Website defacement is an illegal electronic act of changing a website. In this paper, robust machine learning classifiers’ capabilities were exploited to select the best input feature set for evaluating a website’s defacement risk. Zone-H, a private organization, offered us a defacement mining dataset. A sample of 93644 datapoints was concisely pre-processed and used for modelling purposes. Considering multidimensional features as input, reason and hackmode variables were chosen as outputs. Massive machine learning models were examined; however, decision tree (DT), k-nearest neighbour (k-NN), and random forest (RF) were the most powerful algorithms used to predict the target model. The input variables 'domain', 'system', 'web_server','redefacement', 'type', 'def_grade', and 'reason/hackmode' were tested and used to shape the final model. Using the cross-validation (CV) technique, the model’s key performance factors were calculated and reported. After calculating the average scores for the hyperbolic metrics (i.e., max-depth, min-sample-leaf, weight, max-features, and CV), both targets were evaluated, and the learning algorithms were ranked as RF, DT, and k-NN. The reason and hackmode variables were thoroughly analysed. The average score accuracies for the reason and hackmode targets were 0.85 and 0.585, respectively. The results showed a significant development in terms of modelling and optimizing website defacement risk. The study also successfully addresses the main cybersecurity concerns, in particular website defacement.

Motion related human activity recognition using wearable sensors can potentially enable various useful daily applications. So far, most studies view it as a stand-alone mathematical classification problem without considering the physical nature of human motions. Consequently, they suffer from data dependencies and encounter the dimension disaster problem and the over-fitting issue, and their models are never human-readable. In this study, we start from a deep analysis on natural physical properties of human motions, and then propose a useful feature selection method to quantify each feature's classification contribution capability. On one hand, the "dimension disaster" problem can be avoid to some extent, due to the affined dimension of key features; On the other hand, over-fitting issue can be depressed since the knowledge implied in human motions are nearly invariant, which compensates the possible data inadequacy. The experiment results indicate that the proposed method performs superior to those adopted in related works, such as decision tree, k-NN, SVM, neural networks.

The characteristics of the Sentinel-2 mission with a decametric resolution and frequent acquisitions allow to improve the identification of crops. The majority of the studies on crop classification using RS were targeted at herbaceous and gramineous crop classes while fewer results were obtained on woody crops which present a strong variability in management practices that make their identification difficult. Thus, this study aimed to propose a rapid, accurate, and cost-effective analytical approach for the delineation of fruit orchards (OC), vineyards (VY), and olive groves (OL) in the Mediterranean (Southern France) considering two locations. A classification based on phenology metrics (PM) de-rived from temporal Sentinel-2 time series was developed to perform the classification. The PM were computed by fitting a double logistic model on temporal profiles of vegeta-tion indices to delineate OC, VY, and a DC class gathering all remaining surfaces. The generated PM were introduced in a random forest (RF) algorithm to identify woody crops across the two sites. The method was tested on different vegetation indices, the best results being obtained with the leaf area index (LAI). To delineate OL in the DC class, the tem-poral features of the green chlorophyll vegetation index (GCVI) were found to be the most appropriated with a typical drop of the signal during the mid-season (DOY 150-250). As a final result, we obtained an overall accuracy ranging from 89-96% and Kappa of 0.86-0.95 by considering each study site and year (2016-2021), separately. This accuracy is much better than applying the RF algorithm on the LAI times series, which led to a Kappa rang-ing between 0.3 and 0.52 and demonstrates the interest of using phenological traits rather than the raw time series of the RS data. The method can be well reproduced from one year to another. Moreover, it is possible to apply the classification model of a given year to an-other, keeping good accuracy. This is an interesting feature to reduce the burden of col-lecting ground truth information. On the contrary, the use of a classification model cali-brated in one site and applied to another led to a strong degradation of the classification accuracy. Woody crop phenology is dependent on site climatic conditions as well as the cultivar and management practices that can differ from one site to another.

The dynamics of surface and sub-surface water events can lead to slope instability resulting in anomalies such as slough slides on earthen levees. Early detection of these anomalies by a remote sensing approach could save time versus direct assessment. We have implemented a supervised Mahalanobis distance classification algorithm for the detection of slough slides on levees using complex polarimetric Synthetic Aperture Radar (polSAR) data. The classifier output was followed by a spatial majority filter post-processing step which improved the accuracy. The effectiveness of the algorithm is demonstrated using fully quad-polarimetric L-band Synthetic Aperture Radar (SAR) imagery from the NASA Jet Propulsion Laboratory’s (JPL’s) Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR). The study area is a section of the lower Mississippi River valley in the southern USA. Slide detection accuracy of up to 98 percent was achieved, although the number of available slides examples was small.

In this paper we describe a method which combines sentiment analysis with machine learning techniques and/or multivariate statistical analysis. By applying this methodology it is possible to classify a collection of texts into two or more groups or clusters. On the basis of a number of previously defined clusters, the novelty of the outlined approach is the use of the sentiment analysis results as input to the machine learning model or multivariate statistical analysis. Once the classifier has been obtained, we can assign a given text into one of the pre-established clusters. The groups or clusters can represent different time periods, classes of texts transcribed from different conversations, etc. The method is illustrated through an example taken from one of the two studies in which we have applied this methodology. In one of the studies, the method was used to classify press news of a volcanic eruption, while in the other study it was used to classify the conversations recorded between a chatbot with different kinds of speakers (humans or chatbots). This last study was the seminal work in which we introduced this methodology.

Vehicle identification is an important task in traffic monitoring because it allows for efficient inference and provides a cause for action. Vehicle classification via deep learning and other approaches such as segmentation is a critical tool for re-identification. In this paper, instance segmentation is used to identify vehicle makes with license plate detection, allowing for better unique vehicle recognition for re-identification. A dataset is annotated and modified, for example, by segmenting it with polygonal bounding boxes that capture the vehicle's unique frontal features. In addition, license plate localization is performed. The results showed improved classification as well as a high mAP for the dataset when compared to previous approaches based on CNN and deformed CNN. Furthermore, a deep residual network and fully connected layer-based classification were utilized as the backbone for feature representation. Instance segmentation detects objects by segmenting and classifying regions of interest. The imbalance in the dataset is resolved using a mosaic-tiled approach, which produces greater precision than other approaches.

Accurate diagnosis for the 400 million people with rare diseases is critical for healthcare decisions, prognosis, understanding disease mechanisms, and identification of treatments. Despite advances in genome sequencing, barriers such as high interpretation costs, diagnostic expertise, throughput associated delays, and uncertain variant classifications persist, with demand exceeding capacity. Many variant classification methods focus narrowly on specific consequences, leading to the use of complex integrative pipelines that often overlook transcript variability and lack prediction transparency. To overcome these limitations, we introduce DITTO. This transparent, transcript-aware machine-learning method demonstrates superior overall performance in accuracy, recall, and precision when compared to existing tools. DITTO is publicly available at https://github.com/uab-cgds-worthey/DITTO

This paper focuses on the crucial role that remote sensing plays in divining land features. Data that is collected distantly provides information in spectral, spatial, temporal and radiometric domains, with each domain having the specific resolution to information collected. Diverse sectors such as hydrology, geology, agriculture, land cover mapping, forestry, urban development and planning, oceanography and others are known to use and rely on information that is gathered remotely from different sensors. In the present study, IRS LISS IV Multi-spectral data is used for land cover mapping. It is known, however, that the task of classifying high-resolution imagery of land cover through manual digitizing consumes time and is way too costly. Therefore, this paper proposes accomplishing classifications by way of enforcing algorithms in computers. These classifications fall in three classes: supervised, unsupervised, and object-based classification. In the case of supervised classification, two approaches are relied upon for land cover classification of high-resolution LISS-IV multispectral image. These approaches are Maximum Likelihood and Support Vector Machine (SVM). Finally, the paper proposes a step-by-step procedure for optical image classification methodology. This paper concludes that in optical data classification, SVM classification gives a better result than the ML classification technique.

Neutral facial expression recognition is of great importance in various domains and applications. This study introduces a data-centric approach for neutral facial expression recognition, presenting a comprehensive study that explores different methodologies, techniques, and challenges in the field to foster a deeper understanding. The results show that data augmentation plays a crucial role in improving dataset performance. Additionally, the study investigates different model architectures and training techniques to identify the most effective approach, with the InceptionV3 model achieving the highest accuracy of 72%. Furthermore, the research examines the influence of preprocessing methods on the performance of both InceptionV3 and a simplified CNN model. Interestingly, the results indicate that preprocessing techniques positively affect the performance of the simpler CNN model but negatively impact the InceptionV3 model. The implemented system, used to evaluate the findings, demonstrates promising results, correctly classifying 77% of neutral expressions. However, there are still areas for improvement. Creating a specialized dataset that includes both neutral and non-neutral expressions would greatly enhance the accuracy of the system. By addressing limitations and implementing suggested improvements, neutral facial expression recognition can be significantly enhanced, leading to more effective and accurate results.

Many metrics exist for the evaluation of binary classifiers, all with their particular advantages and shortcomings. Recently an “Efficiency Index” for the evaluation of classifiers has been proposed, based on the consistency, or matching, and contradiction, or mismatching, of outcomes. This metric and its confidence intervals are easy to calculate from base data in a 2x2 contingency table, and values can be qualitatively and semi-quantitatively categorised. For medical tests, in which context the Efficiency Index was originally proposed, it facilitates communication of risk (of correct diagnosis versus misdiagnosis) to both clinicians and patients. Variants of the efficiency index (balanced, unbiased) which take into account disease prevalence and test cut-offs have also been described. The objectives of the current paper were firstly to extend the EI construct to other formulations (balanced level, quality) and secondly to explore the utility of EI and all four of its variants when applied to the dataset of a large prospective test accuracy study of a cognitive screening instrument. This showed that the balanced level, quality, and unbiased formulations of EI are more stringent measures.

Few-shot classification is challenging since the goal is to classify unlabeled samples with very few labeled samples provided. It has been shown that cross attention helps generate more discriminative features for few-shot learning. This paper extends the idea and proposes two cross attention modules, namely the cross scaled attention (CSA) and the cross aligned attention (CAA). Specifically, CSA scales different feature maps to make them better matched, and CAA adopts the principal component analysis to further align features from different images. Experiments showed that both CSA and CAA achieve consistent improvements over state-of-the-art methods on four widely used few-shot classification benchmark datasets, miniImageNet, tieredImageNet, CIFAR-FS, and CUB-200-2011, while CSA is slightly faster and CAA achieves higher accuracies.

Over the last decade, the prevalence of health issues has increased by approximately 29.1%, putting a substantial strain on healthcare services. This has accelerated the integration of machine learning in healthcare, particularly following the COVID-19 pandemic. The utilization of machine learning in healthcare has grown significantly, however many present approaches are unsuitable for real-world implementation due to high memory footprints and lack of interpretability. We introduce DeClEx, a pipeline designed to address these issues. DeClEx ensures that data mirrors real-world settings by incorporating gaussian noise and blur and employing autoencoders to learn intermediate feature representations. Subsequently, our convolutional neural network, paired with spatial attention, provides comparable accuracy to state of the art pre-trained models while achieving threefold improvement in training speed. Furthermore, we provide interpretable results using explainable AI techniques. We integrate denoising and deblurring, classification and explainability in a single pipeline called DeClEx.

Lately, the Critical Pathway(CP) of Electronic Medical Record(EMR) is used to the guideline for a treatment in the public hospital. We propose a healthcare promotion service using disease pattern with lifestyle risk factors. We classify a medical historical patient data with disease codes with lifestyle risk factors (hypertension, diabetes, smoking, overweight, excessive alcohol intake, and low physical activity) to make the lifestyle risk factors through the classification. We finally make the clusters of disease code with lifestyle risk factors using the medical historical data based on EMR's electronic discharge summary data. As the result of that, we do a healthcare recommending service based on the disease pattern with lifestyle risk. We can build a medical help desk of a public hospital to support people as we check into the public hospital; how to get the procedure of curing, the desired curing clinical method for the healthcare promotion service by each disease code, and how to be better our healthcare. We evaluate the performance of the proposed system by experimenting with the datasets collected at the medical center to measure performance and report some experimental results.

