Search

The main purpose of this paper is to provide information on how to create a convolutional neural network (CNN) for extracting features from EEG signals. Our task was to understand the primary aspects of creating and fine-tuning CNNs for various application scenarios. We considered the characteristics of EEG signals, coupled with an exploration of various signal processing and data preparation techniques. These techniques include noise reduction, filtering, encoding, decoding, and dimension reduction, among others. In addition, we conduct an in-depth analysis of well-known CNN architectures, categorizing them into four distinct groups: standard implementation, recurrent convolutional, decoder architecture, and combined architecture. This paper further offers a comprehensive evaluation of these architectures, covering accuracy metrics, hyperparameters, and an appendix that contains a table outlining the parameters of commonly used CNN architectures for feature extraction from EEG signals. [ABSTRACT FROM AUTHOR]

Parkinson's Disease (PD) is a complex neurodegenerative disorder characterized by a spectrum of motor and non-motor symptoms, prominently featuring the freezing of gait (FOG), which significantly impairs patients' quality of life. Despite extensive research, the precise mechanisms underlying FOG remain elusive, posing challenges for effective management and treatment. This paper presents a comprehensive meta-analysis of FOG prediction and detection methodologies, with a focus on the integration of wearable sensor technology and machine learning (ML) approaches. Through an exhaustive review of the literature, this study identifies key trends, datasets, preprocessing techniques, feature extraction methods, evaluation metrics, and comparative analyses between ML and non-ML approaches. The analysis also explores the utilization of cueing devices. The limited adoption of explainable AI (XAI) approaches in FOG prediction research represents a significant gap. Improving user acceptance and comprehension requires an understanding of the logic underlying algorithm predictions. Current FOG detection and prediction research has a number of limitations, which are identified in the discussion. These include issues with cueing devices, dataset constraints, ethical and privacy concerns, financial and accessibility restrictions, and the requirement for multidisciplinary collaboration. Future research avenues center on refining explainability, expanding and diversifying datasets, adhering to user requirements, and increasing detection and prediction accuracy. The findings contribute to advancing the understanding of FOG and offer valuable guidance for the development of more effective detection and prediction methodologies, ultimately benefiting individuals affected by PD. [ABSTRACT FROM AUTHOR]

Assessing mobility in daily life can provide significant insights into several clinical conditions, such as Chronic Obstructive Pulmonary Disease (COPD). In this paper, we present a comprehensive analysis of wearable devices' performance in gait speed estimation and explore optimal device combinations for everyday use. Using data collected from smartphones, smartwatches, and smart shoes, we evaluated the individual capabilities of each device and explored their synergistic effects when combined, thereby accommodating the preferences and possibilities of individuals for wearing different types of devices. Our study involved 20 healthy subjects performing a modified Six-Minute Walking Test (6MWT) under various conditions. The results revealed only little performance differences among devices, with the combination of smartwatches and smart shoes exhibiting superior estimation accuracy. Particularly, smartwatches captured additional health-related information and demonstrated enhanced accuracy when paired with other devices. Surprisingly, wearing all devices concurrently did not yield optimal results, suggesting a potential redundancy in feature extraction. Feature importance analysis highlighted key variables contributing to gait speed estimation, providing valuable insights for model refinement. [ABSTRACT FROM AUTHOR]

The global concern regarding the monitoring of construction workers' activities necessitates an efficient means of continuous monitoring for timely action recognition at construction sites. This paper introduces a novel approach—the multi-scale graph strategy—to enhance feature extraction in complex networks. At the core of this strategy lies the multi-feature fusion network (MF-Net), which employs multiple scale graphs in distinct network streams to capture both local and global features of crucial joints. This approach extends beyond local relationships to encompass broader connections, including those between the head and foot, as well as interactions like those involving the head and neck. By integrating diverse scale graphs into distinct network streams, we effectively incorporate physically unrelated information, aiding in the extraction of vital local joint contour features. Furthermore, we introduce velocity and acceleration as temporal features, fusing them with spatial features to enhance informational efficacy and the model's performance. Finally, efficiency-enhancing measures, such as a bottleneck structure and a branch-wise attention block, are implemented to optimize computational resources while enhancing feature discriminability. The significance of this paper lies in improving the management model of the construction industry, ultimately aiming to enhance the health and work efficiency of workers. [ABSTRACT FROM AUTHOR]

Ultrasonic diagnostics is the earliest way to predict industrial faults. Usually, a contact microphone is employed for detection, but the recording will be contaminated with noise. In this paper, a dataset that contains 10 main faults of pipelines and motors is analyzed from which 30 different features in the time and frequency domains are extracted. Afterward, for dimensionality reduction, principal component analysis (PCA), linear discriminant analysis (LDA), and t-distributed stochastic neighbor embedding (t-SNE) are performed. In the subsequent phase, recursive feature elimination (RFE) is employed as a strategic method to analyze and select the most relevant features for the classifiers. Next, predictive models consisting of k-Nearest Neighbor (KNN), Logistic Regression (LR), Decision Tree (DT), Gaussian Naive Bayes (GNB), and Support Vector Machine (SVM) are employed. Then, in order to solve the classification problem, a stacking classifier based on a meta-classifier which combines multiple classification models is introduced. Furthermore, the k-fold cross-validation technique is employed to assess the effectiveness of the model in handling new data for the evaluation of experimental results in ultrasonic fault detection. With the proposed method, the accuracy is around 5% higher over five cross folds with the least amount of variation. The timing evaluation of the meta model on the 64 MHz Cortex M4 microcontroller unit (MCU) revealed an execution time of 11 ms, indicating it could be a promising solution for real-time monitoring. [ABSTRACT FROM AUTHOR]

Non-invasive detection of hemoglobin (Hb) concentration is of great clinical value for health screening and intraoperative blood transfusion. However, the accuracy and stability of non-invasive detection still need to be improved to meet clinical requirement. This paper proposes a non-invasive Hb detection method using ensemble extreme learning machine (EELM) regression based on eight-wavelength PhotoPlethysmoGraphic (PPG) signals. Firstly, a mathematical model for non-invasive Hb detection based on the Beer-Lambert law is established. Secondly, the captured eight-channel PPG signals are denoised and fifty-six feature values are extracted according to the derived mathematical model. Thirdly, a recursive feature elimination (RFE) algorithm is used to select the features that contribute most to the Hb prediction. Finally, a regression model is built by integrating several independent ELM models to improve prediction stability and accuracy. Experiments conducted on 249 clinical data points (199 cases as the training dataset and 50 cases as the test dataset) evaluate the proposed method, achieving a root mean square error (RMSE) of 1.72 g/dL and a Pearson correlation coefficient (PCC) of 0.76 (p < 0.01) between predicted and reference values. The results demonstrate that the proposed non-invasive Hb detection method exhibits a strong correlation with traditional invasive methods, suggesting its potential for non-invasive detection of Hb concentration. [ABSTRACT FROM AUTHOR]

