Search

The Internet of Vehicles(IoV) employs vehicle-to-everything (V2X) technology to establish intricate interconnections among the Internet, the IoT network, and the Vehicle Networks (IVNs), forming a complex vehicle communication network. However, the vehicle communication network is very vulnerable to attacks. The implementation of an intrusion detection system (IDS) emerges as an essential requisite to ensure the security of in-vehicle/inter-vehicle communication in IoV. Within this context, the imbalanced nature of network traffic data and the diversity of network attacks stand as pivotal factors in IDS performance. On the one hand, network traffic data often heavily suffer from data imbalance, which impairs the detection performance. To address this issue, this paper employs a hybrid approach combining the Synthetic Minority Over-sampling Technique (SMOTE) and RandomUnderSampler to achieve a balanced class distribution. On the other hand, the diversity of network attacks constitutes another significant factor contributing to poor intrusion detection model performance. Most current machine learning-based IDSs mainly perform binary classification, while poorly dealing with multiclass classification. This paper proposes an adaptive tree-based ensemble network as the intrusion detection engine for the IDS in IoV. This engine employs a deep-layer structure, wherein diverse ML models are stacked as layers and are interconnected in a cascading manner, which enables accurate and efficient multiclass classification, facilitating the precise identification of diverse network attacks. Moreover, a machine learning-based approach is used for feature selection to reduce feature dimensionality, substantially alleviating the computational overhead. Finally, we evaluate the proposed IDS performance on various cyber-attacks from the in-vehicle and external networks in IoV by using the network intrusion detection dataset CICIDS2017 and the vehicle security dataset Car-Hacking. The experimental results demonstrate remarkable performance, with an F1-score of 0.965 on the CICIDS2017 dataset and an F1-score of 0.9999 on the Car-Hacking dataset. These scores demonstrate that our IDS can achieve efficient and precise multiclass classification. This research provides a valuable reference for ensuring the cybersecurity of IoV. [ABSTRACT FROM AUTHOR]

Real-time monitoring of rock stability during the mining process is critical. This paper first proposed a RIME algorithm (CCRIME) based on vertical and horizontal crossover search strategies to improve the quality of the solutions obtained by the RIME algorithm and further enhance its search capabilities. Then, by constructing a binary version of CCRIME, the key parameters of FKNN were optimized using a binary conversion method. Finally, a discrete CCRIME-based BCCRIME was developed, which uses an S-shaped function transformation approach to address the feature selection issue by converting the search result into a real number that can only be zero or one. The performance of CCRIME was examined in this study from various perspectives, utilizing 30 benchmark functions from IEEE CEC2017. Basic algorithm comparison tests and sophisticated variant algorithm comparison experiments were also carried out. In addition, this paper also used collected microseismic and blasting data for classification prediction to verify the ability of the BCCRIME-FKNN model to process real data. This paper provides new ideas and methods for real-time monitoring of rock mass stability during deep well mineral resource mining. [ABSTRACT FROM AUTHOR]

This article introduces an algorithm for detecting glucose and silicon levels in solution. The research focuses on addressing the critical need for accurate and efficient glucose monitoring, particularly in the context of diabetic management. Understanding and monitoring silicon levels in the body is crucial due to its significant role in various physiological processes. Silicon, while often overshadowed by other minerals, plays a vital role in bone health, collagen formation, and connective tissue integrity. Moreover, recent research suggests its potential involvement in neurological health and the prevention of certain degenerative diseases. Investigating silicon levels becomes essential for a comprehensive understanding of its impact on overall health and well-being and paves the way for targeted interventions and personalized healthcare strategies. The approach presented in this paper is based on the integration of hyperspectral data and artificial intelligence techniques. The algorithm investigates the effectiveness of two distinct models utilizing SVMR and a perceptron independently. SVMR is employed to establish a robust regression model that maps input features to continuous glucose and silicon values. The study outlines the methodology, including feature selection, model training, and evaluation metrics. Experimental results demonstrate the algorithm's effectiveness at accurately predicting glucose and silicon concentrations and showcases its potential for real-world application in continuous glucose and silicon monitoring systems. [ABSTRACT FROM AUTHOR]

This paper explores the energy-intensive cement industry, focusing on a plant in Greece and its mill and kiln unit. The data utilized include manipulated, non-manipulated, and uncontrolled variables. The non-manipulated variables are computed based on the machine learning (ML) models and selected by the minimum value of the normalized root mean square error (NRMSE) across nine (9) methods. In case the distribution of the data displayed in the user interface changes, the user should trigger the retrain of the AI models to ensure their accuracy and robustness. To form the objective function, the expert user should define the desired weight for each manipulated or non-manipulated variable through the user interface (UI), along with its corresponding constraints or target value. The user selects the variables involved in the objective function based on the optimization strategy, and the evaluation is based on the comparison of the optimized and the active value of the objective function. The differential evolution (DE) method optimizes the objective function that is formed by the linear combination of the selected variables. The results indicate that using DE improves the operation of both the cement mill and kiln, yielding a lower objective function value compared to the current values. [ABSTRACT FROM AUTHOR]

Federated learning (FL) is a privacy-preserving collective machine learning paradigm. Vertical federated learning (VFL) deals with the case where participants share the same sample ID space but have different feature spaces, while label information is owned by one participant. Early studies of VFL supported two participants and focused on binary-class logistic regression problems, while recent studies have put more attention on specific aspects such as communication efficiency and data security. In this paper, we propose the multi-participant multi-class vertical federated learning (MMVFL) framework for multi-class VFL problems involving multiple parties. By extending the idea of multi-view learning (MVL), MMVFL enables label sharing from its owner to other VFL participants in a privacy-preserving manner. To demonstrate the effectiveness of MMVFL, a feature selection scheme is incorporated into MMVFL to compare its performance against supervised feature selection and MVL-based approaches. The proposed framework is capable of quantifying feature importance and measuring participant contributions. It is also simple and easy to combine with other communication and security techniques. The experiment results on feature selection for classification tasks on real-world datasets show that MMVFL can effectively share label information among multiple VFL participants and match the multi-class classification performance of existing approaches. [ABSTRACT FROM AUTHOR]

With the massive, worldwide, smart metering roll-out, both energy suppliers and users are starting to tap into the potential of higher resolution energy readings for accurate billing, improved demand response, improved tariffs better tuned to users and the grid, and empowering end-users to know how much their individual appliances contribute to their electricity bills via nonintrusive load monitoring (NILM). A number of NILM approaches, based on machine learning (ML), have been proposed over the years, focusing on improving the NILM model performance. However, the trustworthiness of the NILM model itself has hardly been addressed. It is important to explain the underlying model and its reasoning to understand why the model underperforms in order to satisfy user curiosity and to enable model improvement. This can be done by leveraging naturally interpretable or explainable models as well as explainability tools. This paper adopts a naturally interpretable decision tree (DT)-based approach for a NILM multiclass classifier. Furthermore, this paper leverages explainability tools to determine local and global feature importance, and design a methodology that informs feature selection for each appliance class, which can determine how well a trained model will predict an appliance on any unseen test data, minimising testing time on target datasets. We explain how one or more appliances can negatively impact classification of other appliances and predict appliance and model performance of the REFIT-data trained models on unseen data of the same house and on unseen houses on the UK-DALE dataset. Experimental results confirm that models trained with the explainability-informed local feature importance can improve toaster classification performance from 65% to 80%. Additionally, instead of one five-classifier approach incorporating all five appliances, a three-classifier approach comprising a kettle, microwave, and dishwasher and a two-classifier comprising a toaster and washing machine improves classification performance for the dishwasher from 72% to 94% and the washing machine from 56% to 80%. [ABSTRACT FROM AUTHOR]

