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.

The early-season area estimation of the winter wheat crop as a strategic product is important for decision makers. Classification of multi-temporal images is an approach which is affected by many factors like appropriate training sample size, proper frequency and acquisition times, vegetation indices (VIs) type, temporal gradient of spectral bands and VIs, appropriate classifier and missed values because of cloudy conditions. This paper addresses the impact of appropriate frequency and acquisition times and VIs type along with the spectral and VI gradient on random forest (RF) classifier when missed values exist in multi-temporal images. To investigate the appropriate temporal resolution for image acquisition, the study area was selected on an overlapping area between two LDCM paths. In our developed method, the miss values of cloudy bands for each pixel are retrieved by the mean of k-nearest ordinary pixels. Then the multi-temporal image analysis is performed by considering different scenarios provided by decision makers in terms of desired crop types that should be extracted at early-season in the study areas. The classification results obtained by the RF decrease by 1.6% when temporally missed values retrieved by the proposed method, which is an acceptable result. Moreover, the experimental results demonstrated that if temporal resolution of Landsat 8 increased to one week the classification task can be conducted earlier with almost better results in terms of OA and kappa. The impact of incorporating VIs along with the temporal gradients of spectral bands and VIs as new features in RF demonstrated that the OA and Kappa are improved 3.1% and 6.6%, respectively. Furthermore, the obtained result showed that if only one image from seasonal changes of crops is available, the temporal gradient of VIs and spectral bands play the main role to discriminate remarkably wheat from barley. The experiments also demonstrated that if both wheat and barley merge to a single class the crop area can be estimated two months earlier with 97.1 and 93.5 in terms of OA and kappa, respectively.

Cash crops are agricultural crops intended to be sold for profit as opposed to subsistence crops, meant to support the producer, or to support livestock. Since cash crops are intended for future sale, they translate into large financial value when considered on a wide geographical scale, so their production directly involves financial risk. At a national level, extreme weather events including destructive rain or hail, as well as drought, can have a significant impact on the overall economic balance. It is thus important to map such crops in order to set up insurance and mitigation strategies. Using locally generated data -such as municipality-level records of crop seeding- for mapping purposes implies facing a series of issues like data availability, quality, homogeneity etc. We thus opted for a different approach relying on global datasets. Global datasets ensure homogeneity and availability of data, although sometimes at the expense of precision and accuracy. A typical global approach makes use of spaceborne remote sensing, for which different land cover classification strategies are available in literature at different levels of cost and accuracy. We selected the optimal strategy in the perspective of a global processing chain. Thanks to a specifically developed strategy for fusing unsupervised classification results with environmental constraints and other geospatial inputs including ground-based data, we managed to obtain good classification results despite the constraints placed. The overall production process was composed using ``good-enough" algorithms at each step, ensuring that the precision, accuracy, and data-hunger of each algorithm was commensurate to the precision, accuracy, and amount of data available. This paper describes the tailored strategy developed on the occasion as a cooperation among different groups with diverse backgrounds, a strategy which is believed to be profitably reusable in other, similar contexts. The paper presents the problem, the constraints and the adopted solutions; it then summarizes the main findings including that efforts and costs can be saved on the side of Earth Observation data processing when additional ground-based data are available to support the mapping task.

The visualization of hyperspectral images in display devices, having RGB colour composition channels is quite difficult due to the high dimensionality of these images. Thus, principal component analysis has been used as a dimensionality reduction algorithm to reduce information loss, by creating uncorrelated features. To classify regions in the hyperspectral images, K-means clustering has been used to form clusters/regions. These two algorithms have been implemented on the three datasets imaged by AVIRIS and ROSIS sensors.

The study concentrates on researching possibilities of using computer image analysis and neural modeling in order to assess selected quality discriminants of spray-dried chokeberry powder. The aim of the paper is quality identification of chokeberry powders on account of their highest dying power, the highest bioactivity as well as technologically satisfying looseness of powder. The article presents neural models with vision technique backed up by devices such as digital camera as well as electron microscope. Reduction in size of input variables with PCA has influence on improving the processes of learning data sets, thus increasing effectiveness of identifying chokeberry fruit powders included in digital pictures, which is shown in the results of the conducted research. The effectiveness of image recognition are presented by classifying abilities as well as low Root Mean Square Error (RMSE), for which the best results are achieved with typology of network type Multi-Layer Perceptron (MLP). The selected networks type MLP are characterized by the highest degree of classification at 0.99 and RMSE at 0.11 at most at the same time.

Psoriasis is a chronic, multisystem, inflammatory disease. The typical clinical cutaneous manifestation of psoriasis is scaly erythema or plaque, limited or widely distributed. However, psoriasis is far beyond the skin involvement and provides many challenges, including associated comorbidities. In this review, we classify psoriasis as cutaneous and systemic psoriasis, according to the clinical diversity and associated comorbid diseases, and recommend classification criteria for psoriasis. The key objective of this novel classification is to raise awareness of the complexity of this multifaceted disease and help to better understand and manage this complex disease comprehensively.

Opportunistic routing is the latest technique that uses the broadcasting nature of the wireless medium to increase the number of potential forwarding nodes in the network. This, in turn improves the delivery rate and reliability of data transmission in the network. Compared to all previous classes of routing protocols, opportunistic routing offers numerous advantages which is exploited by the latest applications for efficient communication and resource sharing in dynamic ad hoc networks. These applications provide dynamic communication in disaster recovery environments. The objective of this research work is to review and classify all the major opportunistic routing protocols proposed for dynamic ad hoc networks. Further the issues and challenges with each of these existing protocol is discussed and future research directions are put forward

A sustainable business model describes the rationale of how an organization creates, delivers, and captures value, in economic, social, cultural or other contexts in a sustainable way. The process of sustainable business model construction forms an innovative part of business strategy. Different industries and business types have utilized sustainability business models to satisfy their economic, environmental and social goals simultaneously. This study is conducted to present the state of the art of sustainable business models in various application areas. The business models are classified and reviewed in different application groups. To do so, a review is conducted, and the findings reveal that the application of sustainability business models can be classified in 16 unique categories. The key contribution of this study is providing an insight about the state of the art of sustainable business models in various application areas and its research path.

The Japanese Association for Acute Medicine Committee recently proposed a novel classification system for the severity of heat-related illnesses. The illnesses are simply classified into three stages based on symptoms and management or treatment. Stages I, II, and III broadly correspond to heat cramp and syncope, heat exhaustion, and heat stroke, respectively. Our objective was to examine whether this novel severity classification is useful in the diagnosis by healthcare professionals of patients with severe heat-related illness and organ failure. A nationwide surveillance study of heat-related illnesses was conducted between June 1 and September 30, 2012, at emergency departments in Japan. Among the 2130 patients who attended 102 emergency departments, the severity of their heat-related illness was recorded for 1799 patients, who were included in this study. In the patients with heat cramp and syncope or heat exhaustion (but not heat stroke), the blood test data (alanine aminotransferase, creatinine, blood urea nitrogen, and platelet counts) for those classified as stage III were significantly higher than those of patients classified as stage I or II. There were no deaths among the patients classified as stage I. This novel classification may avoid underestimating the severity of heat-related illness.

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.

To improve the tangerine crop yield, the work of recognizing and then disposing of specific pests is becoming increasingly important. The task of recognition is based on the features extracted from the images that have been collected from websites and outdoors. Traditional recognition and deep learning methods, such as KNN (k-nearest neighbors) and AlexNet, are not preferred by knowledgeable researchers, who have proven them inaccurate. In this paper, we exploit four kinds of structures of advanced deep learning to classify 10 citrus pests. The experimental results show that Inception-ResNet-V3 obtains the minimum classification error.

Recent advances in recording and real-time analysis of surface electromyographic signals (sEMG) have fostered the use of sEMG human-machine interfaces for controlling personal computers, prostheses of upper limbs, and exoskeletons among others. Despite a relatively high mean performance, sEMG-interfaces still exhibit strong variance in the fidelity of gesture recognition among different users. Here we systematically study the latent factors determining the performance of sEMG-interfaces in synthetic tests and in an arcade game. We show that the degree of muscle cooperation and the amount of the body fatty tissue are the decisive factors in synthetic tests. Our data suggest that these factors can only be adjusted by a long-term training, which promotes fine-tuning of low-level neural circuits driving the muscles. A short-term training has no effect on synthetic tests, but significantly increases the game scoring. This implies that it works at a higher decision-making level, not relevant for synthetic gestures. We propose a procedure that enables quantification of the gestures’ fidelity in a dynamic gaming environment. For each individual subject the approach allows identifying “problematic” gestures that decrease gaming performance. This information can be used for optimizing the training strategy and for adapting the signal processing algorithms to individual users, which could be a way for a qualitative leap in the development of future sEMG-interfaces.

Emotions are indicators of affective states and play a significant role in human daily life, behavior, and interactions. Giving emotional intelligence to the machines could, for instance, facilitate early detection and prediction of (mental) diseases and symptoms. Electroencephalography (EEG) -based emotion recognition is being widely applied because it measures electrical correlates directly from the brain rather than the indirect measurement of other physiological responses initiated by the brain. The recent development of non-invasive and portable EEG sensors makes it possible to use them in real-time applications. Therefore, this paper presents a real-time emotion classification pipeline, which trains different binary classifiers for the dimensions of Valence and Arousal from an incoming EEG data stream. After achieving a 23.9% (Arousal) and 25.8% (Valence) higher f1-score on the state-of-art AMIGOS dataset, this pipeline was applied to the dataset achieved by an emotion elicitation experimental framework developed within the scope of this thesis. Following two different protocols, 15 participants were recorded using two different consumer-grade EEG devices while watching 16 short emotional videos in a controlled environment. For an immediate label setting, the mean f1-score of 87% and 82% were achieved for Arousal and Valence, respectively. In a live scenario, while continuously being updated on the incoming data stream with delayed labels, the pipeline proved to be fast enough to achieve predictions in real time. However, the significant discrepancy from the readily available labels on the classification scores leads to future work to include more data with frequent delayed labels in the live settings.