This paper proposes a new fault diagnosis method for centrifugal pumps by combining signal processing with deep learning techniques. Centrifugal pumps facilitate fluid transport through the energy generated by the impeller. Throughout the operation, variations in the fluid pressure at the pump's inlet may impact the generalization of traditional machine learning models trained on raw statistical features. To address this concern, first, vibration signals are collected from centrifugal pumps, followed by the application of a lowpass filter to isolate frequencies indicative of faults. These signals are then subjected to a continuous wavelet transform and Stockwell transform, generating two distinct time–frequency scalograms. The Sobel filter is employed to further highlight essential features within these scalograms. For feature extraction, this approach employs two parallel convolutional autoencoders, each tailored for a specific scalogram type. Subsequently, extracted features are merged into a unified feature pool, which forms the basis for training a two-layer artificial neural network, with the aim of achieving accurate fault classification. The proposed method is validated using three distinct datasets obtained from the centrifugal pump under varying inlet fluid pressures. The results demonstrate classification accuracies of 100%, 99.2%, and 98.8% for each dataset, surpassing the accuracies achieved by the reference comparison methods. [ABSTRACT FROM AUTHOR]

Myocardial Infarction (MI), commonly known as heart attack, is a cardiac condition characterized by damage to a portion of the heart, specifically the myocardium, due to the disruption of blood flow. Given its recurring and often asymptomatic nature, there is the need for continuous monitoring using wearable devices. This paper proposes a single-microcontroller-based system designed for the automatic detection of MI based on the Edge Computing paradigm. Two solutions for MI detection are evaluated, based on Machine Learning (ML) and Deep Learning (DL) techniques. The developed algorithms are based on two different approaches currently available in the literature, and they are optimized for deployment on low-resource hardware. A feasibility assessment of their implementation on a single 32-bit microcontroller with an ARM Cortex-M4 core was examined, and a comparison in terms of accuracy, inference time, and memory usage was detailed. For ML techniques, significant data processing for feature extraction, coupled with a simpler Neural Network (NN) is involved. On the other hand, the second method, based on DL, employs a Spectrogram Analysis for feature extraction and a Convolutional Neural Network (CNN) with a longer inference time and higher memory utilization. Both methods employ the same low power hardware reaching an accuracy of 89.40% and 94.76%, respectively. The final prototype is an energy-efficient system capable of real-time detection of MI without the need to connect to remote servers or the cloud. All processing is performed at the edge, enabling NN inference on the same microcontroller. [ABSTRACT FROM AUTHOR]

A significant majority of the population in India makes their living through agriculture. Different illnesses that develop due to changing weather patterns and are caused by pathogenic organisms impact the yields of diverse plant species. The present article analyzed some of the existing techniques in terms of data sources, pre-processing techniques, feature extraction techniques, data augmentation techniques, models utilized for detecting and classifying diseases that affect the plant, how the quality of images was enhanced, how overfitting of the model was reduced, and accuracy. The research papers for this study were selected using various keywords from peer-reviewed publications from various databases published between 2010 and 2022. A total of 182 papers were identified and reviewed for their direct relevance to plant disease detection and classification, of which 75 papers were selected for this review after exclusion based on the title, abstract, conclusion, and full text. Researchers will find this work to be a useful resource in recognizing the potential of various existing techniques through data-driven approaches while identifying plant diseases by enhancing system performance and accuracy. [ABSTRACT FROM AUTHOR]

Autonomous vehicles have become a topic of interest in recent times due to the rapid advancement of automobile and computer vision technology. The ability of autonomous vehicles to drive safely and efficiently relies heavily on their ability to accurately recognize traffic signs. This makes traffic sign recognition a critical component of autonomous driving systems. To address this challenge, researchers have been exploring various approaches to traffic sign recognition, including machine learning and deep learning. Despite these efforts, the variability of traffic signs across different geographical regions, complex background scenes, and changes in illumination still poses significant challenges to the development of reliable traffic sign recognition systems. This paper provides a comprehensive overview of the latest advancements in the field of traffic sign recognition, covering various key areas, including preprocessing techniques, feature extraction methods, classification techniques, datasets, and performance evaluation. The paper also delves into the commonly used traffic sign recognition datasets and their associated challenges. Additionally, this paper sheds light on the limitations and future research prospects of traffic sign recognition. [ABSTRACT FROM AUTHOR]

In this paper, the performance of machine learning methods for squirrel cage induction motor broken rotor bar (BRB) fault detection is evaluated. Decision tree classification (DTC), artificial neural network (ANN), and deep learning (DL) methods are developed, applied, and studied to compare their performance in detecting broken rotor bar faults in squirrel cage induction motors. The training data were collected through experimental measurements. The BRB fault features were extracted from measured line-current signatures through a transformation from the time domain to the frequency domain using discrete Fourier Transform (DFT) of the frequency spectrum of the current signal. Eighty percent of the data were used for training the models, and twenty percent were used for testing. A confusion matrix was used to validate the models' performance using accuracy, precision, recall, and f1-scores. The results evidence that the DTC is less load-dependent, and it has better accuracy and precision for both unloaded and loaded squirrel cage induction motors when compared with the DL and ANN methods. The DTC method achieved higher accuracy in the detection of the magnitudes of the twice-frequency sideband components induced in stator currents by BRB faults when compared with the DL and ANN methods. Although the detection accuracy and precision are higher for the loaded motor than the unloaded motor, the DTC method managed to also exhibit a high accuracy for the unloaded current when compared with the DL and ANN methods. The DTC is, therefore, a suitable candidate to detect broken rotor bar faults on trained data for lightly or thoroughly loaded squirrel cage induction motors using the characteristics of the measured line-current signature. [ABSTRACT FROM AUTHOR]

