in the identification of optimal SFRC formulations, offering tangible insights for real-world applications. The developed ML model stands out not only for its sophistication but also its tangible accuracy, evidenced by exemplary performance against inde-pendent datasets, boasting a commendable mean target-prediction ratio of 99%. To bridge the theory-practice gap, we introduce a user-friendly digital interface, thri-ughly designed to guide professionals in optimizing and accurately predicting the compressive strength of SFRC. This research thus contributes to the construction and civil engineering sectors by enhancing predictive capabilities and refining mix designs, fostering innovation, and addressing the evolving needs of the industry.

A morphological feature estimation method is presented, that can be used to monitor fish from low contrast underwater images and videos. The fish orientation is classified in order to apply a shape alignment technique that is based on the Ensemble of Regression Trees machine learning method. Shape alignment allows the estimation of fish dimensions (length, height, mass) and the location of fish body parts of particular interest such as the eyes and gills. The developed system can be exploited both for fish monitoring in open sea as well as aquacultures where non-invasive, low cost morphological feature extraction is essential. Fish health can be assessed from malformations in body shape, the color of the eyes or the gills as well as the fish behavior. The proposed method can estimate the position of 18 landmarks with an accuracy of about 95% from low resolution and low contrast underwater images where the fish can be hardly distinguished from its background. Hardware acceleration can be applied at various stages of the proposed method for real time video processing. As a case study, the developed system has been trained and tested with several Mediterranean fish species in the category of seabream or similar: diplodous sargus annularis (white seabream), diplodus annularis seabream (spawn), oblada melanura (saddled seabream), pagrus pagrus (common seabream), etc. A large dataset with low resolution underwater videos and images has been created in the context of this work.

Malicious apps specifically aimed at the Android platform have increased in tandem with the proliferation of mobile devices. Malware is now so carefully written that it is difficult to detect. Due to the exponential growth in malware, manual methods of malware are increasingly ineffec-tive. Although prior writers have proposed numerous high-quality approaches, static and dy-namic assessments inherently necessitate intricate procedures. The obfuscation methods used by modern malware are incredibly complex and clever. As a result, it cannot be detected using only static malware analysis. As a result, this work presents a hybrid analysis approach, partially tai-lored for multiple-feature data, for identifying Android malware and classifying malware families to improve Android malware detection and classification. This paper offers a hybrid method that combines static and dynamic malware analysis to give a full view of the threat. Three distinct phases make up the framework proposed in this research. Normalization and feature extraction procedures are used in the first phase of pre-processing. Both static and dynamic features undergo feature selection in the second phase. Two feature selection strategies are proposed to choose the best subset of features to use for both static and dynamic features. The third phase involves ap-plying a newly proposed detection model to classify android apps; this model uses a neural net-work optimized with an improved version of HHO. Application of binary and multi-class classi-fication is used, with binary classification for benign and malware apps and multi-class classifica-tion for detecting malware categories and families. By utilizing the features gleaned from static and dynamic malware analysis, several machine-learning methods are used for malware classifi-cation. According to the results of the experiments, the hybrid approach improves the accuracy of detection and classification of Android malware compared to the scenario when considering static and dynamic information separately.

While thunderstorms can pose severe risks to property and life, forecasting remains challenging, even at short lead times, as these often arise in meta-stable atmospheric conditions. In this paper, we examine the question of how well we could perform short-term (up to 180min) forecasts using exclusively multi-spectral satellite images and past lighting events as data. We employ representation learning based on deep convolutional neural networks in an “end-to-end” fashion. Here, a crucial problem is handling the imbalance of the positive and negative classes appropriately in order to be able to obtain predictive results (which is not addressed by many previous machine-learning-based approaches). The resulting network outperforms previous methods based on physically-based features and optical flow methods (similar to operational prediction models) and generalizes across different years. A closer examination of the classifier performance over time and under masking of input data indicates that the learned model actually draws most information from structures in the visible spectrum, with infrared imaging sustaining some classification performance during the night.

One of the critical tools for early detection and subsequent evaluation of the incidence of lung diseases is chest radiography. At a time when the speed and reliability of results, especially for COVID-19 positive patients, is important, the development of applications that would facilitate the work of untrained staff involved in the evaluation is also crucial. Our model takes the form of a simple and intuitive application, into which you only need to upload X-rays: tens or hundreds at once. In just a few seconds, the physician will determine the patient's diagnosis, including the percentage accuracy of the estimate. While the original idea was a mere binary classifier that could tell if a patient was suffering from pneumonia or not, in this paper we present a model that distinguishes between a bacterial disease, a viral infection, or a finding caused by COVID-19. The aim of this research is to demonstrate whether pneumonia can be detected or even spatially localized using a uniform, supervised classification.