This paper presents a script that classify spatial patterns of residential urban growth using a morpho-structural approach. The script performs a combination of variography analysis and morphological closings over buildings possessing a residential function in 2002 and 2017 within a region located in southern France named Centre-Var. The different bounding regions then allow classifying new residential buildings into different categories according to their degrees of clustering/scattering and to their locations regarding existing urban areas. Preliminary results show that this protocol is able to provide useful insights regarding the degree of contribution of each new residential building to different patterns of urban growth (clustered infill, scattered infill, clustered edge-expansion, scattered edge-expansion, clustered leapfrog and scattered leapfrog). Open-access to the script and to the test region data is provided.

This paper proposes an ARIMA approach to battery health forecasting with accuracy improvement by K shape-based clustered predictors. The health prediction of the battery pack is an important function of a battery management system in data centers. Accurate forecasting of battery life turns out to be very difficult without failure data to train a good forecasting model in real life. The conventional ARIMA model is compared with total and clustered predictors for battery health forecasting. Results show that the forecasting accuracy of the ARIMA model significantly improved by utilizing the results of the clustered predictors for 40 batteries in a real data center. One year of actual historical data of 40 batteries of large scale datacenter is presented to validate the effectiveness of the proposed methodology.

Obtaining classification confidence at the pixel level is a challenging task for accuracy assessment in remote sensing image classification. Among the various methods for estimating classification confidence at the pixel level, interpolation-based methods have drawn special attention in the literature. Even though they have been widely recognized in the literature, their usefulness has not been rigorously evaluated. This paper conducts a comprehensive evaluation of three interpolation-based methods: local error matrix method, bootstrap method, and geostatistical method. We applied each of the three methods to three representative datasets with different spatial resolutions, spectral bands, and the number of classes. We then derive the estimated classification confidence and true classification confidence and compared the results with each other using both exploratory data analysis (bi-histogram) and statistical analysis (Willmott's d and Binned classification quality). The results indicate that the three interpolation methods provide some interesting insights on various aspects of estimating per-pixel classification confidence. Unfortunately, the interpolation assumes that classification confidence is smooth across the space, which is usually not true in practice. In other words, interpolation-based methods have limited practical use.

Superpixels are a representation of still images as pixel grids because of their more meaningful information compared with atomic pixels. However, their usefulness for video classification has been given little attention. In this paper, rather than using spatial RGB values as low-level features, we use optical flows mapped into hue-saturation-value (HSV) space to capture rich motion features over time. We introduce motion superpixels, which are superpixels generated from flow fields. After mapping flow fields into HSV space, independent superpixels are formed by iteration of seeded regions. Every grid of a motion superpixel is tracked over time using nearest neighbors in the histogram of flow (HOF) for consecutive flow fields. To define the temporal representation, the evolution of three features within the superpixel region, namely the HOF, HOG, and the center of superpixel mass are used as descriptors. The bag of features algorithm is used to quantify final features, and generalized histogram-kernel support vector machines are used as learning algorithms. We evaluate the proposed superpixel tracking on first-person videos and action sports videos.

Classification algorithms are very widely used algorithms for the study of various categories of data located in multiple databases that have real-world implementations. The main purpose of this research work is to identify the efficiency of classification algorithms in the study of breast cancer analysis. Mortality rate of women increases due to frequent cases of breast cancer. The conventional method of diagnosing breast cancer is time consuming and hence research works are being carried out in multiple dimensions to address this issue. In this research work, Google colab, an excellent environment for Python coders, is used as a tool to implement machine learning algorithms for predicting the type of cancer. The performance of machine learning algorithms is analyzed based on the accuracy obtained from various classification models such as logistic regression, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Naïve Bayes, Decision Tree and Random forest. Experiments show that these classifiers work well for the classification of breast cancers with accuracy>90% and the logistic regression stood top with an accuracy of 98.5%. Also implementation using Google colab made the task very easier without spending hours of installation of environment and supporting libraries which we used to do earlier.

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.

Scene classification plays an important role in the intelligent processing of high-resolution satellite (HRS) remotely sensed image. In HRS image classification, multiple features, e.g. shape, color, and texture features, are employed to represent scenes from different perspectives. Accordingly, effective integration of multiple features always results in better performance compared to methods based on a single feature in the interpretation of HRS image. In this paper, we introduce a multi-task joint sparse and low-rank representation model to combine the strength of multiple features for HRS image interpretation. Specifically, a multi-task learning formulation is applied to simultaneously consider sparse and low-rank structure across multiple tasks. The proposed model is optimized as a non-smooth convex optimization problem using an accelerated proximal gradient method. Experiments on two public scene classification datasets demonstrate that the proposed method achieves remarkable performance and improves upon the state-of-art methods in respective applications.

Memristive spiking neural networks are a promising emerging technology in the field of deep learning. These models can be implemented using neuromorphic hardware and therefore offer low power consumption and low latency, crucial to edge-computing applications. These systems, however, pose several challenges, including on-chip training and connectivity reduction. The latter is essential to ease the manufacturing complexity of the system. On-chip training can be realized using synaptic plasticity enabled by memristors. In this work, we compare two methods of connectivity reduction applicable to memristive spiking networks: an ensemble-based approach and a probabilistic sparse connectivity approach. We evaluate both of these methods in conjunction with a three-layer spiking neural network on the handwritten and spoken digits classification tasks using two memristive plasticity models and a classical time-dependent plasticity rule. On the handwritten digits recognition task, both methods achieve the F1-score of 0.89–0.93, and yield the 0.80–0.96 F1-score on the spoken digits recognition task.

The objectives of this paper are to investigate the tradeoffs between a physically constrained neural network and a deep, convolutional neural network and to design a combined ML approach ("VarioCNN"). Our solution is provided in the framework of a cyberinfrastructure that includes a newly designed ML software, GEOCLASS-image, modern high-resolution satellite image data sets (Maxar WorldView data) and instructions/descriptions that may facilitate solving similar spatial classification problems. Combining the advantages of the physically-driven connectionist-geostatistical classification method with those of an efficient CNN, VarioCNN provides a means for rapid and efficient extraction of complex geophysical information from submeter resolution satellite imagery. A retraining loop overcomes the difficulties of creating a labeled training data set. Computational analyses and developments are centered on a specific, but generalizable, geophysical problem: The classification of crevasse types that form during the surge of a glacier system. A surge is a glacial catastrophe, an acceleration of a glacier to typically 100-200 times its normal velocity. GEOCLASS-image is applied to study the current (2016-2024) surge in the Negribreen Glacier System, Svalbard. The geophysical result is a description of the structural evolution and expansion of the surge, based on crevasse types that capture ice deformation in six simplified classes.

Hyperspectral (HS) imaging plays a pivotal role in various fields, including medical diagnostics, where precise human vein detection is crucial. Hyperspectral image data are very large and can cause computational complexities. Dimensionality reduction techniques are often employed to streamline HS image data processing. This paper investigates the effectiveness of three dimensionality reduction techniques, namely: Principal Component Analysis (PCA), Folded PCA (FPCA), and Ward’s Linkage Strategy using Mutual Information (WaLuMI) for vein detection using HS images. A HS image dataset, encompassing left and right-hand images captured from 100 subjects with varying skin tones was created and annotated using anatomical data to represent vein and non-vein areas within the images. To generate experimental results, the HS image dataset was divided into train and test datasets. Optimum performing parameters for each of the dimensionality reduction techniques in conjunction with The Support Vector Machine binary classification were determined using the Training dataset. The performance of the three dimensionality reduction based vein detection methods was then assessed and compared using the test image dataset. Results show that the FPCA-based method outperforms the other two methods in terms of accuracy. For visualization purposes, the classification prediction image for each technique is post-processed using morphological operators, and results show the significant potential of HS imaging in vein detection.

Image segmentation and classification still represent an active area of research since no universal solution can be identified. Established segmentation algorithms like thresholding are problem specific, treat well the easy cases and mostly relied on single parameter i.e intensity. Machine learning approaches offer alternatives where predefined features are combined into different classifiers. On the other hand, the outcome of machine learning is only as good as the underlying feature space. Differential geometry can substantially improve the outcome of machine learning since it can enrich the underlying feature space with new geometrical objects, called invariants. In this way, the geometrical features form a high-dimensional feature space for each pixel, where original objects can be resolved. Alternatives based on the geometry of the image scale-invariant interest points have been exploited successfully in the field of computer vision. Here, we integrate geometrical feature extraction based on signal processing, machine learning, and input relying on domain knowledge. The approach is exemplified on the ISBI 2012 image segmentation challenge data set. As a second application, we demonstrate powerful image classification functionality based on the same principles, which was applied to the HeLa and HEp-2 data sets. Obtained results demonstrate that feature space enrichment properly balanced with feature selection functionality can achieve performance comparable to deep learning approaches.

To address three important issues related to extraction of water features from Landsat imagery, i.e., selection of water indexes and classification algorithms for image classification, collection of ground truth data for accuracy assessment, this study applied four sets (ultra-blue, blue, green, and red light based) of water indexes (NWDI, MNDWI, MNDWI2, AWEI_ns, and AWEI_s) combined with three types of image classification methods (zero-water index threshold, Otsu, and kNN) to 24 selected lakes across the globe to extract water features from Landsat-8 OLI imagery. 1440 (4x5x3x24) image classification results were compared with the extracted water features from high resolution Google Earth images with the same (or ±1 day) acquisition dates through computing the Kappa coefficients. Results show the kNN method is better than the Otsu method, and the Otsu method is better than the zero-water index threshold method. If the computational cost is not an issue, the kNN method combined with the ultra-blue light based AWEI_ns is the best method for extracting water features from Landsat imagery because it produced the highest Kappa coefficients. If the computational cost is taken into account, the Otsu method is a good choice. AWEI_ns and AWEI_s are better than NDWI, MNDWI and MNDWI2. AWEI_ns works better than AWEI_s under the Otsu method, and the average rank of the image classification accuracy from high to low is the ultra-blue, blue, green, and red light-based AWEI_ns.

With the ever-increasing popularity of unmanned aerial vehicles and other platforms providing dense point clouds, filters for identification of ground points in such dense clouds are needed. Many filters have been proposed and are widely used, usually based on the determination of an original surface approximation and subsequent identification of points within a predefined dis-tance from such surface. We present a new filter, Multi-view and shift rasterization algorithm (MVSR) is based on a different principle, i.e., on the identification of just the lowest points in in-dividual grid cells, shifting the grid along both planar axis and subsequent tilting of the entire grid. The principle is presented in detail and compared both visually and numerically to other commonly used ground filters (PMF, SMRF, CSF, ATIN) on three sites with different ruggedness and vegetation density. Visually, the MVSR filter showed the smoothest and thinnest ground profiles, with ATIN the only filter performing comparably. The same was confirmed when comparing ground filtered by other filters with the MVSR-based surface. The goodness of fit with the original cloud is demonstrated by the root mean square deviations (RMSD) of the points from the original cloud found below the MVSR-generated surface (ranging, depending on site, between 0.6-2.5 cm). The MVSR filter performed outstandingly at all sites, identifying the ground points with great accuracy while filtering out the maximum of vegetation/above-ground points. The filter dilutes the cloud somewhat; in such dense point clouds, however, this can be perceived rather as a benefit than as a disadvantage.

With the ever-increasing popularity of unmanned aerial vehicles and other platforms providing dense point clouds, universal filters for accurate identification of ground points in such dense clouds are needed. Many filters have been proposed and are widely used, usually based on the determination of an original surface approximation and subsequent identification of points within a predefined distance from such surface. In this paper, we present a new filter. This Multi-view and shift rasterization algorithm (MVSR) is based on an entirely different principle, i.e., on the identification of just the lowest points in individual grid cells, shifting the grid along both planar axis and subsequent tilting of the entire grid – after each of these steps, one lowest point per cell is detected. The principle is presented in detail and compared both visually and numerically to other commonly used ground filters (PMF, SMRF, CSF, ATIN) on three sites with different ruggedness and vegetation density. Visually, the MVSR filter showed the smoothest and thinnest ground profiles, with ATIN the only filter performing comparably (although the profiles were somewhat thicker and not as complete as MVSR-acquired ground). The same was confirmed when comparing ground filtered by other filters with the MVSR-based surface. The goodness of fit with the original cloud is demonstrated by the root mean square deviations (RMSD) of the points from the original cloud found below the MVSR-generated surface (ranging, depending on site, between 0.6-2.5 cm). ATIN again performed closest to MVSR, with RMSDs of ground filtered points found above MVSR-based surface at individual sites ranging between 4.5-7.4 cm. The remaining filters performed comparable in the simplest flat area but poorly in rugged and much-vegetated sites, with RMSDs above the MVSR surface ranging at such sites from 21 to 95 cm. In conclusion, the novel filter presented in this paper performed outstandingly at all sites, identifying the ground points with great accuracy while filtering out the maximum of vegetation/above-ground points. The filter dilutes the cloud somewhat; in such dense point clouds, however, this can be perceived rather as a benefit than as a disadvantage.