Image-based gender classification is very useful in many applications, such as intelligent surveillance, micromarketing, etc. One common approach is to adopt a machine learning algorithm to recognize the gender class of the captured subject based on spatio-temporal gait features extracted from the image. The image input can be generated from the video of the walking cycle, e.g., gait energy image (GEI). Recognition accuracy depends on the similarity of intra-class GEIs, as well as the dissimilarity of inter-class GEIs. However, we observe that, at some viewing angles, the GEIs of both gender classes are very similar. Moreover, the GEI does not exhibit a clear appearance of posture. We postulate that distinctive postures of the walking cycle can provide additional and valuable information for gender classification. This paper proposes a gender classification framework that exploits multiple inputs of the GEI and the characteristic poses of the walking cycle. The proposed framework is a cascade network that is capable of gradually learning the gait features from images acquired in multiple views. The cascade network contains a feature extractor and gender classifier. The multi-stream feature extractor network is trained to extract features from the multiple input images. Features are then fed to the classifier network, which is trained with ensemble learning. We evaluate and compare the performance of our proposed framework with state-of-the-art gait-based gender classification methods on benchmark datasets. The proposed framework outperforms other methods that only utilize a single input of the GEI or pose. [ABSTRACT FROM AUTHOR]

The main application scenario for wearable sensors involves the generation of data and monitoring metrics. fNIRS (functional near-infrared spectroscopy) allows the nonintrusive monitoring of human visual perception. The quantification of visual perception by fNIRS facilitates applications in engineering-related fields. This study designed a set of experimental procedures to effectively induce visible alterations and to quantify visual perception in conjunction with the acquisition of Hbt (total hemoglobin), Hb (hemoglobin), and HbO2 (oxygenated hemoglobin) data obtained from HfNIRS (high-density functional near-infrared spectroscopy). Volunteers completed the visual task separately in response to different visible changes in the simulated scene. HfNIRS recorded the changes in Hbt, Hb, and HbO2 during the study, the time point of the visual difference, and the time point of the task change. This study consisted of one simulated scene, two visual variations, and four visual tasks. The simulation scene featured a car driving location. The visible change suggested that the brightness and saturation of the car operator interface would change. The visual task represented the completion of the layout, color, design, and information questions answered in response to the visible change. This study collected data from 29 volunteers. The volunteers completed the visual task separately in response to different visual changes in the same simulated scene. HfNIRS recorded the changes in Hbt, Hb, and HbO2 during the study, the time point of the visible difference, and the time point of the task change. The data analysis methods in this study comprised a combination of channel dimensionality reduction, feature extraction, task classification, and score correlation. Channel downscaling: This study used the data of 15 channels in HfNIRS to calculate the mutual information between different channels to set a threshold, and to retain the data of the channels that were higher than those of the mutual information. Feature extraction: The statistics derived from the visual task, including time, mean, median, variance, extreme variance, kurtosis, bias, information entropy, and approximate entropy were computed. Task classification: This study used the KNN (K-Nearest Neighbors) algorithm to classify different visual tasks and to calculate the accuracy, precision, recall, and F1 scores. Scoring correlation: This study matched the visual task scores with the fluctuations of Hbt, Hb, and HbO2 and observed the changes in Hbt, Hb, and HbO2 under different scoring levels. Mutual information was used to downscale the channels, and seven channels were retained for analysis under each visual task. The average accuracy was 96.3% ± 1.99%; the samples that correctly classified the visual task accounted for 96.3% of the total; and the classification accuracy was high. By analyzing the correlation between the scores on different visual tasks and the fluctuations of Hbt, Hb, and HbO2, it was found that the higher the score, the more obvious, significant, and higher the fluctuations of Hbt, Hb, and HbO2. Experiments found that changes in visual perception triggered changes in Hbt, Hb, and HbO2. HfNIRS combined with Hbt, Hb, and HbO2 recorded by machine learning algorithms can effectively quantify visual perception. However, the related research in this paper still needs to be further refined, and the mathematical relationship between HfNIRS and visual perception needs to be further explored to realize the quantitative study of subjective and objective visual perception supported by the mathematical relationship. [ABSTRACT FROM AUTHOR]

The abnormal wear of a rolling element bearing caused by early failures, such as pitting and spalling, will deteriorate the running state and reduce the life. This paper demonstrates the importance of oil debris monitoring and its effective feature extraction for bearing health assessment. In this paper, a rolling bearing-rotor test rig with forced lubrication is set up and the nonferrous contaminants with higher hardness were introduced artificially to accelerate the occurrence of pitting and spalling. The early failure and abnormal wear of rolling bearings cannot be effectively detected only through the vibration signal; the temperature and oil debris monitoring data are also collected synchronously. Two features regarding the ferrous particle size distribution are extracted and fused with vibration based-features to form a feature set. The sensitive features are extracted from the features set using the Neighborhood Component Analysis method to avoid feature redundancy. Finally, the importance of the oil debris based-features for the diagnosis of abnormal bearing wear is analyzed with different machine learning algorithms. Taking SVM classifier as an example, the experiment results show that the introduction of oil debris based-features increases the diagnostic accuracy by 15.7%. [ABSTRACT FROM AUTHOR]

This paper presents a critical review and comparison of the results of recently published studies in the fields of human–machine interface and the use of sonomyography (SMG) for the control of upper limb prothesis. For this review paper, a combination of the keywords "Human Machine Interface", "Sonomyography", "Ultrasound", "Upper Limb Prosthesis", "Artificial Intelligence", and "Non-Invasive Sensors" was used to search for articles on Google Scholar and PubMed. Sixty-one articles were found, of which fifty-nine were used in this review. For a comparison of the different ultrasound modes, feature extraction methods, and machine learning algorithms, 16 articles were used. Various modes of ultrasound devices for prosthetic control, various machine learning algorithms for classifying different hand gestures, and various feature extraction methods for increasing the accuracy of artificial intelligence used in their controlling systems are reviewed in this article. The results of the review article show that ultrasound sensing has the potential to be used as a viable human–machine interface in order to control bionic hands with multiple degrees of freedom. Moreover, different hand gestures can be classified by different machine learning algorithms trained with extracted features from collected data with an accuracy of around 95%. [ABSTRACT FROM AUTHOR]

Text summarization is an information compression technology to extract important information from long text, which has become a challenging research direction in the field of natural language processing. At present, the text summary model based on deep learning has shown good results, but how to more effectively model the relationship between words, more accurately extract feature information and eliminate redundant information is still a problem of concern. This paper proposes a graph neural network model GA-GNN based on gated attention, which effectively improves the accuracy and readability of text summarization. First, the words are encoded using a concatenated sentence encoder to generate a deeper vector containing local and global semantic information. Secondly, the ability to extract key information features is improved by using gated attention units to eliminate local irrelevant information. Finally, the loss function is optimized from the three aspects of contrastive learning, confidence calculation of important sentences, and graph feature extraction to improve the robustness of the model. Experimental validation was conducted on a CNN/Daily Mail dataset and MR dataset, and the results showed that the model in this paper outperformed existing methods. [ABSTRACT FROM AUTHOR]