In today's world it is very much important to maintain the security of information and its risks. The biometric-based techniques are very much useful in these problems. Among the several kinds of biometric-based technique, face detection is much complex and much more important. Due to the age and several other problems, a human face structure changes over time, again a human has lots of expressions. Sometimes due to the lighting condition or the variation of the angle of an input device, the pattern of a human face structure also changed. As a result, the face cannot be detected properly. In this paper, a method is proposed that can detect the human faces both automatically and manually very efficiently. In manual mode, a user can select the input faces referred by the system according to their choice. In automated mode, the system detected all possible face areas using the Kohonen Self-Organizing Feature Map technique. This method reduced the complex color image into a vector quantized image with desired colors. Then a color segmentation technique is used to detect the possible face skin areas from the vector quantized image. Then the Histogram Oriented Gradient technique used to detect the feature from the faces and K-Nearest Neighbour Classifier is used to compare both face images detected by the two modes. The automated method prosed better accuracy than the manual method.

Due to the substantial growth of internet users and its spontaneous access via electronic devices, the amount of electronic contents is growing enormously in recent years through instant messaging, social networking posts, blogs, online portals, and other digital platforms. Unfortunately, the misapplication of technologies has boosted with this rapid growth of online content which leads to the rise in suspicious activities. People misuse the web media to disseminate malicious activity, perform the illegal movement, abuse other people, and publicize suspicious contents on the web. The suspicious contents usually available in the form of text, audio or video, whereas text contents have been used in most of the cases to perform suspicious activities. Thus, one of the most challenging issues for NLP researchers is to develop a system that can identify suspicious text efficiently from the specific contents. In this paper, a Machine Learning (ML)-based classification model is proposed (hereafter called STD) to classify Bengali text into non-suspicious and suspicious categories based on its original contents. A set of ML classifiers with various features has been used on our developed corpus, consisting of 7000 Bengali text documents where 5600 documents used for training and 1400 documents used for testing. The performance of the proposed system is compared with the human baseline and existing ML techniques. The SGD classifier `tf-idf’ with the combination of unigram and bigram features are used to achieve the highest accuracy of 84.57%.

The use of Hyperspectral (HS) and LiDAR acquisitions has a great potential to enhance mapping and monitoring practices of endangered grasslands habitats, beyond conventional botanical field surveys. In this study we assess the potentiality of Recursive Feature Elimination (RFE) in combination with Random Forest (RF) classification in extracting the main HS and LiDAR features needed to map selected Natura 2000 grasslands along Polish lowland river valleys, in particular alluvial meadows 6440, lowland hay meadows 6510 and xeric and calcareous grasslands 6120. We developed an automated RFE-RF system capable to combine the potentials of both techniques and applied it to multiple acquisitions. Several LiDAR-based products and different Spectral Indexes (SI) were computed and used as input in the system, with the aim of shedding light on the best-to-use features. Results showed a remarkable increase in classification accuracy when LiDAR and SI products are added to the HS dataset, strengthening in particular the importance of employing LiDAR in combination with HS. Using only the 24 optimal features selection generalized over the three study areas, strongly linked to the highly heterogeneous characteristics of the habitats and landscapes investigated, it was possible to achieve rather high classification results (K around 0.7-0.77 and habitats F1 accuracy around 0.8-0.85), indicating that the selected Natura 2000 meadows and dry grasslands habitats can be automatically mapped by airborne HS and LiDAR data. Similar approaches might be considered for future monitoring activities in the context of habitats protection and conservation

Accurate estimation of body fat percentage is essential for various health and fitness applications. Traditional methods for measuring body fat, such as underwater weighing, can be costly and inconvenient. In this study, we apply machine learning techniques to predict body fat percentage using easily accessible body measurements and data. The results highlight the effectiveness of regression models in estimating body fat, with Linear Regression, Ridge Regression, and Bayesian Ridge models achieving R-squared scores of approximately 74%, 73%, and 73%, respectively. These models provide a practical and cost-effective solution for individuals and professionals seeking reliable body fat estimates.

Deep learning methods have been widely used in PolSAR image classification. To learn the polarimetric information, many deep learning methods expect to learn high-level semantic features from original PolSAR data. However, only original data cannot learn multiple scattering features and complex structures for extremely heterogeneous terrain objects. In addition, deep learning methods always cause edge confusion due to the high-level features. To overcome these shortages, we propose a double-channel CNN network combined with an edge-preserving MRF model(DCCNN-MRF) for PolSAR image classification. Firstly, to combine complex matrix data and multiple scattering features together, a double-channel convolution network(DCCNN) is developed, which consists of a Wishart-based complex matrix and multi-feature subnetworks. The Wishart-based complex matrix network can learn the statistical characteristics and channel correlation well, and the multi-feature network can learn high-level semantic features well. Then, a unified network framework is designed to fuse two kinds of features to enhance advantageous features and reduce redundant ones. Finally, an edge preserving MRF model is designed to combine with the DCCNN network. In the MRF model, a sketch map-based edge energy function is designed by defining adaptive weighted neighborhood for edge pixels. Experiments are conducted on four real PolSAR data sets with different sensors and bands. Experimental results demonstrate the effectiveness of the proposed DCCNN-MRF method.