Objective: To evaluate the existing meta-analytic evidence of associations between exposure to ultra-processed foods, as defined by the Nova food classification system, and adverse health outcomes. Design: Systematic umbrella review of existing meta-analyses. Data Sources: MEDLINE, PsycINFO, Embase, and the Cochrane Database of Systematic Reviews, as well as manually searching reference lists from 2009 to June 2023. Inclusion Criteria: Systematic reviews and meta-analyses of cohort, case-control, and/or cross-sectional study designs that evaluated the associations between exposure to ultra-processed foods and adverse health outcomes in humans across the lifespan. Results: The search identified 45 unique pooled analyses, including 13 dose-response and 32 non-dose-response associations (n=9,888,373). Overall, direct associations were found between exposure to ultra-processed foods and 32 (71%) health outcome domains spanning cardiometabolic, gastrointestinal, and respiratory conditions, cancer, mental health, and mortality. Based on a pre-specified evidence classification criteria, convincing evidence (Class I) supported direct associations between greater ultra-processed food exposure and higher risks of incident cardiovascular disease-related mortality (RR: 1.50; 95%CIs: 1.37 to 1.63), type two diabetes (dose-response RR: 1.12; 95%CIs: 1.11 to 1.13), and depressive outcomes (HR: 1.21; 95%CIs: 1.16 to 1.28), as well as higher risks of prevalent anxiety outcomes (OR: 1.48; 95%CIs: 1.37 to 1.59) and combined common mental disorder outcomes (OR: 1.53; 95%CIs: 1.43 to 1.63). Highly suggestive (Class II) evidence indicated that greater exposure to ultra-processed foods was directly associated with higher risks of incident all-cause mortality (RR: 1.21; 95%CIs: 1.15 to 1.27), heart disease-related mortality (dose-response HR: 1.66; 95%CIs: 1.51 to 1.84), and type two diabetes (OR: 1.40; 95%CIs: 1.23 to 1.59), together with higher risks of prevalent obesity (OR: 1.55; 95%CIs: 1.36 to 1.77), adverse sleep-related outcomes (OR: 1.41; 95%CIs: 1.24 to 1.60), and wheezing (RR: 1.40; 95%CIs: 1.27 to 1.55). Out of the remaining 34 pooled analyses, 21 were graded as suggestive or weak strength (Class III-IV) and 13 were graded as no evidence (Class V). Using the GRADE framework, 22 pooled analyses were rated as "Low" quality, with 19 rated as "Very Low” and four rated as "Moderate" quality. Conclusions: Higher exposure to ultra-processed food was associated with a greater risk of adverse health outcomes, especially cardiometabolic, common mental disorder, and mortality outcomes. These findings provide a rationale to evaluate the effectiveness of using population-based measures to target and reduce dietary exposure to ultra-processed foods for improved human health. Systematic Review Registration: PROSPERO CRD42023412732.

Antimicrobial use (AMU) is one of the major drivers of emerging antimicrobial resistance (AMR). Surveillance of AMU, a pillar of AMR stewardship (AMS), helps devise strategies to mitigate AMR. This descriptive, longitudinal retrospective study quantified the trends in human antibiotic utilization between 2010 and 2016 using data on all antibiotics imported for systemic human use into Tanzania's mainland. Regression and time series analyses were used to establish trends in antibiotics use. A total of 12,073 records for antibiotics were retrieved, totaling 154.51Daily Defined Doses per 1,000 inhabitants per day (DID) with a mean (± standard deviation) of 22.07 (±48.85) DID. The private sector contributed 93.76%% of utilized antibiotics. The top-ranking antibiotics were amoxicillin, metronidazole, tetracycline, ciprofloxacin and cefalexin. The DDIs and percentage contribution of these antibiotics were 53.78 (34.81%), 23.86 (15.44), 20.53 (13.29), 9.27 (6.0) and 6.94 (4.49), respectively. The time series model predicted significant increase in utilization(p-value =0.002). The model forecasted that by 2022, the total antibiotics consumed would reach 89.6 DIDs, corresponding to a 13-fold increase compared to 2010. Government intervention to curb inappropriate antibiotic utilization to mitigate the rising threat of antibiotic resistance should focus on implementing AMS programs in pharmacies and hospitals in Tanzania.

Although Support Vector Machines (SVM) are widely used for classifying human motion patterns, their application in the automatic recognition of dynamic and static activities of daily life in the healthy older adults is limited. Using a body mounted wireless inertial measurement unit (IMU), this paper explores the use of SVM approach for classifying dynamic (walking) and static (sitting, standing and lying) activities of the older adults. Specifically, data formatting and feature extraction methods associated with IMU signals are discussed. To evaluate the performance of the SVM algorithm, the effects of two parameters involved in SVM algorithm—the soft margin constant C and the kernel function parameter $\mathsf{\gamma }$—are investigated. The changes associated with adding white-noise and pink-noise on these two parameters along with adding different sources of movement variations (i.e., localized muscle fatigue and mixed activities) are further discussed. The results indicate that the SVM algorithm is capable of keeping high overall accuracy by adjusting the two parameters for dynamic as well as static activities, and may be applied as a tool for automatically identifying dynamic and static activities of daily life in the older adults.

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.

The article describes a classification solution for amber stones. The problem of classifying amber is known for a long time among jewelers and artisans of amber art. Existing solutions can classify amber pieces according to color, but a need to classify by shape and texture is not satisfied up to now. The proposed solution is capable of classifying the gemstones according to a shape. Amber can be considered as a specific object since the form is difficult to define unambiguously. Data for amber experiments was gathered from amber art craftsmen. In the proposed solution amber form can be classified into 10 different classes (7 classes chosen during the experiment).

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.

Time recordings of impulse-type oscillation responses are short and highly transient. These characteristics may complicate the usage of classical spectral signal processing techniques for a) describing the dynamics and b) deriving discriminative features from the data. However, common model identification and validation techniques mostly rely on steady-state recordings, characteristic spectral properties and non-transient behavior. In this work, a recent method, which allows reconstructing differential equations from time series data, is extended for higher degrees of automation. With special focus on short and strongly damped oscillations, an optimization procedure is proposed that fine-tunes the reconstructed dynamical models with respect to model simplicity and error reduction. This framework is analyzed with particular focus on the amount of information available to the reconstruction, noise contamination and non-linearities contained in the time series input. Using the example of a mechanical oscillator, we illustrate how the optimized reconstruction method can be used to identify a suitable model and to extract features from uni-variate and multivariate time series recordings in an engineering-compliant environment. Moreover, the determined minimal models allow for identifying the qualitative nature of the underlying dynamical systems as well as testing for the degree and strength of non-linearity. The reconstructed differential equations would then be potentially available for classical numerical studies, such as bifurcation analysis. These results represent a physically interpretable enhancement of data-driven modeling approaches in structural dynamics.

Automation is at the core of modern industry. It aims to increase production rates, decrease production costs, and reduce human intervention in order to avoid human mistakes and time delays during manufacturing. On the other hand, human assistance is usually required to customize products and reconfigure control systems through a special process interface called Human Machine Interface (HMI). Machine Learning (ML) algorithms can effectively be used to resolve this tradeoff between full automation and human assistance. This paper provides an example of the industrial application of ML algorithms to help human operators save their mental effort and avoid time delays and unintended mistakes for the sake of high production rates. Based on real-time sensor measurements, several ML algorithms have been tried to classify paper rolls according to paper grammage in a white paper mill. The performance evaluation shows that the AdaBoost algorithm is the best ML algorithm for this application with classification accuracy (CA), precision, and recall of 97.1%. The generalization of the proposed approach for achieving a cost-effective mill construction by reducing the total number of the required physical sensors will be the subject of our future research.

A multi-decadal change analysis of the irrigation ponds in Taoyuan, Taiwan was conducted by using multi-source data including digitized ancient maps, declassified single-band CORONA satellite images, and multispectral SPOT images. Supervised LULC classifications were conducted using four textural features derived from the single-band CORONA images and spectral features derived from SPOT images. Post-classification analysis revealed that the number of irrigation ponds in the study area decreased during the post-World War II farmland consolidation period (1945 – 1965) and the subsequent industrialization period (1970 – 2000). However, efforts on restoration of irrigation ponds in recent years have resulted in gradual increases in the number (9%) and total area (12%) of irrigation ponds in the study area.

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.

Electronic invoicing has become mandatory for Italian companies since January 2019. Invoices are structured in a predefined xml template where the information reported can be easily extracted and analyzed. The main aim of this paper is to exploit the information structured in electronic invoices to build an intelligent system which can facilitate accountants work. More precisely, this contribution shows how it is possible to automate part of the accounting process: all sent or received invoices of a company are classified into specific codes which represent the economic nature of the the financial transactions. In order to classify data contained in the invoices a machine learning multiclass classification problem is proposed using as input variables the information of the invoices to predict two different target variables, account codes and the VAT codes, which composes a general ledger entry. Different approaches are compared in terms of prediction accuracy. The best performance is achieved considering the hierarchical structure of the account codes.

In recent years, the field of deep learning achieved considerable success in pattern recognition, image segmentation and may other classification fields. There are a lot of studies and practical applications of deep learning on images, video or text classification. In this study, we suggest a method for changing the architecture of the most performing CNN models with the aim of designing new models to be used as stand-alone networks or as a component of an ensemble. We propose to replace each activation layer of a CNN (usually a ReLu layer) by a different activation function stochastically drawn from a set of activation functions: in this way the resulting CNN has a different set of activation function layers.

Delineating the cropping area of cocoa agroforests is a major challenge for quantifying the contribution of the land use expansion to tropical deforestation. Discriminating cocoa agroforests from tropical transition forests using multi-spectral optical images is difficult due to a similarity in the spectral characteristics of their canopy; moreover, optical sensors are largely impeded by the frequent cloud cover in the tropics. This study explores multi-season Sentinel-1 C-band SAR image to discriminate cocoa agroforests from transition forests for a heterogeneous landscape in central Cameroon. We use an ensemble classifier, random forest, to average SAR image texture features of GLCM (Grey Level Co-occurrence Matrix) across seasons; next, we compare classification performance with results from RapidEye optical data. Moreover, we assess the performance of GLCM texture feature extraction at four different grey level quantization: 32bits, 8bits, 6bits, and 4bits. The classification overall accuracy (OA) of texture-based maps outperformed that from an optical image; the highest OA of 88.8% was recorded at 6bits grey level. This quantization level, in comparison to the initial 32bits in SAR images, reduced the class prediction error by 2.9%. Although this prediction gain may be large for the landscape area, the resultant thematic map reveals the decrease and fragmentation of forest cover by cocoa agroforests. According to our classification validation, the Shannon entropy (H) or uncertainty provides a reliable validation for class predictions and reveals detail inference for discriminating inherently heterogeneous vegetation categories. The texture-based classification achieved a reliable accuracy considering the heterogeneity of the landscape and vegetation classes.

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.

We present and benchmark FilterNet, a flexible deep learning architecture for time series classification tasks, such as activity recognition via multichannel sensor data. It adapts popular CNN and CNN-LSTM motifs which have excelled in activity recognition benchmarks, implementing them in a many-to-many architecture to markedly improve frame-by-frame accuracy, event segmentation accuracy, model size, and computational efficiency. We propose several model variants, evaluate them alongside other published models using the Opportunity benchmark dataset, demonstrate the effect of model ensembling and of altering key parameters, and quantify the quality of the models’ segmentation of discrete events. We also offer recommendations for use and suggest potential model extensions. FilterNet advances the state of the art in all measured accuracy and speed metrics on the benchmarked dataset, and it can be extensively customized for other applications.

