Search

Background: Emotion is a complex phenomenon that greatly affects human behavior and thinking in daily life. Electroencephalography (EEG), one of the human physiological signals, has been emphasized by most researchers in emotion recognition as its specific properties are closely associated with human emotion. However, the number of human emotion recognition studies using computer games as stimuli is still insufficient as there were no relevant publicly available datasets provided in the past decades. Most of the recent studies using the Gameemo public dataset have not clarified the relationship between the EEG signal's changes and the emotion elicited using computer games. Thus, this paper is proposed to introduce the use of data mining techniques in investigating the relationships between the frequency changes of EEG signals and the human emotion elicited when playing different kinds of computer games. The data acquisition stage, data pre-processing, data annotation and feature extraction stage were designed and conducted in this paper to obtain and extract the EEG features from the Gameemo dataset. The cross-subject and subject-based experiments were conducted to evaluate the classifiers' performance. The top 10 association rules generated by the RCAR classifier will be examined to determine the possible relationship between the EEG signal's frequency changes and game-induced emotions. Results: The RCAR classifier constructed for cross-subject experiment achieved highest accuracy, precision, recall and F1-score evaluated with over 90% in classifying the HAPV, HANV and LANV game-induced emotions. The 20 experiment cases' results from subject-based experiments supported that the SVM classifier could accurately classify the 4 emotion states with a kappa value over 0.62, demonstrating the SVM-based algorithm's capabilities in precisely determining the emotion label for each participant's EEG features' instance. Conclusion: The findings in this study fill the existing gap of game-induced emotion recognition field by providing an in-depth evaluation on the ruleset algorithm's performance and feasibility of applying the generated rules on the game-induced EEG data for justifying the emotional state prediction result. [ABSTRACT FROM AUTHOR]

Optical tracking sensor technology has been widely used in the field of motion. However, there are still some challenges in the recognition of badminton players, and more accurate methods are needed to capture the dynamic characteristics of badminton players. The aim of this study is to design an optical tracking sensor system based on image feature extraction for badminton player motion recognition. In this paper, a high resolution camera is used to collect the image sequence of badminton match. Then through image processing and computer vision technology, the key image features are extracted from the image sequence. Then, machine learning algorithm is used to classify and recognize the extracted features to achieve accurate recognition of badminton players' movements. The experimental results show that the optical tracking sensor system can effectively extract the movement features of badminton players and identify their movements accurately. Compared with the traditional method, the system in this paper has higher precision and real-time performance, and can meet the needs of practical applications. [ABSTRACT FROM AUTHOR]

Automated and accurate detection of power quality (PQ) events is important from the point of view of safety as well as maintaining the reliability of the power transmission and distribution network. However, detection of multiple PQ events in a noisy environment is challenging task. Another important issue is the choice of meaningful features that can directly influence the accuracy of PQ detection. Considering these two aforesaid facts, this paper presents a novel framework for automated classification of PQ signals in a noisy environment employing cross Stockwell Transform (XST). The XST proposed in this paper has better noise suppression capability compared to conventional Stockwell Transform. Here, XST was used to convert 1D PQ signals to 2D time–frequency (T–F) images. To improve the accuracy of PQ detection, an automated feature extraction method employing deep learning is implemented in this work. The noise free T–F images obtained using XST were fed as inputs to several pre-trained convolutional neural networks (CNNs) for deep feature extraction. Transfer learning technique was implemented to reduce the computational cost. The extracted deep features were further undergone selection using one-way analysis of variance test followed by false discovery rate correction. The statistically significant deep features were subsequently fed to three benchmark machine learning classifiers for classification of PQ signals. In addition, tests were also carried out on real-life PQ signals to verify the practicability of the proposed framework. Investigations revealed that the proposed method returned mean accuracy of 99.72% and 96.45% for classification of simulated and real-life PQ signals, respectively. [ABSTRACT FROM AUTHOR]

Tabular data analysis is a critical task in various domains, enabling us to uncover valuable insights from structured datasets. While traditional machine learning methods can be used for feature engineering and dimensionality reduction, they often struggle to capture the intricate relationships and dependencies within real-world datasets. In this paper, we present Multi-representation DeepInsight (MRep-DeepInsight), a novel extension of the DeepInsight method designed to enhance the analysis of tabular data. By generating multiple representations of samples using diverse feature extraction techniques, our approach is able to capture a broader range of features and reveal deeper insights. We demonstrate the effectiveness of MRep-DeepInsight on single-cell datasets, Alzheimer's data, and artificial data, showcasing an improved accuracy over the original DeepInsight approach and machine learning methods like random forest, XGBoost, LightGBM, FT-Transformer and L2-regularized logistic regression. Our results highlight the value of incorporating multiple representations for robust and accurate tabular data analysis. By leveraging the power of diverse representations, MRep-DeepInsight offers a promising new avenue for advancing decision-making and scientific discovery across a wide range of fields. [ABSTRACT FROM AUTHOR]

In the past decades, a variety of learning-based algorithms have been emerged to try to explore a better solution for stereo matching by leveraging various machine learning algorithms. For enriching learning-based stereo matching algorithm's methodologies, we cast the disparity estimation as a regression problem by leveraging Structured Support Vector Machine (SSVM) in this paper. There are three categories of features have been extracted on account of disparity cues for training the SSVM. Particularly, one of the three feature is named as 'Coarse-to-Fine PatchMatch Filtering', which effectively exploits region and pixel disparity cues. For attaining region disparity cues, we adopt MeshStereo and MeshStereo with Cross-Scale algorithms; for attaining pixel disparity cues, PatchMatch and Cross-Scale PatchMatch stereo matching algorithms are utilized. Performance evaluations on Middlebury v.2 and v.3 stereo data sets demonstrate that the proposed algorithm reveals comparable accuracy with other challenging learning-based ones. It is worth pointing out that our proposal performs over several orders of magnitude faster than others on training time. [ABSTRACT FROM AUTHOR]

Internet of Things (IoTs) has been playing an important role in many sectors, such as smart cities, smart agriculture, smart healthcare, and smart manufacturing. However, IoT devices are highly vulnerable to cyber-attacks, which may result in security breaches and data leakages. To effectively prevent these attacks, a variety of machine learning-based network intrusion detection methods for IoT networks have been developed, which often rely on either feature extraction or feature selection techniques for reducing the dimension of input data before being fed into machine learning models. This aims to make the detection complexity low enough for real-time operations, which is particularly vital in any intrusion detection systems. This paper provides a comprehensive comparison between these two feature reduction methods of intrusion detection in terms of various performance metrics, namely, precision rate, recall rate, detection accuracy, as well as runtime complexity, in the presence of the modern UNSW-NB15 dataset as well as both binary and multiclass classification. For example, in general, the feature selection method not only provides better detection performance but also lower training and inference time compared to its feature extraction counterpart, especially when the number of reduced features K increases. However, the feature extraction method is much more reliable than its selection counterpart, particularly when K is very small, such as K = 4 . Additionally, feature extraction is less sensitive to changing the number of reduced features K than feature selection, and this holds true for both binary and multiclass classifications. Based on this comparison, we provide a useful guideline for selecting a suitable intrusion detection type for each specific scenario, as detailed in Table 14 at the end of Sect. 4. Note that such the comparison between feature selection and feature extraction over UNSW-NB15 as well as theoretical guideline have been overlooked in the literature. [ABSTRACT FROM AUTHOR]