The availability of current land cover and land use (LCLU) information for monitoring the status of land resources has considerable value in ensuring sustainable land use planning. Similarly, the need to provide updated information on the extent of LCLU change in West Africa has become apparent, given the increasing demand for land resources driven by the rapid population growth in the sub-region. SERVIR West Africa, a regional consortium jointly supported by USAID and NASA to foster the use of geospatial and earth observation data and science for decision-making on critical environmental and food security challenges, in collaboration with the Food and Agriculture Organization of the United Nations (FAO), is building technical capacity in the sub-region to develop and implement harmonized regional land cover classification system for LULC change monitoring in West Africa, based on the Land Cover Meta Language (LCML-ISO 19144-2). This article focuses on the process, potential opportunities, outputs of this collaboration, exemplary use cases, and recommendations for the next steps.

Transarterial chemoembolization (TACE) has been used to treat hepatocellular carcinoma (HCC) for more than 4 decades. So far, there is no consensus on which substances and which method should be used for the most effective treatment. A publication commissioned by CIRSE 2021 attempted to formulate recommendations. However, only the spectrum of currently implemented procedures is outlined. No recommendation was made as to how the various patients should be treated. In this article, therefore, basic considerations regarding the technique of chemoembolization are presented. Additionally, the authors discuss fundamental considerations about the embolism materials used, the cytostatic drugs and their dosage, as well as about pain therapy during treatment. Then, a technique is presented which used degradable starch microspheres (DSM) as an embolic agent. This technique allows multiple treatments over a longer period. The aim is to provide interventionalists with a decision-making aid for the TACE technique. A major problem when evaluating publications from different working groups is that the technology used is not adequately described and the individual studies are therefore not comparable. Therefore, a classification is presented that systematizes the possible different techniques. Future randomized trials should use this classification. Hopefully, if they are carried out on a sufficient number of patients, it will finally be possible to identify what is the best TACE procedure for individual patients. Until then the technique proposed by the authors can be applied.

Positron-emission tomography is powerful but costly tool for various medical investigations. In particular, it is used in Parkinson’s disease and essential tremor diagnostics. However, yet there is no standardized figures of the references, for it. We examined the PET efficiency for the analysis of development and degradation of dophaminergic neurons in Parkinson’s disease. The informative indices are determined from the observed PET data. Also, high efficiency of PET for Parkinson’s disease as approved.

The rapid development of algorithms for skeleton detection with relatively inexpensive contactless systems and cameras opens the possibility of virtual exercise therapy for patients with different complications. However, evaluation and confirmation of posture classifications is still needed. The purpose of this study was therefore to find the most accurate algorithm for automatic classification of human exercise movement. A Kinect V2 with 25 joints identification was used to record movements for data analysis. A total of 10 subjects volunteered for this study. Four algorithms were tested for the classification of different postures in Matlab. These were based on: total error of vector lengths, total error of angles, multiplication of these two parameters and simultaneous analysis of the first and second parameters. A base of 13 exercises was then created to test the recognition of postures by the algorithm, and to analyse subject performance. The best results for posture classification was shown by the second algorithm with an accuracy of 94.9%. The average correctness of exercises among the 10 participants was 94.2% (SD1.8%). The algorithms tested in this study therefore proved to be effective and could potentially form the basis for developing a system for remote monitoring of rehabilitation involving exercise.

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.

We describe a multi-resolution approach for audio classification and illustrate its application to the open data set for environmental sound classification. The proposed approach utilizes a multi-resolution based ensemble consisting of targeted feature extraction of approximation (coarse scale) and detail (fine scale) portions of the signal under the action of multiple transforms. This is paired with an automatic machine learning engine for algorithm and parameter selection and the LSTM algorithm, capable of mapping several sequences of features to a predicted class membership probability distribution. Initial results show an improvement in multi-class classification accuracy.

Land-cover classification that uses very-high-resolution (VHR) remote sensing images is a topic of considerable interest. Although many classification methods have been developed, there is still room for improvements in the accuracy and usability of classification systems. In this paper, a novel post-processing approach based on a dual-adaptive majority voting strategy (D-AMVS) is proposed for improving the performance of initial classification maps. D-AMVS defines a strategy for refining each label of a classified map that is obtained by different classification methods from the same original image and fusing the different refined classification maps to generate a final classification result. The proposed D-AMVS contains three main blocks. 1) An adaptive region is generated by extending gradually the region around a central pixel based on two predefined parameters (T1 and T2) in order to utilize the spatial feature of ground targets in a VHR image. 2) For each classified map, the label of the central pixel is refined according to the majority voting rule within the adaptive region. This is defined as adaptive majority voting (AMV). Each initial classified map is refined in this manner pixel by pixel. 3) Finally, the refined classified maps are used to generate a final classification map, and the label of the central pixel in the final classification map is determined by applying AMV again. Each entire classified map is scanned and refined pixel by pixel based on the proposed D-AMVS. The accuracies of the proposed D-AMVS approach are investigated through two remote sensing images with high spatial resolutions of 1.0 and 1.3 m, respectively. Compared with the classical majority voting method and a relatively new post-processing method called general post-classification framework, the proposed D-AMVS can achieve a land-cover classification map with less noise and higher classification accuracies.

Feature selection is one of the main data preprocessing steps in machine learning. Its goal is to reduce the number of features by removing extra and noisy features. Feature selection methods must consider the accuracy of classification algorithms while performing feature reduction on a dataset. Meta-heuristic algorithms are the most successful and promising methods for solving this issue. The symbiotic organisms search algorithm is one of the successful meta-heuristic algorithms which is inspired by the interaction of organisms in the nature called Parasitism Commensalism Mutualism. In this paper, three engulfing binary methods based on the symbiotic organisms search algorithm are presented for solving the feature selection problem. In the first and second methods, several S-shaped and V-shaped transfer functions are used for binarizing the symbiotic organisms search algorithm, respectively. These methods are called BSOSS and BSOSV. In the third method, two new operators called BMP and BCP are presented for binarizing the symbiotic organisms search algorithm. This method is called EBSOS. The third approach presents an advanced binary version of the coexistence search algorithm with two new operators, BMP and BCP, to solve the feature selection problem, named EBSOS. The proposed methods are run on 18 standard UCI datasets and compared to base and important meta-heuristic algorithms. The test results show that the EBSOS method has the best performance among the three proposed approaches for binarization of the coexistence search algorithm. Finally, the proposed EBSOS approach was compared to other meta-heuristic methods including the genetic algorithm, binary bat algorithm, binary particle swarm algorithm, binary flower pollination algorithm, binary grey wolf algorithm, binary dragonfly algorithm, and binary chaotic crow search algorithm. The results of different experiments showed that the proposed EBSOS approach has better performance compared to other methods in terms of feature count and accuracy criteria. Furthermore, the proposed EBSOS approach was practically evaluated on spam email detection in particular. The results of this experiment also verified the performance of the proposed EBSOS approach. In addition, the proposed EBSOS approach is particularly combined with the classifiers including SVM, KNN, NB and MLP to evaluate this method performance in the detection of spam emails. The obtained results showed that the proposed EBSOS approach has significantly improved the accuracy and speed of all the classifiers in spam email detection.

To effectively preserve marine environments and manage endangered species, it is necessary to employ efficient, precise, and scalable solutions for environmental monitoring. Ecoacoustics provides several benefits as it enables non-intrusive, prolonged sampling of environmental sounds, making it a promising tool for conducting biodiversity surveys. However, analyzing and interpreting acoustic data can be time-consuming and often demands substantial human supervision. This challenge can be addressed by harnessing contemporary methods for automated audio signal analysis, which have exhibited remarkable performance due to advancements in deep learning research. This paper introduces a research investigation into developing an automatic computerized system to detect dolphin whistles. The proposed method utilizes a fusion of various resnet50 networks integrated with data augmentation techniques. Through extensive experiments conducted on a publically available benchmark, our findings demonstrate that our ensemble yields significant performance enhancements across all evaluated metrics. The MATLAB/PyTorch source code is freely available at: https://github.com/LorisNanni/

Perceptual and statistical evidence has underlined voice characteristics of individuals affected by genetic syndromes different from that of normophonic subjects. In this paper we propose a procedure for the systematic collection of such pathological voices and the development of AI-based automatic tools to support differential diagnosis. Guidelines are provided concerning most suitable recording devices, vocal tasks and acoustical parameters, in order to simplify, speed up and make the whole procedure homogenous and replicable. The proposed procedure was applied to a set of 56 subjects, affected by Costello syndrome (CS), Down syndrome (DS), Noonan syndrome (NS) and Smith-Magenis syndrome (SMS). The whole database has been divided into three groups, respectively called: paediatric subjects (PS, individuals < 12 years of age), female adults (FA) and male adults (MA) subjects. In line with literature results, the Kruskal-Wallis test and post-hoc analysis with Dunn-Bonferroni test highlighted several significant differences in acoustical features not only between healthy subjects and patients, but also across syndromes within PS, FA and MA groups. Machine learning provided for the PS group a k-nearest neighbour classifier with 75% accuracy, for the FA group a support vector machine (SVM) model with 84% accuracy and for the MA group a SVM model with 97% accuracy. These preliminary results suggest that the proposed procedure, based on acoustical analysis and AI, might be helpful for an effective non-invasive automatic characterization of genetic syndromes.

Biologists seek to identify a small number of significant features that are important, non-redundant, and relevant from diverse omics data. For example, statistical methods like LIMMA and DEseq distinguish differentially expressed genes between a case and control group from the transcript profile. Researchers also apply various column subset selection algorithms on genomics datasets for a similar purpose. Unfortunately, genes selected by such statistical or machine learning methods are often highly co-regulated, making their performance inconsistent. Here, we introduce a novel feature selection algorithm that selects highly disease-related and non-redundant features from a diverse set of omics datasets. We successfully applied this algorithm to three different biological problems: a) disease to normal sample classification, b) multiclass classification of different disease samples, and c) disease subtypes detection. Considering classification ROC-AUC, False-positive, and False-negative rates, our algorithm outperformed other gene selection and differential expression (DE) methods for all six types of cancer datasets from TCGA considered here for binary and multiclass classification problems. Moreover, genes picked by our algorithm improved the disease subtyping accuracy for four different cancer types over the state-of-the-art methods. Hence, we posit that our proposed feature reduction method can support the community to solve various problems, including the selection of disease-specific biomarkers, precision medicine design, and disease sub-type detection.

Rapid eye movement sleep behavior disorder (RBD) is often prodromal to Parkinson’s disease (PD). Thus there should be detectable in vivo functional signatures shared between RBD and PD that aid in disease classification. To assess common in-vivo phenotypes, resting state data was collected on a 3T clinical MRI platform and a novel functional connectivity magnetic resonance imaging (fcMRI) approach, which combined independent component analysis (ICA) and graph theory, was used to evaluate deficits in interconnectivity among 15 PD, 14 RBD and 13 control participants. Whole brain and network-level analyses revealed the largest deficits in network connectivity in PD compared with controls, with less severe differences between RBD and controls. Importantly, the network-level analysis demonstrated decreased network interconnectivity, with the greatest aberrant networks in PD, and a subset in RBD. Additionally, a disease classification algorithm predicted PD cases by being trained on RBD cases with 0.87 sensitivity and 0.68 specificity. The functional alterations in cortical networks in RBD extended beyond the brainstem. These findings demonstrate progressive reductions in connectivity between brain networks, with less severe deficits in RBD than PD. Moreover, RBD phenotypes can be used to predict PD status in a cross-sectional sample, which suggests RBD is an intermediate phenotype.