This paper discusses the computer-aided (CAD) classification between Hepatocellular Carcinoma (HCC), i.e., the most common type of liver cancer, and Liver Abscess, based on ultrasound image texture features and Support Vector Machine (SVM) classifier. Among 79 cases of liver diseases, with 44 cases of HCC and 35 cases of liver abscess, this research extracts 96 features of Gray-Level Co-occurrence Matrix (GLCM) and Gray-Level Run-Length Matrix (GLRLM) from the region of interests (ROIs) in ultrasound images. Three feature selection models, i) Sequential Forward Selection, ii) Sequential Backward Selection, and iii) F-score, are adopted to determine the identification of these liver diseases. Finally, the developed system can classify HCC and liver abscess by SVM with the accuracy of 88.875%. The proposed methods can provide diagnostic assistance while distinguishing two kinds of liver diseases by using a CAD system.

Successful engineering of a microbial host for efficient production of a target product from a given substrate can be viewed as an extensive optimization task. Such a task involves the selection of high activity enzymes as well as their gene expression regulatory control elements (i.e., promoters and ribosome binding sites). Finally, there is also the need to tune expression of multiple genes along a heterologous pathway to relieve constraints from rate-limiting step and help reduce metabolic burden on cells from unnecessary over-expression of high activity enzymes. While the aforementioned tasks could be performed through combinatorial experiments, such an approach incurs significant cost, time and effort, which is a handicap that can be relieved by application of modern machine learning tools. Such tools could attempt to predict high activity enzymes from sequence, but they are currently most usefully applied in classifying strong promoters from weaker ones as well as combinatorial tuning of expression of multiple genes. This perspective reviews the application of machine learning tools to aid metabolic pathway optimization through identifying challenges in metabolic engineering that could be overcome with the help of machine learning tools.

Rotavirus species H (RVH) has been detected in pigs, humans and bats. Moreover, porcine RVHs have been recently identified in several swine-producing countries. Despite their zoonotic impact, genome information of RVHs is still limited. This study aimed to establish a tentative complete genome-based genotyping system for RVHs, by appending genomic sequences from 12 porcine RVHs identified in Japan between 2013 and 2015 to those from human and other porcine RVHs reported in previous studies. Phylogenetic analysis of 11 RNA segments indicated that porcine RVHs could be classified into multiple genotypes. Consequently, the genotype classification for RVHs revealed the existence of genotypes 10G, 6P, 6I, 3R, 4C, 7M, 6A, 2N, 4T, 6E, 3H for the genes VP7, VP4, VP6, VP1, VP2, VP3, NSP1, NSP2, NSP3, NSP4 and NSP5, respectively. Surprisingly, two distinctive types in NSP1 and NSP3 genes were identified from among the twelve porcine RVHs. Our data suggest a potentially novel gene rearrangement event between porcine RVH and rotavirus species C in the NSP3 gene. These findings would provide a new insight in understanding for evolution of RV.

Deep learning has shown remarkable results in every field, especially in the biomedical field, due to its ability to exploit large-scale datasets. A convolutional neural network (CNN) is a widely used deep learning approach to solve medical imaging problems. Over the past few years, many studies have focused on CNN-based techniques for brain tumor diagnosis. There are, however, still some critical challenges that CNNs face towards clinic application. This study presents a comprehensive review of current literature that involves CNN architectures for brain tumor classification. We compare the key achievements in the performance evaluation metrics of the applied classification algorithms. In addition, this review assesses the clinical effectiveness of the included studies to elaborate on the limitations and directions of this area for future work. No review focusing on the clinical effectiveness of previous works in this field has been published. We believe that this study has the potential to elevate the application of CNN-based deep learning methods in clinical practice and also can be a quick reference for biomedical researchers who are interested in this field.

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

Genetic testing allows for identification of germline DNA variations which are associated with a significant increase in risk of developing breast and ovarian cancer. Detection of a BRCA1 or BRCA2 pathogenic variant triggers several clinical management actions, which may include increased surveillance and prophylactic surgery for healthy carriers or treatment with PARP inhibitor therapy for carriers diagnosed with cancer. Thus, standardized validated criteria for annotation of BRCA1 and BRCA2 variants according to their pathogenicity are necessary to support clinical decision making and ensure improved outcomes. Upon detection, variants whose pathogenicity can be inferred by the genetic code are typically classified as pathogenic, likely pathogenic, likely benign, or benign. Variants whose impact on function cannot be directly inferred by the genetic code are labeled as Variants of Uncertain Clinical Significance (VUS) and are evaluated by multifactorial likelihood models that use personal and family history of cancer, segregation data, prediction tools, and co-occurrence with a pathogenic BRCA variant. Missense variants, coding alterations that replace a single amino acid residue with another, are a class of variants for which determination of clinical relevance is particularly challenging. Here, we discuss current issues in variant classification by following a typical life cycle of a BRCA1 missense variant through detection, annotation and information dissemination. Advances in massively parallel sequencing have led to a substantial increase in VUS findings. Although comprehensive assessment and classification of missense variants according to their pathogenicity remains the bottle neck, new developments in functional analysis, high throughput assays, data sharing, and statistical models are rapidly changing this scenario.

Nowadays, according to spectacular improvement in health care and biomedical level, a tremendous amount of data is recorded by hospitals. In addition, the most effective approach to reduce disease mortality is to diagnose it as soon as possible. As a result, data mining by applying machine learning in the field of diseases provides good opportunities to examine the hidden patterns of this collection. An exact forecast of the mortality after heart surgery will cause Successful medical treatment and fewer costs. This research wants to recommend a new stacking predictive model after utilizing the random forest feature importance method to foresee the mortality after heart surgery on a highly unbalanced dataset by using the most practical features. To solve the unbalanced data problem, a combination of the SVM-SMOTE over-sampling algorithm and the Edited-Nearest-Neighbor under-sampling algorithm is used. This research compares the introduced model with some other machine learning classifiers to ensure efficiency through shuffle hold-out and 10-fold cross-validation strategies. In order to validate the performance of the implemented machine learning methods in this research, both shuffle hold-out, and 10-fold cross-validation results indicated that our model had the highest efficiency compared to the other models. Furthermore, the Friedman statistical test is applied to survey the differences between models. The result demonstrates that the introduced stacking model reached the most accurate predicting performance after Logistic Regression.

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.

Retinoid X receptor (RXR) antagonists are not only useful as chemical tools for biological research, but also are candidate drugs for treatment of various diseases, including diabetes and allergy, although no RXR antagonist has yet been approved for clinical use. In this review, we describe currently available RXR antagonists, their structural classification, and their evaluation, focusing on the latest research.

Despite the long and extensive history of 3D technology, it has recently attracted the attention of researchers. This technology has become the center of interest of young people because of the real feelings and sensations it creates. People see their environment as 3D because of their eye structure. In this study, it is hypothesized that people lose their perception of depth during sleepy moments and that there is a sudden transition from 3D vision to 2D vision. Regarding these transitions, the EEG signal analysis method was used for deep and comprehensive analysis of 2D and 3D brain signals. In this study, a single-stream anaglyph video of random 2D and 3D segments was prepared. After watching this single video, the obtained EEG recordings were considered for two different analyses: the part involving the critical transition (transition-state) and the state analysis of only the 2D versus 3D or 3D versus 2D parts (steady-state). The main objective of this study is to see the behavioral changes of brain signals in 2D and 3D transitions. To clarify the impacts of the human brain’s power spectral density (PSD) in 2D-to-3D (2D_3D) and 3D-to-2D (3D_2D) transitions of anaglyph video, 9 visual healthy individuals were prepared for testing in this pioneering study. Spectrogram graphs based on Short Time Fourier transform (STFT) were considered to evaluate the power spectrum analysis in each EEG channel of transition or steady-state. Thus, in 2D and 3D transition scenarios, important channels representing EEG frequency bands and brain lobes will be identified. To classify the 2D and 3D transitions, the dominant bands and time intervals representing the maximum difference of PSD were selected. Afterward, effective features were selected by applying statistical methods such as standard deviation (SD), maximum (max), and Hjorth parameters to epochs indicating transition intervals. Ultimately, k-Nearest Neighbors (k-NN), Support Vector Machine (SVM), and Linear Discriminant Analysis (LDA) algorithms were applied to classify 2D_3D and 3D_2D transitions. The frontal, temporal, and partially parietal lobes show 2D_3D and 3D_2D transitions with a good classification success rate. Overall, it was found that Hjorth parameters and LDA algorithms have 71.11% and 77.78% classification success rates for transition and steady-state, respectively.

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.

：Sleep stage on the whole night is not steady. Sleepers generally pass through three to five cycles. In each cycle, there are occur four typical sleep stages, such as wake stage (WS), light stage (LS), deep sleep (DS), rapid eye movement sleep stage (REM). According to the natural routine, in this paper, we investigate the stage transition and analyze the feature of stage transition using the local cluster Algorithm (LCA). Two-cycle sleep model (TCSM) is proposed to automatically classify sleep stages using over-night continuous heart rate variability (HRV) data. The generated model is based on the characteristics of the nested cycle's sleep stage distribution and the transition probabilities of sleep stages. Experiments were conducted using a public data set including 400 healthy subjects (female 239, male 161) and the model’s classification accuracy was evaluated for four sleep stages: WS, LS, DS, REM. The experimental results showed that based on the TCSM model, the segmentation classification of pure sleep is 5.2% higher than that of the traditional method, and the accuracy of segmentation classification is 11.2% higher than the traditional sleep staging accuracy. The experimental performance is promising in terms of the accuracy, sensitivity, and specificity rates compared with the ones of the state-of-the-art methods. The study contributes to improve the quality of sleep monitoring in daily life using easy-to-wear HRV sensors.

The article presents the methodology for classifying economic regions with regards to selected factors that characterize a region, such as: the economic structure of the region, and thus the share of individual sectors in the economy; employment; the dynamics of the development of individual sectors expressed as an increase or decrease in production value; the population density in the region and also the level of occupational safety. Cluster analysis, which is a method of multidimensional statistical analysis available in Statistica software, was used to solve the task. The proposed methodology was used to group Polish voivodships with regards to the speed of economic development and occupational safety in the construction industry. Data published by the Central Statistical Office was used for this purpose, such as the value of construction and assembly production, the number of people employed in the construction industry, the population of an individual region and the number of people injured in occupational accidents.