Effective management of dementia requires the timely detection of mild cognitive impairment (MCI). This paper introduces a multi-objective optimization approach for selecting EEG channels (and features) for the purpose of detecting MCI. Firstly, each EEG signal from each channel is decomposed into subbands using either variational mode decomposition (VMD) or discrete wavelet transform (DWT). A feature is then extracted from each subband using one of the following measures: standard deviation, interquartile range, band power, Teager energy, Katz's and Higuchi's fractal dimensions, Shannon entropy, sure entropy, or threshold entropy. Different machine learning techniques are used to classify the features of MCI cases from those of healthy controls. The classifier's performance is validated using leave-one-subject-out (LOSO) cross-validation (CV). The non-dominated sorting genetic algorithm (NSGA)-II is designed with the aim of minimizing the number of EEG channels (or features) and maximizing classification accuracy. The performance is evaluated using a publicly available online dataset containing EEGs from 19 channels recorded from 24 participants. The results demonstrate a significant improvement in performance when utilizing the NSGA-II algorithm. By selecting only a few appropriate EEG channels, the LOSO CV-based results show a significant improvement compared to using all 19 channels. Additionally, the outcomes indicate that accuracy can be further improved by selecting suitable features from different channels. For instance, by combining VMD and Teager energy, the SVM accuracy obtained using all channels is 74.24%. Interestingly, when only five channels are selected using NSGA-II, the accuracy increases to 91.56%. The accuracy is further improved to 95.28% when using only 8 features selected from 7 channels. This demonstrates that by choosing informative features or channels while excluding noisy or irrelevant information, the impact of noise is reduced, resulting in improved accuracy. These promising findings indicate that, with a limited number of channels and features, accurate diagnosis of MCI is achievable, which opens the door for its application in clinical practice. [ABSTRACT FROM AUTHOR]

The core premise of cancelable biometrics lies in the creation of a distinct biometric template for every individual, which can be either canceled or regenerated as needed. This process requires the use of a uniquely-defined key during the generation of such template. The generated templates are tailored to be key-specific. This ensures that each distinct key will generate a unique template, while preserving the integrity and security of the original biometric data, ensuring that it remains uncompromised. In this paper, a cancelable biometric system based on electrocardiography (ECG) and photoplethysmography (PPG) signals is introduced. A signal fusion process is implemented for the two traits to generate a single template per user. In order to enhance the security of generated templates, a well-designed permutation stage is implemented according to a user-specific key. The permutation key is obtained through a well-designed look-up table created by the authors. The user verification is conducted on the cancelable template, without the need for any inversion processes. The user verification scheme depends on a two-pronged approach: robust feature extraction followed by the application of a machine learning (ML) classifier. The mel-frequency cepstral coefficients (MFCCs) extraction algorithm is employed for feature extraction due to the low frequency range of the adopted biometric signals and the nonlinearity of the filter bank used for MFCC extraction. Several ML classifiers are adopted to validate the system with cancelable templates without any inversion process. Simulation results with multilayer perceptron (MLP) and logistic regression (LR) classifiers demonstrated superior effectiveness of the proposed authentication framework, with accuracy rates up to 100% and 99.7% on the pulse transit time PPG and BIDMC datasets, respectively. Hence, the proposed system proves effective access control and user verification in the Internet-of-Things (IoT) applications. [ABSTRACT FROM AUTHOR]

Optical processing technology can improve the accuracy and efficiency of image processing. Visual packaging art design simulation is to quickly generate realistic packaging effects in the early stage of packaging design, so as to make better design decisions. Traditional simulation methods often require a lot of time and human resources, and the results lack realism and detail. Machine vision technology based on optical processing can make full use of image processing algorithms and computer vision technology to achieve efficient and accurate packaging design simulation. In this paper, a machine vision technology framework based on image optical processing is proposed. In the image acquisition stage, high-resolution cameras are used to acquire real packaging images, and in the optical processing stage, algorithms are used to enhance, reduce noise and correct images to improve image quality and clarity. In the image analysis stage, machine learning algorithms are used to extract features and detect and identify packaging elements, providing data support for subsequent simulation rendering. The results show that the machine vision technology based on image optical processing can generate high quality and realistic simulation effect of packaging design. Compared with traditional methods, this technique has achieved significant improvements in terms of time cost and design quality. [ABSTRACT FROM AUTHOR]

In this paper, a novel method is introduced to diagnose the cardiac arrhythmias. Automatic diagnosis of cardiac arrhythmias is crucial for successful treatment of heart diseases, and nowadays, machine learning is used to facilitate this purpose. For accurate classification of arrhythmias, it is vital to extract some appropriate features which distinguish different classes. In this research, a deep convolutional neural network is used to extract the features. Since the heart rates of various patients are very different, arrhythmias of a specific class will be placed in different locations of feature space. To reduce the intra-class variations, each patient's heart rate is mapped with a dedicated function to increase its similarity to the heart rate of a training patient. The proposed patient-specific mapping decreases the intra-class variation and significantly increases the classification accuracy of cardiac arrhythmias. The calculated accuracy is about 91.08%, which shows the better performance compared to other similar works. [ABSTRACT FROM AUTHOR]

The unsupervised anomaly detection in high-dimensional and complex settings poses a formidable challenge. To tackle the challenges associated with the recognition of high-dimensional data, this paper proposes a feedback channel between the Variational Auto Encoder and the Gaussian process to enhance its data feature extraction capabilities. In order to alleviate the impact of common mislabeling issues within unsupervised contexts, the proposed model introduces a method for the selection of representative data. Subsequently, these representative data points are employed as anchors for the construction of a full-data Gaussian process model covering the entire dataset. To further disentangle the intertwined normal and abnormal data, the proposed model employs a Bayesian framework to guide the displacement of each data point within the latent space toward its position with the highest confidence. This strategic approach effectively discriminates between normal and abnormal data. This innovative method significantly enhances data consolidation within the latent space, thus preserving robustness, particularly when processing high-complexity data. Also, the numerical experiments not only validate the method's effectiveness but also showcase the model's robustness. These experiments highlight that even a small number of incorrect labels do not significantly impact the accuracy of anomaly detection. [ABSTRACT FROM AUTHOR]

This review paper presents the practical development of imaging biomarkers in the scope of the PRIMAGE (PRedictive In silico Multiscale Analytics to support cancer personalized diaGnosis and prognosis, Empowered by imaging biomarkers) project, as a noninvasive and reliable way to improve the diagnosis and prognosis in pediatric oncology. The PRIMAGE project is a European multi-center research initiative that focuses on developing medical imaging-derived artificial intelligence (AI) solutions designed to enhance overall management and decision-making for two types of pediatric cancer: neuroblastoma and diffuse intrinsic pontine glioma. To allow this, the PRIMAGE project has created an open-cloud platform that combines imaging, clinical, and molecular data together with AI models developed from this data, creating a comprehensive decision support environment for clinicians managing patients with these two cancers. In order to achieve this, a standardized data processing and analysis workflow was implemented to generate robust and reliable predictions for different clinical endpoints. Magnetic resonance (MR) image harmonization and registration was performed as part of the workflow. Subsequently, an automated tool for the detection and segmentation of tumors was trained and internally validated. The Dice similarity coefficient obtained for the independent validation dataset was 0.997, indicating compatibility with the manual segmentation variability. Following this, radiomics and deep features were extracted and correlated with clinical endpoints. Finally, reproducible and relevant imaging quantitative features were integrated with clinical and molecular data to enrich both the predictive models and a set of visual analytics tools, making the PRIMAGE platform a complete clinical decision aid system. In order to ensure the advancement of research in this field and to foster engagement with the wider research community, the PRIMAGE data repository and platform are currently being integrated into the European Federation for Cancer Images (EUCAIM), which is the largest European cancer imaging research infrastructure created to date. [ABSTRACT FROM AUTHOR]

Lithium-ion batteries are becoming more popular due to their superior performance like high power density, long lifespan, broad operating range of temperatures, quick charging capabilities, and low self-discharge. The implementation of a Battery Management System (BMS) is crucial in order to guarantee the secure and optimal functioning of electric vehicle batteries. BMS monitors, controls, and maintains the health and performance of rechargeable batteries by monitoring the State of Charge (SoC), State of Health (SoH), and State of Temperature (SoT). SoC quantifies the amount of energy stored in a battery at a certain moment, and it is employed to approximate the remaining distance that may be covered. SoH describe the overall health or state of a rechargeable battery. It reveals how well a battery performs in comparison to its original state. SoT estimation keeps the battery temperature within a safe range, allowing it to reach a higher age and safety, which is critical for battery reliability. In this paper SoC, SoH, SoT estimation models for a lithium-ion battery have been developed using an improved EP-based R110-BLSTM approach. The Emperor Penguin based Residual Network-110 incorporated Bidirectional Long-Short Term Memory (EP-based R110-BLSTM) is ideal for estimating SoC, SoH, and SoT and features great accuracy, a quick estimation speed, and strong generalization capabilities. However, Extreme Learning Machine performance is heavily reliant on proper feature extraction. In order to enhance estimate performance by extracting the best features, Simulated-Annealing-based Golden Eagle optimization is utilized. Electric vehicle drive cycles are used to test the model's resilience to temperature changes. MATLAB 2018b software is used in the execution of this research. The results demonstrate that the proposed model performs better in terms of accuracy and has lower SoC, SoH, and SoT error rates than existing models. A thorough comparison between the recommended model and existing methods is also made, further demonstrating the proposed model's superiority. [ABSTRACT FROM AUTHOR]