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

In the food industry, quality and safety issues are associated with consumers' health condition. There is a growing interest in applying various noninvasive sensorial techniques to obtain quickly quality attributes. One of them, hyperspectral/multispectral imaging technique has been extensively used for inspection of various food products. In this paper, a stacking-based ensemble prediction system has been developed for the prediction of total viable counts of microorganisms in beef fillet samples, an essential cause to meat spoilage, utilizing multispectral imaging information. As the selection of important wavelengths from the multispectral imaging system is considered as an essential stage to the prediction scheme, a features fusion approach has been also explored, by combining wavelengths extracted from various feature selection techniques. Ensemble sub-components include two advanced clustering-based neuro-fuzzy network prediction models, one utilizing information from average reflectance values, while the other one from the standard deviation of the pixels' intensity per wavelength. The performances of neurofuzzy models were compared against established regression algorithms such as multilayer perceptron, support vector machines and partial least squares. Obtained results confirmed the validity of the proposed hypothesis to utilize a combination of feature selection methods with neurofuzzy models in order to assess the microbiological quality of meat products. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) and network-enabled smart devices are crucial to the digitally interconnected society of the present day. However, the increased reliance on IoT devices increases their susceptibility to malicious activities within network traffic, posing significant challenges to cybersecurity. As a result, both system administrators and end users are negatively affected by these malevolent behaviours. Intrusion-detection systems (IDSs) are commonly deployed as a cyber attack defence mechanism to mitigate such risks. IDS plays a crucial role in identifying and preventing cyber hazards within IoT networks. However, the development of an efficient and rapid IDS system for the detection of cyber attacks remains a challenging area of research. Moreover, IDS datasets contain multiple features, so the implementation of feature selection (FS) is required to design an effective and timely IDS. The FS procedure seeks to eliminate irrelevant and redundant features from large IDS datasets, thereby improving the intrusion-detection system's overall performance. In this paper, we propose a hybrid wrapper-based feature-selection algorithm that is based on the concepts of the Cellular Automata (CA) engine and Tabu Search (TS)-based aspiration criteria. We used a Random Forest (RF) ensemble learning classifier to evaluate the fitness of the selected features. The proposed algorithm, CAT-S, was tested on the TON_IoT dataset. The simulation results demonstrate that the proposed algorithm, CAT-S, enhances classification accuracy while simultaneously reducing the number of features and the false positive rate. [ABSTRACT FROM AUTHOR]

Due to increasing demands for ensuring the safety and reliability of a system, fault detection (FD) has received considerable attention in modern industries to monitor their machines. Bulk materials are transported worldwide using belt conveyors as an essential transport system. The majority of conveyor components are monitored continuously to ensure their reliability, but idlers remain a challenge to monitor due to the large number of idlers (rollers) distributed throughout the working environment. These idlers are prone to external noises or disturbances that cause a failure in the underlying system operations. The research community has begun using machine learning (ML) to detect idler's defects to assist industries in responding to failures on time. Vibration and acoustic measurements are commonly employed to monitor the condition of idlers. However, there has been no comprehensive review of FD for belt conveyor idlers. This paper presents a recent review of acoustic and vibration signal-based fault detection for belt conveyor idlers using ML models. It also discusses major steps in the approaches, such as data collection, signal processing, feature extraction and selection, and ML model construction. Additionally, the paper provides an overview of the main components of belt conveyor systems, sources of defects in idlers, and a brief introduction to ML models. Finally, it highlights critical open challenges and provides future research directions. [ABSTRACT FROM AUTHOR]

Internet of Things (IoT) enables day-to-day objects to connect with the Internet and transmit and receive data for meaningful purposes. Recently, IoT has resulted in many revolutions in all sectors. Nonetheless, security risks to IoT networks and devices are persistently disruptive due to the growth of Internet technology. Phishing becomes a common threat to Internet users, where the attacker aims to fraudulently extract confidential data of the system or user by using websites, fictitious emails, etc. Due to the dramatic growth in IoT devices, hackers target IoT gadgets, including smart cars, security cameras, and so on, and perpetrate phishing attacks to gain control over the vulnerable device for malicious purposes. These scams have been increasing and advancing over the last few years. To resolve these problems, this paper presents a binary Hunter–prey optimization with a machine learning-based phishing attack detection (BHPO-MLPAD) method in the IoT environment. The BHPO-MLPAD technique can find phishing attacks through feature selection and classification. In the presented BHPO-MLPAD technique, the BHPO algorithm primarily chooses an optimal subset of features. The cascaded forward neural network (CFNN) model is employed for phishing attack detection. To adjust the parameter values of the CFNN model, the variable step fruit fly optimization (VFFO) algorithm is utilized. The performance assessment of the BHPO-MLPAD method takes place on the benchmark dataset. The results inferred the betterment of the BHPO-MLPAD technique over compared approaches in different evaluation measures. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) has brought significant advancements that have connected our world more closely than ever before. However, the growing number of connected devices has also increased the vulnerability of IoT networks to several types of attacks. In this paper, we present an approach for detecting attacks on IoT networks using a combination of two convolutional neural networks (CNN-CNN). The first CNN model is leveraged to select the significant features that contribute to IoT attack detection from the raw data on network traffic. The second CNN utilizes the features identified by the first CNN to build a robust detection model that accurately detects IoT attacks. The proposed approach is evaluated using the BoT IoT 2020 dataset. The results reveal that the proposed approach achieves 98.04% detection accuracy, 98.09% precision, 99.85% recall, 98.96% recall, and a 1.93% false positive rate (FPR). Furthermore, the proposed approach is compared with other deep learning algorithms and feature selection methods; the results show that it outperforms these algorithms. [ABSTRACT FROM AUTHOR]

Distributed denial-of-service (DDoS) attacks pose a significant cybersecurity threat to software-defined networks (SDNs). This paper proposes a feature-engineering- and machine-learning-based approach to detect DDoS attacks in SDNs. First, the CSE-CIC-IDS2018 dataset was cleaned and normalized, and the optimal feature subset was found using an improved binary grey wolf optimization algorithm. Next, the optimal feature subset was trained and tested in Random Forest (RF), Support Vector Machine (SVM), K-Nearest Neighbor (k-NN), Decision Tree, and XGBoost machine learning algorithms, from which the best classifier was selected for DDoS attack detection and deployed in the SDN controller. The results show that RF performs best when compared across several performance metrics (e.g., accuracy, precision, recall, F1 and AUC values). We also explore the comparison between different models and algorithms. The results show that our proposed method performed the best and can effectively detect and identify DDoS attacks in SDNs, providing a new idea and solution for the security of SDNs. [ABSTRACT FROM AUTHOR]

Motion blur recovery is a common method in the field of remote sensing image processing that can effectively improve the accuracy of detection and recognition. Among the existing motion blur recovery methods, the algorithms based on deep learning do not rely on a priori knowledge and, thus, have better generalizability. However, the existing deep learning algorithms usually suffer from feature misalignment, resulting in a high probability of missing details or errors in the recovered images. This paper proposes an end-to-end generative adversarial network (SDD-GAN) for single-image motion deblurring to address this problem and to optimize the recovery of blurred remote sensing images. Firstly, this paper applies a feature alignment module (FAFM) in the generator to learn the offset between feature maps to adjust the position of each sample in the convolution kernel and to align the feature maps according to the context; secondly, a feature importance selection module is introduced in the generator to adaptively filter the feature maps in the spatial and channel domains, preserving reliable details in the feature maps and improving the performance of the algorithm. In addition, this paper constructs a self-constructed remote sensing dataset (RSDATA) based on the mechanism of image blurring caused by the high-speed orbital motion of satellites. Comparative experiments are conducted on self-built remote sensing datasets and public datasets as well as on real remote sensing blurred images taken by an in-orbit satellite (CX-6(02)). The results show that the algorithm in this paper outperforms the comparison algorithm in terms of both quantitative evaluation and visual effects. [ABSTRACT FROM AUTHOR]