Pain management is a crucial concern in medicine, particularly in the case of children who may struggle to effectively communicate their pain. Despite the longstanding reliance on various assessment scales by medical professionals, these tools have shown limitations and subjectivity. In this paper, we present a pain assessment scheme based on skin potential signals, aiming to convert subjective pain into objective indicators for pain identification using machine learning methods. We have designed and implemented a portable non-invasive measurement device to measure skin potential signals and conducted experiments involving 623 subjects. From the experimental data, we selected 358 valid records, which were then divided into 218 silent samples and 262 pain samples. A total of 38 features were extracted from each sample, with seven features displaying superior performance in pain identification. Employing three classification algorithms, we found that the random forest algorithm achieved the highest accuracy, reaching 70.63%. While this identification rate shows promise for clinical applications, it is important to note that our results differ from state-of-the-art research, which achieved a recognition rate of 81.5%. This discrepancy arises from the fact that our pain stimuli were induced by clinical operations, making it challenging to precisely control the stimulus intensity when compared to electrical or thermal stimuli. Despite this limitation, our pain assessment scheme demonstrates significant potential in providing objective pain identification in clinical settings. Further research and refinement of the proposed approach may lead to even more accurate and reliable pain management techniques in the future. [ABSTRACT FROM AUTHOR]

Gun violence has been on the rise in recent years. To help curb the downward spiral of this negative influence in communities, machine learning strategies on gunshot detection can be developed and deployed. After outlining the procedure by which a typical type of gunshot-like sounds were measured, this paper focuses on the analysis of feature importance pertaining to gunshot and gunshot-like sounds. The random forest mean decrease in impurity and the SHapley Additive exPlanations feature importance analysis were employed for this task. From the feature importance analysis, feature reduction was then carried out. Via the Mel-frequency cepstral coefficients feature extraction process on 1-sec audio clips, these extracted features were then reduced to a more manageable quantity using the above-mentioned feature reduction processes. These reduced features were sent to a random forest classifier. The SHapley Additive exPlanations feature importance output was compared to that of the mean decrease in impurity feature importance. The results show what Mel-frequency cepstral coefficients features are important in discriminating gunshot sounds and various gunshot-like sounds. Together with the feature importance/reduction processes, the recent uniform manifold approximation and projection method was used to compare the closeness of various gunshot-like sounds to gunshot sounds in the feature space. Finally, the approach presented in this paper provides people with a viable means to make gunshot sounds more discernible from other sounds. [ABSTRACT FROM AUTHOR]

The synthesis between face sketches and face photos has important application values in law enforcement and digital entertainment. In cases of a lack of paired sketch-photo data, this paper proposes an unsupervised model to solve the problems of missing key facial details and a lack of realism in the synthesized images of existing methods. The model is built on the CycleGAN architecture. To retain more semantic information in the target domain, a multi-scale feature extraction module is inserted before the generator. In addition, the convolutional block attention module is introduced into the generator to enhance the ability of the model to extract important feature information. Via CBAM, the model improves the quality of the converted image and reduces the artifacts caused by image background interference. Next, in order to preserve more identity information in the generated photo, this paper constructs the multi-level cycle consistency loss function. Qualitative experiments on CUFS and CUFSF public datasets show that the facial details and edge structures synthesized by our model are clearer and more realistic. Meanwhile the performance indexes of structural similarity and peak signal-to-noise ratio in quantitative experiments are also significantly improved compared with other methods. [ABSTRACT FROM AUTHOR]

Recently, stereoscopic image quality assessment has attracted a lot attention. However, compared with 2D image quality assessment, it is much more difficult to assess the quality of stereoscopic images due to the lack of understanding of 3D visual perception. This paper proposes a novel no-reference quality assessment metric for stereoscopic images using natural scene statistics with consideration of both the quality of the cyclopean image and 3D visual perceptual information (binocular fusion and binocular rivalry). In the proposed method, not only is the quality of the cyclopean image considered, but binocular rivalry and other 3D visual intrinsic properties are also exploited. Specifically, in order to improve the objective quality of the cyclopean image, features of the cyclopean images in both the spatial domain and transformed domain are extracted based on the natural scene statistics (NSS) model. Furthermore, to better comprehend intrinsic properties of the stereoscopic image, in our method, the binocular rivalry effect and other 3D visual properties are also considered in the process of feature extraction. Following adaptive feature pruning using principle component analysis, improved metric accuracy can be found in our proposed method. The experimental results show that the proposed metric can achieve a good and consistent alignment with subjective assessment of stereoscopic images in comparison with existing methods, with the highest SROCC (0.952) and PLCC (0.962) scores being acquired on the LIVE 3D database Phase I. [ABSTRACT FROM AUTHOR]

Good data feature representation and high precision classifiers are the key steps for pattern recognition. However, when the data distributions between testing samples and training samples do not match, the traditional feature extraction methods and classification models usually degrade. In this paper, we propose a domain adaptation approach to handle this problem. In our method, we first introduce cross-domain mean approximation (CDMA) into semi-supervised discriminative analysis (SDA) and design semi-supervised cross-domain mean discriminative analysis (SCDMDA) to extract shared features across domains. Secondly, a kernel extreme learning machine (KELM) is applied as a subsequent classifier for the classification task. Moreover, we design a cross-domain mean constraint term on the source domain into KELM and construct a kernel transfer extreme learning machine (KTELM) to further promote knowledge transfer. Finally, the experimental results from four real-world cross-domain visual datasets prove that the proposed method is more competitive than many other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Wearable exoskeletons can help people with mobility impairments by improving their rehabilitation. As electromyography (EMG) signals occur before movement, they can be used as input signals for the exoskeletons to predict the body's movement intention. In this paper, the OpenSim software is used to determine the muscle sites to be measured, i.e., rectus femoris, vastus lateralis, semitendinosus, biceps femoris, lateral gastrocnemius, and tibial anterior. The surface electromyography (sEMG) signals and inertial data are collected from the lower limbs while the human body is walking, going upstairs, and going uphill. The sEMG noise is reduced by a wavelet-threshold-based complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) reduction algorithm, and the time-domain features are extracted from the noise-reduced sEMG signals. Knee and hip angles during motion are calculated using quaternions through coordinate transformations. The random forest (RF) regression algorithm optimized by cuckoo search (CS), shortened as CS-RF, is used to establish the prediction model of lower limb joint angles by sEMG signals. Finally, root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) are used as evaluation metrics to compare the prediction performance of the RF, support vector machine (SVM), back propagation (BP) neural network, and CS-RF. The evaluation results of CS-RF are superior to other algorithms under the three motion scenarios, with optimal metric values of 1.9167, 1.3893, and 0.9815, respectively. [ABSTRACT FROM AUTHOR]