Considering that serious hand function damage will greatly affect the daily life of patients, its recovery mainly depends on the regular inspection and manual training of medical staff, and medical monitoring based on bioelectric signals can largely replace manual re-examination as autonomous rehabilitation technology. So, for the rationality of feature selection and the diversity of classifier design in the gesture recognition process based on electromyography (EMG) signals, this paper proposes a hand medical monitoring system based on feature selection method of feature subset average recognition rate and optimal machine learning algorithm selection, which mainly depends on the prediction of hand movement. At the same time, since most experiments are conducted in different non-public proprietary databases, the comparison between various gesture recognition methods can only be analyzed to a certain extent. Therefore, this paper uses the DB1 dataset in the large publicly available NinaPro database and combines with presently well-known 11 time-domain (TD) features and 5 frequency domain (FD) features, then uses the support vector machine (SVM) classifier to comparative analysis total 136 feature combinations under various feature numbers. Under the premise of ensuring the overall recognition rate of electromyography gesture, this method will be able to reduce the number of features in feature set, according to the change of the average remove redundant features, and construct an optimal reduced EMG feature set. Finally, through the four common hand motion classifiers based on machine learning: SVM, back propagation neural network, linear discriminant analysis, and K-nearest neighbor, this paper tests and verifies the separability of the optimal reduced EMG feature set, and based on this, selects the optimal hand motion classifier to build the optimal hand motion recognition system, improve the hand medical monitoring system, and provide technical reference for the construction of real-time medical monitoring system. [ABSTRACT FROM AUTHOR]

Purpose: There are millions of people who lose their life due to several types of fatal diseases. Cancer is one of the most fatal diseases which may be due to obesity, alcohol consumption, infections, ultraviolet radiation, smoking, and unhealthy lifestyles. Cancer is abnormal and uncontrolled tissue growth inside the body which may be spread to other body parts other than where it has originated. Hence it is very much required to diagnose the cancer at an early stage to provide correct and timely treatment. Also, manual diagnosis and diagnostic error may cause of the death of many patients hence much research are going on for the automatic and accurate detection of cancer at early stage. Methods: In this paper, we have done the comparative analysis of the diagnosis and recent advancement for the detection of various cancer types using traditional machine learning (ML) and deep learning (DL) models. In this study, we have included four types of cancers, brain, lung, skin, and breast and their detection using ML and DL techniques. In extensive review we have included a total of 130 pieces of literature among which 56 are of ML-based and 74 are from DL-based cancer detection techniques. Only the peer reviewed research papers published in the recent 5-year span (2018–2023) have been included for the analysis based on the parameters, year of publication, feature utilized, best model, dataset/images utilized, and best accuracy. We have reviewed ML and DL-based techniques for cancer detection separately and included accuracy as the performance evaluation metrics to maintain the homogeneity while verifying the classifier efficiency. Results: Among all the reviewed literatures, DL techniques achieved the highest accuracy of 100%, while ML techniques achieved 99.89%. The lowest accuracy achieved using DL and ML approaches were 70% and 75.48%, respectively. The difference in accuracy between the highest and lowest performing models is about 28.8% for skin cancer detection. In addition, the key findings, and challenges for each type of cancer detection using ML and DL techniques have been presented. The comparative analysis between the best performing and worst performing models, along with overall key findings and challenges, has been provided for future research purposes. Although the analysis is based on accuracy as the performance metric and various parameters, the results demonstrate a significant scope for improvement in classification efficiency. Conclusion: The paper concludes that both ML and DL techniques hold promise in the early detection of various cancer types. However, the study identifies specific challenges that need to be addressed for the widespread implementation of these techniques in clinical settings. The presented results offer valuable guidance for future research in cancer detection, emphasizing the need for continued advancements in ML and DL-based approaches to improve diagnostic accuracy and ultimately save more lives. [ABSTRACT FROM AUTHOR]

Lung cancer is an uncontrolled growth of tissue causing a lump in the human lung. If lung cancer can be detected early, it can increase the survival rate. Therefore, a multi-classification approach of lung nodule detection with high computational effectiveness is required. In this paper, a multi-classification approach of lung nodule detection and classification is proposed using artificial intelligence on computed tomography (CT) scan images. Different preprocessing steps are applied for resizing, smoothing, and enhancement of the CT images. Then, two different approaches for feature extraction using VGG16 transfer learning and morphological segmentation are proposed. Morphological segmentation and feature extraction are applied for the segmentation of the region of interest and to extract the distinct features. Finally, the proposed deep learning architecture and seven different machine learning algorithms are applied on the preprocessed data and the extracted features for the classification of lung nodules into three classes: malignant, benign, and normal. It is observed that the stacked ensemble model of deep learning convolutional neural network (CNN) and VGG16 transfer learning models (CNN+VGG16) can achieve 99.55% accuracy using preprocessed data. It is also observed that all the ML algorithms perform with reasonably high accuracy using the low-dimensional morphological features. It is observed from the fivefold cross-validation results that logistic regression performs with 99.36% accuracy in 23.71 s time using the preprocessed data. Whereas, using the morphological features, k-nearest neighbor, and the support vector machine perform with the highest accuracy of 99.76% with very reduced computational time of 0.017 and 0.008 s, respectively. [ABSTRACT FROM AUTHOR]

Microelectronics production failure analysis is an important step in improving product quality and development. In fact, the understanding of the failure mechanisms and therefore the implementation of corrective actions on the cause of the failure depend on the results of this analysis. These analyses are saved under textual features format. Then such data need first to be preprocessed and vectorized (converted to numeric). Second, to overcome the curse of dimensionality caused by the vectorisation process, a dimension reduction is applied. A two-stage variable selection and feature extraction is used to reduce the high dimensionality of a feature space. We are first interested in studying the potential of using an unsupervised variable selection technique, the genetic algorithm, to identify the variables that best demonstrate discrimination in the separation and compactness of groups of textual data. The genetic algorithm uses a combination of the K-means or Gaussian Mixture Model clustering and validity indices as a fitness function for optimization. Such a function improves both compactness and class separation. The second work looks into the feasibility of applying a feature extraction technique. The adopted methodology is a Deep learning algorithm based on variational autoencoder (VAE) for latent space disentanglement and Gaussian Mixture Model for clustering of the latent space for cluster identification. The last objective of this paper is to propose a new methodology based on the combination between variational autoencoder (VAE) for the latent space disentanglement, and genetic algorithm (GA) to find, in an unsupervised way, the latent variables allowing the best discrimination of clusters of failure analysis data. This methodology is called VAE-GA. Experiments on textual datasets of failure analysis demonstrate the effectiveness of the VAE-GA proposed method which allows better discrimination of textual classes compared to the use of GA or VAE separately or the combination of PCA with GA (PCA-GA) or a simple Auto-encoders with GA (AE-GA). [ABSTRACT FROM AUTHOR]

This paper presents the identification and classification of Indian agricultural crop species using a novel combined local binary histogram pattern of gradient (LBHPG) image feature extraction technique. Initially, a partition of the leaf image background is done through the newly developed fast adaptive fuzzy C-mean clustering (FAFCM) technique. After that, leaf objects within the image are identified using the LBHPG method. For the classification, KNN, PNN, and SVM shallow machine learning classifiers are used for crop species identification. The performance evaluation is done using LBP and HOG individually along with the new proposed LBHPG technique for classification using KNN, PNN, and SVM Classifiers. The performance evaluation is based on six metrics parameters of the confusion matrix, viz., accuracy, sensitivity, specificity, precision, recall, and F-measure. The experimental results show that the proposed novel LBHP feature extraction technique with PNN Classifier gives the highest accuracy of 94.58%. [ABSTRACT FROM AUTHOR]