For permanent magnet DC motors (PMDCMs), the amplitude of the current signals gradually decreases after the motor starts. In this work, the time domain features and time-frequency-domain features extracted from several successive segments of current signals make up a feature vector, which is adopted for fault diagnosis of PMDCMs. Many redundant features will lead to a decrease in diagnosis efficiency and increase the computation cost, so it is necessary to eliminate redundant features and features that have negative effects. This paper presents a novel supervised filter feature selection method for reducing data dimension by employing the Gaussian probability density function (GPDF) and named Gaussian vote feature selection (GVFS). To evaluate the effectiveness of the proposed GVFS, we compared it with the other five filter feature selection methods by utilizing the PMDCM's data. Additionally, Gaussian naive Bayes (GNB), k -nearest neighbor algorithm (k -NN), and support vector machine (SVM) are utilized for the construction of fault diagnosis models. Experimental results show that the proposed GVFS has a better diagnostic effect than the other five feature selection methods, and the average accuracy of fault diagnosis improves from 97.89% to 99.44%. This paper lays the foundation of fault diagnosis for PMDCMs and provides a novel filter feature selection method. [ABSTRACT FROM AUTHOR]

The past few years have witnessed a substantial increase in cyberattacks on Internet of Things (IoT) devices and their networks. Such attacks pose a significant threat to organizational security and user privacy. Utilizing Machine Learning (ML) in Intrusion Detection Systems (NIDS) has proven advantageous in countering novel zero-day attacks. However, the performance of such systems relies on several factors, one of which is prediction time. Processing speed in anomaly-based NIDS depends on a few elements, including the number of features fed to the ML model. NetFlow, a networking industry-standard protocol, offers many features that can be used to predict malicious attacks accurately. This paper examines NetFlow features and assesses their suitability in classifying network traffic. Our paper presents a model that detects attacks with (98–100%) accuracy using as few as 13 features. This study was conducted using a large dataset of over 16 million records released in 2021. [ABSTRACT FROM AUTHOR]

In healthcare, the Internet of Things (IoT) is used to remotely monitor patients and provide real-time diagnoses, which is referred to as the Internet of Medical Things (IoMT). This integration poses a risk from cybersecurity threats that can harm patient data and well-being. Hackers can manipulate biometric data from biosensors or disrupt the IoMT system, which is a major concern. To address this issue, intrusion detection systems (IDS) have been proposed, particularly using deep learning algorithms. However, developing IDS for IoMT is challenging due to high data dimensionality leading to model overfitting and degraded detection accuracy. Feature selection has been proposed to prevent overfitting, but the existing methods assume that feature redundancy increases linearly with the size of the selected features. Such an assumption does not hold, as the amount of information a feature carries about the attack pattern varies from feature to feature, especially when dealing with early patterns, due to data sparsity that makes it difficult to perceive the common characteristics of selected features. This negatively affects the ability of the mutual information feature selection (MIFS) goal function to estimate the redundancy coefficient accurately. To overcome this issue, this paper proposes an enhanced feature selection technique called Logistic Redundancy Coefficient Gradual Upweighting MIFS (LRGU-MIFS) that evaluates candidate features individually instead of comparing them with common characteristics of the already-selected features. Unlike the existing feature selection techniques, LRGU calculates the redundancy score of a feature using the logistic function. It increases the redundancy value based on the logistic curve, which reflects the nonlinearity of the relationship of the mutual information between features in the selected set. Then, the LRGU was incorporated into the goal function of MIFS as a redundancy coefficient. The experimental evaluation shows that the proposed LRGU was able to identify a compact set of significant features that outperformed those selected by the existing techniques. The proposed technique overcomes the challenge of perceiving common characteristics in cases of insufficient attack patterns and outperforms existing techniques in identifying significant features. [ABSTRACT FROM AUTHOR]

Intrusion detection systems (IDS) play a crucial role in securing networks and identifying malicious activity. This is a critical problem in cyber security. In recent years, metaheuristic optimization algorithms and deep learning techniques have been applied to IDS to improve their accuracy and efficiency. Generally, optimization algorithms can be used to boost the performance of IDS models. Deep learning methods, such as convolutional neural networks, have also been used to improve the ability of IDS to detect and classify intrusions. In this paper, we propose a new IDS model based on the combination of deep learning and optimization methods. First, a feature extraction method based on CNNs is developed. Then, a new feature selection method is used based on a modified version of Growth Optimizer (GO), called MGO. We use the Whale Optimization Algorithm (WOA) to boost the search process of the GO. Extensive evaluation and comparisons have been conducted to assess the quality of the suggested method using public datasets of cloud and Internet of Things (IoT) environments. The applied techniques have shown promising results in identifying previously unknown attacks with high accuracy rates. The MGO performed better than several previous methods in all experimental comparisons. [ABSTRACT FROM AUTHOR]

Tool wear is an important concern in the manufacturing sector that leads to quality loss, lower productivity, and increased downtime. In recent years, there has been a rise in the popularity of implementing TCM systems using various signal processing methods and machine learning algorithms. In the present paper, the authors propose a TCM system that incorporates the Walsh–Hadamard transform for signal processing, DCGAN aims to circumvent the issue of the availability of limited experimental dataset, and the exploration of three machine learning models: support vector regression, gradient boosting regression, and recurrent neural network for tool wear prediction. The mean absolute error, mean square error and root mean square error are used to assess the prediction errors from three machine learning models. To identify these relevant features, three metaheuristic optimization feature selection algorithms, Dragonfly, Harris hawk, and Genetic algorithms, were explored, and prediction results were compared. The results show that the feature selected through Dragonfly algorithms exhibited the least MSE (0.03), RMSE (0.17), and MAE (0.14) with a recurrent neural network model. By identifying the tool wear patterns and predicting when maintenance is required, the proposed methodology could help manufacturing companies save money on repairs and replacements, as well as reduce overall production costs by minimizing downtime. [ABSTRACT FROM AUTHOR]

Speaker Recognition (SR) is a common task in AI-based sound analysis, involving structurally different methodologies such as Deep Learning or "traditional" Machine Learning (ML). In this paper, we compared and explored the two methodologies on the DEMoS dataset consisting of 8869 audio files of 58 speakers in different emotional states. A custom CNN is compared to several pre-trained nets using image inputs of spectrograms and Cepstral-temporal (MFCC) graphs. AML approach based on acoustic feature extraction, selection and multi-class classification by means of a Naïve Bayes model is also considered. Results show how a custom, less deep CNN trained on grayscale spectrogram images obtain the most accurate results, 90.15% on grayscale spectrograms and 83.17% on colored MFCC. AlexNet provides comparable results, reaching 89.28% on spectrograms and 83.43% on MFCC.The Naïve Bayes classifier provides a 87.09% accuracy and a 0.985 average AUC while being faster to train and more interpretable. Feature selection shows how F0, MFCC and voicing-related features are the most characterizing for this SR task. The high amount of training samples and the emotional content of the DEMoS dataset better reflect a real case scenario for speaker recognition, and account for the generalization power of the models. [ABSTRACT FROM AUTHOR]