Selecting a feature in data mining is one of the most challenging and important activities in pattern recognition. The issue of feature selection is to find the most important subset of the main features in a specific domain, the main purpose of which is to remove additional or unrelated features and ultimately improve the accuracy of the categorization algorithms. As a result, the issue of feature selection can be considered as an optimization problem and to solve it, meta-innovative algorithms can be used. In this paper, a new hybrid model with a combination of whale optimization algorithms and flower pollination algorithms is presented to address the problem of feature selection based on the concept of opposition-based learning. In the proposed method, we tried to solve the problem of optimization of feature selection by using natural processes of whale optimization and flower pollination algorithms, and on the other hand, we used opposition-based learning method to ensure the convergence speed and accuracy of the proposed algorithm. In fact, in the proposed method, the whale optimization algorithm uses the bait siege process, bubble attack method and bait search, creates solutions in its search space and tries to improve the solutions to the feature selection problem, and along with this algorithm, Flower pollination algorithm with two national and local search processes improves the solution of the problem selection feature in contrasting solutions with the whale optimization algorithm. In fact, we used both search space solutions and contrasting search space solutions, all possible solutions to the feature selection problem. To evaluate the performance of the proposed algorithm, experiments are performed in two stages. In the first phase, experiments were performed on 10 sets of data selection features from the UCI data repository. In the second step, we tried to test the performance of the proposed algorithm by detecting spam emails. The results obtained from the first step show that the proposed algorithm, by running on 10 UCI data sets, has been able to be more successful in terms of average selection size and classification accuracy than other basic meta-heuristic algorithms. Also, the results obtained from the second step show that the proposed algorithm has been able to perform spam emails more accurately than other similar algorithms in terms of accuracy by detecting spam emails.

Fish feeding behavior analysis plays a critical role in aquaculture, marine fisheries, and ecological monitoring. At present, the accuracy of current fish feeding behavior analysis is easily affected by the environment, and the hypoxia state in water and high temperature have a huge impact on behavior. In addition, the poor stability, and the speed is affected by the calculation amount of the model, so it cannot be applied to aquaculture ponds. In order to solve the above problems, we propose an improved RepVGG-based method for fish feeding behavior analysis to identify nine behavioral states of fish populations, including hypoxia, hot, and normal states of none, medium, and strong feeding. Firstly, our method adds the identity and residual branches to the block of the VGG network, focusing on the acceleration operation to ensure accuracy. At the same time, the Efficient Channel Attention (ECA) module is added to reduce dimensionality to balance speed and accuracy. To evaluate the effectiveness of the method, it is validated on a constructed fish feeding behavior dataset and compared with a Convolutional Neural Network (CNN) including AlexNet, VGG16, ResNet34, MobileNet V3, and RepVGG. The experimental results show that after 15 epochs of training, the average precision of proposed method reached 97%. Compared with the basic classification algorithm, our method can increase by at least 3% while the inference speed exceeds 85 Frames Per Second (FPS). This study can be integrated into the aquaculture vision system to guide users to plan feeding strategies, and provide new ideas and methods for water quality monitoring.

Effective healthcare relies on accurate and timely diagnosis; however, obtaining large amounts of training data while maintaining patient privacy remains challenging. This study introduces a novel approach utilizing federated learning (FL) and a cross-device multi-modal model for clin-ical event classification using vital signs data. Our architecture leverages FL to train machine learning models, including Random Forest, AdaBoost, and SGD ensemble model, on vital signs data from a diverse clientele at a Boston hospital (MIMIC-IV dataset). The FL structure preserves patient privacy by training directly on each client's device without transferring sensitive data. The study demonstrates the potential of FL in privacy-preserving clinical event classification, achieving an impressive accuracy of 98.9%. These findings underscore the significance of FL and cross-device ensemble technology in healthcare applications, enabling the analysis of large amounts of sensitive patient data while safeguarding privacy.

Medical health systems have been concentrating on artificial intelligence techniques for speedy diagnosis. However, the recording of health data in a standard form still requires attention so that machine learning can be more accurate and reliable by considering multiple parameters. The aim of this study is to develop a general framework for recording diagnostic data in an international standard format to facilitate auto-prediction of eye diseases. Efforts were made to ensure error-free data entry by developing a user-friendly interface. Furthermore, different machine learning algorithms were used to analyze patient data based on multiple parameters, including age, illness history, and clinical observations. This data was formatted according to structured hierarchies designed by medical experts, whereas diagnosis was made as per the ICD-10 coding developed by the American Academy of Ophthalmology. Furthermore, the system is designed to evolve through self-learning by adding new classifications for both diagnosis and symptoms. The classification results from tree-based methods demonstrated that the proposed framework performs satisfactorily given a sufficient amount of data. The random forest and decision tree algorithms predicted more accurately as compared to neural networks and the na{\"i}ve Bayes algorithm owing to structured data arrangement.

The paradigm of leveraging code as a dataset has recently gained traction, offering innovative solutions in domains such as automated commit message generation, pull request description automation, and program repair mechanisms. Consider the challenge in generating commit messages: traditional methods treat source code as a mere token sequence, applying neural machine translation models. This approach, however, overlooks the critical syntactic structures inherent in programming languages, which could offer deeper insights and improved accuracy. Building upon prior research, specifically the Code2Seq framework, which utilized Abstract Syntax Tree (AST) structural data for source code representation to automate method name generation, this paper extends and refines this concept. We introduce "CSR", a novel methodology adapted to represent code edits effectively. This paper investigates the impact of employing syntactic structure, focusing on the classification of code edits. Drawing inspiration from Code2Seq, "CSR" utilizes AST's structural properties, particularly the paths connecting leaf nodes, to enhance the task of code edit classification. This approach is rigorously evaluated on two distinct datasets, comprising fine-grained syntactic edits. Our comprehensive experiments reveal that incorporating syntactic structures does not significantly outperform simpler methodologies. While methods like Code2Seq and our proposed "CSR" show potential, our findings highlight that there is considerable scope for improvement and refinement before such techniques can be universally applied for learning representations of code edits. We anticipate that our findings will spark further research in this field, paving the way for more effective use of syntactic structures in code representation.

Vehicular traffic in urban areas continues to be a constant challenge today, due to the continuous population growth and the increase of vehicles in circulation. Vehicular congestion, as a recurrent problem, generates a negative impact on urban mobility and citizens’ quality of life. It is hypothesized that a dynamic clustering method of vehicle trajectory data can provide an accurate and up-to-date representation of real-time traffic behavior. To evaluate this hypothesis, data were collected from three different cities: San Francisco, Rome and Guayaquil. A dynamic clustering algorithm was applied to identify traffic congestion patterns and an indicator was applied to identify and evaluate the congestion conditions of the areas. The results show a high precision and recall in congestion classification compared to a method based on static cells.

We describe a dataset that contains job description published on a popular online website in the information and technology sector. As the website focus mainly on United Kingdom based jobs, the data have a specific focus on this country. It contains 11.501 job vacancies and 13 related meta data information. The dataset is suitable for HR analysis using machine learning techniques such as natural language processing and neural networks.

In recent years, using multispectral cameras on UAVs has provided an opportunity to capture separate bands that offer the extraction of spectral features used for early detection of diseased plants. One of the main steps in disease detection is radiometric calibration that converts digital numbers to reflectance values commonly using white reference panels. This paper focused on the necessity of radiometric calibration to distinguish disease trees in orchards based on aerial multi-spectral images. For this purpose, two study sites with various climate conditions and tree species as well as different disease types were selected where multispectral images were taken using a multirotor UAV. The impact of radiometric correction on plant disease detection was assessed in two ways: 1) comparison of separability between the healthy and diseased classes using T-test and entropy distances; 2) radiometric calibration effect on the accuracy of classification. The experimental result showed the insignificant effect of radiometric calibration on separability criteria. Furthermore, based on T-test and entropy distances criteria, NIR and R spectral features made highest distances between healthy and Greening infected citrus trees, respectively, at the first study site while NDRE and BNDVI spectral features made highest distances between healthy and peach leaf curl infected trees, respectively, at the other study site. In the second strategy, the experimental result showed that radiometric calibration had no effect on the accuracy of classification. As a result, the overall accuracy and kappa values for both un-calibrated and calibrated orthomosaic classifications of the citrus orchard were 96.6% and 0.94%, respectively, using five spectral bands as well as DVI, NDRE, NDVI and GNDVI vegetation indices using a random forest classifier. The experimental results were also similar at the other study site. Therefore, the overall accuracy and kappa values for both the un-calibrated and calibrated orthomosaic classifications were 96.1%, 0.92, respectively, using five spectral bands as well as NDRE, BNDVI, GNDVI, DVI, and NDVI vegetation indices.

Using machine learning or deep learning to solve the problem of garbage recognition and classification is an important application in computer vision, but due to the incomplete establishment of garbage datasets and the poor performance of complex network models on smart terminal devices, the existing garbage classification models The effect is not good.This paper presents a waste classification and identification method base on transfer learning and lightweight neural network. By migrating the lightweight neural network MobileNetV2 and rebuild it, The reconstructed network is used for feature extraction, and the extracted features are introduced into the SVM to realize the identification of 6 types of garbage. The model was trained and verified by using 2527 pieces of garbage labeled data in the TrashNet dataset, which ultimately resulted in a classification accuracy of 98.4% of the method, which proves that the method can effectively improve the classification accuracy and time and overcome the problem of weak data and less labeling. The over-fitting phenomenon encountered by small data sets in deep learning makes the model robust.

Image classification in Remote Sensing and Geographic Information Systems (GIS) containing various land-cover classes is essential for efficient and sustainable land-use estimation, and other tasks like object detection, localization and segmentation. Deep Learning (DL) techniques have shown a tremendous potential in the GIS domain. While Convolutional Neural Networks (CNN) have dominated most of the image analysis domain, a new architecture called transformers have proved to be a unifying solution for several AI-based processing pipelines. Vision Transformers (ViT), a variant of transformers can have comparable and in some cases better accuracy than a CNN. However, they suffer from a significant drawback associated with an excessive use of training parameters. In this research we explore several modifications in the vision transformer architectures, especially MobileViT that can be optimized while boosting accuracy. To verify our proposed approach these new architectures are trained on four land-cover datasets AID, EuroSAT, UC-Merced, and WHU-RS19. Experiments reveal that combination of lightweight convolutional layers including ShuffleNet along with depthwise separable convolutions and average pooling can reduce the trainable parameters by 17.85% and yet achieve higher accuracy than the base MobileViT. It is also observed that utilizing a combination of convolution layers along with multi-headed self attention layers in MobileViT variants provide better performance in capturing local and global features unlike the standalone ViT architecture that utilizes almost 95% more parameters than the proposed MobileViT variant.

The article’s goal is to overview challenges and problems on the way from the state of the art CUDA accelerated neural networks code to multi-GPU code. For this purpose, the authors describe the journey of porting the existing in the GitHub, fully-featured CUDA accelerated Darknet engine to OpenCL. The article presents lessons learned and the techniques that were put in place to make this port happen. There are few other implementations on the GitHub that leverage the OpenCL standard, and a few have tried to port Darknet as well. Darknet is a well known convolutional neural network (CNN) framework. The authors of this article investigated all aspects of the porting and achieved the fully-featured Darknet engine on OpenCL. The effort was focused not only on the classification with the use of YOLO1, YOLO2, and YOLO3 CNN models. They also covered other aspects, such as training neural networks, and benchmarks to look for the weak points in the implementation. The GPU computing code substantially improves Darknet computing time compared to the standard CPU version by using underused hardware in existing systems. If the system is OpenCL-based, then it is practically hardware independent. In this article, the authors report comparisons of the computation and training performance compared to the existing CUDA-based Darknet engine in the various computers, including single board computers, and, different CNN use-cases. The authors found that the OpenCL version could perform as fast as the CUDA version in the compute aspect, but it is slower in memory transfer between RAM (CPU memory) and VRAM (GPU memory). It depends on the quality of OpenCL implementation only. Moreover, loosening hardware requirements by the OpenCL Darknet can boost applications of DNN, especially in the energy-sensitive applications of Artificial Intelligence (AI) and Machine Learning (ML).