Falls are extremely damaging to the elderly. The number of elderly who have experienced falls has increased over the years, several of the elderly stay alone or in in badly maintained elderly homes. This makes a low-cost fall detection system a necessity. There has been huge improvements in terms of IoT systems, ML algorithms. Varied data sets have been collected across the world for fall detection. These data sets have a very little in common among them, in terms of user demographics, sensors used, the ADL and Fall activities Hence in this paper we present a data set that has wide user demographics, we used various sensors – such as accelerometer, gyroscope, magnetometer and hear rate. We used wrist worn sensors to collect data. In this paper we present a detailed analysis of the data set we collected using common ML algorithms such as – Naïve Bayes (NB), K Nearest Neighbor (KNN), Logistic Regression (LR), Random Forest (RF) and Support Vector Machines (SVM). We analyzed the performance of these algorithms for variations in accuracy with respect to age, gender, height, weight and health issues and we have identified outliers by analyzing each incorrect prediction. This paper provides the complete details of the data collection methodology, The methods used for analysis and presents the results of analysis in complete detail.

The fourth Industrial Revolution, well-known as “Industry 4.0”, based on the integration of information and communication technologies, has introduced significant improvements in manufacturing. However, vision systems still experience various impracticalities in dealing with the effect of complex lighting on the systems platform. Therefore, a machine vision system for automatic identification of pen parts under varying lighting conditions at a digital learning factory is proposed. The developed vision system presents a straightforward approach by effectively minimizing the environmental lighting effect on the identification process. First, the obtained information of the designed vision framework is exported to a program, where a reduction of non-uniform illumination is achieved through the implementation of Retinex image enhancement techniques. Then, the color-based Fuzzy C-means (FCM) algorithm, including improved mark watershed segmentation, is employed for pen parts object classification. Finally, the position features of the selected pen part are reported. The process applied to a total number of 210 upper pen parts (caps) and 241 lower pen parts (tubes) images under different lighting scenarios. Results indicate that average parts identification precision for cap and tube parts is different and equals to 98.64% and 95.26%, respectively. The present methodology provides a promising scheme that can be feasibly adapted for other industrial Color-based object recognition applications.

With the rapid advancements in remote sensing technology, the spectral information from hyperspectral remote sensing images has become increasingly rich, facilitating detailed spectral analysis of the Earth's surface objects. However, this abundance of spectral data poses significant challenges in data processing, such as the curse of dimensionality leading to the “Hughes” phenomenon, "strong correlation" due to high resolution, and "non-linear characteristics" caused by varied surface reflectance rates. Therefore, dimensionality reduction of hyperspectral data has become a crucial task. This paper, grounded in manifold theory and manifold learning techniques, and considering the non-linear structures and features in hyperspectral remote sensing data, elucidates the principles and processes of dimensionality reduction in hyperspectral remote sensing images using manifold learning, with a formalized expression of the process. This article introduces spectral information divergence (SID) into the nearest neighbor graph computation of manifold learning algorithms. The principles and computational processes of nearest neighbor graph algorithms based on Euclidean distance (ED), spectral angle mapping (SAM), and SID are studied, and a comparative analysis of the dimensionality reduction effects under these three metrics in hyperspectral data is conducted. Experiments on feature extraction under different metrics were performed using the publicly available Indian Pines hyperspectral dataset. The intrinsic features obtained post-dimensionality reduction were used as inputs for classification algorithms in ground objects classification experiments, with algorithm runtime, overall accuracy, and Kappa coefficient as evaluation metrics for dimensionality reduction quality. The results demonstrate that nearest neighbor graph computation based on SAM and SID outperforms traditional ED methods; SAM-based computation has the lowest time complexity, while SID-based manifold learning yields the highest accuracy in ground objects classification. Thus, manifold learning based on SAM and SID metrics proves to be an effective method for feature extraction in hyperspectral remote sensing data, underscoring the potential of manifold learning techniques in the dimensionality reduction of hyperspectral remote sensing images.