As Android is a popular a mobile operating system, Android malware is on the rise, which poses a great threat to user privacy and security. Considering the poor detection effects of the single feature selection algorithm and the low detection efficiency of traditional machine learning methods, we propose an Android malware detection framework based on stacking ensemble learning—MFDroid—to identify Android malware. In this paper, we used seven feature selection algorithms to select permissions, API calls, and opcodes, and then merged the results of each feature selection algorithm to obtain a new feature set. Subsequently, we used this to train the base learner, and set the logical regression as a meta-classifier, to learn the implicit information from the output of base learners and obtain the classification results. After the evaluation, the F1-score of MFDroid reached 96.0%. Finally, we analyzed each type of feature to identify the differences between malicious and benign applications. At the end of this paper, we present some general conclusions. In recent years, malicious applications and benign applications have been similar in terms of permission requests. In other words, the model of training, only with permission, can no longer effectively or efficiently distinguish malicious applications from benign applications. [ABSTRACT FROM AUTHOR]

Distributed Denial of Service (DDoS) attacks, advanced persistent threats, and malware actively compromise the availability and security of Internet services. Thus, this paper proposes an intelligent agent system for detecting DDoS attacks using automatic feature extraction and selection. We used dataset CICDDoS2019, a custom-generated dataset, in our experiment, and the system achieved a 99.7% improvement over state-of-the-art machine learning-based DDoS attack detection techniques. We also designed an agent-based mechanism that combines machine learning techniques and sequential feature selection in this system. The system learning phase selected the best features and reconstructed the DDoS detector agent when the system dynamically detected DDoS attack traffic. By utilizing the most recent CICDDoS2019 custom-generated dataset and automatic feature extraction and selection, our proposed method meets the current, most advanced detection accuracy while delivering faster processing than the current standard. [ABSTRACT FROM AUTHOR]

Terminal neurological conditions can affect millions of people worldwide and hinder them from doing their daily tasks and movements normally. Brain computer interface (BCI) is the best hope for many individuals with motor deficiencies. It will help many patients interact with the outside world and handle their daily tasks without assistance. Therefore, machine learning-based BCI systems have emerged as non-invasive techniques for reading out signals from the brain and interpreting them into commands to help those people to perform diverse limb motor tasks. This paper proposes an innovative and improved machine learning-based BCI system that analyzes EEG signals obtained from motor imagery to distinguish among various limb motor tasks based on BCI competition III dataset IVa. The proposed framework pipeline for EEG signal processing performs the following major steps. The first step uses a meta-heuristic optimization technique, called the whale optimization algorithm (WOA), to select the optimal features for discriminating between neural activity patterns. The pipeline then uses machine learning models such as LDA, k-NN, DT, RF, and LR to analyze the chosen features to enhance the precision of EEG signal analysis. The proposed BCI system, which merges the WOA as a feature selection method and the optimized k-NN classification model, demonstrated an overall accuracy of 98.6%, outperforming other machine learning models and previous techniques on the BCI competition III dataset IVa. Additionally, the EEG feature contribution in the ML classification model is reported using Explainable AI (XAI) tools, which provide insights into the individual contributions of the features in the predictions made by the model. By incorporating XAI techniques, the results of this study offer greater transparency and understanding of the relationship between the EEG features and the model's predictions. The proposed method shows potential levels for better use in controlling diverse limb motor tasks to help people with limb impairments and support them while enhancing their quality of life. [ABSTRACT FROM AUTHOR]

The performance of human gait recognition (HGR) is affected by the partial obstruction of the human body caused by the limited field of view in video surveillance. The traditional method required the bounding box to recognize human gait in the video sequences accurately; however, it is a challenging and time-consuming approach. Due to important applications, such as biometrics and video surveillance, HGR has improved performance over the last half-decade. Based on the literature, the challenging covariant factors that degrade gait recognition performance include walking while wearing a coat or carrying a bag. This paper proposed a new two-stream deep learning framework for human gait recognition. The first step proposed a contrast enhancement technique based on the local and global filters information fusion. The high-boost operation is finally applied to highlight the human region in a video frame. Data augmentation is performed in the second step to increase the dimension of the preprocessed dataset (CASIA-B). In the third step, two pre-trained deep learning models—MobilenetV2 and ShuffleNet—are fine-tuned and trained on the augmented dataset using deep transfer learning. Features are extracted from the global average pooling layer instead of the fully connected layer. In the fourth step, extracted features of both streams are fused using a serial-based approach and further refined in the fifth step by using an improved equilibrium state optimization-controlled Newton–Raphson (ESOcNR) selection method. The selected features are finally classified using machine learning algorithms for the final classification accuracy. The experimental process was conducted on 8 angles of the CASIA-B dataset and obtained an accuracy of 97.3, 98.6, 97.7, 96.5, 92.9, 93.7, 94.7, and 91.2%, respectively. Comparisons were conducted with state-of-the-art (SOTA) techniques, and showed improved accuracy and reduced computational time. [ABSTRACT FROM AUTHOR]

The recognition of hand signs is essential for several applications. Due to the variation of possible signals and the complexity of sensor-based systems for hand gesture recognition, a new artificial neural network algorithm providing high accuracy with a reduced architecture and automatic feature selection is needed. In this paper, a novel classification method based on an extreme learning machine (ELM), supported by an improved grasshopper optimization algorithm (GOA) as a core for a weight-pruning process, is proposed. The k-tournament grasshopper optimization algorithm was implemented to select and prune the ELM weights resulting in the proposed k-tournament grasshopper extreme learner (KTGEL) classifier. Myographic methods, such as force myography (FMG), deliver interesting signals that can build the basis for hand sign recognition. FMG was investigated to limit the number of sensors at suitable positions and provide adequate signal processing algorithms for perspective implementation in wearable embedded systems. Based on the proposed KTGEL, the number of sensors and the effect of the number of subjects was investigated in the first stage. It was shown that by increasing the number of subjects participating in the data collection, eight was the minimal number of sensors needed to result in acceptable sign recognition performance. Moreover, implemented with 3000 hidden nodes, after the feature selection wrapper, the ELM had both a microaverage precision and a microaverage sensitivity of 97% for the recognition of a set of gestures, including a middle ambiguity level. The KTGEL reduced the hidden nodes to only 1000, reaching the same total sensitivity with a reduced total precision of only 1% without needing an additional feature selection method. [ABSTRACT FROM AUTHOR]

Intrusion detection systems (IDS) are crucial for network security because they enable detection of and response to malicious traffic. However, as next-generation communications networks become increasingly diversified and interconnected, intrusion detection systems are confronted with dimensionality difficulties. Prior works have shown that high-dimensional datasets that simulate real-world network data increase the complexity and processing time of IDS system training and testing, while irrelevant features waste resources and reduce the detection rate. In this paper, a new intrusion detection model is presented which uses a genetic algorithm (GA) for feature selection and optimization algorithms for gradient descent. First, the GA-based method is used to select a set of highly correlated features from the NSL-KDD dataset that can significantly improve the detection ability of the proposed model. A Back-Propagation Neural Network (BPNN) is then trained using the HPSOGWO method, a hybrid combination of the Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO) algorithms. Finally, the hybrid HPSOGWO-BPNN algorithm is used to solve binary and multi-class classification problems on the NSL-KDD dataset. The experimental outcomes demonstrate that the proposed model achieves better performance than other techniques in terms of accuracy, with a lower error rate and better ability to detect different types of attacks. [ABSTRACT FROM AUTHOR]