The Independent Component Analysis (ICA) has been recently introduced as a reliable alternative to identify canonical scattering mechanisms within Polarimetric Synthetic Aperture Radar (PolSAR) images. This manuscript addresses two important aspects when applying such methods on real data, namely speckle filtering and statistical classification with ICA. A novel PolSAR data processing framework is introduced by adjusting the Lee's sigma filter to the particular nature of the Touzi's polarimetric decomposition. In its current form, it allows the use of the ICA mixing matrix in the derived speckle filter. An extension of the Fromont at al. iterative segmentation is introduced, equally. This proposed framework is tested using P band airborne PolSAR data acquired for the ESA campaign TropiSAR campaign.

Folk nomenclature is habitually established for species that have attained high utilitarian and cultural significance by custodians of such plants worldwide. Such folk names assigned to species often carry etymological values such as therapeutic effects, morphological features, mythical connotations, and their allegorical values. This research sought to unveil the etymology in folk nomenclatures of Sphenostysis stenocarpa (Hosch ex A. Rich) Harms (African Yam Bean). Three hundred and fifty respondents were randomly selected from 13 local communities in Ebonyi State in South-eastern, Nigeria. Data were collected through oral interviews with semi-structural questionnaires, along with focused group discussions. Analysis of data was carried out using simple statistical methods involving frequencies and percentages. The results recorded ten folk nomenclatures assigned to this species in seven dialects affiliated to cultural values within these communities. Etymologically, the results also revealed that out of the ten folk names of AYB cryptic connotations, five reflected their trust in the gods that answered their prayers, two were attributed to the healing potentials inherent in this crop for medicine, three names were associated with the seeds, while one referred to feminist attachment to the crop, another to its resilience/ adaptability to climatic stress and one as a sustainer of farmers. Considering that folk nomenclature is based mainly on qualitative data and the information outside the scientific domain, they are nonetheless highly valued because they are based on long-term interactions, utilization and observations of the custodians of these natural resources. However, these data are equally vulnerable to erosion if not properly documented and conserved for posterity.

Disease classification based on biological data is an important area in bioinformatics and biomedical research. It helps the doctors and medical practitioners for the early detection of disease and support them as a computer-aided diagnostic tool for accurate diagnosis, prognosis, and treatment of disease. Earlier Microarray gene expression data have wide application for the classification of disease, but now Next-generation sequencing (NGS) has replaced the Microarray technology. From the last few years, RNA sequence (RNA-Seq) data are widely used for the transcriptomic analysis. Hence, RNA-Seq based classification of disease is in its infancy. In this article, we present a general framework for the classification of disease constructed on RNA-Seq data. This framework will guide the researchers to process RNA-Seq, extract relevant features and apply the appropriate classifier to classify any kind of disease.

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.

Deep neural networks with powerful auto-optimization tools have been widely applied in various research fields, e.g., NLP and computer vision. However, existing neural network architectures typically are constructed using different inductive biases, e.g., preconceptions, expecting to decrease parameter search space during training, reduce computational cost or introduce expert knowledge in the neural network design. As an alternative, Multilayer Perceptron (MLP) provides much better freedom for exploration, has a lower inductive bias than convolutional neural networks (CNNs), and offers good flexibility in learning complex patterns. Even though, such neural architectures are commonly built in a flat Euclidean space, which is not necessarily the optimal space for any data, and is especially not good for modeling hierarchical correlations. Hyperbolic neural networks (HNNs) have gained attention for their ability to capture hierarchical structures present in complex data types like graphs. Recently, there has been an increasing interest to extend HNNs to computer vision tasks, motivated by the observations that images possess rich hierarchical relations. However, this is generally applied by employing a Euclidean backbone for learning higher-level semantic representations and only incorporating a hyperbolic classifier for classification, which, we argue, does not make full use of the advantage of hyperbolic space. Considering the recovery of the attention-free Multilayer Perceptron(MLP), in this paper, we extend it to non-Euclidean space and propose a novel architecture, named Hyperbolic Res-MLP (HR-MLP), that leverages fully hyperbolic layers to learn feature embeddings and perform image classification in an end-to-end fashion. With the help of the proposed Lorentz cross-patch and cross-channel layers, we can directly perform operations in the hyperbolic domain with fewer parameters, making it faster to train and providing comparatively better performance than its Euclidean counterpart. Experiments on CIFAR10, CIFAR100, and MiniImageNet demonstrate a comparable and superior performance when compared to Euclidean baselines. Our code is available at (https://github.com/Ahmad-Omar-Ahsan/HR-MLP)

The aim of this paper is to develop an intelligent event-driven Electrocardiogram (ECG) processing module in order to achieve an efficient solution for diagnosis of the cardiac diseases. The suggested method acquires the signal with an event-driven A/D converter (EDADC). The output of EDADC is passed through the activity selection and interpolation blocks. It allows focusing only on the important signal parts and resampling it uniformly. Later on, the signal is de-noised. The autoregressive (AR) method is used to extract the classifiable features of the de-noised signal. Afterwards, the output is classified by employing different robust classification techniques such as support vector machines (SVMs), K- Nearest Neighbor (KNN) and Artificial Neural Network (ANN). The event-driven feature enables to adapt the system processing load according to the signal temporal variations. This interesting feature of the devised system aptitudes a drastic reduction in its processing activity and therefore in the power consumption as compared to the traditional ones. A comparison of the performance of different classifiers is also made in terms of accuracy. Results show that the proposed system is a potential candidate for an automatic diagnosis of the cardiac diseases.

Incorrect sitting posture, characterized by asymmetrical or uneven positioning of the body, often leads to spinal misalignment and muscle tone imbalance. Prolonged maintenance of such postures can adversely impact well-being and contribute to the development of spinal deformities and musculoskeletal disorders. In response, smart-sensing chairs equipped with cutting-edge sensor technologies have been introduced as a viable solution for real-time detection, classification, and monitoring of sitting postures, aiming to mitigate the risk of musculoskeletal disorders and promote overall health. This comprehensive literature review evaluates the current body of research on smart-sensing chairs, with a specific focus on the strategies used for posture detection and classification, as well as the effectiveness of different sensor technologies. A meticulous search across MDPI, IEEE, and Google Scholar databases yielded 34 pertinent studies that utilize non-invasive methods for posture monitoring. The analysis reveals that Force Sensing Resistors (FSR) are the predominant sensors utilized for posture detection, whereas Convolutional Neural Networks (CNN) and Artificial Neural Networks (ANN) are the leading machine learning models for posture classification. However, it was observed that CNNs and ANNs do not outperform traditional statistical models in terms of classification accuracy, due to constrained size and lack of diversity within training datasets. These datasets often fail to comprehensively represent the array of human body shapes and musculoskeletal configurations. Moreover, this review identifies a significant gap in the evaluation of user feedback mechanisms, essential for alerting users to their sitting posture and facilitating corrective adjustments.

With the increasing utilization of intelligent mobile devices for online inspection of electrical equipment in smart grids, the limited computing power and storage capacity of these devices pose challenges for deploying large algorithm models and it’s hard to obtain a substantial number of images of electrical equipment in public. In this paper, we propose a novel distillation method that compresses the knowledge of teacher networks into a compact few-shot classification network, employing a global and local knowledge distillation strategy. Central to our method is exploiting the global and local relationship between the features exacted by the backbone of the teacher network and student network. We compare our method with recent state-of-the-art (SOTA) methods on three public datasets and achieve superior performance. Additionally, we contribute a new dataset, namely EEI-100, which is specifically designed for classification of electrical equipment. We validate our method on this dataset and demonstrate its exceptional prediction accuracy of 94.12% when utilizing only 5-shot images.

Chickpea is one of the most widely consumed pulses globally because of its high protein content. The morphological features of chickpea seed, such as colour, texture, are observable and play a major role in classifying different chickpea varieties. This process is often carried out by human experts, and is time-consuming, inaccurate, and expensive. The objective of the study was to design an automated chickpea classifier using an RGB colour image-based model by considering the morphological features of chickpea seed. As part of the data acquisition process, five hundred and fifty images were collected per variety for four varieties of chickpea (CDC-Alma, CDC-Consul, CDC-Cory, and CDC-Orion) using an industrial RGB camera and a mobile phone camera. Three CNN-based models such as NasNet-A (mobile), MobileNetV3 (small), and EfficientNetB0 were evaluated using a transfer learning-based approach. The classification accuracy was 97%, 99%, and 98% for NasNet-A (mobile), MobileNetV3 (small), and EfficientNetB0 models, respectively. The MobileNetV3 model was used for further deployment on an Android mobile and Raspberry Pi 4 devices based on its higher accuracy and light-weight architecture. The classification accuracy for the four chickpea varieties was 100% while the MobileNetV3 model was deployed on both Android mobile and Raspberry Pi 4 platforms.

It is crucial to select the right machine learning classifier for image classification and face recog-nition. This study examines the effectiveness of four different face recognition classifiers - Support Vector Machines (SVM), Random Forest, K-Nearest Neighbors (KNN), and Neural Networks. An analysis of the Large Faces in the Wild (LFW) dataset was carried out using Principal Component Analysis (PCA). Classifiers are rigorously trained and evaluated based on the extracted features. Comparison of classifier performance is an insightful way to figure out their strengths and weaknesses. Having a visual representation of the classifier's performance gives a complete understanding of its capabilities. Through the selection of the most appropriate classifier, study results contribute to advancements in image classification, recognition, and biometric identification. The comparison study demonstrated that the Neural Network classifier was exceptionally accurate and proficient in recognizing faces from the LFW dataset when used in conjunction with PCA for feature extraction. According to the comparative analysis, the Neural Network classifier proved exceptionally accurate and proficient at identifying faces from the LFW dataset when combined with PCA for feature extraction.

Artificial Intelligence (AI) has seen increased application and widespread adoption over the past decade despite, at times, offering a limited understanding of its inner working. AI algorithms are, in large part, built on weights, and these weights are calculated as a result of large matrix multiplications. Computationally intensive processes are typically harder to interpret. Explainable Artificial Intelligence (XAI) aims to solve this black box approach through the use of various techniques and tools. In this study, XAI techniques are applied to chronic wound classification. The proposed model classifies chronic wounds through the use of transfer learning and fully connected layers. Classified chronic wound images serve as input to the XAI model for an explanation. Interpretable results can help shed new perspectives to clinicians during the diagnostic phase. The proposed method successfully provides chronic wound classification and its associated explanation. This hybrid approach is shown to aid with the interpretation and understanding of AI decision-making processes.

With huge varieties of fabrics, the first challenge for any performance evaluation is to categorize the vast types of the products into fewer, more homogeneous and thus akin groups. Classification or sorting is arguably the first step of any scientific investigation, and comparison of product quality is meaningful only when conducted within a group of comparable products. A new criterion termed fabric linear density λ is first proposed in this paper so that fabrics can in general be divided into 4 groups. The derivation and validation of this parameter are provided. The importance of fabric drape is almost self-evident, but there is still no effective ways to measure this fabric attribute. The Cusick Drapemeter suffers from its low repeatability and low sensitivity, and is hence not widely or frequently used. The PhabrOmeter, along with the fabric linear density λ, is proposed and demonstrated in this study as a much more efficient alternative for fabric drape test. By actually testing 40 various fabrics, the principle, procedure and results of this method is presented in this paper.

In this paper we use quantum machine learning to detect and classify ocular diseases across age related macular degradation, cataract, diabetic, glaucoma, hypertension, and patological myopia categories versus a control group. We analyze fundus imagery from 1000 patients. Early findings indicate there may be benefit in terms of accuracy and loss function minimization of 2.07% and 1.979x respectively compared to a similar method implemented using traditional computers.