Extracting high-accuracy landslide areas using deep learning methods from high spatial resolution remote sensing images is a hot topic in current research. However, the existing deep learning algorithms are affected by background noise and landslide scale effects during the extraction process, leading to poor feature extraction effects. To address this issue, this paper proposes an improved mask regions-based convolutional neural network (Mask R-CNN) model to identify the landslide distribution in unmanned aerial vehicles (UAV) images. The improvement of the model mainly includes three aspects: (1) an attention mechanism of the convolutional block attention module (CBAM) is added to the backbone residual neural network (ResNet). (2) A bottom-up channel is added to the feature pyramidal network (FPN) module. (3) The region proposal network (RPN) is replaced by guided anchoring (GA-RPN). Sanming City, China was selected as the study area for the experiments. The experimental results show that the improved model has a recall of 91.4% and an accuracy of 92.6%, which is 12.9% and 10.9% higher than the original Mask R-CNN model, respectively, indicating that the improved model is more effective in landslide extraction. [ABSTRACT FROM AUTHOR]

Structural health monitoring (SHM) systems are used to analyze the health of infrastructures such as bridges, using data from various types of sensors. While SHM systems consist of various stages, feature extraction and pattern recognition steps are the most important. Consequently, signal processing techniques in the feature extraction stage and machine learning algorithms in the pattern recognition stage play an effective role in analyzing the health of bridges. In other words, there exists a plethora of signal processing techniques and machine learning algorithms, and the selection of the appropriate technique/algorithm is guided by the limitations of each technique/algorithm. The selection also depends on the requirements of SHM in terms of damage identification level and operating conditions. This has provided the motivation to conduct a Systematic literature review (SLR) of feature extraction techniques and pattern recognition algorithms for the structural health monitoring of bridges. The existing literature reviews describe the current trends in the field with different focus aspects. However, a systematic literature review that presents an in-depth comparative study of different applications of machine learning algorithms in the field of SHM of bridges does not exist. Furthermore, there is a lack of analytical studies that investigate the SHM systems in terms of several design considerations including feature extraction techniques, analytical approaches (classification/ regression), operational functionality levels (diagnosis/prognosis) and system implementation techniques (data-driven/model-based). Consequently, this paper identifies 45 recent research practices (during 2016–2023), pertaining to feature extraction techniques and pattern recognition algorithms in SHM for bridges through an SLR process. First, the identified research studies are classified into three different categories: supervised learning algorithms, neural networks and a combination of both. Subsequently, an in-depth analysis of various machine learning algorithms is performed in each category. Moreover, the analysis of selected research studies (total = 45) in terms of feature extraction techniques is made, and 25 different techniques are identified. Furthermore, this article also explores other design considerations like analytical approaches in the pattern recognition process, operational functionality and system implementation. It is expected that the outcomes of this research may facilitate the researchers and practitioners of the domain during the selection of appropriate feature extraction techniques, machine learning algorithms and other design considerations according to the SHM system requirements. [ABSTRACT FROM AUTHOR]

Considering the detrimental effects of dyslexia on academic performance and its common occurrence, developing tools for dyslexia detection, monitoring, and treatment poses a task of significant priority. The research performed in this paper was focused on detecting and analyzing dyslexic tendencies in Serbian children based on eye-tracking measures. The group of 30 children (ages 7–13, 15 dyslexic and 15 non-dyslexic) read 13 different text segments on 13 different color configurations. For each text segment, the corresponding eye-tracking trail was recorded and then processed offline and represented by nine conventional features and five newly proposed features. The features were used for dyslexia recognition using several machine learning algorithms: logistic regression, support vector machine, k-nearest neighbor, and random forest. The highest accuracy of 94% was achieved using all the implemented features and leave-one-out subject cross-validation. Afterwards, the most important features for dyslexia detection (representing the complexity of fixation gaze) were used in a statistical analysis of the individual color effects on dyslexic tendencies within the dyslexic group. The statistical analysis has shown that the influence of color has high inter-subject variability. This paper is the first to introduce features that provide clear separability between a dyslexic and control group in the Serbian language (a language with a shallow orthographic system). Furthermore, the proposed features could be used for diagnosing and tracking dyslexia as biomarkers for objective quantification. [ABSTRACT FROM AUTHOR]

The past few decades have seen ongoing development of continuous glucose monitoring (CGM) systems that are noninvasive and accurately measure blood glucose levels. The conventional finger-prick method, though accurate, is not feasible for use multiple times a day, as it is painful and test strips are expensive. Although minimally invasive and noninvasive CGM systems have been introduced into the market, they are expensive and require finger-prick calibrations. As the diabetes trend is high in low- and middle-income countries, a cost-effective and easy-to-use noninvasive glucose monitoring device is the need of the hour. This review paper briefly discusses the noninvasive glucose measuring technologies and their related research work. The technologies discussed are optical, transdermal, and enzymatic. The paper focuses on Near Infrared (NIR) technology and NIR Photoplethysmography (PPG) for blood glucose prediction. Feature extraction from PPG signals and glucose prediction with machine learning methods are discussed. The review concludes with key points and insights for future development of PPG NIR-based blood glucose monitoring systems. [ABSTRACT FROM AUTHOR]

With the growing diversity of cyberattacks in recent years, anomaly-based intrusion detection systems that can detect unknown attacks have attracted significant attention. Furthermore, a wide range of studies on anomaly detection using machine learning and deep learning methods have been conducted. However, many machine learning and deep learning-based methods require significant effort to design the detection feature values, extract the feature values from network packets, and acquire the labeled data used for model training. To solve the aforementioned problems, this paper proposes a new model called DOC-IDS, which is an intrusion detection system based on Perera's deep one-class classification. The DOC-IDS, which comprises a pair of one-dimensional convolutional neural networks and an autoencoder, uses three different loss functions for training. Although, in general, only regular traffic from the computer network subject to detection is used for anomaly detection training, the DOC-IDS also uses multi-class labeled traffic from open datasets for feature extraction. Therefore, by streamlining the classification task on multi-class labeled traffic, we can obtain a feature representation with highly enhanced data discrimination abilities. Simultaneously, we perform variance minimization in the feature space, even on regular traffic, to further improve the model's ability to discriminate between normal and abnormal traffic. The DOC-IDS is a single deep learning model that can automatically perform feature extraction and anomaly detection. This paper also reports experiments for evaluating the anomaly detection performance of the DOC-IDS. The results suggest that the DOC-IDS offers higher anomaly detection performance while reducing the load resulting from the design and extraction of feature values. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach to creating a graphical summary of a subject's activity during a protocol in a Semi Free-Living Environment. Thanks to this new visualization, human behavior, in particular locomotion, can now be condensed into an easy-to-read and user-friendly output. As time series collected while monitoring patients in Semi Free-Living Environments are often long and complex, our contribution relies on an innovative pipeline of signal processing methods and machine learning algorithms. Once learned, the graphical representation is able to sum up all activities present in the data and can quickly be applied to newly acquired time series. In a nutshell, raw data from inertial measurement units are first segmented into homogeneous regimes with an adaptive change-point detection procedure, then each segment is automatically labeled. Then, features are extracted from each regime, and lastly, a score is computed using these features. The final visual summary is constructed from the scores of the activities and their comparisons to healthy models. This graphical output is a detailed, adaptive, and structured visualization that helps better understand the salient events in a complex gait protocol. [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]