The monitoring of emotional state is important in the prevention and management of mental health problems and is increasingly being used to support affective computing. As such, researchers are exploring various modalities from which emotion can be inferred, such as through facial images or via electroencephalography (EEG) signals. Current research commonly investigates the performance of machine-learning-based emotion recognition systems by exposing users to stimuli that are assumed to elicit a single unchanging emotional response. Moreover, in order to demonstrate better results, many models are tested in evaluation frameworks that do not reflect realistic real-world implementations. Consequently, in this paper, we explore the design of EEG-based emotion recognition systems using longer, variable stimuli using the publicly available AMIGOS dataset. Feature engineering and selection results are evaluated across four different cross-validation frameworks, including versions of leave-one-movie-out (testing with a known user, but a previously unseen movie), leave-one-person-out (testing with a known movie, but a previously unseen person), and leave-one-person-and-movie-out (testing on both a new user and new movie). Results of feature selection lead to a 13% absolute improvement over comparable previously reported studies, and demonstrate the importance of evaluation framework on the design and performance of EEG-based emotion recognition systems. [ABSTRACT FROM AUTHOR]

Gait-based gender classification is a challenging task since people may walk in different directions with varying speed, gait style, and occluded joints. The majority of research studies in the literature focused on gender-specific joints, while there is less attention on the comparison of all of a body's joints. To consider all of the joints, it is essential to determine a person's gender based on their gait using a Kinect sensor. This paper proposes a logistic-regression-based machine learning model using whole body joints for gender classification. The proposed method consists of different phases including gait feature extraction based on three dimensional (3D) positions, feature selection, and classification of human gender. The Kinect sensor is used to extract 3D features of different joints. Different statistical tools such as Cronbach's alpha, correlation, t-test, and ANOVA techniques are exploited to select significant joints. The Coronbach's alpha technique yields an average result of 99.74%, which indicates the reliability of joints. Similarly, the correlation results indicate that there is significant difference between male and female joints during gait. t-test and ANOVA approaches demonstrate that all twenty joints are statistically significant for gender classification, because the p-value for each joint is zero and less than 1%. Finally, classification is performed based on the selected features using binary logistic regression model. A total of hundred (100) volunteers participated in the experiments in real scenario. The suggested method successfully classifies gender based on 3D features recorded in real-time using machine learning classifier with an accuracy of 98.0% using all body joints. The proposed method outperformed the existing systems which mostly rely on digital images. [ABSTRACT FROM AUTHOR]

Soil moisture, soil organic carbon, and nitrogen content prediction are considered significant fields of study as they are directly related to plant health and food production. Direct estimation of these soil properties with traditional methods, for example, the oven-drying technique and chemical analysis, is a time and resource-consuming approach and can predict only smaller areas. With the significant development of remote sensing and hyperspectral (HS) imaging technologies, soil moisture, carbon, and nitrogen can be estimated over vast areas. This paper presents a generalized approach to predicting three different essential soil contents using a comprehensive study of various machine learning (ML) models by considering the dimensional reduction in feature spaces. In this study, we have used three popular benchmark HS datasets captured in Germany and Sweden. The efficacy of different ML algorithms is evaluated to predict soil content, and significant improvement is obtained when a specific range of bands is selected. The performance of ML models is further improved by applying principal component analysis (PCA), a dimensional reduction method that works with an unsupervised learning method. The effect of soil temperature on soil moisture prediction is evaluated in this study, and the results show that when the soil temperature is considered with the HS band, the soil moisture prediction accuracy does not improve. However, the combined effect of band selection and feature transformation using PCA significantly enhances the prediction accuracy for soil moisture, carbon, and nitrogen content. This study represents a comprehensive analysis of a wide range of established ML regression models using data preprocessing, effective band selection, and data dimension reduction and attempt to understand which feature combinations provide the best accuracy. The outcomes of several ML models are verified with validation techniques and the best- and worst-case scenarios in terms of soil content are noted. The proposed approach outperforms existing estimation techniques. [ABSTRACT FROM AUTHOR]

The proliferation of the internet of things (IoT) technology has led to numerous challenges in various life domains, such as healthcare, smart systems, and mission-critical applications. The most critical issue is the security of IoT nodes, networks, and infrastructures. IoT uses the routing protocol for low-power and lossy networks (RPL) for data communication among the devices. RPL comprises a lightweight core and thus does not support high computation and resource-consuming methods for security implementation. Therefore, both IoT and RPL are vulnerable to security attacks, which are broadly categorized into RPL-specific and sensor-network-inherited attacks. Among the most concerning protocol-specific attacks are rank attacks and wormhole attacks in sensor-network-inherited attack types. They target the RPL resources and components including control messages, repair mechanisms, routing topologies, and sensor network resources by consuming. This leads to the collapse of IoT infrastructure. In this paper, a lightweight multiclass classification-based RPL-specific and sensor-network-inherited attack detection model called MC-MLGBM is proposed. A novel dataset was generated through the construction of various network models to address the unavailability of the required dataset, optimal feature selection to improve model performance, and a light gradient boosting machine-based algorithm optimized for a multiclass classification-based attack detection. The results of extensive experiments are demonstrated through several metrics including confusion matrix, accuracy, precision, and recall. For further performance evaluation and to remove any bias, the multiclass-specific metrics were also used to evaluate the model, including cross-entropy, Cohn's kappa, and Matthews correlation coefficient, and then compared with benchmark research. [ABSTRACT FROM AUTHOR]

Machine learning (ML) has been widely used worldwide to develop crop yield forecasting models. However, it is still challenging to identify the most critical features from a dataset. Although either feature selection (FS) or feature extraction (FX) techniques have been employed, no research compares their performances and, more importantly, the benefits of combining both methods. Therefore, this paper proposes a framework that uses non-feature reduction (All-F) as a baseline to investigate the performance of FS, FX, and a combination of both (FSX). The case study employs the vegetation condition index (VCI)/temperature condition index (TCI) to develop 21 rice yield forecasting models for eight sub-regions in Vietnam based on ML methods, namely linear, support vector machine (SVM), decision tree (Tree), artificial neural network (ANN), and Ensemble. The results reveal that FSX takes full advantage of the FS and FX, leading FSX-based models to perform the best in 18 out of 21 models, while 2 (1) for FS-based (FX-based) models. These FXS-, FS-, and FX-based models improve All-F-based models at an average level of 21% and up to 60% in terms of RMSE. Furthermore, 21 of the best models are developed based on Ensemble (13 models), Tree (6 models), linear (1 model), and ANN (1 model). These findings highlight the significant role of FS, FX, and specially FSX coupled with a wide range of ML algorithms (especially Ensemble) for enhancing the accuracy of predicting crop yield. [ABSTRACT FROM AUTHOR]