Diabetes mellitus is a chronic disease that affects millions of people worldwide. Article focuses on detecting the presence of diabetes in patients using microarray gene data obtained from the pancreas. Handle the high-dimensional nature of the data, four different dimensionality reduction techniques, namely Bessel Function, Discrete Cosine Transform (DCT), Least Square Linear Regression (LSLR), and Artificial Algae Algorithm (AAA) are used. After reduced the data, Meta-heuristic algorithms are applied like Dragonfly Optimization Algorithm (DOA) and Elephant Herding Optimization Algorithm (EHO) for feature selection. Ten classification techniques are using to classify the data in both the format like without feature selection method and with feature selection method. The classification techniques are Non-Linear Regression (NLR), Linear Regression (LR), Gaussian Mixture Model (GMM), Expectation Maximum (EM), Bayesian Linear Discriminant Classifier (BLDC), Logistic Regression (LoR), Softmax Discriminant Classifier (SDC), Support Vector Machine (SVM) with linear kernel, Support Vector Machine (SVM) with polynomial kernel, and Support Vector Machine (SVM) with Radial Basis Function (RBF) kernel. Results showed that the AAA with SVM(RBF) achieved an accuracy of 90% without feature selection. However, when feature selection was applied, with EHO of AAA with SVM(RBF) exhibited the highest accuracy of 95.714%, followed closely by with DOA of AAA with SVM (RBF) at 94.28%.

Delay in data transmission is one of key performance indicators (KPIs) of a network. The planning and project value of delay in network management is of crucial importance for the optimal allocation of network resources and their performance focuses. To create optimal solutions, predictive models, which are currently most often based on machine learning (ML), are used. This paper aims to investigate the training, testing and selection of the best predictive delay model for a VoIP service in an Long Term Evolution (LTE) network using three ML techniques - Neural Networks (NN), Support Vector Machines (SVM) and k-Nearest Neighbors (k-NN). The space of model input variables is optimized by dimensionality reduction techniques: RReliefF algorithm, Backward selection via the recursive feature elimination algorithm and the Pareto 80/20 rule. A three-segment road in the geo-space between the cities of Banja Luka (BL) and Doboj (Db) in the Republic of Srpska (RS), Bosnia and Herzegovina (BiH), covered by the cellular network (LTE) of the M:tel BL operator was chosen for the case study. The results show that, in all three optimization approaches, the k-NN model is selected as the best solution. For the RReliefF optimization algorithm, the best model has 6 inputs and minimum relative error (RE), RE=0.109; for the Backward selection via the recursive feature elimination algorithm, the best model has 4 inputs and RE=0.041; and for the Pareto 80/20 rule, the best model has 11 inputs and RE= 0.049. The comparative analysis of the results concludes that according to observed criteria for the selection of the final model, the best solution is an approach to optimizing the number of predictors based on the Backward selection via the recursive feature elimination algorithm.

Deep learning classification is the state-of-the-art of machine learning approach. Earlier work proves that the deep convolutional neural network has successfully and brilliantly in different applications such as images or video data. Recognizing and clarifying the remote sensing aspect of the earth's surface and exploit land cover and land use (LCLU). First, this article summarized the remote sensing emerging application and challenges for deep learning methods. Second, we propose four approaches to learn efficient and effective CNNs to transfer image representation on the ImageNet dataset to recognize LCLU datasets. We use VGG16, Inception-ResNet-V2, Inception-V3, and DenseNet201 models to extract features from the EACC dataset. We use pre-trained CNNs on ImageNet to extract features. For feature selection we proposed principal component analysis (PCA) to improve accuracy and speed up the model. We train our model by multi-layer perceptron (MLP) as a classifier. Lastly, we apply the multi-granularity encoding ensemble model. We achieve an overall accuracy of 92.3% for the nine-class classification problem. This work will help remote sensing scientists understand deep learning tools and apply them in large-scale remote sensing challenges

Pain is a multifaceted multisystem disorder that adversely affects neuro-psychological processes. This study compares the effectiveness of central-stimulation (tDCS) and peripheral-stimulation (TENS) in pain-inhibition during a cognitive-task in healthy volunteers and to observe potential neuro-cognitive improvements. Healthy eighty volunteers went through a complete experimental protocol comprising pain-induction (CPT), administration of tDCS/TENS, EEG-data acquisition, and cognitive assessments. The protocol for this study is categorized into 04-groups: G1(Control), G2(TENS), G3(Anodal-tDCS), and G4(Cathodal-tDCS). Paired t-tests (p