From the beginning of COVID-19 pandemic, numerous mutants of SARS-CoV-2 have since been evolved owing to high transmissibility and virulence. Due to the limited effectiveness of previously imposed vaccines and preventive therapies, these strains are still causing concern. This paper proposes comparative evaluation of three novel genomic signal processing-based methods employing discrete wavelet decomposition with lifting (DWT), discrete Fourier transform (DFT), and singular value decomposition (SVD) for the classification of emerging SARS-CoV-2 variants utilizing feature extraction from collected SARS-CoV-2 variants acquired from the NCBI virus database. The efficiency and accuracy of the proposed alignment-free algorithms have been tested using three Coronavirus datasets including human Coronavirus (HCoV), SARS-CoV-2 variants (CoV-Variants and Omicron). The viral nucleotide sequences which are converted into numerical representation leveraging purine-pyrimidine mapping, DNA walk & Z-curve are fed into DWT, SVD, & DFT processors, respectively. In the approach with DWT, the second-generation wavelet transform employs two best wavelet bases Daubechies (Db) and Biorthogonal (Bior) based on the validation of the HCoV dataset for the feature extraction of the CoV-Variants dataset. Various machine learning algorithms, such as Support Vector Machine, K-nearest neighbors, and ensemble, are used to classify the virus strains and evaluate the efficacy of the algorithm. Finally, hyper-parametric tuning is done utilizing the Bayesian optimization technique to select the best fit model for KNN and SVM. The proposed algorithm has successfully classified the CoV-Variants dataset with an average accuracy of 98.76% utilizing the DWT, DFT, and SVD, while the best-achieved accuracy for this dataset is 98.9% using the DWT technique employing purine–pyrimidine mapping. The best-achieved accuracy rate for predicting Omicron is 99.8% using SVD-based technique. The best-obtained accuracy for HCoV dataset is 100% resulted in all three methods. [ABSTRACT FROM AUTHOR]

A rapid expansion in the world's population needs an enormous supply of food grains to satisfy agricultural needs. Unfortunately, crop diseases adversely impact food production and disrupt the supply chain. To circumvent the limitations of continuous human monitoring, machine learning techniques can automatically diagnose leaf diseases in their early stages based on image data. In this paper, an Interpretable Leaf Disease Detector (I-LDD) framework for image-based leaf disease detection using Extreme Learning Machine (ELM) is proposed. The choice of ELM for this work has been motivated by its quicker convergence, good generalization capability, and shorter learning time compared to the standard gradient-based learning algorithms. Experiments have been carried out using a publicly available PlantVillage dataset comprising healthy and diseased leaf images for 32 categories. In the first phase, the leaf images are preprocessed and segmented using the k-means clustering algorithm. In the second phase, textural and frequency-based features are extracted from the segmented images. In the third phase, several machine learning classifiers are trained using tenfold cross-validation. It is observed that I-LDD achieves an accuracy of 0.9322 ± 0.0088 at a 95% confidence level, outperforming the state-of-the-art methods. Moreover, a statistical significance test on the classification performance metrics also revealed the superiority of I-LDD over the state-of-the-art classifiers. Further, Local Interpretable Model-agnostic Explanations (LIME) is used to obtain the top 10 superpixels that contributed most to the class predicted by I-LDD. [ABSTRACT FROM AUTHOR]

Feature selection is an important component of the machine learning domain, which selects the ideal subset of characteristics relative to the target data by omitting irrelevant data. For a given number of features, there are 2n possible feature subsets, making it challenging to select the optimal set of features from a dataset via conventional feature selection approaches. We opted to investigate glaucoma infection since the number of individuals with this disease is rising quickly around the world. The goal of this study is to use the feature set (features derived from fundus images of benchmark datasets) to classify images into two classes (infected and normal) and to select the fewest features (feature selection) to achieve the best performance on various efficiency measuring metrics. In light of this, the paper implements and recommends a metaheuristics-based technique for feature selection based on emperor penguin optimization, bacterial foraging optimization, and proposes their hybrid algorithm. From the retinal fundus benchmark images, a total of 36 features were extracted. The proposed technique for selecting features minimizes the number of features while improving classification accuracy. Six machine learning classifiers classify on the basis of a smaller subset of features provided by these three optimization techniques. In addition to the execution time, eight statistically based performance metrics are calculated. The hybrid optimization technique combined with random forest achieves the highest accuracy, up to 0.95410. Because the proposed medical decision support system is effective and ensures trustworthy decision-making for glaucoma screening, it might be utilized by medical practitioners as a second opinion tool, as well as assist overworked expert ophthalmologists and prevent individuals from losing their eyesight. [ABSTRACT FROM AUTHOR]

Purpose: To propose a new quality scoring tool, METhodological RadiomICs Score (METRICS), to assess and improve research quality of radiomics studies. Methods: We conducted an online modified Delphi study with a group of international experts. It was performed in three consecutive stages: Stage#1, item preparation; Stage#2, panel discussion among EuSoMII Auditing Group members to identify the items to be voted; and Stage#3, four rounds of the modified Delphi exercise by panelists to determine the items eligible for the METRICS and their weights. The consensus threshold was 75%. Based on the median ranks derived from expert panel opinion and their rank-sum based conversion to importance scores, the category and item weights were calculated. Result: In total, 59 panelists from 19 countries participated in selection and ranking of the items and categories. Final METRICS tool included 30 items within 9 categories. According to their weights, the categories were in descending order of importance: study design, imaging data, image processing and feature extraction, metrics and comparison, testing, feature processing, preparation for modeling, segmentation, and open science. A web application and a repository were developed to streamline the calculation of the METRICS score and to collect feedback from the radiomics community. Conclusion: In this work, we developed a scoring tool for assessing the methodological quality of the radiomics research, with a large international panel and a modified Delphi protocol. With its conditional format to cover methodological variations, it provides a well-constructed framework for the key methodological concepts to assess the quality of radiomic research papers. Critical relevance statement: A quality assessment tool, METhodological RadiomICs Score (METRICS), is made available by a large group of international domain experts, with transparent methodology, aiming at evaluating and improving research quality in radiomics and machine learning. Key points: • A methodological scoring tool, METRICS, was developed for assessing the quality of radiomics research, with a large international expert panel and a modified Delphi protocol. • The proposed scoring tool presents expert opinion-based importance weights of categories and items with a transparent methodology for the first time. • METRICS accounts for varying use cases, from handcrafted radiomics to entirely deep learning-based pipelines. • A web application has been developed to help with the calculation of the METRICS score (https://metricsscore.github.io/metrics/METRICS.html) and a repository created to collect feedback from the radiomics community (https://github.com/metricsscore/metrics). [ABSTRACT FROM AUTHOR]

With the increased use of social network sites, such as Twitter, attackers exploit these platforms to spread counterfeit content. Such content can be fake advertisements or illegal content. Classifying such content is a challenging task, especially in Arabic. The Arabic language has a complex structure and makes classification tasks more difficult. This paper presents an approach to classifying Arabic tweets using classical machine learning (non-deep machine learning) and deep learning techniques. Tweets corpus were collected through Twitter API and labelled manually to get a reliable dataset. For an efficient classifier, feature extraction is applied to the corpus dataset. Then, two learning techniques are used for each feature extraction technique on the created dataset using N-gram models (uni-gram, bi-gram, and char-gram). The applied classical machine learning algorithms are support vector machines, neural networks, logistics regression, and naïve Bayes. Global vector (GloVe) and fastText learning models are utilised for the deep learning approaches. The Precision, Recall, and F1-score are the suggested performance measures calculated in this paper. Afterwards, the dataset is increased using the synthetic minority oversampling technique class to create a balanced dataset. After applying the classical machine learning models, the experimental results show that the neural network algorithm outperforms the other algorithms. Moreover, the GloVe outperforms the fastText model for the deep learning approach. [ABSTRACT FROM AUTHOR]