An electrocardiogram (ECG) is an essential piece of medical equipment that helps diagnose various heart-related conditions in patients. An automated diagnostic tool is required to detect significant episodes in long-term ECG records. It is a very challenging task for cardiologists to analyze long-term ECG records in a short time. Therefore, a computer-based diagnosis tool is required to identify crucial episodes. Myocardial infarction (MI) and conduction disorders (CDs), sometimes known as heart blocks, are medical diseases that occur when a coronary artery becomes fully or suddenly stopped or when blood flow in these arteries slows dramatically. As a result, several researchers have utilized deep learning methods for MI and CD detection. However, there are one or more of the following challenges when using deep learning algorithms: (i) struggles with real-life data, (ii) the time after the training phase also requires high processing power, (iii) they are very computationally expensive, requiring large amounts of memory and computational resources, and it is not easy to transfer them to other problems, (iv) they are hard to describe and are not completely understood (black box), and (v) most of the literature is based on the MIT-BIH or PTB databases, which do not cover most of the crucial arrhythmias. This paper proposes a new deep learning approach based on machine learning for detecting MI and CDs using large PTB-XL ECG data. First, all challenging issues of these heart signals have been considered, as the signal data are from different datasets and the data are filtered. After that, the MI and CD signals are fed to the deep learning model to extract the deep features. In addition, a new custom activation function is proposed, which has fast convergence to the regular activation functions. Later, these features are fed to an external classifier, such as a support vector machine (SVM), for detection. The efficiency of the proposed method is demonstrated by the experimental findings, which show that it improves satisfactorily with an overall accuracy of 99.20% when using a CNN for extracting the features with an SVM classifier. [ABSTRACT FROM AUTHOR]

Cardiac arrhythmias pose a significant danger to human life; therefore, it is of utmost importance to be able to efficiently diagnose these arrhythmias promptly. There exist many techniques for the detection of arrhythmias; however, the most widely adopted method is the use of an Electrocardiogram (ECG). The manual analysis of ECGs by medical experts is often inefficient. Therefore, the detection and recognition of ECG characteristics via machine-learning techniques have become prevalent. There are two major drawbacks of existing machine-learning approaches: (a) they require extensive training time; and (b) they require manual feature selection. To address these issues, this paper presents a novel deep-learning framework that integrates various networks by stacking similar layers in each network to produce a single robust model. The proposed framework has been tested on two publicly available datasets for the recognition of five micro-classes of arrhythmias. The overall classification sensitivity, specificity, positive predictive value, and accuracy of the proposed approach are 98.37%, 99.59%, 98.41%, and 99.35%, respectively. The results are compared with state-of-the-art approaches. The proposed approach outperformed the existing approaches in terms of sensitivity, specificity, positive predictive value, accuracy and computational cost. [ABSTRACT FROM AUTHOR]

Laser beam welding offers high productivity and relatively low heat input and is one key enabler for efficient manufacturing of sandwich constructions. However, the process is sensitive to how the laser beam is positioned with regards to the joint, and even a small deviation of the laser beam from the correct joint position (beam offset) can cause severe defects in the produced part. With tee joints, the joint is not visible from top side, therefore traditional seam tracking methods are not applicable since they rely on visual information of the joint. Hence, there is a need for a monitoring system that can give early detection of beam offsets and stop the process to avoid defects and reduce scrap. In this paper, a monitoring system using a spectrometer is suggested and the aim is to find correlations between the spectral emissions from the process and beam offsets. The spectrometer produces high dimensional data and it is not obvious how this is related to the beam offsets. A machine learning approach is therefore suggested to find these correlations. A multi-layer perceptron neural network (MLPNN), support vector machine (SVM), learning vector quantization (LVQ), logistic regression (LR), decision tree (DT) and random forest (RF) were evaluated as classifiers. Feature selection by using random forest and non-dominated sorting genetic algorithm II (NSGAII) was applied before feeding the data to the classifiers and the obtained results of the classifiers are compared subsequently. After testing different offsets, an accuracy of 94% was achieved for real-time detection of the laser beam deviations greater than 0.9 mm from the joint center-line. [ABSTRACT FROM AUTHOR]

In recent years, due to the advancements in machine learning, object detection has become a mainstream task in the computer vision domain. The first phase of object detection is to find the regions where objects can exist. With the improvements in deep learning, traditional approaches, such as sliding windows and manual feature selection techniques, have been replaced with deep learning techniques. However, object detection algorithms face a problem when performed in low light, challenging weather, and crowded scenes, similar to any other task. Such an environment is termed a challenging environment. This paper exploits pixel-level information to improve detection under challenging situations. To this end, we exploit the recently proposed hybrid task cascade network. This network works collaboratively with detection and segmentation heads at different cascade levels. We evaluate the proposed methods on three complex datasets of ExDark, CURE-TSD, and RESIDE, and achieve a mAP of 0.71, 0.52, and 0.43, respectively. Our experimental results assert the efficacy of the proposed approach. [ABSTRACT FROM AUTHOR]

Like smart phones, the recent years have seen an increased usage of internet of things (IoT) technology. IoT devices, being resource constrained due to smaller size, are vulnerable to various security threats. Recently, many distributed denial of service (DDoS) attacks generated with the help of IoT botnets affected the services of many websites. The destructive botnets need to be detected at the early stage of infection. Machine-learning models can be utilized for early detection of botnets. This paper proposes one-class classifier-based machine-learning solution for the detection of IoT botnets in a heterogeneous environment. The proposed one-class classifier, which is based on one-class KNN, can detect the IoT botnets at the early stage with high accuracy. The proposed machine-learning-based model is a lightweight solution that works by selecting the best features leveraging well-known filter and wrapper methods for feature selection. The proposed strategy is evaluated over different datasets collected from varying network scenarios. The experimental results reveal that the proposed technique shows improved performance, consistent across three different datasets used for evaluation. [ABSTRACT FROM AUTHOR]

Existing material identification for loose particles inside sealed relays focuses on the selection and optimization of classification algorithms, which ignores the features in the material dataset. In this paper, we propose a feature optimization method of material identification for loose particles inside sealed relays. First, for the missing value problem, multiple methods were used to process the material dataset. By comparing the identification accuracy achieved by a Random-Forest-based classifier (RF classifier) on the different processed datasets, the optimal direct-discarding method was obtained. Second, for the uneven data distribution problem, multiple methods were used to process the material dataset. By comparing the achieved identification accuracy, the optimal min–max standardization method was obtained. Then, for the feature selection problem, an innovative multi-index–fusion feature selection method was designed, and its superiority was verified through several tests. Test results show that the identification accuracy achieved by RF classifier on the dataset was improved from 59.63% to 63.60%. Test results of ten material verification datasets show that the identification accuracies achieved by RF classifier were greatly improved, with an average improvement of 3.01%. This strongly promotes research progress in loose particle material identification and is an important supplement to existing loose particle detection research. This is also the highest loose particle material identification accuracy achieved to in aerospace engineering, which has important practical value for improving the reliability of aerospace systems. Theoretically, it can be applied to feature optimization in machine learning. [ABSTRACT FROM AUTHOR]

Accurate assessment of physical fatigue is crucial to preventing physical injury caused by excessive exercise, overtraining during daily exercise and professional sports training. However, as a subjective feeling of an individual, physical fatigue is difficult for others to objectively evaluate. Heart rate variability (HRV), which is derived from electrocardiograms (ECG) and controlled by the autonomic nervous system, has been demonstrated to be a promising indicator for physical fatigue estimation. In this paper, we propose a novel method for the automatic and objective classification of physical fatigue based on HRV. First, a total of 24 HRV features were calculated. Then, a feature selection method was proposed to remove useless features that have a low correlation with physical fatigue and redundant features that have a high correlation with the selected features. After feature selection, the best 11 features were selected and were finally used for physical fatigue classifying. Four machine learning algorithms were trained to classify fatigue using the selected features. The experimental results indicate that the model trained using the selected 11 features could classify physical fatigue with high accuracy. More importantly, these selected features could provide important information regarding the identification of physical fatigue. [ABSTRACT FROM AUTHOR]