Background: Ongoing molecular profiling studies enabled by advances in biomedical technologies are producing vast amounts of ‘omic’ data for early detection, monitoring, and prognosis of diverse diseases. A major common limitation is the scarcity of biological samples, necessitating integrative modeling frameworks that can make optimal use of available data for disease classification tasks. Related data sets are often available from different studies, but may have been generated using different technology platforms. Thus, there is a critical need for flexible modeling methods that can handle data from diverse sources to facilitate the discovery of robust biomarkers that underlie disease regulatory processes. Results: In this paper, we introduce a novel framework called Knowledge Augmented Rule Learning (KARL), which incorporates two sources of knowledge, domain, and data, for pattern discovery from small and high-dimensional datasets, such as transcriptomic data. We propose KARL as a transfer rule learning framework in which knowledge of the domain is transferred to the learning process on data in order to 1) improve the reliability of the discovered patterns, and 2) study the knowledge of the domain when used along with data for modeling. In this work, we generated KARL models on gene expression datasets for five types of cancer, including brain, breast, colon, lung, and prostate. As our knowledge of the domain, we used the Ingenuity Knowledge Base (IKB) to extract genes related to hallmarks of cancer and annotated these prior relationships before learning classifiers from these datasets. Conclusions: Our results show that KARL produces, on average, rule models that are more robust classifiers than the baseline without such background knowledge, for our tasks of cancer prediction using 25 publicly available gene expression datasets. Moreover, KARL helped us learn insights about previously known relationships in these gene expression datasets, along with new relationships not input as known, to enable informed biomarker discovery for cancer prediction tasks. KARL can be applied to modeling similar data from any other domain and classification task. Future work would involve extensions to KARL to handle hierarchical knowledge to derive more general hypotheses to drive biomedicine.

The COVID-19 is a highly contagious viral infection which played havoc on everyone's life in many different ways. According to the world health organization and scientists, more testing potentially helps governments and disease control organizations in containing the spread of the virus. The use of chest radiographs is one of the early screening tests to determine the onset of disease, as the infection affects the lungs severely. This study will investigate and automate the process of testing by using state-of-the-art CNN classifiers to detect the COVID19 infection. However, the viral could of many different types; therefore, we only regard for COVID19 while the other viral infection types are treated as non-COVID19 in the radiographs of various viral infections. The classification task is challenging due to the limited number of scans available for COVID19 and the minute variations in the viral infections. We aim to employ current state-of-the-art CNN architectures, compare their results, and determine whether deep learning algorithms can handle the crisis appropriately. All trained models are available at https://github.com/saeed-anwar/COVID19-Baselines

Appropriate estimation of soil settlement is of significant importance since it directly influences the performance of building and infrastructures that are built on soil. In particular, the settlement of fine-grained soils is critical because of low permeability and continuous settlement with time. Coefficient of consolidation (Cc) is a key parameter to estimate settlement of fine-grained soil layers. However, estimation of this parameter is time consuming, needs skilled technicians, and specific equipment. In this study, Cc was estimated using several soil parameters such as liquid limit (LL), plastic limit (PL), and initial void ratio (e0). Estimating such parameters in laboratory is straight forward and needs substantially less time and cost compared to conventional tests to estimate Cc such as Oedometer test. This study presents a novel prediction model for Cc of fine-grained soils using gene-expression programming (GEP). GEP is a biologically inspired technique capable of offering closed-form solution for the optimal solution. A database consisted of 108 different data points was used to develop the model. A closed-form equation solution was derived to estimate Cc based on LL, PL, and e0. The performance of developed GEP-based model was evaluated through coefficient of determination (R2), root mean squared error (RMSE), and mean average error (MAE). High R2 and low error values indicated the descent performance of the model. Furthermore, the model was evaluated using the additional performance measures and met all the suggested criteria. Furthermore, the model had a better performance in terms of R2, RMSE, and MAE compared to most of existing models. It is expected that the developed model will decrease the time and cost associate with determining Cc of fine-grained soils.

Segmentation of a region of interest is an important pre-processing step for many colour image analysis techniques. Similarly segmentation of plant in digital images is an important preprocessing step in phenotying plants by image analysis. In this paper we present an analytical study to statistically determine the suitability of colour space representation of an image to best detect plant pixels and separate them from background pixels. Our hypothesis is that the colour space representation in which the separation of the distributions representing plant pixels and background pixels is maximized would be the best for detection of plant pixels. The two classes of pixels are modelled as a Gaussian mixture model (GMM). In our GM modelling we don't make any prior assumption about the number of Gaussians in the model. Rather a constant bandwidth mean-shift filter is used to cluster the data and the number of clusters and hence the number of Gaussians is automatically determined. Here we have analysed following representative colour spaces like $RGB$, $rgb$, $HSV$, $Ycbcr$ and $CIE-Lab$. This is because these colour spaces represent several other similar colour spaces and also an exhaustive study of all the colour space will be too voluminous. We also analyse the colour space feature from the two-class variance ratio perspective and compare the results of our hypothesis with this metric. The dataset for this empirical study consist of 378 digital images of plants and their manual segmentation. Dataset consist of various species of plants (arabidopsi, tobacco, wheat, rye grass etc.) imaged under different lighting conditions, indoor and outdoor, controlled and uncontrolled background. In results we obtain better segmentation of the plants in $HSV$ colour space, which is supported by its Earth mover distance (EMD) on the GMM distribution of plant and background pixels.

Recently, much attention has been devoted to finding highly efficient and powerful activation functions for CNN layers. Because activation functions inject different nonlinearities between layers that affect performance, varying them is one method for building robust ensembles of CNNs. The objective of this study is to examine the performance of CNN ensembles made with different activation functions, including six new ones presented here: 2D Mexican ReLU, TanELU, MeLU+GaLU, Symmetric MeLU, Symmetric GaLU, and Flexible MeLU. The highest performing ensemble was built with CNNs having different activation layers that randomly replaced the standard ReLU. A comprehensive evaluation of the proposed approach was conducted across fifteen biomedical data sets representing various classification tasks. The proposed method was tested on two basic CNN architectures: Vgg16 and ResNet50. Results demonstrate the superiority in performance of this approach. The MATLAB source code for this study will be available at https://github.com/LorisNanni.

Predicting the popularity of posts on social networks has taken on significant importance in recent years, and several social media management tools now offer solutions to improve and optimize the quality of published content and to enhance the attractiveness of companies and organizations. Scientific research has recently moved in this direction, with the aim of exploiting advanced techniques such as machine learning, deep learning, natural language processing, etc., to support such tools. In light of the above, in this work we aim to address the challenge of predicting the popularity of a future post on Instagram, by defining the problem as a classification task and by proposing an original approach based on Gradient Boosting and feature engineering, which led us to promising experimental results. The proposed approach exploits big data technologies for scalability and efficiency and is general enough to be applied to other social media as well.

Pure monocular 3D reconstruction is an ill-posed problem that has attracted the research community's interest due to the affordability and availability of RGB sensors. SLAM, VO, and SFM are disciplines formulated to solve the 3D reconstruction problem and estimate the camera’s ego-motion, so many methods have been proposed. However, most of these methods were not evaluated in large datasets, under various motion patterns, had not been tested under the same metrics, and most of them had not been evaluated following a taxonomy, making their comparison and selection difficult. In this research, we performed a comparison of ten publicly available SLAM and VO methods following a taxonomy, including one method for each category of the primary taxonomy, three machine learning-based methods, and two updates of the best methods, to identify the advantages and limitations of each category of the taxonomy and test if the addition of machine learning or the updates made on those methods improved them significantly. Thus, we evaluated each algorithm under the TUM-Mono benchmark and performed an inferential statistical analysis to identify significative differences through its metrics. Results determined that sparse-direct methods significantly outperformed the rest of the taxonomy, and fusing them with machine learning techniques significantly improves the performance of geometric-based methods from different perspectives.

While the mobile phone is the world’s most popular media device, it is actually not one single medium, but is effectively used as a different medium by different user groups. The article characterizes polymodal differences in mobile apps usage among different user groups, including gender, education, occupation, screen size, and price. We monitored the complete app usage of 10,725 smartphone users for one month each (56 million sessions, recording almost 1 million hours). Our key contribution consists in developing and analyzing a theoretical framework to classify the over 16,000 apps used into five categories. Exploring nine research questions we provide a broad characterization by asking who, with which characteristics, uses which kinds of apps in what extensity and intensity? For example, it is not the young and high occupational grades that use the mobile phone as a human-to-machine computer (including gaming and artificial intelligence tools). Large screen size is related to extensive long sessions, while a small screen size is related to intensive frequent usage. The results go beyond providing ample empirical evidence for the inherently polymodal nature of the mobile phone, but also proposes a framework on how to possibility deal with it analytically.

Ransomware is one of the most dangerous types of malware, which is frequently intended to spread through a network to damage the designated client by encrypting the client’s vulnerable data. Conventional signature-based ransomware detection technique falls behind because it can only detect known anomalies. When it comes to new and non-familiar ransomware traditional system unveils huge shortcomings. For detecting unknown patterns and sorts of new ransomware families,behavior-based anomaly detection approaches are likely to be the most efficient approach. In the wake of this alarming condition, this paper presents an ensemble classification model consisting of three widely used machine learning techniques that include Decision Tree (DT), RandomForest (RF), and K-nearest neighbor (KNN). To achieve the best outcome ensemble soft voting and hard voting techniques are used while classifying ransomware families based on attack attributes. Performance analysis is done by comparing our proposed ensemble models with standalone models on behavioral attributes based ransomware dataset..

The prompt and accurate diagnosis of breast lesions, including the distinction between cancer, non-cancer, and suspicious cancer, plays a crucial role in the prognosis of breast cancer. In this paper, we introduce a novel method based on feature extraction and reduction for detection of breast cancer in mammography images. First, we extract features from multiple pre-trained convolutional neural network (CNN) models, and then concatenate them. The most informative features are selected based on their mutual information with the target variable. Subsequently, the selected features can be classified using a machine learning algorithm. We evaluate our approach using four different machine learning algorithms, and our results demonstrate that the neural network-based classifier yields an accuracy as high as 92% for the RSNA dataset which is a new dataset that provides two views and additional features such as age. We compare our proposed algorithm with state-of-the-art methods and demonstrate its superiority, particularly in terms of accuracy and sensitivity. For the MIAS dataset, we achieve an accuracy as high as 94.5%, and for the DDSM dataset, an accuracy of 96% is attained. These results highlight the effectiveness of our method in accurately diagnosing breast lesions and surpassing existing approaches.