Pulse-coupled neural networks perform well in many fields such as information retrieval, depth estimation and object detection. Based on pulse coupled neural network (PCNN) theory, this paper constructs a visual perception model framework and builds a real image reproduction platform. The model firstly analyzes the structure and generalization ability of neural network multi-class classifier, uses the minimax criterion of feature space as the splitting criterion of visual perception decision node, which solves the generalization problem of neural network learning algorithm. In the simulation process, the initial threshold is optimized by the two-dimensional maximum inter-class variance method, and in order to improve the real-time performance of the algorithm, the fast recurrence formula of neural network is derived and given. The PCNN image segmentation method based on genetic algorithm is analyzed. The genetic algorithm improves the loop termination condition and the adaptive setting of model parameters of PCNN image segmentation algorithm, but the PCNN image segmentation algorithm still has the problem of complexity. In order to solve this problem, this paper proposed an IGA-PCNN image segmentation method combining the improved algorithm and PCNN model. Firstly, it used the improved immune genetic algorithm to adaptively obtain the optimal threshold, and then replaced the dynamic threshold in PCNN model with the optimal threshold, and finally used the pulse coupling characteristics of PCNN model to complete the image segmentation. From the coupling characteristics of PCNN, junction close space of image and gray level characteristics, it determined the local gray mean square error of image connection strength coefficient. The feature extraction and object segmentation properties of PCNN come from the spike frequency of neurons, and the number of neurons in PCNN is equal to the number of pixels in the input image. In addition, the spatial and gray value differences of pixels should be considered comprehensively to determine their connection matrix. Digital experiments show that the multi-scale multi-task pulse coupled neural network model can shorten the total training time by 17 h, improve the comprehensive accuracy of the task test data set by 1.04%, and shorten the detection time of each image by 4.8 s compared with the series network model of multiple single tasks. Compared with the traditional PCNN algorithm, it has the advantages of fast visual perception and clear target contour segmentation, and effectively improves the anti-interference performance of the model. [ABSTRACT FROM AUTHOR]

Collecting and analyzing data from all devices to improve the efficiency of business processes is an important task of Industrial Internet of Things (IIoT). In the age of data explosion, extensive text data generated by the IIoT have given birth to a variety of text representation methods. The task of text representation is to convert the natural language to a form that computer can understand with retaining the original semantics. However, these methods are difficult to effectively extract the semantic features among words and distinguish polysemy in natural language. Combining the advantages of convolutional neural network (CNN) and variational autoencoder (VAE), this paper proposes an intelligent CNN-VAE text representation algorithm as an advanced learning method for social big data within next-generation IIoT, which help users identify the information collected by sensors and perform further processing. This method employs the convolution layer to capture the local features of the context and uses the variational technique to reconstruct feature space to make it conform to the normal distribution. In addition, the improved word2vec model based on topical word embedding (TWE) is utilized to add topical information to word vectors to distinguish polysemy. This paper takes the social big data as an example to illustrate the way of the proposed algorithm applied in the next-generation IIoT and utilizes Cnews dataset to verify the performance of proposed method with four evaluating metrics (i.e., recall, accuracy, precision, and F1-score). Experimental results indicate that the proposed method outperforms word2vec-avg and CNN-AE in K-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) classifiers and distinguishes polysemy effectively. [ABSTRACT FROM AUTHOR]

This paper presents an efficient approach to estimate the failures of various components in an induction motor using motor current signature analysis. Conventional sensor-based fault detection methods lead to huge manpower and require greater number of sensors. To overcome these drawbacks, current signature base fault detection is proposed. An advanced spectral analysis, namely discrete wavelet transform (DWT), is used for frequency domain analysis. This paper also presents fault severity estimation using feature extraction-based evaluation of DWT coefficients. As the DWT gives many coefficients at higher level decomposition which is essential for high resolution, fault classification and severity index become challenging. To address this issue, artificial neural network (ANN) algorithm is used after DWT decomposition. The fault severity is predicted by proposed fault indexing parameter of various features like energy, standard deviation, skewness, variance, RMS values. Conventional algorithms like support vector machine, k‐nearest neighbour, local mean decomposition-singular value decomposition and extreme learning machine have given maximum of 98–99% accuracy, Whereas the proposed DWT-based ANN has given 100% accuracy with tanh function. Moreover, the testing loss with this function is also very less. Experimental results have affirmed the accuracy of proposed fault detection of various faults in induction motor of rating 3—Phase, 1. 5KW, 440 V and 50 Hz. [ABSTRACT FROM AUTHOR]

Penetration recognition is the critical technology to improve manufacturing quality and automation level in arc welding. In this paper, recent research advances concerning penetration recognition based on machine learning are comprehensively reviewed, focused on signals feature extraction and application of machine learning in this field. Three types of signals originating from arc welding, namely, weld pool image, arc sound, and arc voltage, are used to analyze the correlation with the penetration state and extract effective features. Next, the following contents briefly introduce some machine learning methods including conventional machine learning and deep learning, and emphatically summarize their application and performance in penetration recognition. Notably, the deep learning method possesses higher classification accuracy and better generalization ability in penetration recognition due to its deeper architecture and effective learning capacity. In the end, some challenges and tendencies, involving multi-sensor information fusion, data-driven recognition, model development incorporating attention mechanism, lightweight model deployment, and real-time control, are presented for further research. This paper is an attempt to provide a reference source and some guidance for researchers who use machine learning methods for penetration monitoring. [ABSTRACT FROM AUTHOR]

In the process of facial expression recognition, face detection is the prerequisite, image preprocessing is the foundation, facial expression feature extraction is the key, and facial expression classification is the target. Effective feature extraction in this process can improve the accuracy of facial expression classifications. On the other hand, traditional facial expression recognition methods are not only complicated in the feature extraction process, but also unable to obtain more in-depth high-semantic features and deep features from the original image. To solve the above problems, this paper proposes a facial expression recognition method based on multi-channel fusion and lightweight neural network. First, a cascade classifier based on Haar features is used to detect the face region of the facial expression image. Second, the local binary pattern (LBP) is used to extract the local texture features from the face region. Third, face edge features are simultaneously obtained by performing edge detection in the face region based on the Canny edge detection algorithm. Fourth, the obtained face image, LBP texture feature image, and edge detection Canny image are fused, and the fused image is input into the constructed lightweight neural network for training and recognition. Experiments are carried out on the public image databases Facial Expression Recognition 2013 (Fer2013) and extended Cohn–Kanade (CK +) using the hold-out cross-validation method. The experimental results show that the proposed method effectively extracts more complete image features by combining traditional feature extraction algorithms with deep learning feature extraction algorithms, improves the accuracy and robustness of facial expression recognition, and has better recognition rate and generalization ability compared to other mainstream methods. [ABSTRACT FROM AUTHOR]

Because of the massive multimedia in daily life, people perceive the world by concurrently processing and fusing multi-modalities with high-dimensional data which may include text, vision, audio and some others. Depending on the popular Machine Learning, we would like to get much better fusion results. Therefore, multi-modal analysis has become an innovative field in data processing. By combining different modes, data can be more informative. However the difficulties of multi-modality analysis and processing lie in Feature extraction and Feature fusion. This paper focussed on this point to propose the BERT-HMAG model for feature extraction and LMF-SA model for multi-modality fusion. During the experiment, compared with traditional models, such as LSTM and Transformer, they are improved to a certain extent. [ABSTRACT FROM AUTHOR]

We introduce Shennong, a Python toolbox and command-line utility for audio speech features extraction. It implements a wide range of well-established state-of-the-art algorithms: spectro-temporal filters such as Mel-Frequency Cepstral Filterbank or Predictive Linear Filters, pre-trained neural networks, pitch estimators, speaker normalization methods, and post-processing algorithms. Shennong is an open source, reliable and extensible framework built on top of the popular Kaldi speech processing library. The Python implementation makes it easy to use by non-technical users and integrates with third-party speech modeling and machine learning tools from the Python ecosystem. This paper describes the Shennong software architecture, its core components, and implemented algorithms. Then, three applications illustrate its use. We first present a benchmark of speech features extraction algorithms available in Shennong on a phone discrimination task. We then analyze the performances of a speaker normalization model as a function of the speech duration used for training. We finally compare pitch estimation algorithms on speech under various noise conditions. [ABSTRACT FROM AUTHOR]