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]

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]

Recently, the scientific community has placed great emphasis on the recognition of human activity, especially in the area of health and care for the elderly. There are already practical applications of activity recognition and unusual conditions that use body sensors such as wrist-worn devices or neck pendants. These relatively simple devices may be prone to errors, might be uncomfortable to wear, might be forgotten or not worn, and are unable to detect more subtle conditions such as incorrect postures. Therefore, other proposed methods are based on the use of images and videos to carry out human activity recognition, even in open spaces and with multiple people. However, the resulting increase in the size and complexity involved when using image data requires the use of the most recent advanced machine learning and deep learning techniques. This paper presents an approach based on deep learning with attention to the recognition of activities from multiple frames. Feature extraction is performed by estimating the pose of the human skeleton, and classification is performed using a neural network based on Bidirectional Encoder Representation of Transformers (BERT). This algorithm was trained with the UP-Fall public dataset, generating more balanced artificial data with a Generative Adversarial Neural network (GAN), and evaluated with real data, outperforming the results of other activity recognition methods using the same dataset. [ABSTRACT FROM AUTHOR]

In this paper, a novel approach to evaluation of feature extraction methodologies is presented. In the case of machine learning algorithms, extracting and using the most efficient features is one of the key problems that can significantly influence overall performance. It is especially the case with parameter-heavy problems, such as tool condition monitoring. In the presented case, images of drilled holes are considered, where state of the edge and the overall size of imperfections have high influence on product quality. Finding and using a set of features that accurately describes the differences between the edge that is acceptable or too damaged is not always straightforward. The presented approach focuses on detailed evaluation of various feature extraction approaches. Each chosen method produced a set of features, which was then used to train a selected set of classifiers. Five initial feature sets were obtained, and additional ones were derived from them. Different voting methods were used for ensemble approaches. In total, 38 versions of the classifiers were created and evaluated. Best accuracy was obtained by the ensemble approach based on Weighted Voting methodology. A significant difference was shown between different feature extraction methods, with a total difference of 11.14% between the worst and best feature set, as well as a further 0.2% improvement achieved by using the best voting approach. [ABSTRACT FROM AUTHOR]

Defects or cracks in roads, building walls, floors, and product surfaces can degrade the completeness of the product and become an impediment to quality control. Machine learning can be a solution for detecting defects effectively without human experts; however, the low-power computing device cannot afford that. In this paper, we suggest a crack detection system accelerated by edge computing. Our system consists of two: Rsef and Rsef-Edge. Rsef is a real-time segmentation method based on effective feature extraction that can perform crack image segmentation by optimizing conventional deep learning models. Then, we construct the edge-based system, named Rsef-Edge, to significantly decrease the inference time of Rsef, even in low-power IoT devices. As a result, we show both a fast inference time and good accuracy even in a low-powered computing environment. [ABSTRACT FROM AUTHOR]

To extract the phase information from multiple receivers, the conventional sound source localization system involves substantial complexity in software and hardware. Along with the algorithm complexity, the dedicated communication channel and individual analog-to-digital conversions prevent an increase in the system's capability due to feasibility. The previous study suggested and verified the single-channel sound source localization system, which aggregates the receivers on the single analog network for the single digital converter. This paper proposes the improved algorithm for the single-channel sound source localization system based on the Gaussian process regression with the novel feature extraction method. The proposed system consists of three computational stages: homomorphic deconvolution, feature extraction, and Gaussian process regression in cascade. The individual stages represent time delay extraction, data arrangement, and machine prediction, respectively. The optimal receiver configuration for the three-receiver structure is derived from the novel similarity matrix analysis based on the time delay pattern diversity. The simulations and experiments present precise predictions with proper model order and ensemble average length. The nonparametric method, with the rational quadratic kernel, shows consistent performance on trained angles. The Steiglitz–McBride model with the exponential kernel delivers the best predictions for trained and untrained angles with low bias and low variance in statistics. [ABSTRACT FROM AUTHOR]

In recent years, massive development in the malware industry changed the entire landscape for malware development. Therefore, cybercriminals became more sophisticated by advancing their development techniques from file-based to fileless malware. As file-based malware depends on files to spread itself, on the other hand, fileless malware does not require a traditional file system and uses benign processes to carry out its malicious intent. Therefore, it evades conventional detection techniques and remains stealthy. This paper briefly explains fileless malware, its life cycle, and its infection chain. Moreover, it proposes a detection technique based on feature analysis using machine learning for fileless malware detection. The virtual machine acquired the memory dumps upon executing the malicious and non-malicious samples. Then the necessary features are extracted using the Volatility memory forensics tool, which is then analyzed using machine learning classification algorithms. After that, the best algorithm is selected based on the k-fold cross-validation score. Experimental evaluation has shown that Random Forest outperforms other machine learning classifiers (Decision Tree, Support Vector Machine, Logistic Regression, K-Nearest Neighbor, XGBoost, and Gradient Boosting). It achieved an overall accuracy of 93.33% with a True Positive Rate (TPR) of 87.5% at zeroFalse Positive Rate (FPR) for fileless malware collected from five widely used datasets (VirusShare, AnyRun, PolySwarm, HatchingTriage, and JoESadbox). [ABSTRACT FROM AUTHOR]