Cooling fans are one of the critical components of air-forced (AF) dry-type transformers for regulating internal temperatures. Therefore, effective malfunction detection is crucial to maintain the transformer temperature within an acceptable range and prevent overheating. Regular maintenance occurs periodically and issues with cooling fans may arise between maintenance periods, leading to prolonged operation under malfunctioning conditions and potential failures. In addition, utilities typically have online information about whether a fan works or not without providing information about cooling fan malfunctioning circumstances. To address these challenges, this study proposes learning-based online monitoring techniques to detect malfunctions in AF transformer cooling fans. Random forests (RFs) and convolutional neural networks (CNNs) are developed to classify the audio signals from cooling fans into normal and malfunctioning classes. Unlike RFs, which require separate feature extraction, CNNs are trained based on spectrogram images derived from audio signals. Thus, various time-frequency techniques are utilized for feature extraction in RFs. Besides, multiple data augmentation techniques are employed to enhance the dataset size and diversity. Algorithmic performance is optimized through hyperparameter tuning and classifier threshold adjustment. Simulations reveal that CNNs outperform RFs, whereas the latter provides superior interpretability of acoustic features compared to the former.

Panoramic and periapical radiograph tools help dentists diagnose the most common dental diseases. Generally, dentists identify dental caries manually by inspecting X-ray images. However, due to their heavy workload, or poor image quality, dentists may sometimes overlook some unnoticeable dental caries, which may ultimately hinder the patient treatment. The purpose of this study was to develop an algorithm that classifies the teeth X-Ray images into three categories of “Normal”, “Caries”, and “Filled”. Our study used a dataset of 116 patients and 3712 single teeth images for training, validation and testing. Images were pre-processed using a sharpening filter and an intensity color map. We used a pre-trained transfer learning model, the NASNetMobile, which served as the feature extractor and the Convolutional Neural Network (CNN) model served as the classifier. The training dataset had a “Recall” of 0.92, 0.90 and 0.91 for “Normal”, “Caries” and “Filled” respectively and the test dataset had a “Recall” of 0.86, 0.81 and 0.85 for “Normal”, “Caries” and “Filled” respectively. The classification of the teeth X-Rays was successful and can be valuable for dentist as the artificial intelligence algorithm can serve as a decision support tool to aid dentists when they need to diagnose dental treatment.

Longitudinal image registration of pulmonary computed tomography (PCT) images may serve as an essential tool for investigating the relationship between radiation dose distribution and the occurrence and phenotype of radiation-induced lung disease (RILD). Although numerous longitudinal registration algorithms have been developed for PCT, most similarity-based approaches are not suitable for PCT involving RILD due to the complex tissue variation between two PCT images. Moreover, conventional feature-based approaches might fail to find a sufficient number of matched pairs of feature points due to the disparate lung deformation caused by breathing and RILD. To overcome the challenges resulting from RILD, component structure coherence point drift (CSCPD) was proposed to establish a deformation model by decomposing the chest into several components and matching them with individual parameters based on coherence point drift (CPD). Moreover, a regional vascular point matching (RVPM) algorithm was proposed to generate a vascular subtree and to substantially increase the number of corresponding pairs between two images. Eventually, the components were recomposed and aligned by a thin plate spline algorithm. A performance assessment on 15 pairs of PCT images of patients with RILD yielded recall and precision values of 0.85 and 0.89 for RVPM, respectively. Moreover, the target registration error of CSCPD with RVPM (2.3 ± 1.79) was significantly better than that of conventional CPD with RVPM (2.95 ± 1.89) and conventional CPD (5.04 ± 2.87). Therefore, the proposed registration system is robust enough to address the disparate deformation of lungs with RILD, and it improves registration accuracy within the parenchyma.

Satellite communication (Satcom) is an artificial geostationary satellite that facilitates a wide range of telecommunications. Considering its quality of service (QoS) and security is crucial in government/military applications. The most challenging situation for efficient Satcom is radio frequency interference (RFI) environment. Thus, it is necessary to ensure that transmissions are incorruptible or at least sense the quality of its spectrum. This paper presents a new method to recognize received signal characteristics using a hierarchical classification in a multi-layer perceptron neural network. We consider signal modulation and the type of RFI as the characteristics of a real-time video stream transmitted in the direct broadcast satellite. Four different modulation types are investigated in this study. Moreover, the combination of the communication signal with various kinds of interference and their effects on the classification method widely have been analyzed. Besides, two robust feature selection techniques have been developed to reduce the data-set dimensional, which leads to optimizing the classification process. The results show that the Genetic Algorithm (GA) slightly outperforms Principal Component Analysis (PCA) for feature selection. Furthermore, the robustness of the proposed techniques is assessed to detect unknown signals at different signal to noise ratios.