Partial least square (PLS) regression is a well-known chemometric method used for predictive modelling, especially in the presence of many variables. Although PLS was not initially developed as a technique for classification tasks, scientists have reportedly used this approach successfully for discrimination purposes. Whereas some non-supervised learning approaches including but not limited to PCA, and k-means clustering do well in identifying/understanding grouping and clustering patterns in multidimensional data, they are limited when the end target is discrimination, making PLS a preferable alternative. A total of fertilized 672 chicken egg hyperspectral imaging data, consisting of 336 white eggs and 336 brown eggs were used in this study. Hyperspectral images in the NIR region of 900-1700 nm wavelength range were captured prior to incubation on day 0 and on days 1-4 after incubation. Eggs were candled on incubation day 5 and broken out on day 10 to confirm fertility. While a total number of 312 and 314 eggs were found to be fertile in the brown and white egg batches respectively, total numbers of non-fertile eggs in the same set of batches were 23 and 21 respectively. Spectral information was extracted from a segmented region of interest (ROI) of each hyperspectral image and spectral transmission characteristics were obtained by averaging the spectral information. A moving-thresholding technique was implemented for discrimination based on PLS regression results on the calibration set. With true positive rates (TPR) of up to 100% obtained at selected threshold values of between 0.50-0.85 and on different days of incubation, the results indicated that the proposed PLS technique can accurately discriminate between fertile and non-fertile eggs. The adaptive PLS approach was thereby presented as suitable for handling hyperspectral imaging-based chicken egg fertility data

Seismic imaging is the main technology used for subsurface hydrocarbon prospection. It provides an image of the subsurface using the same principles as ultrasound medical imaging. It is based on emitting a sound (pressure) wave through the subsurface and recording the reflected echoes using hydrophones (pressure sensors) and/or geophones (velocity/acceleration sensors). Contrary to medical imaging, which is done in real time, subsurface seismic imaging is an offline process that involves a huge volume of data and needs considerable computing power. The raw seismic data are heavily contaminated with noise and unwanted reflections that need to be removed before further processing. Therefore, the noise attenuation is done at an early stage and often while acquiring the data. Quality control (QC) is mandatory to give confidence in the denoising process and to ensure that a costly data re-acquisition is not needed. QC is done manually by humans and comprises a major portion of the cost of a typical seismic processing project. It is therefore advantageous to automate this process to improve cost and efficiency. Here, we propose a supervised learning approach to build an automatic QC system. The QC system is an attribute-based classifier that is trained to classify three types of filtering (mild = underfiltering, noise remaining in the data; optimal = good filtering; harsh = overfiltering, the signal is distorted). The attributes are computed from the data and represent geophysical and statistical measures of the quality of the filtering. The system is tested on a full-scale survey (9000 km2) to QC the results of the swell noise attenuation process in marine seismic data. The results are encouraging and helped identify localized issues that were difficult for a human to spot.

Bulgaria and North Macedonia have a long history of production and use of honey, however, there is an obvious lack of systematic and in-depth research on honey from both countries. Of particular interest is the oak honeydew honey, highly valued by consumers because of its health benefits. Aim of this study was to characterize honeydew and floral honeys from Bulgaria and North Macedonia based on their NMR profiles. 1D and 2D 1H and 13C NMR spectra were measured of 16 North Macedonian and 22 Bulgarian honey samples. 25 individual substances were identified, including quinovose, which was found for the first time in honey. Chemometric methods (PCA - principal component analysis, PLS-DA - partial least squares discriminant analysis, ANOVA) were used to detect similarities and differences between samples, as well as to determine their botanical and geographical origin. Semiquantitative data on individual sugars and some other constituents were obtained; which allowed reliable classification of honey samples by botanical and geographical origin, based on chemometric approaches. The results enabled to distinguish oak honeydew honey from other honey types, and to determine the country of origin. NMR was a rapid and convenient method, avoiding the need for other more time-consuming analytical techniques.

Increasingly measured data in the context of smart cities can be used to develop new and innovative business models to increase efficiency and the value of life. A time-series classification algorithm can support to automatize many different processes such as forecasting services. In order to ensure data security and privacy, Federated Learning trains a global model collaboratively on multiple clients. Having different data-distributions and data-quantities across participating clients, neural networks suffer from slow convergence and overfitting. Based on different data-distributions, data-quantities and number of clients, we develop and evaluate different data-clustering strategies to update global model weights in comparison to the state of the art. We use public time-series data, generate various synthetic datasets and train a Relational-Regularized Autoencoder for classification purposes. Our results show an improvement of model performance concerning generalization.

In videos, the human's actions are of three-dimensional (3D) signals. These videos investigate the spatiotemporal knowledge of human behavior. The promising ability is investigated using 3D convolution neural networks (CNNs). The 3D CNNs have not yet achieved high output for their well-established two-dimensional (2D) equivalents in still photographs. Board 3D Convolutional Memory and Spatiotemporal fusion face training difficulty preventing 3D CNN from accomplishing remarkable evaluation. In this paper, we implement Hybrid Deep Learning Architecture that combines STIP and 3D CNN features to enhance the performance of 3D videos effectively. After implementation, the more detailed and deeper charting for training in each circle of space-time fusion. The training model further enhances the results after handling complicated evaluations of models. The video classification model is used in this implemented model. Intelligent 3D Network Protocol for Multimedia Data Classification using Deep Learning is introduced to further understand space-time association in human endeavors. In the implementation of the result, the well-known dataset, i.e., UCF101 to, evaluates the performance of the proposed hybrid technique. The results beat the proposed hybrid technique that substantially beats the initial 3D CNNs. The results are compared with state-of-the-art frameworks from literature for action recognition on UCF101 with an accuracy of 95%.

Sleep disorder is a disease that can be categorized as both an emotional and physical problem. It imposes several difficulties and problems, such as distress during the day, sleep-wake disorders, anxiety, and several other problems. Hence, the main objective of this research is to utilize the strong capabilities of machine learning in the prediction of sleep disorders. In specific, this research aims to meet three main objectives. These objectives are to identify the best regression model, the best classification model, and the best learning strategy that highly suits sleep disorder datasets. Considering two related datasets and several evaluation metrics that are related to the tasks of regression and classification, the results revealed the superiority of the MultilayerPerceptron, SMOreg, and KStar regression models compared with the other twenty-three regression models. Also, IBK, RandomForest, and RandomizableFilteredClassifier showed superior performance compared with other classification models that belong to several learning strategies. Finally, the Function learning strategy showed the best predictive performance among the six considered strategies in both datasets and with respect to the most evaluation metrics.

This paper focuses on optimal sensor positioning for monitoring activities of daily living and investigates different combinations of features and models on different sensor positions, i.e., the side of the waist, front of the waist, chest, thigh, head, upper arm, wrist, and ankle. Sixteen features are extracted and the feature importance is measured by using the Relief-F feature selection algorithm. Eight classification algorithms are evaluated on a dataset collected from young subjects and that collected from elderly subjects, with two different experimental settings. To deal with different sampling rates, signals with a high data rate are down-sampled and a transformation matrix is used for aligning signals to the same coordinate system. The thigh, chest, side of the waist, and front of the waist are the best four sensor positions for the first dataset (young subjects), with average accuracy values being greater than 95%. The best model obtained from the first dataset for the side of the waist is validated on the second dataset (elderly subjects). The most appropriate number of features for each sensor position is reported. The results provide a reference for building activity recognition models for different sensor positions, as well as for data acquired from different hardware platforms and subject groups.

In recent years web applications and on-line business transactions have grown many folds. Consequently, also cyberattacks have increased and represent a serious threat to the pervasive digital services upon which our society relies. To mitigate cyberattacks, many countermeasures are deployed on computing nodes (e.g., anti-malware software) as well as on network devices to detect and possibly block malicious packets in transit; these monitoring devices broadly go under the name of firewalls. Firewalls are designed according to two main architectural approaches: software running on a standard or embedded computer, or purposedly designed hardware, e.g., ASICs. Software-based solutions have the advantage of high flexibility and can be ported on easily upgradable hardware. However, hardware implementation represents the only viable solution for high data rates. On the market, very fast devices of the latter kind are available, but their cost is typically very high, especially considering that their ultra-optimized design makes updating them very difficult, with the consequence of a rather short lifespan. As a more balanced alternative, we wanted to investigate the use of an FPGA architecture, , which is significantly easier to update than custom-built chips, and features low-latency and high-throughput characteristics concurrently, making it preferrable to other programmable systems based on GPUs or microcontrollers. In this paper a packet sniffer that has been designed on FPGA with a 1 Gbit/s data transfer rate is presented. The system is implemented on the FPGA development board KC705 by Xilinx, can analyze Ethernet frames, checking the frame fields against a set of rules defined by the user and calculates statistics of the received Ethernet frames over time. The designed packet sniffer has been successfully tested both with Ethernet frames ad hoc generated using a packets generator, and with real web traffic by connecting the packet sniffer to the internet.

The point cloud is a form of three-dimensional data that comprises various detailed features at multiple scales. Due to this characteristic and its irregularity, point cloud analysis based on deep learning is challenging. While previous works utilize the sampling-grouping operation of PointNet++ for feature description and then explore geometry by means of sophisticated feature extractors or deep networks, such operations fail to describe multi-scale features effectively. Additionally, these techniques have led to performance saturation. And it is difficult for standard MLPs to directly "mine" point cloud. To address above problems, we propose the Detail Activation (DA) module, which encodes data based on Fourier transform after sampling and grouping. We activate the channels at different frequency levels from low to high in the DA module to gradually recover finer point cloud details. As training progresses, the proposed Point-MDA can uncover local and global geometries of point cloud progressively. Our experiments show that Point-MDA achieves superior classification accuracy, outperforming PointNet++ by 3.3% and 7.9% in terms of overall accuracy on the ModelNet40 and ScanObjectNN dataset, respectively. Furthermore, it accomplishes this without employing complicated operations, while exploring the full potential of PointNet++.

Recent neuroscience research results show that the nerve information in the brain is not only encoded by the spatial information. Spiking neural network based on pulse frequency coding plays a very important role in dealing with the problem of brain signal, especially complicated space-time information. In this paper, an unsupervised learning algorithm for bilayer feedforward spiking neural networks based on spike-timing dependent plasticity (STDP) competitiveness is proposed and applied to SAR image classification on MSTAR for the first time. The SNN learns autonomously from the input value without any labeled signal and the overall classification accuracy of SAR targets reached 80.8%. The experimental results show that the algorithm adopts the synaptic neurons and network structure with stronger biological rationality, and has the ability to classify targets on SAR image. Meanwhile, the feature map extraction ability of neurons is visualized by the generative property of SNN, which is a beneficial attempt to apply the brain-like neural network into SAR image interpretation.

Gelephu, located in the Himalayan region, has experienced one of the strongest development activities due to the suitable topography and geographic location, which has led to rapid urbanization. The main objective of the study is to perform land use land cover (LULC) mapping for Gelephu for 2016 and 2023 by a Random Forest (RF) classifier, using the Semi-automatic Classification Plugin (SCP) in QGIS and identify LULC changes. Furthermore, the study assessed the vegetation change dynamics within the study area by analysing the Normalized Difference Vegetation Index (NDVI) for 2016 and 2023. Additionally, the study characterized the resulting LULC change for Gelephu Thromde, a sub-administrative municipal entity, as a result of the notable intensity of the infrastructure development activities. The current study used a framework to collect Sentiniel-2 satellite data, which was then used for pre- and post-processing to create LULC and NDVI maps. The classification model achieved high accuracy, with an area under the curve (AUC) of up to 0.89. The corresponding LULC and NDVI statistics were analysed to determine the current status of the LULC and vegetation indices, respectively. The LULC change analysis reveals urban growth of 5.65% and 15.05% for Gelephu and Gelephu Thromde, respectively. The NDVI assessment shows significant deterioration in vegetation health with a 75.11% loss of healthy vegetation in Gelephu between 2016 and 2023. This research provides the first version of LULC and NDVI maps of Gelephu. The analysis results indicate possible future implications on sustainable development management in Gelephu Bhutan.