The failure of insulators may seriously threaten the safe operation of the power system, where the state detection of high-voltage insulators is a must for the normal and safe operation of the power system. Based on the data of insulators in aerial images, this work explored an enhanced particle swarm algorithm to optimize the parameters of the support vector machine. A support vector machine model was therefore established for the identification of the normal and defective states of the insulators. This methodology works with the structure minimization principle of SVM and the characteristics of particle swarm fast optimization. First, the aerial insulator image was segmented as a target by way of the seed region growth based on double-layer cascade morphological improvements, and then, HOG features plus GLCM features were extracted as sample data. Finally, an ameliorated PSO-SVM classifier was designed to realize insulator state identification. Comparisons were made between PSO-SVM and conventional machine learning algorithms, SVM and Random Forest, and an optimization algorithm, Gray Wolf Optimization Support Vector Machine (GWO-SVM), and advanced neural network CNN. The experimental results showed that the performance of the algorithm proposed in this paper touched the top level, where the recognition accuracy rate was 92.11%, the precision rate 90%, the recall rate 94.74%, and the F1-score 92.31%. [ABSTRACT FROM AUTHOR]

Indoor 3D positioning is useful in multistory buildings, such as shopping malls, libraries, and airports. This study focuses on indoor 3D positioning using wireless access points (AP) in an environment without adding additional hardware facilities in large-scale complex places. The integration of a deep learning algorithm into indoor 3D positioning is studied, and a 3D dynamic positioning model based on temporal fingerprints is proposed. In contrast to the traditional positioning models with a single input, the proposed method uses a sliding time window to build a temporal fingerprint chip as the input of the positioning model to provide abundant information for positioning. Temporal information can be used to distinguish locations with similar fingerprint vectors and to improve the accuracy and robustness of positioning. Moreover, deep learning has been applied for the automatic extraction of spatiotemporal features. A temporal convolutional network (TCN) feature extractor is proposed in this paper, which adopts a causal convolution mechanism, dilated convolution mechanism, and residual connection mechanism and is not limited by the size of the convolution kernel. It is capable of learning hidden information and spatiotemporal relationships from the input features and the extracted spatiotemporal features are connected with a deep neural network (DNN) regressor to fit the complex nonlinear mapping relationship between the features and position coordinates to estimate the 3D position coordinates of the target. Finally, an open-source public dataset was used to verify the performance of the localization algorithm. Experimental results demonstrated the effectiveness of the proposed positioning model and a comparison between the proposed model and existing models proved that the proposed model can provide more accurate three-dimensional position coordinates. [ABSTRACT FROM AUTHOR]

Landslide susceptibility mapping (LSM) is of great significance for the identification and prevention of geological hazards. LSM is based on convolutional neural networks (CNNs); CNNs use fixed convolutional kernels, focus more on local information and do not retain spatial information. This is a property of the CNN itself, resulting in low accuracy of LSM. Based on the above problems, we use Vision Transformer (ViT) and its derivative model Swin Transformer (Swin) to conduct LSM for the selected study area. Machine learning and a CNN model are used for comparison. Fourier transform amplitude, feature similarity and other indicators were used to compare and analyze the difference in the results. The results show that the Swin model has the best accuracy, F1-score and AUC. The results of LSM are combined with landslide points, faults and other data analysis; the ViT model results are the most consistent with the actual situation, showing the strongest generalization ability. In this paper, we believe that the advantages of ViT and its derived models in global feature extraction ensure that ViT is more accurate than CNN and machine learning in predicting landslide probability in the study area. [ABSTRACT FROM AUTHOR]

In the machine learning and data science pipelines, feature extraction is considered the most crucial component according to researchers, where generating a discriminative feature matrix is the utmost challenging task to achieve high classification accuracy. Generally, the classical feature extraction techniques are sensitive to the noisy component of the signal and need more time for training. To deal with these issues, a comparatively new feature extraction technique, referred to as a wavelet scattering transform (WST) is utilized, and incorporated with ML classifiers to design a framework for bearing fault classification in this paper. The WST is a knowledge-based technique, and the structure is similar to the convolution neural network. This technique provides low-variance features of real-valued signals, which are usually necessary for classification tasks. These signals are resistant to signal deformation and preserve information at high frequencies. The current signal data from a publicly available dataset for three different bearing conditions are considered. By combining the scattering path coefficients, the decomposition coefficients from the 0th and 1st layers are considered as features. The experimental results demonstrate that WST-based features, when used with ensemble ML algorithms, could achieve more than 99% classification accuracy. The performance of ANN models with these features is similar. This work exhibits that utilizing WST coefficients for the motor current signal as features can improve the bearing fault classification accuracy when compared to other feature extraction approaches such as empirical wavelet transform (EWT), information fusion (IF), and wavelet packet decomposition (WPD). Thus, our proposed approach can be considered as an effective classification method for the fault diagnosis of rotating machinery. [ABSTRACT FROM AUTHOR]

The perception of hunger and satiety is of great importance to maintaining a healthy body weight and avoiding chronic diseases such as obesity, underweight, or deficiency syndromes due to malnutrition. There are a number of disease patterns, characterized by a chronic loss of this perception. To our best knowledge, hunger and satiety cannot be classified using non-invasive measurements. Aiming to develop an objective classification system, this paper presents a multimodal sensory system using associated signal processing and pattern recognition methods for hunger and satiety detection based on non-invasive monitoring. We used an Empatica E4 smartwatch, a RespiBan wearable device, and JINS MEME smart glasses to capture physiological signals from five healthy normal weight subjects inactively sitting on a chair in a state of hunger and satiety. After pre-processing the signals, we compared different feature extraction approaches, either based on manual feature engineering or deep feature learning. Comparative experiments were carried out to determine the most appropriate sensor channel, device, and classifier to reliably discriminate between hunger and satiety states. Our experiments showed that the most discriminative features come from three specific sensor modalities: Electrodermal Activity (EDA), infrared Thermopile (Tmp), and Blood Volume Pulse (BVP). [ABSTRACT FROM AUTHOR]

A good approximation to power amplifier (PA) behavioral modeling requires precise baseband models to mitigate nonlinearities. Since digital predistortion (DPD) is used to provide the PA linearization, a framework is necessary to validate the modeling figures of merit support under signal conditioning and transmission restrictions. A field-programmable gate array (FPGA)-based testbed is developed to measure the wide-band PA behavior using a single-carrier 64-quadrature amplitude modulation (QAM) multiplexed by orthogonal frequency-division multiplexing (OFDM) based on long-term evolution (LTE) as a stimulus, with different bandwidths signals. In the search to provide a heuristic target approach modeling, this paper introduces a feature extraction concept to find an appropriate complexity solution considering the high sparse data issue in amplitude to amplitude (AM-AM) and amplitude to phase AM-PM models extraction, whose penalties are associated with overfitting and hardware complexity in resulting functions. Thus, experimental results highlight the model performance for a high sparse data regime and are compared with a regression tree (RT), random forest (RF), and cubic-spline (CS) model accuracy capabilities for the signal conditioning to show a reliable validation, low-complexity, according to the peak-to-average power ratio (PAPR), complementary cumulative distribution function (CCDF), coefficients extraction, normalized mean square error (NMSE), and execution time figures of merit. The presented models provide a comparison with original data that aid to compare the dimension and robustness for each surrogate model where (i) machine learning (ML)-based and (ii) CS interpolate-based where high sparse data are present, NMSE between the CS interpolated based are also compared to demonstrate the efficacy in the prediction methods with lower convergence times and complexities. [ABSTRACT FROM AUTHOR]