Building contour extraction from high-resolution remote sensing images is a basic task for the reasonable planning of regional construction. Recently, building segmentation methods based on the U-Net network have become popular as they largely improve the segmentation accuracy by applying 'skip connection' to combine high-level and low-level feature information more effectively. Meanwhile, researchers have demonstrated that introducing an attention mechanism into U-Net can enhance local feature expression and improve the performance of building extraction in remote sensing images. In this paper, we intend to explore the effectiveness of the primeval attention gate module and propose the novel Attention Gate Module (AG) based on adjusting the position of 'Resampler' in an attention gate to Sigmoid function for a building extraction task, and a novel Attention Gates U network (AGs-Unet) is further proposed based on AG, which can automatically learn different forms of building structures in high-resolution remote sensing images and realize efficient extraction of building contour. AGs-Unet integrates attention gates with a single U-Net network, in which a series of attention gate modules are added into the 'skip connection' for suppressing the irrelevant and noisy feature responses in the input image to highlight the dominant features of the buildings in the image. AGs-Unet improves the feature selection of the attention map to enhance the ability of feature learning, as well as paying attention to the feature information of small-scale buildings. We conducted the experiments on the WHU building dataset and the INRIA Aerial Image Labeling dataset, in which the proposed AGs-Unet model is compared with several classic models (such as FCN8s, SegNet, U-Net, and DANet) and two state-of-the-art models (such as PISANet, and ARC-Net). The extraction accuracy of each model is evaluated by using three evaluation indexes, namely, overall accuracy, precision, and intersection over union. Experimental results show that the proposed AGs-Unet model can improve the quality of building extraction from high-resolution remote sensing images effectively in terms of prediction performance and result accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we investigate various machine learning classifiers used in our Virtual Reality (VR) system for treating acrophobia. The system automatically estimates fear level based on multimodal sensory data and a self-reported emotion assessment. There are two modalities of expressing fear ratings: the 2-choice scale, where 0 represents relaxation and 1 stands for fear; and the 4-choice scale, with the following correspondence: 0—relaxation, 1—low fear, 2—medium fear and 3—high fear. A set of features was extracted from the sensory signals using various metrics that quantify brain (electroencephalogram—EEG) and physiological linear and non-linear dynamics (Heart Rate—HR and Galvanic Skin Response—GSR). The novelty consists in the automatic adaptation of exposure scenario according to the subject’s affective state. We acquired data from acrophobic subjects who had undergone an in vivo pre-therapy exposure session, followed by a Virtual Reality therapy and an in vivo evaluation procedure. Various machine and deep learning classifiers were implemented and tested, with and without feature selection, in both a user-dependent and user-independent fashion. The results showed a very high cross-validation accuracy on the training set and good test accuracies, ranging from 42.5% to 89.5%. The most important features of fear level classification were GSR, HR and the values of the EEG in the beta frequency range. For determining the next exposure scenario, a dominant role was played by the target fear level, a parameter computed by taking into account the patient’s estimated fear level. [ABSTRACT FROM AUTHOR]

Long-range ground targets are difficult to detect in a noisy cluttered environment using either synthetic aperture radar (SAR) images or infrared (IR) images. SAR-based detectors can provide a high detection rate with a high false alarm rate to background scatter noise. IR-based approaches can detect hot targets but are affected strongly by the weather conditions. This paper proposes a novel target detection method by decision-level SAR and IR fusion using an Adaboost-based machine learning scheme to achieve a high detection rate and low false alarm rate. The proposed method consists of individual detection, registration, and fusion architecture. This paper presents a single framework of a SAR and IR target detection method using modified Boolean map visual theory (modBMVT) and feature-selection based fusion. Previous methods applied different algorithms to detect SAR and IR targets because of the different physical image characteristics. One method that is optimized for IR target detection produces unsuccessful results in SAR target detection. This study examined the image characteristics and proposed a unified SAR and IR target detection method by inserting a median local average filter (MLAF, pre-filter) and an asymmetric morphological closing filter (AMCF, post-filter) into the BMVT. The original BMVT was optimized to detect small infrared targets. The proposed modBMVT can remove the thermal and scatter noise by the MLAF and detect extended targets by attaching the AMCF after the BMVT. Heterogeneous SAR and IR images were registered automatically using the proposed RANdom SAmple Region Consensus (RANSARC)-based homography optimization after a brute-force correspondence search using the detected target centers and regions. The final targets were detected by feature-selection based sensor fusion using Adaboost. The proposed method showed good SAR and IR target detection performance through feature selection-based decision fusion on a synthetic database generated by OKTAL-SE. [ABSTRACT FROM AUTHOR]

We live in a period when smart devices gather a large amount of data from a variety of sensors and it is often the case that decisions are taken based on them in a more or less autonomous manner. Still, many of the inputs do not prove to be essential in the decision-making process; hence, it is of utmost importance to find the means of eliminating the noise and concentrating on the most influential attributes. In this sense, we put forward a method based on the swarm intelligence paradigm for extracting the most important features from several datasets. The thematic of this paper is a novel implementation of an algorithm from the swarm intelligence branch of the machine learning domain for improving feature selection. The combination of machine learning with the metaheuristic approaches has recently created a new branch of artificial intelligence called learnheuristics. This approach benefits both from the capability of feature selection to find the solutions that most impact on accuracy and performance, as well as the well known characteristic of swarm intelligence algorithms to efficiently comb through a large search space of solutions. The latter is used as a wrapper method in feature selection and the improvements are significant. In this paper, a modified version of the salp swarm algorithm for feature selection is proposed. This solution is verified by 21 datasets with the classification model of K-nearest neighborhoods. Furthermore, the performance of the algorithm is compared to the best algorithms with the same test setup resulting in better number of features and classification accuracy for the proposed solution. Therefore, the proposed method tackles feature selection and demonstrates its success with many benchmark datasets. [ABSTRACT FROM AUTHOR]

In this paper, we provide external image features and use the internal attention mechanism to solve the VQA problem given a dataset of textual questions and related images. Most previous models for VQA use a pair of images and questions as input. In addition, the model adopts a question-oriented attention mechanism to extract the features of the entire image and then perform feature fusion. However, the shortcoming of these models is that they cannot effectively eliminate the irrelevant features of the image. In addition, the problem-oriented attention mechanism lacks in the mining of image features, which will bring in redundant image features. In this paper, we propose a VQA model based on adversarial learning and bidirectional attention. We exploit external image features that are not related to the question to form an adversarial mechanism to boost the accuracy of the model. Target detection is performed on the image—that is, the image-oriented attention mechanism. The bidirectional attention mechanism is conducive to promoting model attention and eliminating interference. Experimental results are evaluated on benchmark datasets, and our model performs better than other models based on attention methods. In addition, the qualitative results show the attention maps on the images and leads to predicting correct answers. [ABSTRACT FROM AUTHOR]

During the processing and planting of soybeans, it is greatly significant that a reliable, rapid, and accurate technique is used to detect soybean varieties. Traditional chemical analysis methods of soybean variety sampling (e.g., mass spectrometry and high-performance liquid chromatography) are destructive and time-consuming. In this paper, a robust and accurate method for nondestructive soybean classification is developed through hyperspectral imaging and ensemble machine learning algorithms. Image acquisition, preprocessing, and feature selection are used to obtain different types of soybean hyperspectral features. Based on these features, one of ensemble classifiers-random subspace linear discriminant (RSLD) algorithm is used to classify soybean seeds. Compared with the linear discrimination (LD) and linear support vector machine (LSVM) methods, the results show that the RSLD algorithm in this paper is more stable and reliable. In classifying soybeans in 10, 15, 20, and 25 categories, the RSLD method achieves the highest classification accuracy. When 155 features are used to classify 15 types of soybeans, the classification accuracy of the RSLD method reaches 99.2%, while the classification accuracies of the LD and LSVM methods are only 98.6% and 69.7%, respectively. Therefore, the ensemble classification algorithm RSLD can maintain high classification accuracy when different types and different classification features are used. [ABSTRACT FROM AUTHOR]