The K-complex is one of the most important and noticeable features in the electroencephalography (EEG) signal, therefore its detection is critical for EEG signal analysis. It is used to diagnose neurophysiologic and cognitive disorders as well as sleep studies. Existing detection methods largely depend on tedious, time-consuming, and error-prone manual inspection of the EEG waveform. In this paper, a highly accurate K-complex detection system is developed. Based on multiple convolutional neural network (CNN) feature extraction backbones and EEG waveform images, you only look once v3 (YOLOv3) detector was designed, trained, and tested. Extensive performance evaluation was performed using five deep transfer learning feature extraction models; Darknet-53, MobileNets, ResNet-18, SqueezeNet, and Darknet-53-coco. The dataset was comprised of 10948 images of EEG waveforms, with the K-complex location automatically annotated with bounding boxes. The Darknet-53 model performed consistently high (i.e., 89.84–99.44% precision and 10.41–0.55% miss rate). Thus, it is possible to perform automatic K-complex detection in real-time with high accuracy that aid practitioners in speedy EEG inspection. [ABSTRACT FROM AUTHOR]

In the last few decades, technological improvements have had a considerable impact on education, much like many other fields of society and human endeavor. The applications of today's cutting-edge technology are numerous in education, but recently researchers focused on using these technologies, especially artificial intelligence (AI) and machine learning (ML), for students' performance prediction prior to the exam. It makes perfect sense to forecast student success to help all participants in the educational process. Student performance prediction may assist them in the selection of suitable courses and in creating their academic schedules. Keeping in mind the importance of student performance evaluation, this paper analyzes the prediction rate of college English level 4 by using one of the powerful ML algorithms called random forest (RF). RF uses numerous classifiers, or "ensembles", rather than just one classifier, and is based on the decision tree technique. To do this, we constructed input and output variables and collected data for these variables, including basic student information (gender, ethnicity, major), English scores on college admission exams, college English scores (total of four semesters), and extracurricular activities of college students. Preprocessing was performed on the collected data, which included the removal of unnecessary attributes, handling outliers, normalization, and data cleaning. After the preprocessing, the features were extracted and transformed into reduced dimensionality by the local-preserving projection (LPP) algorithm. From the extracted features, we selected only the most relevant in order to feed them as input to the RF model. The model is implemented in MATLAB in order to evaluate its performance. The efficiency of the proposed model is evaluated with the help of experiments in order to verify the effectiveness of the model. The performance of the RF algorithm-based college English IV pass rate prediction model is evaluated by computing the prediction accuracy, recall rate, and hit rate of the classification results. We achieved a prediction accuracy of 96.5%, a recall rate of 89.5%, and a hit rate of 93.3%. The results show that the random RF-based prediction model for college English level 4 has a good classification effect and that the prediction results are more accurate. [ABSTRACT FROM AUTHOR]

Sentence-level sentiment analysis (SLSA) aims to identify the overall sentiment polarity conveyed in a given sentence. The state-of-the-art performance of SLSA has been achieved by deep learning models. However, depending on the i.i.d (independent and identically distributed) assumption, the performance of these deep learning models may fall short in real scenarios, where the distributions of training and target data are almost certainly different to some extent. In this paper, we propose a supervised solution based on the non-i.i.d paradigm of gradual machine learning (GML) for SLSA. It begins with some labeled observations, and gradually labels target instances in the order of increasing hardness by iterative knowledge conveyance. It leverages labeled samples for supervised deep feature extraction, and constructs a factor graph based on the extracted features to enable gradual knowledge conveyance. Specifically, it employs a polarity classifier to detect polarity similarity between close neighbors in an embedding space, and a separate binary semantic network to extract implicit polarity relations between arbitrary instances. Our extensive experiments on benchmark datasets show that the proposed approach achieves the state-of-the-art performance on all benchmark datasets. Our work clearly demonstrates that by leveraging DNN for feature extraction, GML can easily outperform the pure DNN solutions. [ABSTRACT FROM AUTHOR]

The novel fault diagnosis method of gearbox based on Fourier Bessel series expansion-based empirical wavelet transform (FBEWT) and manifold regularization extreme learning machine (MRELM) is proposed to obtain excellent fault diagnosis results of gearbox in this paper. A new feature extraction strategy based on Fourier Bessel series expansion-based empirical wavelet transform is used to capture the key non-stationary features of the vibrational signal of gearbox, and significantly improve the diagnosis ability of gearbox. The ELM with manifold regularization is proposed for fault diagnosis of gearbox. In order to outstand the superiority and stability of the proposed FBEWT and manifold regularization ELM, the balanced dataset and unbalanced dataset, respectively, are used. The experimental results testify that FBEWT-MRELM are more superior and stable than FBEWT-ELM, EWT-MRELM, and EWT-ELM regardless of balanced dataset and unbalanced dataset. [ABSTRACT FROM AUTHOR]

Locally advanced cervical cancer (LACC) and anal and oropharyngeal squamous cell carcinoma (ASCC and OPSCC) are mostly caused by oncogenic human papillomaviruses (HPV). In this paper, we developed machine learning (ML) models based on clinical, biological, and radiomic features extracted from pre-treatment fluorine-18-fluorodeoxyglucose positron emission tomography ([18F]-FDG PET) images to predict the survival of patients with HPV-induced cancers. For this purpose, cohorts from five institutions were used: two cohorts of patients treated for LACC including 104 patients from Gustave Roussy Campus Cancer (Center 1) and 90 patients from Leeds Teaching Hospitals NHS Trust (Center 2), two datasets of patients treated for ASCC composed of 66 patients from Institut du Cancer de Montpellier (Center 3) and 67 patients from Oslo University Hospital (Center 4), and one dataset of 45 OPSCC patients from the University Hospital of Zurich (Center 5). Radiomic features were extracted from baseline [18F]-FDG PET images. The ComBat technique was applied to mitigate intra-scanner variability. A modified consensus nested cross-validation for feature selection and hyperparameter tuning was applied on four ML models to predict progression-free survival (PFS) and overall survival (OS) using harmonized imaging features and/or clinical and biological variables as inputs. Each model was trained and optimized on Center 1 and Center 3 cohorts and tested on Center 2, Center 4, and Center 5 cohorts. The radiomic-based CoxNet model achieved C-index values of 0.75 and 0.78 for PFS and 0.76, 0.74, and 0.75 for OS on the test sets. Radiomic feature-based models had superior performance compared to the bioclinical ones, and combining radiomic and bioclinical variables did not improve the performances. Metabolic tumor volume (MTV)-based models obtained lower C-index values for a majority of the tested configurations but quite equivalent performance in terms of time-dependent AUCs (td-AUC). The results demonstrate the possibility of identifying common PET-based image signatures for predicting the response of patients with induced HPV pathology, validated on multi-center multiconstructor data. [ABSTRACT FROM AUTHOR]