There are many theories of carcinogenesis arguing against the orthodox mutation theory, debating on such as “epigenetic alteration” that is inheritable and yet, theoretically, reversible. Our integrated theory describes that any extracellular, intracellular, or intranuclear stressors, mutagenic or not, can initiate a lengthy tumorigenesis to engender a benign or malignant tumor, but the aberrations directly establishing cellular immortality and autonomy may be epigenetic or genetic alterations in the genomic DNA. A neoplasm is considered a semi-new organism with autonomy; it therefore should have genetic mutations to be “new”. We may be able to direct cancer cells towards differentiation as a remedy, because the extracellular milieu may control the phenotype of a cell and the tissue or organ made of the cell’s progenies, and the cytoplasm of a cell may override the nucleus in the phenotypic control. However, the nucleus retains the capacity to manifest itself if allowed by the microenvironment, which then allows the already reversed cells to revert back to tumor cells again. Neoplasms are malignant if they bear epigenetic or genetic anomalies in mutator genes defined as those whose alterations allow or accelerate alterations to occur in other genes, whereas neoplasms are benign if they bear epigenetic or genetic aberrations only in non-mutator genes. It is imperative to identify the immediate tumor-causing cellular alterations defined as those directly responsible for immortality and autonomy, and for treatment purposes to identify the extracellular and intracellular factors that control the phenotype of cancer cells.

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

The widespread deployment of social media has helped researchers access an enormous amount of data in various domains, including the pandemic caused by the COVID-19 spread. This study presents a heuristic approach to classify Commercial Instagram Posts (CIPs) and explores how the businesses around the Holy Shrine – a sacred complex in Mashhad, Iran, surrounded by numerous shopping centers – were impacted by the pandemic. Two datasets of Instagram posts (one gathered data from March 14th to April 10th, 2020, when Holy Shrine and nearby shops were closed, and one extracted data from the same period in 2019), two word embedding models – aimed at vectorizing associated caption of each post, and two neural networks – multi-layer perceptron and convolutional neural network – were employed to classify CIPs in 2019. Among the scenarios defined for the 2019 CIPs classification, the results revealed that the combination of MLP and CBoW achieved the best performance, which was then used for the 2020 CIPs classification. It is found out that the fraction of CIPs to total Instagram posts has increased from 5.58% in 2019 to 8.08% in 2020, meaning that business owners were using Instagram to increase their sales and continue their commercial activities to compensate for the closure of their stores during the pandemic. Moreover, the portion of non-commercial Instagram posts (NCIPs) in total posts has decreased from 94.42% in 2019 to 91.92% in 2020, implying the fact that since the Holy Shrine was closed, Mashhad citizens and tourists could not visit it and take photos to post on their Instagram accounts.

Background: Digital clinical measures collected via various digital sensing technologies such as smartphones, smartwatches, wearables, ingestible, and implantable are increasingly used by individuals and clinicians to capture health outcomes or behavioral and physiological characteristics of individuals. Time series classification (TSC) is very commonly used in modeling digital clinical measures. While deep learning models for TSC are very common and powerful, there exist some fundamental challenges. This review presents non-deep learning models commonly used for time series classification in biomedical applications that achieve high performance. Objective: We performed a systematic review to characterize the techniques used in time series classification of digital clinical measures throughout all stages of data processing and model building. Methods: We conducted a literature search on PubMed, and the Institute of Electrical and Electronics Engineers (IEEE), Web of Science, and SCOPUS databases using a range of search terms to retrieve peer-reviewed articles reporting academic research on digital clinical measures in the five year period between June 2016 and June 2021. We identified and categorized research studies based on the types of classification algorithms and sensor input types. Results: We found 452 papers in total from four different databases: PubMed, IEEE, Web of Science Database, and SCOPUS. After removing duplicates and irrelevant papers, 135 articles remained for detailed review and data extraction. Among these, engineered features using time series methods that were subsequently fed into widely-used machine learning classifiers was the most commonly used technique and also most frequently achieved the best performance metrics (77 out of 135 articles). Statistical modeling (24 out of 135 articles) algorithms were the second most common and also second best classification technique. Wavelet-based classification models (8 out of 135 articles) were also common. Electroencephalogram (29 out of 135 articles) was the most common data type used as an input. Accuracy was the most commonly reported performance metric, with 67.65% of articles reporting on accuracy. In this review paper, we provide summaries of signal pre-processing methods, feature engineering and selection methods, time series models, as well as model interpretations. Importantly, we found that about 50% of the papers only report one performance metric, which may result in a skewed view of overall performance. Conclusion: While high time series classification performance has been achieved in digital clinical, physiological, or biomedical measures, no standard benchmark datasets, modeling methods, or reporting methodology exist. There is no single widely used method for time series model development or feature interpretation– many different methods have proven successful.

On October 18, 2017, Chinese President Xi Jinping presented the blueprint for building a modernized socialist nation through the realization of the Xiao Kang (Every nation enjoys a peaceful and affluent life, it is meaningless to eliminate the poor) social construction at the 19th Congress of China. Subsequent to the 2008 financial crisis, the world has moved on to the new economic status of the New Normal. China has also entered the era of “Xinchang Thai,” which is moving from the high-growth to the moderate-growth phase. Therefore, the government of China emphasizes privatization, liberalization, and deregulation. China is also influenced by government policies due to the nature of socialism. This study confirms China’s current stage of economic development based on Barro’s theory. Thus, we use a quantile regression model and examine the correlation between economic growth and functional classification of government expenditure during Xi Jinping's term of office. Furthermore, we selected Korea as a comparative country as the two countries have common features.

One of the most common forms of dementia is Alzheimer’s disease (AD), which leads to progressive mental deterioration. Unfortunately, there is no definitive diagnosis and cure that can stop the condition progressing. The diagnosis is often performed based on the clinical history and neuropsychological data, including magnetic resonance imaging (MRI). Deep neural networks (DNN) algorithms are gaining popularity for medical diagnosis, and have been used widely for the analysis of MRI data. DNNs can extract hidden features from thousands of training images automatically. However, they cannot judge how confident they are about their predictions. To use DNNs in safety-critical applications such as medical diagnosis, uncertainty quantification of DNNs predictions is crucial. For this purpose, Monte Carlo dropout (MCD) has been widely used, however, it may lead to overconfident and miss calibrated results. This paper proposes a framework in which the MCD algorithm’s hyper-parameters are optimized during training using Bayesian optimization for the first time. The conducted optimization leads to assigning high predictive entropy to erroneous predictions and making it possible to recognize risky predictions. The proposed framework is used for AD diagnosis, which has not been done before. We compare our method with some existing methods in the literature based on different uncertainty quantification criteria. The results of comprehensive experiments on the Kaggle dataset using a deep model pre-trained on the ImageNet dataset show that the proposed algorithm can quantify uncertainty much better than the existing methods.

Wearable technology will become available and allow prolonged electroencephalography (EEG) monitoring in the home environment of patients with epilepsy. Neurologists analyse the EEG visually and annotate all seizures, which patients often under report. Visual analysis of a 24 hour EEG recording typically takes one to two hours. Reliable automated seizure detection algorithms will be crucial to reduce this analysis. We study a dataset of behind-the-ear EEG measurements. Our first aim was to develop a methodology to reduce the EEG dataset by classifying part of the data automatically, while retaining 100% detection sensitivity (DS). Prediction confidences are determined by temperature scaling of the classification model outputs and trust scores. A DS of approximately 90% (99%) can be achieved when automatically classifying around 90% (60%) of the data. Perfect DS can be achieved when automatically classifying 50% of the data. Our second contribution demonstrates that a common modelling strategy, where predictions from several short EEG segments are used to obtain a final prediction, can be improved by filtering out untrustworthy segments with low trust scores. The false detection rate shows a relative decrease between 21% and 43%, and the DS shows a small increase or decrease.

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.

Advancements in deep learning and availability of medical imaging data have led to use of CNN based architectures in disease diagnostic assisted systems. In spite of the abundant use of reverse transcription-polymerase chain reaction (RT-PCR) based tests in COVID-19 diagnosis, CT images offer an applicable supplement with its high sensitivity rates. Here, we study classification of COVID-19 pneumonia (CP) and non-COVID-19 pneumonia (NCP) in chest CT scans using efficient deep learning methods to be readily implemented by any hospital. We report our deep network framework design that encompasses Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory (biLSTM) architectures. Our study achieved high specificity (CP: 98.3%, NCP: 96.2% Healthy: 89.3%) and high sensitivity (CP: 84.0%, NCP: 93.9% Healthy: 94.9%) in classifying COVID-19 pneumonia, non-COVID-19 pneumonia and healthy patients. Next, we provide visual explanations for the CNN predictions with gradient-weighted class activation mapping (Grad-CAM). The results provided a model explainability by showing that Ground Glass Opacities (GGO), indicators of COVID-19 pneumonia disease, were captured by our CNN network. Finally, we have implemented our approach in three hospitals proving its compatibility and efficiency.

The interpretation of land use and land cover (LULC) is an important issue in the fields of high-resolution remote sensing (RS) image processing and land resource management. Fully training a new or existing convolutional neural network (CNN) architecture for LULC classification requires a large amount of remote sensing images. Thus, fine-tuning a pre-trained CNN for LULC detection is required. To improve the classification accuracy for high resolution remote sensing images, it is necessary to use another feature descriptor and to adopt a classifier for post-processing. A fully connected conditional random fields (FC-CRF), to use the fine-tuned CNN layers, spectral features, and fully connected pairwise potentials, is proposed for image classification of high-resolution remote sensing images. First, an existing CNN model is adopted, and the parameters of CNN are fine-tuned by training datasets. Then, the probabilities of image pixels belong to each class type are calculated. Second, we consider the spectral features and digital surface model (DSM) and combined with a support vector machine (SVM) classifier, the probabilities belong to each LULC class type are determined. Combined with the probabilities achieved by the fine-tuned CNN, new feature descriptors are built. Finally, FC-CRF are introduced to produce the classification results, whereas the unary potentials are achieved by the new feature descriptors and SVM classifier, and the pairwise potentials are achieved by the three-band RS imagery and DSM. Experimental results show that the proposed classification scheme achieves good performance when the total accuracy is about 85%.

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.

Emotion recognition defined as identifying human emotion and is directly related to different fields such as human-computer interfaces, human emotional processing, irrational analysis, medical diagnostics, data-driven animation, human-robot communi- cation and many more. The purpose of this study is to propose a new facial emotional recognition model using convolutional neural network. Our proposed model, “ConvNet”, detects seven specific emotions from image data including anger, disgust, fear, happiness, neutrality, sadness, and surprise. This research focuses on the model’s training accuracy in a short number of epoch which the authors can develop a real-time schema that can easily fit the model and sense emotions. Furthermore, this work focuses on the mental or emotional stuff of a man or woman using the behavioral aspects. To complete the training of the CNN network model, we use the FER2013 databases, and we test the system’s success by identifying facial expressions in the real-time. ConvNet consists of four layers of convolution together with two fully connected layers. The experimental results show that the ConvNet is able to achieve 96% training accuracy which is much better than current existing models. ConvNet also achieved validation accuracy of 65% to 70% (considering different datasets used for experiments), resulting in a higher classification accuracy compared to other existing models. We also made all the materials publicly accessible for the research community at: https://github.com/Tanoy004/Emotion-recognition-through-CNN.