Faults in distribution networks occur unpredictably, causing a threat to public safety and resulting in power outages. Automated, efficient, and precise detection of faulty sections could be a major element in immediately restoring networks and avoiding further financial losses. Distributed generations (DGs) are used in smart distribution networks and have varied current levels and internal impedances. However, fault characteristics are completely unknown because of their stochastic nature. Therefore, in these circumstances, locating the fault might be difficult. However, as technology advances, micro-phasor measurement units (micro-PMU) are becoming more extensively employed in smart distribution networks, and might be a useful tool for reducing protection uncertainties. In this paper, a new machine learning-based fault location method is proposed for use regardless of fault characteristics and DG performance using recorded data of micro-PMUs during a fault. This method only uses the recorded voltage at the sub-station and DGs. The frequency component of the voltage signals is selected as a feature vector. The neighborhood component feature selection (NCFS) algorithm is utilized to extract more informative features and lower the feature vector dimension. A support vector machine (SVM) classifier is then applied to the decreased dimension training data. The simulations of various fault types are performed on the 11-node IEEE standard feeder equipped with three DGs. Results reveal that the accuracy of the proposed fault section identification algorithm is notable. [ABSTRACT FROM AUTHOR]

The variation in skin textures and injuries, as well as the detection and classification of skin cancer, is a difficult task. Manually detecting skin lesions from dermoscopy images is a difficult and time-consuming process. Recent advancements in the domains of the internet of things (IoT) and artificial intelligence for medical applications demonstrated improvements in both accuracy and computational time. In this paper, a new method for multiclass skin lesion classification using best deep learning feature fusion and an extreme learning machine is proposed. The proposed method includes five primary steps: image acquisition and contrast enhancement; deep learning feature extraction using transfer learning; best feature selection using hybrid whale optimization and entropy-mutual information (EMI) approach; fusion of selected features using a modified canonical correlation based approach; and, finally, extreme learning machine based classification. The feature selection step improves the system's computational efficiency and accuracy. The experiment is carried out on two publicly available datasets, HAM10000 and ISIC2018. The achieved accuracy on both datasets is 93.40 and 94.36 percent. When compared to state-of-the-art (SOTA) techniques, the proposed method's accuracy is improved. Furthermore, the proposed method is computationally efficient. [ABSTRACT FROM AUTHOR]

Unmanned aerial vehicles are prone to several cyber-attacks, including Global Positioning System spoofing. Several techniques have been proposed for detecting such attacks. However, the recurrence and frequent Global Positioning System spoofing incidents show a need for effective security solutions to protect unmanned aerial vehicles. In this paper, we propose two dynamic selection techniques, Metric Optimized Dynamic selector and Weighted Metric Optimized Dynamic selector, which identify the most effective classifier for the detection of such attacks. We develop a one-stage ensemble feature selection method to identify and discard the correlated and low importance features from the dataset. We implement the proposed techniques using ten machine-learning models and compare their performance in terms of four evaluation metrics: accuracy, probability of detection, probability of false alarm, probability of misdetection, and processing time. The proposed techniques dynamically choose the classifier with the best results for detecting attacks. The results indicate that the proposed dynamic techniques outperform the existing ensemble models with an accuracy of 99.6%, a probability of detection of 98.9%, a probability of false alarm of 1.56%, a probability of misdetection of 1.09%, and a processing time of 1.24 s. [ABSTRACT FROM AUTHOR]

Due to the wide availability and usage of connected devices in Internet of Things (IoT) networks, the number of attacks on these networks is continually increasing. A particularly serious and dangerous type of attack in the IoT environment is the botnet attack, where the attackers can control the IoT systems to generate enormous networks of "bot" devices for generating malicious activities. To detect this type of attack, several Intrusion Detection Systems (IDSs) have been proposed for IoT networks based on machine learning and deep learning methods. As the main characteristics of IoT systems include their limited battery power and processor capacity, maximizing the efficiency of intrusion detection systems for IoT networks is still a research challenge. It is important to provide efficient and effective methods that use lower computational time and have high detection rates. This paper proposes an aggregated mutual information-based feature selection approach with machine learning methods to enhance detection of IoT botnet attacks. In this study, the N-BaIoT benchmark dataset was used to detect botnet attack types using real traffic data gathered from nine commercial IoT devices. The dataset includes binary and multi-class classifications. The feature selection method incorporates Mutual Information (MI) technique, Principal Component Analysis (PCA) and ANOVA f-test at finely-granulated detection level to select the relevant features for improving the performance of IoT Botnet classifiers. In the classification step, several ensemble and individual classifiers were used, including Random Forest (RF), XGBoost (XGB), Gaussian Naïve Bayes (GNB), k-Nearest Neighbor (k-NN), Logistic Regression (LR) and Support Vector Machine (SVM). The experimental results showed the efficiency and effectiveness of the proposed approach, which outperformed other techniques using various evaluation metrics. [ABSTRACT FROM AUTHOR]

An accurate step length estimation can provide valuable information to different applications such as indoor positioning systems or it can be helpful when analyzing the gait of a user, which can then be used to detect various gait impairments that lead to a reduced step length (caused by e.g., Parkinson's disease or multiple sclerosis). In this paper, we focus on the estimation of the step length using machine learning techniques that could be used in an indoor positioning system. Previous step length algorithms tried to model the length of a step based on measurements from the accelerometer and some tuneable (user-specific) parameters. Machine-learning-based step length estimation algorithms eliminate these parameters to be tuned. Instead, to adapt these algorithms to different users, it suffices to provide examples of the length of multiple steps for different persons to the machine learning algorithm, so that in the training phase the algorithm can learn to predict the step length for different users. Until now, these machine learning algorithms were trained with features that were chosen intuitively. In this paper, we consider a systematic feature selection algorithm to be able to determine the features from a large collection of features, resulting in the best performance. This resulted in a step length estimator with a mean absolute error of 3.48 cm for a known test person and 4.19 cm for an unknown test person, while current state-of-the-art machine-learning-based step length estimators resulted in a mean absolute error of 4.94 cm and 6.27 cm for respectively a known and unknown test person. [ABSTRACT FROM AUTHOR]

The large number of poststroke recovery patients poses a burden on rehabilitation centers, hospitals, and physiotherapists. The advent of rehabilitation robotics and automated assessment systems can ease this burden by assisting in the rehabilitation of patients with a high level of recovery. This assistance will enable medical professionals to either better provide for patients with severe injuries or treat more patients. It also translates into financial assistance as well in the long run. This paper demonstrated an automated assessment system for in-home rehabilitation utilizing a data glove, a mobile application, and machine learning algorithms. The system can be used by poststroke patients with a high level of recovery to assess their performance. Furthermore, this assessment can be sent to a medical professional for supervision. Additionally, a comparison between two machine learning classifiers was performed on their assessment of physical exercises. The proposed system has an accuracy of 85% (±5.1%) with careful feature and classifier selection. [ABSTRACT FROM AUTHOR]