The purpose of this review is to provide an overview of brain arteriovenous malformations (AVMs) and focus on their management. The therapeutic options differ in each case depending on the location, size, and adjacent anatomical content of the AVM. The surgical resection by microsurgery is the preferred therapeutic option for a small and superficial AVM not related to an eloquent area (e.g., Spetzler-Martin grades I and II). On the other hand, when facing a very large AVM (e.g., Spetzler-Martin grades IV and V), the conservative and symptomatic treatment remains the most common management option due to the high risk-benefit ratio of any intervention. The management of AVMs with features between these two extremes (e.g., Spetzler-Martin grade III) remains less stablished. Stereotactic radiosurgery usually is the option for deep and small AVMs. Embolization has been usually considered before surgery for occlusion of deep arterial supplies of an AVM or to decrease its nidus size. Young patients and AVMs with compact nidus are features that weight in favor of a surgical approach. For the minority of cases that have the AVM diagnosed before bleeding the most common recommendation is to treat conservatively and particularly to avoid embolization. In summary, surgery is the gold-standard approach to cure an AVM and the choice for small AVMs located in non-eloquent area and with superficial venous drainage; large AVMs are mostly treated conservatively; the treatment of AVM with intermediate features is tailored, chosen with the guidance of classification systems, and encompasses radiosurgery and pre-operative embolization.

Artificial intelligence techniques are now widely used in various agricultural applications, including the detection of devastating diseases such as late blight (Phytophthora infestans) and early blight (Alternaria solani) affecting potato (Solanum Tuberorsum L.) crops. In this paper, we present a mobile application for potato crop pest detection based on deep neural networks. The images were taken from the PlantVillage dataset with a batch of 1000 images for each of the three identified classes. An exploratory analysis of the architectures used for early and late blight diagnosis in potatoes was performed, achieving an accuracy of 98.76%, with MobileNetv2. Based on the results obtained, an offline mobile application was implemented, supported on devices with Android 4.1 or later, also featuring an information section on the 27 pests affecting potato crops and a gallery of symptoms. For future work, segmentation techniques will be used to highlight the damaged region in the potato leaf by evaluating its extent and possibly identifying different types of pests affecting the same plant.

A pixel-based segmentation method was demonstrated to be confounded by developmental stage in estimation of flowering of mango. Categorization of panicles into three developmental stages was undertaken with a single and a two-stage deep learning framework (YOLO and R2CNN), using either upright or rotated bounding boxes. For a validation image set and for total panicle count, the models MangoYOLO(-upright), MangoYOLO-rotated, YOLOv3-rotated, R2CNN(-rotated) and R2CNN-upright achieved: (i) RMSEs of 25.6, 16.0, 15.4, 25.8 and 32.3 panicles per tree image, (ii) Mean average precision (mAP) scores of 72.2, 69.1, 65.0, 62.5 and 70.9% and (iii) weighted F1-scores of 76.5, 76.1, 74.9, 74.0 and 82.0, respectively. For a test set of images involving a different orchard and cultivar and use of a different camera, the R2 for machine vision to human count of panicles per tree was 0.86, 0.80, 0.83, 0.81 and 0.76 for the same models, respectively. Thus, models generalised well, but with no consistent benefit from use of rotated over upright bounding boxes. While the YOLOv3-rotated model was superior in terms of total panicle count, the R2CNN-upright model was more accurate for panicle stage classification. To demonstrate practical application, panicle counts were made weekly for an orchard of 994 trees, with a peak detection routine applied to document multiple flowering events.

The use of convolutional neural networks (CNNs) in image classification has become the standard method of approaching computer vision problems. Here we apply pre-trained networks to classify images of non-breaking, plunging and spilling breaking waves. The CNNs are used as basic feature extractors and a classifier is then trained on top of these networks. The dynamic nature of breaking waves is exploited by using image sequences to gain extra information and improve the classification results. We also see improved classification performance in using pre-computed image features such as the optical flow between image pairs. The inclusion of the dynamic information improves the classification between breaking wave classes. We also provide corrections to the methodology from the article from which the data originates to achieve a more accurate assessment of performance.

State-of-the-art remote sensing scene classification methods employ different Convolutional Neural Network architectures for achieving very high classification performance. A trait shared by the majority of these methods is that the class associated with each example is ascertained by examining the activations of the last fully connected layer, and the networks are trained to minimize the cross-entropy between predictions extracted from this layer and ground-truth annotations. In this work, we extend this paradigm by introducing an additional output branch which maps the inputs to low dimensional representations, effectively extracting additional feature representations of the inputs. The proposed model imposes additional distance constrains on these representations with respect to identified class representatives, in addition to the traditional categorical cross-entropy between predictions and ground-truth. By extending the typical cross-entropy loss function with a distance learning function, our proposed approach achieves significant gains across a wide set of benchmark datasets in terms of classification, while providing additional evidence related to class membership and classification confidence.

In recent times, using image-based deep learning techniques has been very useful for classifying fruits. However, mango is a particular challenge because its shelf life is directly related to the degree of maturity at the time of harvest, which is determined mainly through the visual assessment of the operators when sorting them, doing it incorrectly, coupled with the blows and compressions exposed during storage and transport, trigger the deterioration in their quality, hence the importance of this operation. In this sense, the purpose of this study focuses on designing a computational model based on Deep Learning that uses a convolutional neural network (CNN) parameterized to select mangoes according to their color tone based on their maturity stage. A dataset was established from 201 labeled images, then a CNN architecture was built, obtaining a model on which 3 criteria were evaluated: the number of convolution and grouping layers, the resolution of the input images and the number of training epochs required. As a result, an input image resolution of 32 x 32 pixels was achieved, the process included a convolution layer followed by pooling that fed another layer that processed the results and ended in an output layer with 2 neurons under the One Hot Encoding representation. The model required 20 epochs to perfect its training, achieving 96.04 % accuracy in mango image selection. This study supports the potential of CNNs in quality analysis through mango color selection, even in uncertainty scenarios.

Multivariate Time Series Classification (MTSC) is one of most important tasks in time series analysis, aiding in activities such as human motion recognition and medical diagnostics. Existing methods for MTSC do not explicitly model temporal differences and generalize the idea of temporal difference into a efficient temporal module. Additionally, existing methods are not yet able to capture cross-variable relationships well during network training. As a result, they are unable to achieve convincing feature representation, leading to suboptimal classification accuracy. In this paper, we propose a novel MTSC model called Temporal Difference and Cross-variate Fusion Network (TDCFN), which integrates a two-stream differential LSTM network and a cross-variate feature extraction network to enhance feature representation. TDCFN achieves superior classification accuracy by capturing dynamic temporal evolution and inter-variable relationships. The experimental results show that TDCFN can achieve competitive performance with state-of-the-art multivariate time series classification approaches.

Seismic imaging is the main technology used for subsurface hydrocarbon prospection. It~provides an image of the subsurface using the same principles as ultrasound medical imaging. As for any data acquired through hydrophones (pressure sensors) and/or geophones (velocity/acceleration sensors), the raw seismic data are heavily contaminated with noise and unwanted reflections that need to be removed before further processing. Therefore, the noise attenuation is done at an early stage and often while acquiring the data. Quality control (QC) is mandatory to give confidence in the denoising process and to ensure that a costly data re-acquisition is not needed. QC is done manually by humans and comprises a major portion of the cost of a typical seismic processing project. It is therefore advantageous to automate this process to improve cost and efficiency. Here, we propose a supervised learning approach to build an automatic QC system. The~QC system is an attribute-based classifier that is trained to classify three types of filtering (mild = under filtering, noise remaining in the data; optimal = good filtering; harsh = over filtering, the signal is distorted). The attributes are computed from the data and represent geophysical and statistical measures of the quality of the filtering. The system is tested on a full-scale survey (9000 km²) to QC the results of the swell noise attenuation process in marine seismic data.

OSI model used to be common network model for years. In the case of ad hoc networks with dynamic topology and difficult radio communications conditions, gradual departure is happening from the classical kind of OSI network model with a clear delineation of layers (physical, channel, network, transport, application) to the cross-layer approach. The layers of the network model in ad hoc networks strongly influence each other. Thus, the cross-layer approach can improve the performance of an ad hoc network by jointly developing protocols using interaction and collaborative optimisation of multiple layers. The existing cross-layer methods classification is too complicated, because it’s based on the whole manifold of network model layers combinations, regardless their importance. In this work, we review ad hoc networks cross-layer methods, propose the new useful classification of cross-layer methods, and show future research directions in ad hoc networks cross-layer methods development. The proposed classification can help to simplify the goal-oriented cross-layer protocol development.

Deep convolutional neural networks (CNN) are favored methods widely used in medical image processing due to their assured shown performance. Recently, the emergence of new lung diseases and the possibility of early detection of their symptoms has attracted many researchers to classify diseases by training deep CNNs on lung CT images. The trained networks are expected to distinguish between lung indications in different diseases, especially at the early stages of them. With the hope of achieving this purpose, we proposed an efficient deep CNN called AFEX-Net with adaptive feature extraction layers that successfully extract distinguishing features and classify chest CT images. The efficiency of the proposed network has two aspects: it is a lightweight network with low number of parameters and fast training and it has adaptive pooling layers and adaptive activation functions to increase its level of compatibility to the input data. The proposed network has been evaluated on a dataset with more than 10K chest CT slices, while an efficient pre-processing method is developed to remove any bias from the images. Additionally, we evaluated the performance of the proposed model on the public COVID-CTset dataset to prove the generalisability of our model. The obtained results confirm the competence of the proposed network in confronting medical images, where prompt and accurate learning is required.

Machine learning applications often need large amounts of training data to perform well. Whereas unlabeled data can be easily gathered, the labeling process is difficult, time-consuming, or expensive in most applications. Active learning can help solve this problem by querying labels for those data points that will improve the performance the most. Thereby, the goal is that the learning algorithm performs sufficiently well with fewer labels. We provide a library called scikit-activeml that covers the most relevant query strategies and implements tools to work with partially labeled data. It is programmed in Python and builds on top of scikit-learn.

Authentication systems based on biometrics characteristics and data represents one of the most important trend in the evolution of our world. In the near future, biometrics systems will be everywhere in the society, such as government, education, smart cities, banks etc. Due to its uniqueness characteristic, biometrics systems will become also vulnerable, privacy being one of the most important challenge. The classic cryptographic primitives are not sufficient to assure a strong level of secureness for privacy. The following work paper represents an effort to present the main cryptographic techniques and algorithms that can give us the possibility to raise a certain level of secureness for privacy. We will show their own challenges (strengths and weaknesses). We will demonstrate how we can use the most common and well-known techniques and algorithms in order to get a maximum efficiency and a high level in assuring the integrity of the biometrics data.

It is demonstrated in this study that PhabrOmeter creates genuine wrinkle on fabrics comparable to that in AATCC specifications, and measures fabric wrinkle recovery values fast with repeatable and reliable results with high resolution, over wide range of fabric types. It thus provides an appealing alternative to the existing test methods that are known to be slow, insensitive and unreliable. In addition, with enormous varieties of fabrics, we used a new criterion termed fabric linear density λ so that fabrics can in general be divided into relatively homogeneous groups for further study. The calculation and application of this parameter are showed in this report.

Leveraging the open-world understanding capacity of large-scale visual-language pre-trained models has become a hot-spot in point cloud classification. Recent approaches rely on transferable visual-language pre-trained models, classifying point clouds by projecting them into 2D images and evaluating consistency with textual prompts. These methods benefit from the robust open-world understanding capabilities of visual-language pre-trained models and require no additional training. However, they face several challenges summarized as prompt ambiguity, image domain gap, view weights confusion, and feature deviation. In response to these challenges, we propose PointBLIP, a zero-training point cloud classification network based on the recently introduced BLIP-2 visual-language model. PointBLIP is adept at processing similarities between multi-images and multi-prompts. We separately introduce a novel method for point cloud zero-shot and few-shot classification, which involves comparing multiple features to achieve effective classification. Simultaneously, we enhance the input data quality for both the image and text sides of PointBLIP. In point cloud zero-shot classification tasks, we outperform state-of-the-art methods on three benchmark datasets. For few-shot classification tasks, to the best of our knowledge, we present the first zero-training few-shot point cloud method, surpassing previous works under the same conditions and showcasing comparable performance to full-training methods.