A convolutional neural network (CNN) is sometimes understood as a black box in the sense that while it can approximate any function, studying its structure will not give us any insights into the nature of the function being approximated. In other terms, the discriminative ability does not reveal much about the latent representation of a network. This research aims to establish a framework for interpreting the CNNs by profiling them in terms of interpretable visual concepts and verifying them by means of Integrated Gradient. We also ask the question, "Do different input classes have a relationship or are they unrelated?" For instance, could there be an overlapping set of highly active neurons to identify different classes? Could there be a set of neurons that are useful for one input class whereas misleading for a different one? Intuition answers these questions positively, implying the existence of a structured set of neurons inclined to a particular class. Knowing this structure has significant values; it provides a principled way for identifying redundancies across the classes. Here the interpretability profiling has been done by evaluating the correspondence between individual hidden neurons and a set of human-understandable visual semantic concepts. We also propose an integrated gradient-based class-specific relevance mapping approach that takes the spatial position of the region of interest in the input image. Our relevance score verifies the interpretability scores in terms of neurons tuned to a particular concept/class. Further, we perform network ablation and measure the performance of the network based on our approach.

Myoelectric control is the cornerstone of many assistive technologies used in clinical practice, such as prosthetics and orthoses, and human-computer interaction, such as virtual reality control. Although the performance of such devices exceeds 90\% in controlled environments, myoelectric devices still face challenges in robustness to variability of daily living conditions. Within this survey, the intrisic physiological mechanisms limiting practical implementations of myoelectric devices were explored: the limb position effect and the contraction intensity effect. The degradation of electromyography (EMG) pattern recognition in the presence of these factors was demonstrated on six datasets, where performance was 13% and 20% lower in realistic environments compared to controlled environments for the limb position and contraction intensity effect, respectively. The experimental designs of limb position and contraction intensity literature were surveyed. Current state-of-the-art training strategies and robust algorithms for both effects were compiled and presented. Recommendations for future limb position effect studies include: the collection protocol providing exemplars of 6 positions (four limb positions and three forearm orientations), three-dimensional space experimental designs, transfer learning approaches, and multi-modal sensor configurations. Recommendations for future contraction intensity effect studies include: the collection of dynamic contractions, nonlinear complexity features, and proportional control.

Limnologists often adhere to a discretized view of waterbodies—they classify them, divide them into zones, promote discrete management targets, and use research tools, experimental designs, and statistical analyses focused on discretization. This approach to limnology has profoundly benefited the way we understand, manage, and communicate about waterbodies. But the research questions and the research tools in limnology are changing rapidly with consequences for the relevance of our current discretization schemes. Here, I examine how and why we discretize and argue that selectively rethinking the extent to which we must discretize gives us an exceptional chance to advance limnology in new ways.

The modern diet, which consists of food produced with high level of industrial processing, is associated with an increased risk of the development of lifestyle diseases. Current nutritional science is, however, focused on chemical composition of food, and not on the type and degree of processing used during the food production. Here, we take a fresh perspective on the relationship between the extent and type of food processing, and evaluate its impact on consumer health. We argue that the preference for consumption of minimally processed foods, and restriction of ultra-processed foods should be an essential part of a healthy lifestyle, disease prevention, and even treatment. We also present a simple, user-friendly consumer guide, which is intended to be used as a practical, ready-to-go identifier of ultra-processed foods.

With the rapid expansion of intelligent resource-constrained devices and high-speed communication technologies, Internet of Things (IoT) has earned a wide recognition as the primary standard for low-power lossy networks (LLNs). Nevertheless, IoT infrastructures are vulnerable to cyber-attacks due to the constraints in computation, storage, and communication capacity of the endpoint devices. From one side, the majority of newly developed cyber-attacks are formed by slightly mutating formerly established cyber-attacks to produce a new attack tending to be treated as a normal traffic through the IoT network. From the other side, the influence of coupling the deep learning techniques with cybersecurity field has become a recent inclination of many security applications due to their impressive performance. In this paper, we provide a comprehensive development of a new intelligent and autonomous deep learning-based detection and classification system for cyber-attacks in IoT communication networks leveraging the power of convolutional neural networks, abbreviated as (IoT-IDCS-CNN). The proposed IoT-IDCS-CNN makes use of the high-performance computing employing the robust CUDA based Nvidia GPUs and the parallel processing employing the high-speed I9-Cores based Intel CPUs. In particular, the proposed system is composed of three subsystems: Feature Engineering subsystem, Feature Learning subsystem and Traffic classification subsystem. All subsystems are developed, verified, integrated, and validated in this research. To evaluate the developed system, we employed the NSL-KDD dataset which includes all the key attacks in the IoT computing. The simulation results demonstrated more than 99.3% and 98.2% of cyber-attacks’ classification accuracy for the binary-class classifier (normal vs anomaly) and the multi-class classifier (five categories) respectively. The proposed system was validated using k-fold cross validation method and was evaluated using the confusion matrix parameters (i.e., TN, TP, FN, FP) along with other classification performance metrics including precision, recall, F1-score, and false alarm rate. The test and evaluation results of the IoT-IDCS-CNN system outperformed many recent machine-learning based IDCS systems in the same area of study.

One of the most important challenges in the Machine and Deep Learning areas today is to build good models using small datasets, because sometimes it is not possible to have large ones. Several techniques have been proposed in the literature to address this challenge. This paper aims at studying the different available Deep Learning techniques and performing a thorough experimentation to analyze which technique or combination thereof improves the performance and effectiveness of the models. A complete comparison with classical Machine Learning techniques was carried out, to contrast the results obtained using both techniques when working with small datasets. Thirteen algorithms were implemented and trained using three different small datasets (MNIST, Fashion MNIST, and CIFAR-10). Each experiment was evaluated using a well-established set of metrics (Accuracy, Precision, Recall, F1, and the Matthews correlation coefficient). The experimentation allowed concluding that it is possible to find a technique or combination of them to mitigate a lack of data, but this depends on the nature of the dataset, the amount of data, and the metrics used to evaluate them.

The spread of the Coronavirus pandemic has been accompanied by an infodemic. The false information that is embedded in the infodemic affects people’s ability to have access to safety information and follow proper procedures to mitigate the risks. This research aims to target the falsehood part of the infodemic, which prominently proliferates in news articles and false medical publications. Here, we present NeoNet, a novel supervised machine learning text mining algorithm that analyzes the content of a document (news article, a medical publication) and assigns a label to it. The algorithm is trained by TFIDF bigram features which contribute a network training model. The algorithm is tested on two different real-world datasets from the CBC news network and Covid-19 publications. In five different fold comparisons, the algorithm predicted a label of an article with a precision of 97-99 %. When compared with prominent algorithms such as Neural Networks, SVM, and Random Forests NeoNet surpassed them. The analysis highlighted the promise of NeoNet in detecting disputed online contents which may contribute negatively to the COVID-19 pandemic.

The classifier system proposed in this work combines the dissimilarity spaces produced by a set of Siamese neural networks (SNNs) designed using 4 different backbones, with different clustering techniques for training SVMs for automated animal audio classification. The system is evaluated on two animal audio datasets: one for cat and another for bird vocalizations. Different clustering methods reduce the spectrograms in the dataset to a set of centroids that generate (in both a supervised and unsupervised fashion) the dissimilarity space through the Siamese networks. In addition to feeding the SNNs with spectrograms, additional experiments process the spectrograms using the Heterogeneous Auto-Similarities of Characteristics. Once the similarity spaces are computed, a vector space representation of each pattern is generated that is then trained on a Support Vector Machine (SVM) to classify a spectrogram by its dissimilarity vector. Results demonstrate that the proposed approach performs competitively (without ad-hoc optimization of the clustering methods) on both animal vocalization datasets. To further demonstrate the power of the proposed system, the best stand-alone approach is also evaluated on the challenging Dataset for Environmental Sound Classification (ESC50) dataset. The MATLAB code used in this study is available at https://github.com/LorisNanni.

Currently, skin cancer is the most commonly diagnosed form of cancer in humans and is one of the leading causes of death in patients with cancer. Biopsy methods are an invasive research method and are not always available for primary diagnosis. Imaging methods have low accuracy and depend on the experience of the dermatologist. Artificial intelligence technologies can match and surpass visual analysis methods in accuracy, but they have the risk of a false negative response when a malignant pigmented lesion can be recognized as benign. One possible way to improve accuracy and reduce the risk of false negatives is to analyze heterogeneous data, combine different preprocessing methods, and use modified loss functions to eliminate the negative impact of unbalanced dermatological data. The paper proposes a multimodal neural network system with a modified cross-entropy loss function that is sensitive to unbalanced heterogeneous dermatological data. The accuracy of recognition in 10 diagnostically significant categories for the proposed system was 85.19%. The novelty of the proposed system lies in the use of cross-entropy loss when training the modified function with the help of weight coefficients. The introduction of weighting factors has reduced the number of false negative forecasts, as well as improved accuracy by 1.02-4.03 percentage points compared to the original multimodal systems. The introduction of the proposed multimodal system as an auxiliary diagnostic tool can reduce the consumption of financial and labor resources involved in the medical industry, as well as increase the chance of early detection of skin cancer.

Reliable estimates of poplar plantations area are not available at the French national scale due to the unsuitability and low update rate of existing forest databases for this short-rotation species. While supervised classification methods have been shown to be highly accurate in mapping forest cover from remotely sensed images, their performance depends to a great extent on the labelled samples used to build the models. In addition to their high acquisition cost, such samples are often scarce and not fully representative of the variability in class distributions. Consequently, when classification models are applied to large areas with high intra-class variance, they generally yield poor accuracies. In this paper, we propose the use of active learning (AL) to efficiently adapt a classifier trained on a source image to spatially distinct target images with minimal labelling effort and without sacrificing classification performance. The adaptation consists in actively adding to the initial local model, new relevant training samples from other areas, in a cascade that iteratively improves the generalisation capabilities of the classifier, leading to a global model tailored to different areas. This active selection relies on uncertainty sampling to directly focus on the most informative pixels for which the algorithm is the least certain of their class labels. Experiments conducted on Sentinel-2 time series showed that when the same number of training samples was used, active learning outperformed passive learning (random sampling) by up to 5% of overall accuracy and up to 12% of class F-score. In addition, and depending on the class considered, the random sampling required up to 50% more samples to achieve the same performance of an active learning-based model. Moreover, the results demonstrate the suitability of the derived global model to accurately map poplar plantations among other tree species with overall accuracy values up to 14% higher than those obtained with local models. The proposed approach paves the way for national-scale mapping in an operational context.