Diabetes retinopathy (DR) is one of the leading causes of blindness globally. Early detection of this condition is essential for preventing patients' loss of eyesight caused by diabetes mellitus being untreated for an extended period. This paper proposes the design of an augmented bioinspired multidomain feature extraction and selection model for diabetic retinopathy severity estimation using an ensemble learning process. The proposed approach initiates by identifying DR severity levels from retinal images that segment the optical disc, macula, blood vessels, exudates, and hemorrhages using an adaptive thresholding process. Once the images are segmented, multidomain features are extracted from the retinal images, including frequency, entropy, cosine, gabor, and wavelet components. These data were fed into a novel Modified Moth Flame Optimization-based feature selection method that assisted in optimal feature selection. Finally, an ensemble model using various ML (machine learning) algorithms, which included Naive Bayes, K-Nearest Neighbours, Support Vector Machine, Multilayer Perceptron, Random Forests, and Logistic Regression were used to identify the various severity complications of DR. The experiments on different openly accessible data sources have shown that the proposed method outperformed conventional methods and achieved an Accuracy of 96.5% in identifying DR severity levels. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is one of the key applications of health monitoring that requires continuous use of wearable devices to track daily activities. The most efficient supervised machine learning (ML)-based approaches for predicting human activity are based on a continuous stream of sensor data. Sensor data analysis for human activity recognition using conventional algorithms and deep learning (DL) models shows promising results, but evaluating their ambiguity in decision-making is still challenging. In order to solve these issues, the paper proposes a novel Wasserstein gradient flow legonet WGF-LN-based human activity recognition system. At first, the input data is pre-processed. From the pre-processed data, the features are extracted using Haar Wavelet mother- Symlet wavelet coefficient scattering feature extraction (HS-WSFE). After that, the interest features are selected from the extracted features using (Binomial Distribution integrated-Golden Eagle Optimization) BD-GEO. The important features are then post-processed using the scatter plot matrix method. Obtained post-processing features are finally given into the WGF-LN for classifying human activities. From these experiments, the results can be obtained and showed the efficacy of the proposed model. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) using inertial motion data has gained a lot of momentum in recent years both in research and industrial applications. From the abstract perspective, this has been driven by the rapid dynamics for building intelligent, smart environments, and ubiquitous systems that cover all aspects of human life including healthcare, sports, manufacturing, commerce, etc., which necessitate and subsume activity recognition aiming at recognizing the actions, characteristics, and goals of one or more agent(s) from a temporal series of observations streamed from one or more sensors. From a more concrete and seemingly orthogonal perspective, such momentum has been driven by the ubiquity of inertial motion sensors on-board mobile and wearable devices including smartphones, smartwatches, etc. In this paper we give an introductory and a comprehensive survey to the subject from a given perspective. We focus on a subset of topics, that we think are major, that will have significant and influential impacts on the future research and industrial-scale deployment of HAR systems. These include: (1) a comprehensive and detailed description of the inertial motion benchmark datasets that are publicly available and/or accessible, (2) feature selection and extraction techniques and the corresponding learning methods used to build workable HAR systems; we survey classical handcrafted datasets as well as data-oriented automatic representation learning approach to the subject, (3) transfer learning as a way to overcome many hurdles in actual deployments of HAR systems on a large scale, (4) embedded implementations of HAR systems on mobile and/or wearable devices, and finally (5) we touch on adversarial attacks, a topic that is essentially related to the security and privacy of HAR systems. As the field is very huge and diverse, this article is by no means comprehensive; it is though meant to provide a logically and conceptually rather complete picture to advanced practitioners, as well as to present a readable guided introduction to newcomers. Our logical and conceptual perspectives mimic the typical data science pipeline for state-of-the-art AI-based systems. [ABSTRACT FROM AUTHOR]

At present, the trend of familiarization of malicious code is becoming more and more obvious, and the research on the homology of malware (the classification of malicious code family) is of great significance for maintaining network security. In order to better express the overall characteristics of malicious code and improve the effect of detection and homology analysis, this paper proposes a method for detection and homology analysis of malware based on heterogeneous graphs of assembly instructions (AIHGAT). We take the assembly instructions of malicious families as the research object and analyze the importance and correlation of assembly instructions of different malicious families. The malware detection and homology analysis are carried out in three aspects: feature extraction, feature preprocessing, and model construction. In the feature extraction of malicious code, in order to alleviate the problem that it is difficult to extract static features of malicious samples that contain countermeasures such as packing and obfuscation, we obtain binary files from dynamic memory through sandbox and then, analyze its assembly instruction set. In feature preprocessing, we divide the assembly instructions into N-tuples and construct a heterogeneous graph based on assembly instructions according to the internal correlation of the gene sequence composed of the assembly N-grams features. Finally, in terms of model construction, we analyze the homology determination effect of the traditional graph neural network and construct the Graph Attention Network based on residual connection named ResGAT to analyze the homology of malicious code. The experimental results show that the ResGAT can gather the core characteristics of malicious families and enhance the ability to recognize malicious family variants. Our model has an accuracy rate of 98.83%, which is better than traditional machine learning detection methods, and can effectively determine the homology of malicious code families. [ABSTRACT FROM AUTHOR]

The recent trend in network intrusion detection leverages key features of machine learning (ML) algorithms to detect network traffic anomalies. Network traffic flows contain high dimensional features which significantly affect data-driven approaches. Therefore, the performance of ML-based approaches mainly depends on the appropriate set of features of network data. Different feature selection and extraction methods are extensively employed to attain the informative and compact set of features. Existing methods often suffer from achieving the expected performance due to the lacking of effectively removing redundant features as well as incorporating features with complementary information. In this paper, we present a cluster-based feature extraction method using Mahalanobis distance (cFEM) that clusters the correlated features and extracts new feature representations based on a distance metric. The extracted features on the transformed dimensions are employed to train different machine learning classifiers. We conducted extensive experiments using three renowned datasets. The results show that cFEM outperforms the state-of-the-art intrusion detection methods in several performance metrics such as detection rate (99.61%) and false alarm rate (0.26%). Further experiments on extracted features show that our extracted features are discriminative, free of redundancy, and able to capture complementary information. [ABSTRACT FROM AUTHOR]

Phishing is a fraudulent tactic for attackers to obtain victims personal information, such as passwords, account details, credit card details, and other sensitive information. Existing anti-phishing detection methods using at the application layer and cannot be applied at the transport layer. A novel machine learning (ML) based phishing detection technique from transport layer security (TLS) 1.2 and TLS 1.3 encrypted traffic without decryption is proposed in this paper. Our proposed model detects phishing URLs at the transport layer and classifies them as legitimate or phishing. The features are extracted from TLS 1.2 and TLS 1.3 traffic, and phishing detection is performed using ML algorithms based on the extracted features. The datasets for legitimate and phishing sites are created using features derived from TLS 1.2 and TLS 1.3 traffic. According to the experimental results, the proposed model effectively detects phishing URLs in encrypted traffic. The proposed model achieves an accuracy of 93.63% for Random Forest (RF), 95.07% for XGBoost (XGB), and the highest accuracy of 95.40% for Light GBM (LGBM). [ABSTRACT FROM AUTHOR]

Steganalysis is a known practice to detect hidden secrecy within covered e-media. Researches claimed obscured detection attainability via features extraction, as for perceiving concealed data within images. This paper verifies practicality of the claim by testing investigation of a steganalysis system that depicts the existence of hidden data focused on statistical features of color images using artificial neural network techniques. The proposed system is built to work for blind image steganalysis representing common security as looked for the most. The work experimentations adopted common steganography techniques to create the stego images for our intended steganalysis challenging practicality evaluation. The study involved machine learning radial basis function and naïve bayes classifiers to sort the remarks improving discovery accuracy. From the investigational results, the proposed system exemplified reliability and enhancements in the recognition rate for most steganographic methods showing attractive annotations. Further, the correlation features displayed increased correctness showing reliable convalescing practicality overcoming many previous steganalysis defects. [ABSTRACT FROM AUTHOR]

Bidirectional generative adversarial networks (BiGANs) and cycle generative adversarial networks (CycleGANs) are two emerging machine learning models that, up to now, have been used as generative models, i.e., to generate output data sampled from a target probability distribution. However, these models are also equipped with encoding modules, which, after weakly supervised training, could be, in principle, exploited for the extraction of hidden features from the input data. At the present time, how these extracted features could be effectively exploited for classification tasks is still an unexplored field. Hence, motivated by this consideration, in this paper, we develop and numerically test the performance of a novel inference engine that relies on the exploitation of BiGAN and CycleGAN-learned hidden features for the detection of COVID-19 disease from other lung diseases in computer tomography (CT) scans. In this respect, the main contributions of the paper are twofold. First, we develop a kernel density estimation (KDE)-based inference method, which, in the training phase, leverages the hidden features extracted by BiGANs and CycleGANs for estimating the (a priori unknown) probability density function (PDF) of the CT scans of COVID-19 patients and, then, in the inference phase, uses it as a target COVID-PDF for the detection of COVID diseases. As a second major contribution, we numerically evaluate and compare the classification accuracies of the implemented BiGAN and CycleGAN models against the ones of some state-of-the-art methods, which rely on the unsupervised training of convolutional autoencoders (CAEs) for attaining feature extraction. The performance comparisons are carried out by considering a spectrum of different training loss functions and distance metrics. The obtained classification accuracies of the proposed CycleGAN-based (resp., BiGAN-based) models outperform the corresponding ones of the considered benchmark CAE-based models of about 16% (resp., 14%). [ABSTRACT FROM AUTHOR]