Digital medicine based on the integration of all medical data of a particular patient, has become a reality today, thanks to information technology. Traditional medical examinations can be supple-mented by assessment results of the oxidative-anti-oxidative (OAO) status of the body [1]. Elec-trochemical sensors are able to not only determine the integral indicators of the OAO system of the body, but also to depict details of the processes occurring in the system. The main obstacle to the widespread use of electrochemical sensors in medical diagnostics is the extremely small amount of the received information in comparison with tens of thousands of known human dis-eases. The problem can be eliminated only by rethinking the purpose of electrochemical measure-ment within the framework of thermodynamics of information processes and information theory. In the information paradigm of electrochemical analysis of biological fluids, a sample is considered as an electrochemical message created by a sensor. The purpose of electrochemical measurement is to obtain information in a volume sufficient to identify the sample composition within the range of possible concentrations of its components. The fundamentals of the thermodynamics of infor-mation processes are considered and conclusions that are of practical importance for the devel-opment of electrochemical sensors and analyzers are derived. It is shown that potentiostatic con-trol of the sensor is physically impacted by the electromechanical instability of the electrical double layer, which is the main source of sensor signal noise. Estimates are of a minimum amount of an-alytical signal information required for identification of a sample of a known composition, such as a biological fluid, are provided. Examples of highly informative analytical signals for flowing and stationary samples are presented. Problems related to the visualization of such signals are noted.

It's challenging to achieve robust lane detection depending on single frame when considering complicated scenarios. In order to detect more credible lane markings by using sequential frames, a novel approach to fusing vision and Inertial Measurement Unit (IMU) is proposed in this paper. The hough space is employed as the space where lane markings are stored and it's calculated by three steps. Firstly, a basic hough space is extracted by Hough Transform and primary line segments are extracted from it. In order to measure the possibility about line segments belong to lane markings, a CNNs based classifier is introduced to transform the basic hough space into a probabilistic space by using the networks outputs. However, this probabilistic hough space based on single frame is easily disturbed. In the third step, a filtering process is employed to smooth the probabilistic hough space by using sequential information. Pose information provided by IMU is applied to align hough spaces extracted at different times to each other. The final hough space is used to eliminate line segments with low possibility and output those with high confidence as the result. Experiments demonstrate that the proposed approach has achieved a good performance.

The research of object classification and part segmentation is a hot topic in computer vision. A considerable number of studies have been carried out about deep learning on 3D point clouds. However,it is challenging to achieve effective feature learning due to sparsity of point clouds. Recently, a variety of Transformers have been adopted to improve point cloud processing and display great potential. Nevertheless, large numbers of Transformer layers tend to incur huge computational and memory costs. PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks, this does not mean that PointNet++ has no potential.Thus, this paper offer two major contributions that significantly improve PointNet++ performance. Firstly, we introduce a novel contextual feature extraction (CFE) block that significantly enhances the feature extraction capabilities of PointNet++ networks. Secondly, to further enhance feature fusion, we seamlessly integrate a mutual learning (ML) block into the network architecture. By embedding these two innovative blocks within each layer of the network, we not only enrich the network's functionality but also impart it with greater robustness and adaptability. The specific experiments were conducted on the S3DIS (6-fold cross-validation) and Modelnet40 datasets with 86.5% and 92.7% accuracy, respectively, which proved that our model is comparable or even better than most existing methods for classification and segmentation tasks.

Soccer is type of sport that carries a high risk of injury. Injury is not only cause in the unlucky soccer carrier and also team performance as well as financial effects can be worse since soccer is a team-based game. The duration of recovery from a soccer injury typically relies on its type and severity. Therefore, we conduct this research in order to predict the probability of players injury type using machine learning technologies in this paper. Furthermore, we compare different machine learning models to find the best fit model. Supervised classification machine learning models are applied in this paper. We gathered information about 54 professional soccer players who are playing in the top five European leagues based on their career history.

This paper introduces a multi-class hand gesture recognition model developed to identify a set of defined hand gesture sequences in two-dimensional RGB video recordings. The work presents an action detection classifier that looks at both appearance and spatiotemporal parameters of consecutive frames. The classifier utilizes a convolutional-based network combined with a long-short-term memory unit. To leverage the need for a large-scale dataset, the model uses an available dataset to then adopt a technique known as transfer learning to fine-tune the model on the hand gestures of relevance. Validation curves performed over a batch size of 64 indicate an accuracy of 93.95% (± 0.37) with a mean Jaccard index of 0.812 (± 0.105) for 22 participants. The presented model illustrates the possibility of training a model with a small set of data (113,410 fully labelled frames). The proposed pipeline embraces a small-sized architecture that could facilitate its adoption.

Finding an optimal combination of features and classifier is still an open problem in the development of automatic heartbeat classification systems, especially when applications that involve resource-constrained devices are considered. In this paper, a novel study of the selection of informative features and the use of a random forest classifier while following the recommendations of the Association for the Advancement of Medical Instrumentation (AAMI) and an inter-patient division of datasets is presented. Features were selected using a filter method based on the mutual information ranking criterion on the training set. Results showed that normalized R-R intervals and features relative to the width of the QRS complex are the most discriminative among those considered. The best results achieved on the MIT-BIH Arrhythmia Database were an overall accuracy of 96.14% and F1-scores of 97.97%, 73.06%, and 90.85% in the classification of normal beats, supraventricular ectopic beats, and ventricular ectopic beats respectively. In comparison with other state of the art approaches tested under similar constraints, this work represents one of the highest performances reported to date while relying on a very small feature vector.

As Artificial Intelligence (AI) technology, particularly Machine Learning algorithms, becomes increasingly ubiquitous, our abilities to understand and interpret AI and machine learning algorithms are becoming increasingly desirable. Visualization has been used as a common tool to view and understand complex machine learning processes. In this paper, we will focus on developing a general framework for the visualization of machine learning models as a scalar valued multi-dimensional function to help users understand how the models behave over different viewing spaces. We first give a formal definition of the visualization problem. Interpolation-based morphing and subspace sampling techniques are applied to generate various renderings through projections and cross-sections of the model space as 3D surfaces or heatmap images. This method will be applied to two real-world datasets and applications: the diagnosis of Alzheimer's Disease (AD) using a human brain networks dataset and a real-world benchmark dataset for predicting home credit default risks. The visualizations show that different machine learning algorithms can behave quite differently under different conditions.

Evolutionary Machine Learning (EML) has demonstrated its effectiveness in modeling various real-world application domains, including the dynamics of diseases and the creation of predictive models across diverse fields. However, the challenge of data imbalance adversely impacts the performance of EML models. While strategies involving misclassification costs or cost-sensitive learning exist to address this issue, their integration into EML has yet to be thoroughly explored. This paper aims to fill this gap by investigating the application of cost-sensitive EML for intelligent health risk prediction. More specifically, this paper delves into the utilization of cost-sensitive genetic programming (CSGP) and cost-sensitive genetic algorithms (CSGA), which are among the most widely used algorithms in the EML category. The study entails training CSGP and CSGA to predict the early onset of three chronic conditions (hypertension, diabetes, and fatty acid-related disorders) through the development of an EML model. Subsequently, the model's performance is evaluated through standard fitness functions such as sensitivity, specificity, and F1-score. From the experimental results, EML models demonstrate promising results in identifying the occurrence of chronic diseases. Further optimization of the cost-sensitive EML model holds the potential for enhanced outcomes in modeling medical problems.

The rising global population amidst the growing concerns of climate change will have a dire consequence on global food security and socio-economic activities. Wheat is one of the most important staple foods consumed by more than four billion people in the world, but climate change impacts account for a decline of 5.5% in wheat yield and predictions indicate that the production could further dwindle by nearly 30% in 2050, due to trends in temperature, precipitation, and carbon dioxide. An effective annual crop estimate is necessary not only to inform government the status of national food security, but also is used to determine the benchmark on which agricultural commodities are priced in the market. Thus, annual crop monitoring and yield estimate is paramount to determine the amount of wheat imports required to make up for the shortfalls in the national wheat production in South Africa, which has been a net importer of wheat since 1998. A joint project between South Africa and Poland investigated satellite based-crop growth monitoring using Sentinel 2 and determined the most distinguishable crop phenology for an accurate winter wheat classification during the growing season from August – December with Random Forest (RF) algorithm. The winter wheat crop was more accurately identified during the crop ‘heading’ stage in October yielding the highest user’s (75.56%) and producer’s (92.52%) accuracies, despite the relatively lower overall accuracy (78.14%) compared to that of December with OA of 83.58% obtained during the maturity stage. This study, therefore, confirms the suitability of sentinel 2 for an effective phenology-based winter wheat crop classification during the heading stage, reducing the ambiguity of spectral confusion created with surrounding grass and maize crops.

To ensure consumers can purchase high-quality rice, accurate identification of rice varieties is particularly important. Methods: This article conducts research based on machine learning algorithms from the perspectives of image, spectrum, and spectrogram fusion. Six types of hyperspectral image data of rice were preprocessed using convolutional smoothing (SG) and multiple scatter correction (MSC). Texture information of the images was extracted using gray-level co-occurrence matrix. Spectra, texture, and spectrogram data were fused into a new matrix. Spectral, texture, and spectrogram fusion data were used as inputs for the model, and support vector machines (SVM), logistic regression (LR), and K-nearest neighbors (KNN) classification models were constructed and compared. Results: From the classification results, the spectrogram fusion classification performance was better than classification models using only spectra or texture. Conclusion: The research results showed that the accuracy of SVM and LR classification models exceeded 90%, and the LR model performed the best, effectively classifying rice varieties.

Olive Anthracnose (OA) is the most important fungal disease of olive fruits worldwide. In the context of integrated pest management, the development of predictive models could be used for early diagnosis and control. In the current study, a dataset representing 58 cases (6 locations with 12 olive cultivars) was used to study the relationship between ΟΑ incidence (OAI) and 35 heterogeneous variables, including orchard characteristics, olive fruit parameters, foliar and soil nutrients, soil parameters and soil texture classes. The Random Forest-Recursive Feature Elimination with Cross Validation (RF-RFECV) feature selection method identified Location, Water Content, P, Ca, Mg, Exchangeable Mg, Trace Zn, Trace Cu as possible new indicators associated with OAI. Six different classification algorithms, namely Decision Tree (DT), Gradient Boosting (GB), Logistic Regression (LR), Random Forest (RF), K-Nearest Neighbors (KNN) and Support Vector Machine (SVM), were developed for predicting conditions leading to OAI >0% and 10%. Hyperparameter optimization using grid search was used to optimize the parameters of the models and finally the best parameters were applied to predict the OAI. The final models were evaluated in terms of several standard metrics, such as accuracy, sensitivity, specificity and ROC AUC score. Findings suggested that GB performance was superior compared to the other models for the prediction of the occurrence of OA disease (OAI>0%) with an accuracy of 86.7%, a sensitivity of 100%, a specificity of 75% and a ROC-AUC score of 93%, while for the prediction of the spread of the disease (OAI>10%), DT stood out with an accuracy of 86.7%, a sensitivity of 81.8%, a specificity of 100% and a ROC-AUC score of 91%. RF classifier performed very well in both cases, with an accuracy of 80%, a sensitivity of 85.7%, a specificity of 75% and a ROC-AUC score of 93% for the prediction of the occurrence of the disease (OAI>0%), and an accuracy of 86.7%, a sensitivity of 90.9%, a specificity of 75% and a ROC-AUC score of 84% for the prediction of the spread of the disease (OAI>10%).

In August 2020, the World Health Assembly launched a global initiative to eliminate cervical cancer by 2030, setting three primary targets. One key goal is to achieve a 70% screening coverage rate for cervical cancer, primarily relying on the precise analysis of Papanicolaou (Pap) or digital Pap smears. However, the responsibility of reviewing Pap smear samples to identify potentially cancerous cells primarily falls on pathologists, a task known to be exceptionally challenging and time-consuming. This paper proposes a solution to address the shortage of pathologists for cervical cancer screening. It leverages the OpenAI-GYM API to create a deep reinforcement learning environment utilizing liquid-based Pap smear images. By employing the Proximal Policy Optimization algorithm, autonomous agents navigate Pap smear images, identifying cells with the aid of rewards, penalties, and accumulated experiences. Furthermore, the use of a pre-trained convolutional neuronal network like Res-Net54 enhances the classification of detected cells based on their potential for malignancy. The ultimate goal of this study is to develop a highly efficient, automated Papanicolaou analysis system, ultimately reducing the need for human intervention in regions with limited pathologists.