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

Laser-induced breakdown spectroscopy (LIBS) is an important analysis technique with applications in many industrial branches and fields of scientific research. Nowadays, the advantages of LIBS are impaired by the main drawback in the analysis of collected data. This procedure is essentially based on the comparison of lines present in the spectrum with a literature database. This paper proposes the use of various computational intelligence methods to develop a reliable and fast classification of non-destructively acquired LIBS spectra into a set of predefined classes. We focus on a specific problem of classification of paper-ink samples into 30 separate, predefined classes. For each of 30 classes (10 pens of each of 5 ink types combined with 10 sheets of 5 paper types plus empty pages) 100 LIBS spectra are collected. Four variants of preprocessing, seven classifiers (Decision trees, Random forest, k-Nearest Neighbour, Support Vector Machine, Probabilistic Neural Network, Multi-Layer Perceptron, and Generalized Regression Neural Network), 5-fold stratified cross-validation and test on an independent set (for methods evaluation) scenarios are employed. Our developed system yielded an accuracy of 99.08% with average classification time of about 0.12 s is obtained using the random forest classifier. Our results clearly demonstrates that machine learning methods can be used to identify the paper-ink samples based on LIBS reliably at a faster rate.

Following the occurrence of a typhoon, quick damage assessment related to residents can facilitate quick dispatch of house repair and disaster insurance works. Employing a deep learning method, this study used aerial photos of the Chiba prefecture obtained following the Typhoon Faxai in 2019 to automatically detect and evaluate the roof damage. This study comprised three parts: training deep learning model, detecting the roof damage using trained model, and classifying the level of roof damage. The detection object comprised roof outline, blue tarps, and roof completely destroyed. The roofs were divided into three categories: roof without damage, roof with blue tarps and roof completely destroyed. the F value obtained using the proposed method was higher than those obtained using other methods. In addition, it can be further divided into 5 levels from level 0 to 4. Finally, the spatial distribution of the roof damage was analyzed using ArcGIS tools. The proposed method is expected to provide certain reference for the real-time detection of the roof damage after the occurrence of a typhoon.

Smart cities and smart technologies have been incorporated into several axes to increase the comfort of life. The connected building's concept was introduced for this reason. However, it was utilized in power management for better organizing, greater buildings management, and monetary savings. Cars technologies and the number of vehicles are also involved; Nowadays, each house has at least one car. Technological evolution helped to make those cars intelligent and connected. In the latest versions, the majority of those cars were equipped with several sensors, several communication protocols and a principal electrical control unit (ECU), especially for the electric vehicle model. This type of architecture was an essential element in a smart city, thus, it helps to manage power and decide when a vehicle needs to be charged. Based on the smart city concept and using possible network communication between buildings and vehicles, EVs can share their own information related to the powerful experience on a specific path. This information can be gathered in a gigantic database and used for managing the power inside these vehicles. In this field, we propose in this paper a new approach for power management inside an electric vehicle based on bi-communication between vehicles and buildings. The proposed approach is founded on two essential parts; the first is related to vehicles’ classification and buildings’ recommendation according to different car positions. Two algorithms, related to the SVC and neural network was employed in this work for implementing the final process. Different possibilities and situations were discussed for this approach. The proposed method was tested and validated using Simulink/Matlab application. The state of charge of the used battery was compared at the end of this work, for two specified cases, for showing the contribution of this approach.

Indoor localization is an active area of research dominated by traditional machine-learning techniques. Deep learning-based systems have shown unprecedented improvements and have accomplished exceptional results over the past decade, especially the Transformer network within natural language processing (NLP) and computer vision domains. We propose the hyper-class Transformer (HyTra), an encoder-only Transformer with multiple classification heads (one per class) and learnable embeddings, to investigate the effectiveness of Transformer-based models for received signal strength (RSS) based WiFi fingerprinting. HyTra leverages learnable embeddings and the self-attention mechanism to determine the relative position of the wireless access points (WAPs) within the high-dimensional embedding space, improving the prediction of user location. From an NLP perspective, we consider a fixed order sequence of all observed WAPs as a sentence and the captured RSS value(s) for every given WAP at a given reference point from a given user as words. We test our proposed network on public and private datasets of different sizes, proving that the quality of the learned embeddings and overall accuracy improves with increments in samples.

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.

As in many parts of the world, rural-urban, forest-urban interface areas surrounding urban regions expose the natural areas they interact with to a threat of fire risk that can reach various sizes. This risk has been assessed for various regions of the world using many different methods and numerical models so far. Among these, it is seen that machine learning models have successful applications in risk assessment and risk prediction studies. For the fire risk prediction of Istanbul's yet unurbanized regions, but where the city is anticipated to potentially shift, data was collected using the opportunities provided by Geographic Information Systems and Remote Sensing technologies based on fires that occurred between 2000-2021, and the region was examined. Machine learning methods' Random Forest (RF), Extreme Gradient Boosting (XGB), and Light Gradient Boosting (LGB) models were applied for the classification of factors effective in fire. The best result was given by the RF model with 0.93 accuracy, 0.062 F1 score, and 0.753 Area Under Curve (AUC) value. In the classification of factors in the RF model, the grouping between fire-initiating factors and factors effective in spreading is evident, while this distinction is partially noticeable in the other two models.

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.

In many image processing and computer vision applications, the main aim is to describe image contents. So, different visual properties such as color, texture and shape are extracted to make aim. In this respect, texture information play important role in image description and visual pattern classification. Texture is referred to a specific local distribution of intensities that is repeated throughout the image. Since now different operations or descriptors have been proposed to analysis texture characteristics. In the multi object images specific texture operators usually doesn’t provide accurate results. So, in many cases, combination of texture operators are used to achieve more discriminant features. In this paper, some combination methods are survived to analysis effect of combinational texture features in image content description. Also, in the result part, different related methods are compared in terms of accuracy and computational complexity.

This paper proposes a novel approach, based on the adaptive rate processing and analysis, for the isolated speech recognition. The idea is to smartly combine the event-driven signal acquisition and windowing along with adaptive rate processing, analysis and classification for realizing an effective isolated speech recognition. The incoming speech signal is digitized with an event-driven A/D converter (EDADC). The output of EDADC is windowed with an activity selection process. These windows are later on resampled uniformly with an adaptive rate interpolator. The resampled windows are de-noised with an adaptive rate filter and their spectrum are computed with an adaptive resolution short time Fourier transform (ARSTFT). Later on, the magnitude, Delta and Delta-Delta spectral coefficients are extracted. The Dynamic Time Warping (DTW) technique is employed to compare these extracted features with the reference templates. The comparison outcomes are used to make the classification decision. The system functionality is tested for a case study and results are presented. An 8.2 times reduction in acquired number of samples is achieved by the devised approach as compared to the classical one. It aptitudes a significant computational gain and power consumption reduction of the proposed system over the counter classical ones. An average subject dependent isolated speech recognition accuracy of 96.8% is achieved. It shows that the proposed approach is a potential candidate for the automatic speech recognition applications like rehabilitation centers, smart call centers, smart homes, etc.

In this paper, we propose a novel approach of video skimming by exploiting the fusion of video temporal information and keyword information representation extracted from multi-model video information including audio, text and visual indices. In addition, we introduce the brand-safe filtering and sentiment analysis in order to only reserve the user-friendly content in the video skim. In the experiment by using the videos from YouTube-8M dataset, we have proved that the semantic conservation in the video skim from the proposed approach highly outperforms the approaches by only partial information of the video in conserving the semantic content of the video.

Manual interpretation of these huge amounts of image volumes are susceptible to inter-reader variability and human error. Thus, accurate automated CAD scheme is highly desirable in clinical pathological diagnosis. In this research, plethora of machine learning paradigms (e.g. feature extraction, dimensionality reduction and supervised classification methods) were explored, evaluated, compared and analyzed to identify the optimal pathway for brain MR images (normal vs neoplastic) binary classification task. External validation dataset was used to test the generalizability of the optimal predictive models implemented. Relevant and informative features were selected to construct cross-validated decision tree and eventually simple rule set was built based on the decision tree. The experimental results show that almost all pattern recognition paradigms achieve high accuracy with careful selection of number of attributes. LDA+ELM with 55 features are the optimal pipelines which achieve perfect classification when training and test data are of same source; and achieving (accuracy=97.5%, AUC=0.989, sensitivity=95% and specificity=100%) under balanced test dataset; (accuracy=99.5%, AUC=0.988, sensitivity=95% and specificity=100%). Cross-validated decision tree model also shows comparable performance: accuracy=98.8%, AUC=99.1%, sensitivity=99.6% and specificity=98.2%. Three highly relevant and robust attributes are visualized and selected for construction of decision tree models and finally a rule sets are read directly off the decision tree. This rule sets can potentially serve as fast and accurate classification algorithm.

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.

Recent studies on seafloor mapping have presented different modelling methods for the automatic classification of seafloor sediments. However, most of these studies have applied these models to seafloor data with appropriate number of ground-truth samples, which raises the question whether these methods are applicable to studies with smaller numbers of ground-truth data. In this study, we aim to address this issue by conducting sediment class-specific predictions using ensemble modelling to map areas with limited or without ground-truth data and combined with hydro-acoustic datasets. The resulting class-specific maps were then assembled into one map, where the most probable class was assigned to the appropriate location. Our approach was able to predict sediment classes without bias to the class with more ground-truth data and produced reliable seafloor sediment distributions maps that can be used for seafloor monitoring. Sediment shifts of a heterogenous seafloor in the Sylt Outer Reef, German North Sea were also assessed to understand the sediment dynamics in the area. The analyses of sediment shifts showed that the western area of the Sylt Outer Reef is highly active, and the results of the analyses assisted in providing recommendations on future seafloor monitoring activities.

Requirements are predominantly written in Natural Language (NL), which makes them accessible to stakeholders with varying degrees of experience, as compared to a model-based language which requires special training. However, despite its benefits, NL can introduce ambiguities and inconsistencies in requirements, which may eventually result in system quality degradation and system failure altogether. The system complexity that characterizes current systems warrants an integrated and comprehensive approach to system design and development. This need has brought about a paradigm shift towards Model-Based Systems Engineering (MBSE) approaches to system design and a departure from traditional document-centric methods. While, MBSE shows great promise, the ambiguities and inconsistencies present in NL requirements hinder their conversion to models directly. The field of Natural Language Processing (NLP) has demonstrated great potential in facilitating the conversion of NL requirements into a semi-machine-readable format that enables their standardization and use in a model-based environment. A first step towards standardizing requirements consists of classifying them according to the ``type'' (design, functional, performance, etc.) they represent. To that end, a language model capable of classifying requirements needs to be fine-tuned on labeled aerospace requirements. This paper presents the development of an annotated aerospace requirements corpus and its use to fine-tune BERT$_\text{BASE-UNCASED}$ to obtain aeroBERT-Classifier: a new language model for classifying aerospace requirements into design, functional, or performance requirements. A comparison between aeroBERT-Classifier and bart-large-mnli (zero-shot text classification) showcased the superior performance of aeroBERT-Classifier on classifying aerospace requirements despite being fine-tuned on a small labeled dataset.