Alzheimer's disease (AD) is a significant regular type of dementia that causes damage in brain cells. Early detection of AD acting as an essential role in global health care due to misdiagnosis and sharing many clinical sets with other types of dementia, and costly monitoring the progression of the disease over time by magnetic reasoning imaging (MRI) with consideration of human error in manual reading. Our proposed model, in the first stage, apply the medical dataset to a composite hybrid feature selection (CHFS) to extract new features for select the best features to improve the performance of the classification process due to eliminating obscures features. In the second stage, we applied a dataset to a stacked hybrid classification system to combine Jrip and random forest classifiers with six model evaluations as meta-classifier individually to improve the prediction of clinical diagnosis. All experiments conducted on a laptop with an Intel Core i7- 8750H CPU at 2.2 GHz and 16 G of ram running on windows 10 (64 bits). The dataset evaluated using an explorer set of weka data mining software for the analysis purpose. The experimental show that the proposed model of ‏(CHFS) feature extraction ‏performs better than principal component analysis (PCA), and lead to effectively reduced the false-negative rate with a relatively high overall accuracy with support vector machine (SVM) as meta-classifier of 96.50% compared to 68.83% which is considerably better than the previous state-of-the-art result. The receiver operating characteristic (ROC) curve was equal to 95.5%. Also, the experiment on MRI images Kaggle dataset of CNN classification process with 80.21% accuracy result. The results of the proposed model show an accurate classify Alzheimer's clinical samples against MRI neuroimaging for diagnoses AD at a low cost.

Electricity demand forecasting has been a real challenge for power system scheduling in the different levels of the energy sectors. Various computational intelligence techniques and methodologies have been employed in the electricity market for load forecasting; although, scant evidence is available about the feasibility of each of these methods considering the type of data and other potential factors. This work introduces several scientific, technical rationale behind intelligent forecasting methods, based on the work of previous researchers in the field of energy. The fundamental benefits and main drawbacks of the aforementioned methods are discussed in order to depict the efficiency of each approach in various situations. In the end, a proposed hybrid strategy is represented.

This study employs the reflection symmetry decomposition (RSD) method to extract polarization scattering features from ground object images, aiming to determine the optimal data input scheme for deep learning networks in polarimetric synthetic aperture radar classification. Eight distinct polarizing feature combinations are designed, and the classification accuracy of various approaches is evaluated using the classic convolutional neural networks(CNNs) AlexNet and VGG16. The findings reveal that the commonly employed 6-parameter input scheme, favored by many researchers, lacks the comprehensive utilization of polarization information and warrants attention. Intriguingly, leveraging the complete 9-parameter input scheme based on the polarization coherence matrix results in improved classification accuracy. Furthermore, the input scheme incorporating all 21 parameters from the RSD and polarization coherence matrix notably enhances overall accuracy and the Kappa coefficient compared to the other 7 schemes. This comprehensive approach maximizes the utilization of polarization scattering information from ground objects, emerging as the most effective CNN input data scheme in this study. Additionally, the classification performance using the second and third component total power values (P2 and P3) from the RSD surpasses the approach utilizing surface scattering power value (PS) and secondary scattering power value (PD) from the same decomposition.

Reliable prediction of infectious disease is an essential need for public health organizations to minimize or prevent the disease's spread. With the increase of data growth in the healthcare sector, accurate analysis of such data helps for early disease detection and better patient care. With the availability of huge data, it is a great deal for predicting and handling an epidemic occurrence. To control the epidemic disease, a new Artificial Intelligence called Manhattan Hessian Linear Feature Embedding Based Tucker Congruence Deep Convolutional Network (MHLFE-TCDCN) is introduced with higher accuracy and minimum time consumption. The MIoT device is used to collect the data from the patient body. The proposed MHLFE-TCDCN includes two major processes namely feature selection and classification with multiple layers such as input, two hidden layers, and one output layer. First, the feature selection process is performed using the Manhattan Hessian Locally Linear Embedding technique in the first hidden layer to minimize the dimensionality and time complexity. After selecting the feature, the classification is performed using the Tucker coefficient of congruence regression. The Tucker coefficient of congruence measures the similarity between the training and testing disease data. A positive similarity level is used to accurately identify the disease at the output layer based on the similarity measure. Experimental assessment is carried out with various parameters such as accuracy, precision, recall, F-measure, and computational time concerning several numbers of patient data. The quantitative results and discussion that the proposed MHLFE-TCDCN technique achieves higher accuracy with minimal computation time as compared to the conventional methods.