Automatic captioning of images contributes to identifying features of multimedia content and helps in the detection of interesting patterns, trends, and occurrences. English image captioning has recently made incredible progress; however, Arabic image captioning is still lagging. In the field of machine learning, Arabic image-caption generation is generally a very difficult problem. This paper presents a more accurate model for Arabic image captioning by using transformer models in both the encoder and decoder phases as feature extractors from images in the encoder phase and a pre-trained word embedding model in the decoder phase. The models are demonstrated, and all of them are implemented, trained, and tested on Arabic Flickr8k datasets. For the image feature extraction subsystem, we compared using three different individual vision models (SWIN, XCIT, and ConvNexT) with concatenation to get among them the most expressive extracted feature vector of the image, and for the caption generation lingual subsystem, which is tested by four different pre-trained language embedding models: (ARABERT, ARAELECTRA, MARBERTv2, and CamelBERT), to select from them the most accurate pre-trained language embedding model. Our experiments showed that building an Arabic image captioning system that uses a concatenation of the three transformer-based models ConvNexT combined with SWIN and XCIT as an image feature extractor, combined with the CamelBERT language embedding model produces the best results among the other combinations, having scores of 0.5980 with BLEU-1 and with ConvNexT combined with SWIN the araelectra language embedding model having a score of 0.1664 with BLEU-4 which are higher than the previously reported values of 0.443 and 0.157. [ABSTRACT FROM AUTHOR]

Sentence-level sentiment analysis (SLSA) aims to identify the overall sentiment polarity conveyed in a given sentence. The state-of-the-art performance of SLSA has been achieved by deep learning models. However, depending on the i.i.d (independent and identically distributed) assumption, the performance of these deep learning models may fall short in real scenarios, where the distributions of training and target data are almost certainly different to some extent. In this paper, we propose a supervised solution based on the non-i.i.d paradigm of gradual machine learning (GML) for SLSA. It begins with some labeled observations, and gradually labels target instances in the order of increasing hardness by iterative knowledge conveyance. It leverages labeled samples for supervised deep feature extraction, and constructs a factor graph based on the extracted features to enable gradual knowledge conveyance. Specifically, it employs a polarity classifier to detect polarity similarity between close neighbors in an embedding space, and a separate binary semantic network to extract implicit polarity relations between arbitrary instances. Our extensive experiments on benchmark datasets show that the proposed approach achieves the state-of-the-art performance on all benchmark datasets. Our work clearly demonstrates that by leveraging DNN for feature extraction, GML can easily outperform the pure DNN solutions. [ABSTRACT FROM AUTHOR]

The novel fault diagnosis method of gearbox based on Fourier Bessel series expansion-based empirical wavelet transform (FBEWT) and manifold regularization extreme learning machine (MRELM) is proposed to obtain excellent fault diagnosis results of gearbox in this paper. A new feature extraction strategy based on Fourier Bessel series expansion-based empirical wavelet transform is used to capture the key non-stationary features of the vibrational signal of gearbox, and significantly improve the diagnosis ability of gearbox. The ELM with manifold regularization is proposed for fault diagnosis of gearbox. In order to outstand the superiority and stability of the proposed FBEWT and manifold regularization ELM, the balanced dataset and unbalanced dataset, respectively, are used. The experimental results testify that FBEWT-MRELM are more superior and stable than FBEWT-ELM, EWT-MRELM, and EWT-ELM regardless of balanced dataset and unbalanced dataset. [ABSTRACT FROM AUTHOR]

Hyperspectral imaging is a highly advanced and sophisticated method for capturing images in hundreds of narrow, contiguous spectral bands. However, processing and analyzing such large amounts of data are challenging. Deep learning algorithms, especially those based on convolutional neural networks (CNNs), effectively extract rich feature representations from complex datasets, such as hyperspectral images (HSIs). These representations capture high-level patterns and characteristics that can facilitate accurate classification. The success of this approach has led to its widespread use in various remote sensing applications. However, the standard CNN inputs and outputs are scalars, ignoring the relative position relationships between features. In this paper, we propose a hierarchical capsule network for HSI classification. This network incorporates a multi-level convolutional structure for feature extraction and fusion. It utilizes convolutional feature maps of various depths to generate initial capsules, followed by vector computation using capsule neurons and a weight matrix to encode spatial location relationships among features. Furthermore, the shallow convolution of the hierarchical capsule network is pre-trained based on transfer learning to further improve the performance of HSI classification. According to experimental results, the proposed method for hyperspectral image classification has been found to outperform other state-of-the-art deep learning models on four benchmark datasets. [ABSTRACT FROM AUTHOR]

Cardiac-related disorders are rapidly growing throughout the world. Accurate classification of cardiovascular diseases is an important research topic in healthcare. During COVID-19, auscultating heart sounds was challenging as health workers and doctors wear protective clothing, and direct contact with patients can spread the outbreak. Thus, contactless auscultation of heart sound is necessary. In this paper, a low-cost ear contactless stethoscope is designed where auscultation is done with the help of a bluetooth-enabled micro speaker instead of an earpiece. The PCG recordings are further compared with other standard electronic stethoscopes like Littman 3 M. This work is made to improve the performance of deep learning-based classifiers like recurrent neural networks (RNN) and convolutional neural networks (CNN) for different valvular heart problems using tuning of hyperparameters like learning rate of optimizers, dropout rate, and hidden layer. Hyper-parameter tuning is used to optimize the performances of various deep learning models and their learning curves for real-time analysis. The acoustic, time, and frequency domain features are used in this research. The investigation is made on the heart sounds of normal and diseased patients available from the standard data repository to train the software models. The proposed CNN-based inception network model achieved an accuracy of 99.65 ± 0.06% on the test dataset with a sensitivity of 98.8 ± 0.05% and specificity of 98.2 ± 0.19%. The proposed hybrid CNN-RNN architecture attained 91.17 ± 0.03% accuracy on test data after hyperparameter optimization, whereas the LSTM-based RNN model achieved 82.32 ± 0.11% accuracy. Finally, the evaluated results were compared with machine learning algorithms, and the improved CNN-based Inception Net model is the most effective among others. [ABSTRACT FROM AUTHOR]

Wind power generation helps to save energy and reduce emissions. Accurate wind speed prediction can ensure the safe integration of wind power into the energy grid, but due to the intermittent and volatile nature of wind, it brings great difficulties to wind speed prediction. To solve this issue, this paper develops a hybrid forecasting model called WT-VMD-LSTM-TCN, where the wavelet transform (WT) is used to decompose the original wind speed into multiple detailed components and an approximate component, then the variational mode decomposition (VMD) is employed to further decompose the first detailed component, and several intrinsic mode functions and a residual term are obtained. Subsequently, the LSTM-TCN model is established on each component obtained by WT and VMD, where the component is first input into the long short-term memory (LSTM), and then the output sequence of LSTM is input into the temporal convolutional network (TCN) for processing. Ultimately, the predicted results of all components from WT-VMD are reconstructed to obtain the predicted value of wind speed. The performance of the model is verified by simulation experiments with three datasets. The experimental results show that: (a) The developed LSTM-TCN model integrates the feature extraction methods of LSTM and TCN, and the feature extraction ability is more comprehensive, which can improve the forecasting performance of a single model; (b) VMD is used to decompose the subsequence with the largest error, which reduces the difficulty of the prediction of this subsequence; (c) WT-VMD-LSTM-TCN is superior to other comparison models in three datasets, which verifies that the model has good applicability. [ABSTRACT FROM AUTHOR]

Seismic trace editing is a tedious process in data preprocessing that can incur high time costs, especially when handling large 3D datasets. In addition, existing methods to edit seismic traces may miss vital information when killing noisy traces simply. Thus, in this paper, we propose an automated method to edit seismic traces based on machine learning. The proposed method combines the Hough transform technique and a convolutional neural network (CNN) to improve the feasibility of the scheme. The Hough transform is a feature extraction technique that helps identify anomaly lines in images, and we employ it in the proposed method to ascertain the prospective positions of noisy and bad traces. We then implement a bandpass filter and the trained CNN model to identify the precise noisy traces in the target region indicated by the Hough transform process. Upon identification, automated processing is applied to determine whether the processed traces can be useful or should be discarded. This comprehensive framework includes four main steps, i.e., data preprocessing, Hough transform detection, network training, and network prediction. Experiments conducted on real-world data yielded 98% accuracy, which indicates the potential efficacy of the proposed automated trace editing method in practical applications. [ABSTRACT FROM AUTHOR]