ClinVar is a web platform that stores around 774k curated entries, which allows exploring genetic variants and their associations with complex phenotypes. A partial set of ClinVar’s genetic associations were reported with conflict of interpretation or uncertain clinical impact significance, which currently challenges clinicians and geneticists. Here, we evaluate the performance of data pre-processing methods combined with classical prediction methods, such as Naive Bayes, Random Forest, and Support Vector Machine to build a meta-prediction model aiming to improve genetic pathogenicity interpretation. Models were trained with ClinVar data (September 2020), and genetic variants were annotated with eight functional impact predictors catalogued with SnpEff/SnpSift (v4.3). A 10-fold cross-validation strategy was performed for evaluation by accuracy, F1-Score, Receiver Operating Characteristic, Area Under Curve. The best meta-prediction model raises by combining one-hot encoding with tree-based classifiers as Random Forest, which shows Area Under Curve ≥ 0,93. We predict pathogenicity for 109k genetic variants, which were found labeled as uncertain significance or conflict of interpretation. Additionally, we implemented AmazonForest (https://www.lghm.ufpa.br/amazonforest), a web tool to query data for a set of 5k variants that were predicted with high pathogenic probability (RFprob >= 0.9).

CNN-based methods have dominated the field of aerial scene classification for the past few years. While achieving remarkable success, CNN-based methods suffer from excessive parameters and notoriously rely on large amounts of training data. In this work, we introduce few-shot learning to the aerial scene classification problem. Few-shot learning aims to learn a model on base-set that can quickly adapt to unseen categories in novel-set, using only a few labeled samples. To this end, we proposed a meta-learning method for few-shot classification of aerial scene images. First, we train a feature extractor on all base categories to learn a representation of inputs. Then in the meta-training stage, the classifier is optimized in the metric space by cosine distance with a learnable scale parameter. At last, in the meta-testing stage, the query sample in the unseen category is predicted by the adapted classifier given a few support samples. We conduct extensive experiments on two challenging datasets: NWPU-RESISC45 and RSD46-WHU. The experimental results show that our method yields state-of-the-art performance. Furthermore, several ablation experiments are conducted to investigate the effects of dataset scale, the impact of different metrics and the number of support shots; the experiment results confirm that our model is specifically effective in few-shot settings.

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.

Commercial sleep devices and mobile-phone applications for scoring sleep are gaining ground. In order to provide reliable information about the quantity and/or quality of sleep, their performance needs to be assessed against the current gold-standard, i.e. polysomnography (PSG; measuring brain, eye and muscle activity). We here assessed some commercially available sleep trackers, namely; a commercial activity tracker: Mi band (Xiaomi, BJ, CHN), a scientific actigraph: Motionwatch 8 (CamNTech, CB, UK), and a much used sleep application: Sleep Cycle (Northcube, GOT, SE). We recorded 27 nights in healthy sleepers using PSG and these devices. Surprisingly, all devices had very poor agreement with the gold standard. Sleep parameter comparisons revealed that specifically the Mi band and the sleep cycle application had difficulties in detecting wake periods which negatively affected the total sleep time and sleep efficiency estimations. However, all 3 devices were good in detecting the most basic parameter, the actual time in bed. In summary, our results suggest that, to-date; available sleep trackers do not provide meaningful sleep analysis but may be interesting for simply tracking times in bed. A much closer interaction with the scientific field seems necessary if reliable information shall be derived from such devices in the future.

In this study an adjusting post-processing approach is implemented for improving intra-hourly forecasts of solar power and ramp events of PV solar power systems at different locations in the United States. This study also serves as an out-of-sample test to evaluate the performance of the adjusting approach with different locations and timescales. Thus, various individual intra-hourly forecasts of solar power are combined and adjusted by applying the adjusting approach. Both point and probabilistic forecasts of solar power are included. After that, solar power ramp event forecasting by the adjusting approach is carried out.

Background: In this secondary analysis of the Supporting the Modification of Lifestyle In Lowered Emotional States (SMILES) randomised controlled trial, we investigated if the beneficial effects of a dietary intervention on clinical depression were driven, in part, by reducing the consumption of foods classified as ultra-processed.Methods: The SMILES trial enrolled 67 adults with major depressive disorder, randomly assigning them to either a 12-week modified Mediterranean dietary intervention or a social support control. Our analysis included 44 participants with non-missing dietary data and at least one valid Montgomery–Åsberg Depression Rating Scale (MADRS) assessment at 12 weeks of follow-up. The Nova food classification system was used to estimate the proportion of ultra-processed foods in the overall diet (percentage of grams) based on data from seven-day food diaries. We fitted linear regression models under blinded conditions to determine whether ultra-processed food intake-change from baseline to 12 weeks moderated the dietary intervention effects on depressive symptoms. We estimated mean differences in depressive symptoms along with ninety-five per cent confidence intervals (95%CIs).Results: For participants in the dietary intervention, there was an additional 2.5-point improvement in MADRS scores for each 10% reduction in the dietary share of ultra-processed foods compared to participants in the control group (between-group mean differences in depressive symptoms: −2.46, 95%CIs −4.71 to −0.20, p=0.039, η _p ² of 0.10).Conclusions: These preliminary findings suggest that the therapeutic benefit of a dietary intervention for depression may stem, at least in part, from reductions in the dietary share of ultra-processed foods.

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 fatty-acid profiles of five main commercial pistachio cultivars, including Ahmad-Aghaei, Akbari, Chrok, Kalle-Ghouchi and Ohadi, were determined by gas chromatography: palmitic (C16:0), palmitoleic (C16:1), stearic (C18:0), oleic (C18:1), linoleic (C18:2), linolenic (C18:3) arachidic (C20:0) and gondoic (C20:1) acid. Based on the oleic to linoleic acid (O/L) ratio, a quality index was determined for these five cultivars: Ohadi (2.40) < Ahmad-Aghaei (2.60) < Kale-Ghouchi (2.94) < Chrok (3.05) < Akbari (3.66). Principal component analysis (PCA) of the fatty-acid data yielded three significant PCs, which together account for 80.0% of the total variance in the data set. A linear discriminant analysis (LDA) model evaluated with cross validation correctly classified almost all samples: the average percent accuracy for the prediction set was 98.0%. The high predictive power for the prediction set shows the ability to indicate the cultivar of an unknown sample based on its fatty-acid chromatographic fingerprint.

Autonomous image recognition has numerous potential applications in the field of planetary science and geology. For instance, having the ability to classify images of rocks would allow geologists to have immediate feedback without having to bring back samples to the laboratory. Also, planetary rovers could classify rocks in remote places and even in other planets without needing human intervention. Shu et al. classified 9 different types of rock images using a Support Vector Machine (SVM) with the image features extracted autonomously. Through this method, the authors achieved a test accuracy of 96.71%. In this research, Convolutional Neural Networks(CNN) have been used to classify the same set of rock images. Results show that a 3-layer network obtains an average accuracy of 99.60% across 10 trials on the test set. A version of Self-taught Learning was also implemented to prove the generalizability of the features extracted by the CNN. Finally, one model has been chosen to be deployed on a mobile device to demonstrate practicality and portability. The deployed model achieves a perfect classification accuracy on the test set, while taking only 0.068 seconds to make a prediction, equivalent to about 14 frames per second.

In the field of computer vision, large-scale image classification tasks are both important and highly challenging. With the ongoing advances in deep learning and optical character recognition (OCR) technologies, neural networks designed to perform large-scale classification play an essential role in facilitating OCR systems. In this study, we developed an automatic OCR system designed to identify up to 13,070 large-scale printed Chinese characters by using deep learning neural networks and fine-tuning techniques. The proposed framework comprises four components, including training dataset synthesis and background simulation, image preprocessing and data augmentation, the process of training the model, and transfer learning. The training data synthesis procedure is composed of a character font generation step and a background simulation process. Three background models are proposed to simulate the factors of the background noise and anti-counterfeiting patterns on ID cards. To expand the diversity of the synthesized training dataset, rotation and zooming data augmentation are applied. A massive dataset comprising more than 19.6 million images was thus created to accommodate the variations in the input images and improve the learning capacity of the CNN model. Subsequently, we modified the GoogLeNet neural architecture by replacing the FC layer with a global average pooling layer to avoid overfitting caused by a massive amount of training data. Consequently, the number of model parameters was reduced. Finally, we employed the transfer learning technique to further refine the CNN model using a small number of real data samples. Experimental results show that the overall recognition performance of the proposed approach is significantly better than that of prior methods and thus demonstrate the effectiveness of proposed framework, which exhibited a recognition accuracy as high as 99.39% on the constructed real ID card dataset.

Automated machine classifications of galaxies are necessary because the size of upcoming surveys will overwhelm human volunteers. We improve upon existing machine classification methods by adding the output of SpArcFiRe to the inputs of a machine learning model. We use the human classifications from Galaxy Zoo 1 (GZ1) to train a random forest of decision trees to reproduce the human vote distributions of the Spiral class. We prefer the random forest model over other black box models like neural networks because it allows us to trace post hoc the precise reasoning behind the classification of each galaxy. We find that, across a sample of 470,000 Sloan galaxies that are large enough that details could be seen if they were there, the combination of SpArcFiRe outputs with existing SDSS features provides a better machine classification than either one alone on comparison to Galaxy Zoo 1. We suggest that adding SpArcFiRe outputs as features to any machine learning algorithm will likely improve its performance.

The progressive impairment analysis in gait from neurological diseases patients such as Hereditary Ataxias (HA) has been carried out using gait data collected with movement sensors. This research is focused on finding the minimum amount required of gait features to recognize efficiently and less intrusive way, HA patients based on data collected with iPhone movement sensors placed on the ankles from 14 HA patients and 14 healthy people. A twofold proposal is made , first a local minimum prominent peak criterion to find out the starting point of each stride, to get 10-stride window about which 56 spatial-temporal features are derived; second a search strategy based on Hill Climbing algorithm to reduce the number of gait features and sensors. The main results were the findings that with two gait patterns a 96% of classification accuracy was achieved by using K-Nearest Neighbors (KNN) and Multi-Layer Perceptron (MLP) algorithms, but in addition, MLP only right ankle sensor patterns were required which also allows to reduce the intrusion.