Human-to-human communication via the computer is mainly done using a keyboard or microphone. In the field of Virtual Reality (VR), where the most immersive experience possible is desired, the use of a keyboard contradicts this goal, while the use of a microphone is not always desirable (e.g. silent commands during task force training) or simply not possible (e.g. if the user has a hearing loss). Data gloves help to increase immersion within the VR as they correspond to our natural interaction. At the same time, they offer the possibility to accurately capture hand shapes, such as those used in non-verbal communication (e.g. thumbs up, okay gesture, ...) and in sign language. In this paper, we present a hand shape recognition system using Manus Prime X data gloves, including data acquisition, data preprocessing, and data classification to enable nonverbal communication within VR. We investigate the impact on accuracy and classification time of using an Outlier Detection and a Feature Selection approach in our data preprocessing. To obtain a more generalized approach, we also studied the impact of artificial Data Augmentation, i.e., we create new artificial data from the recorded and filtered data to augment the training dataset. With our approach, 56 different hand shapes could be distinguished with an accuracy of up to 93.28%. With a reduced number of 27 hand shapes, an accuracy of up to 95.55% could be achieved. Voting Meta-Classifier (VL2) has proven to be the most accurate, albeit slowest, classifier. A good alternative is Random Forest (RF), which was even able to achieve better accuracy values in a few cases and was generally somewhat faster. Outlier Detection has proven to be a effective approach, especially in improving classification time. Overall, we have shown that our hand shape recognition system using data gloves is suitable for communication within VR.

Chatbots have gained widespread popularity for their task automation capabilities and consistent availability in various domains, including education. However, their ability to adapt to the continuously evolving and dynamic nature of knowledge is limited. This research investigates the implementation of an internet wizard to enhance the knowledge base of an open-domain question-answering chatbot. The proposed approach leverages search engines, particularly Google, and its features, including feature snippets, knowledge graph, and organic search, in conjunction with data science and natural language models. This mechanism empowers the chatbot to dynamically access the extensive and up-to-date knowledge available on the web, enabling the provision of real-time and pertinent answers to user queries sourced from web documents. A pilot study in a higher education context evaluated the chatbot's mechanism and features, confirming its proficiency in generating responses across a broad range of educational and non-educational topics. Positive feedback and high user satisfaction validate these findings. Notably, the chatbot's dynamic feature of retrieving related or follow-up questions from search engines significantly enhances student engagement and facilitates exploration of supplementary information beyond the curriculum.

Maintaining a healthy cyber society is a big challenge due to the users’ freedom of expression and behaving. It can be solved by monitoring and analyzing the users’ behavior and taking proper actions towards them. This research aims to present a platform that monitors the public content on Twitter by extracting tweet data. After maintaining the data, the users’ interactions are analyzed using Graph Analysis methods. Then the users’ behavioral patterns are analyzed by applying Metadata Analysis, in which the timeline of each profile is obtained; also, the time-series behavioral features of users are investigated. Then in the Abnormal Behavior Detection Filtering component, the interesting profiles are selected for further examinations. Finally, in the Contextual Analysis component, the contents will be analyzed using natural language processing techniques; A binary text classification model (SVM + TF-IDF with 88.89% accuracy) for detecting if the tweet is related to crime or not. Then, a sentiment analysis method is applied to the crime-related tweets to perform aspect-based sentiment analysis (DistilBERT + FFNN with 80% accuracy); because sharing positive opinions about a crime-related topic can threaten society. This platform aims to provide the end-user (Police) suggestions to control hate speech or terrorist propaganda.

Table detection is a preliminary step in extracting reliable information from tables in scanned document images. We present CasTabDetectoRS, a novel end-to-end trainable table detection framework that operates on Cascade Mask R-CNN, including Recursive Feature Pyramid network and Switchable Atrous Convolution in the existing backbone architecture. By utilizing a comparatively lightweight backbone of ResNet-50, this paper demonstrates that superior results are attainable without relying on pre and post-processing methods, heavier backbone networks (ResNet-101, ResNeXt-152), and memory-intensive deformable convolutions. We evaluate the proposed approach on five different publicly available table detection datasets. Our CasTabDetectoRS outperforms the previous state-of-the-art results on four datasets (ICDAR-19, TableBank, UNLV, and Marmot) and accomplishes comparable results on ICDAR-17 POD. Upon comparing with previous state-of-the-art results, we obtain a significant relative error reduction of 56.36%, 20%, 4.5%, and 3.5% on the datasets of ICDAR-19, TableBank, UNLV, and Marmot, respectively. Furthermore, this paper sets a new benchmark by performing exhaustive cross-datasets evaluations to exhibit the generalization capabilities of the proposed method.

An effective process monitoring strategy is a requirement for meeting the challenges posed by increasingly complex products and manufacturing processes. To address these needs, this study investigates a comprehensive scheme based on classical machine learning methods, deep learning algorithms, and feature extraction and selection techniques. In a first step, a novel deep learning architecture based on convolutional neural networks (CNN) and gated recurrent units (GRU) is introduced to predict the local weld quality based on mid-wave infrared (MWIR) and near-infrared (NIR) image data. The developed technology is used to discover critical welding defects including lack of fusion (false friends), sagging and lack of penetration, and geometric deviations of the weld seam. Additional work is conducted to investigate the significance of various geometrical, statistical, and spatio-temporal features extracted from the keyhole and weld pool regions. Furthermore, the performance of the proposed deep learning architecture is compared to that of classical supervised machine learning algorithms, such as multi-layer perceptron (MLP), logistic regression (LogReg), support vector machines (SVM), decision trees (DT), random forest (RF) and k-Nearest Neighbors (kNN). Optimal hyperparameters for each algorithm are determined by an extensive grid search. Ultimately, the three best classification models are combined into an ensemble classifier that yields the highest detection rates and achieves the most robust estimation of welding defects among all classifiers studied, which is validated on previously unknown welding trials.

Measure While Drilling (MWD) refers to a comprehensive array of sensors employed to gather performance data throughout the process of rock drilling in mining blast holes. Multiple MWD metrics are collected by researchers depending on the setup of MWD sensors. Trends in MWD data can be correlated with pre-excavation subsurface conditions. The low-cost, extensive MWD data acquisition resolution of blast holes compared to expensive and sparsely collected exploration drill holes make the former one a desirable method for characterizing pre-excavation subsurface conditions. Nevertheless, the application of MWD technology in open pit mining is constrained by a substantial amount of data that requiring manual analysis within a short time. To address this limitation, computerized data acquisition and interpretation of MWD variables has been used to broadly determine open pit mining lithological boundaries. The results of artificial intelligence algorithms, such as Neural Networks, and Gaussian Processes, to recognize subsurface conditions, such as rock type, from MWD data have consistently returned >90% prediction accuracy. However, methods of evaluating the importance of each MWD feature, such as Principal Component Analysis, has not been optimally used. This review focuses on the progression of intelligent MWD analysis using Machine Learning methods in open-pit mining, to determine the geotechnical, geological, and geochemical subsurface characteristics before open-pit mining excavation.

This study explores the integration of Artificial Intelligence (AI) and collaborative robotics in industrial surface finishing, focusing on feature detection on object reflective surfaces using neural networks in computationally constrained environments. Central to this investigation is the utilization of cameras considered as sensors that can capture detailed images of reflective surfaces. These images are then analyzed by a custom neural network, demonstrating the feasibility of feature detection with non-powerful computers. The public dataset for recognizing light reflection defects, available in the SPADD repository, supports this approach. Employing open-source tools like Darknet YOLOv3 and Yolo\_mark, this method proves particularly advantageous for small and medium-sized enterprises (SMEs) due to its low cost and maintenance requirements. This research highlights the challenges of AI and collaborative robotics in industrial applications, especially in adapting to varying conditions and the need for continuous training with new data coming from several sensors. Looking ahead, plans are in place to integrate this system with cobot-assisted polishing tasks, using cameras to enhance manufacturing efficiency and quality. This work contributes to the broader understanding of practical applications of AI in industrial automation, surface finishing processes, and the effective use of sensor technology.

Densely urbanized areas, with a low percentage of green vegetation, are highly exposed to Heat Waves (HW) which nowadays are increasing in terms of frequency and intensity also in the middle-latitude regions, due to ongoing Climate Change (CC). Their negative effects may combine with those of the UHI (Urban Heat Island), a local phenomenon where air temperatures in the compact built up cores of towns increase more than those in the surrounding rural areas, with significant impact on the quality of urban environment, on citizens health and energy consumption and transport, as it has occurred in the summer of 2003 on France and Italian central-northern areas. In this context this work aims at designing and developing a methodology based on aero-spatial remote sensing (EO) at medium-high resolution and most recent GIS techniques, for the extensive characterization of the urban fabric response to these climatic impacts related to the temperature within the general framework of supporting local and national strategies and policies of adaptation to CC. Due to its extension and variety of built-up typologies, the municipality of Rome was selected as test area for the methodology development and validation. First of all, we started by operating through photointerpretation of cartography at detailed scale (CTR 1: 5000) on a reference area consisting of a transect of about 5x20 km, extending from the downtown to the suburbs and including all the built-up classes of interest. The reference built-up vulnerability classes found inside the transect were then exploited as training areas to classify the entire territory of Rome municipality. To this end, the satellite EO HR (High Resolution) multispectral data, provided by the Landsat sensors were used within a on purpose developed "supervised" classification procedure, based on data mining and “object-classification” techniques. The classification results were then exploited for implementing a calibration method, based on a typical UHI temperature distribution, derived from MODIS satellite sensor LST (Land Surface Temperature) data of the summer 2003, to obtain an analytical expression of the vulnerability model, previously introduced on a semi-empirical basis.