Domestic trash detection is an essential technology toward achieving a smart city. Due to the complexity and variability of urban trash scenarios, the existing trash detection algorithms suffer from low detection rates and high false positives, as well as the general problem of slow speed in industrial applications. This paper proposes an i-YOLOX model for domestic trash detection based on deep learning algorithms. First, a large number of real-life trash images are collected into a new trash image dataset. Second, the lightweight operator involution is incorporated into the feature extraction structure of the algorithm, which allows the feature extraction layer to establish long-distance feature relationships and adaptively extract channel features. In addition, the ability of the model to distinguish similar trash features is strengthened by adding the convolutional block attention module (CBAM) to the enhanced feature extraction network. Finally, the design of the involution residual head structure in the detection head reduces the gradient disappearance and accelerates the convergence of the model loss values allowing the model to perform better classification and regression of the acquired feature layers. In this study, YOLOX-S is chosen as the baseline for each enhancement experiment. The experimental results show that compared with the baseline algorithm, the mean average precision (mAP) of i-YOLOX is improved by 1.47%, the number of parameters is reduced by 23.3%, and the FPS is improved by 40.4%. In practical applications, this improved model achieves accurate recognition of trash in natural scenes, which further validates the generalization performance of i-YOLOX and provides a reference for future domestic trash detection research. [ABSTRACT FROM AUTHOR]

Non-surfacing leaks constitute the dominant source of water losses for utilities worldwide. This paper presents advanced data-driven analysis methods for leak monitoring using commercial field-deployable semi-permanent vibro-acoustic sensors, evaluated on live data collected from extensive multi-sensor deployments across a sprawling metropolitan city. This necessarily includes a wide variety of pipeline sizes, materials and surrounding soils, as well as leak sources and rates brought about by external factors. The novel proposition for structural pipe health monitoring shows that excellent leak/no-leak classification results (>94% accuracy) can be observed using Convolutional Neural Networks (CNNs) trained with Short-Time Fourier Transforms (STFTs) of the raw audio files. Most notably, it is shown how this can be achieved irrespective of the sensor used, with four models from different manufactures being part of the investigation, and over time across extended densely populated areas. [ABSTRACT FROM AUTHOR]

The timely detection of equipment failure can effectively avoid industrial safety accidents. The existing equipment fault diagnosis methods based on single-mode signal not only have low accuracy, but also have the inherent risk of being misled by signal noise. In this paper, we reveal the possibility of using multi-modal monitoring data to improve the accuracy of equipment fault prediction. The main challenge of multi-modal data fusion is how to effectively fuse multi-modal data to improve the accuracy of fault prediction. We propose a multi-modal learning framework for fusion of low-quality monitoring data and high-quality monitoring data. In essence, low-quality monitoring data are used as a compensation for high-quality monitoring data. Firstly, the low-quality monitoring data is optimized, and then the features are extracted. At the same time, the high-quality monitoring data is dealt with by a low complexity convolutional neural network. Moreover, the robustness of the multi-modal learning algorithm is guaranteed by adding noise to the high-quality monitoring data. Finally, different dimensional features are projected into a common space to obtain accurate fault sample classification. Experimental results and performance analysis confirm the superiority of the proposed algorithm. Compared with the traditional feature concatenation method, the prediction accuracy of the proposed multi-modal learning algorithm can be improved by up to 7.42%. [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]

This paper proposed a new depth of anaesthesia (DoA) index for the real-time assessment of DoA using electroencephalography (EEG). In the proposed new DoA index, a wavelet transform threshold was applied to denoise raw EEG signals, and five features were extracted to construct classification models. Then, the Gaussian process regression model was employed for real-time assessment of anaesthesia states. The proposed real-time DoA index was implemented using a sliding window technique and validated using clinical EEG data recorded with the most popular commercial DoA product Bispectral Index monitor (BIS). The results are evaluated using the correlation coefficients and Bland–Altman methods. The outcomes show that the highest and the average correlation coefficients are 0.840 and 0.814, respectively, in the testing dataset. Meanwhile, the scatter plot of Bland–Altman shows that the agreement between BIS and the proposed index is 94.91%. In contrast, the proposed index is free from the electromyography (EMG) effect and surpasses the BIS performance when the signal quality indicator (SQI) is lower than 15, as the proposed index can display high correlation and reliable assessment results compared with clinic observations. [ABSTRACT FROM AUTHOR]

With the development of 5G and network technology, the usage of IoT devices has become popular. Because most of these IoT devices can be controlled by an adversary away from the administrator, several security issues such as firmware dumping can arise. Firmware dumping is the cornerstone or goal of many types of hardware hacking. Therefore, many IoT device manufacturers adopt some protection mechanisms such as the restriction of hardware debuggers. However, several recent studies have shown that the operating instructions of an IoT device can be recovered through the profiling-based side-channel analysis. The Side-Channel-Based Disassembler (SCBD) refers to software that recovers instructions of the device only from the side-channel signal. The SCBD is powerful enough to defeat many firmware protection mechanisms. In this paper, we show how an adversary can build an instruction (opcode)-level disassembler using the power consumption signal of commercial microcontrollers (MCUs) such as the 8-bit ATxmega128 and 32-bit STM32F0. To implement the SCBD, we elaborately constructed the instruction template considering the pipeline of the target MCUs through instruction sequence analysis. Furthermore, we preprocessed the side-channel signals using the Continuous Wavelet Transform (CWT) for noise reduction and Kullback-Leibler Divergence (KLD) for instruction feature extraction. Our experimental results show that the machine-learning-based instruction disassembling models can recover the operating instructions with an accuracy of about 91.9% and 98.6% for the ATxmega128 and STM32F0, respectively. Furthermore, we achieved an accuracy of 77% and 96.5% in a cross-board validation. [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]

In recent years, much effort has been devoted to the development of applications capable of detecting different types of human activity. In this field, fall detection is particularly relevant, especially for the elderly. On the one hand, some applications use wearable sensors that are integrated into cell phones, necklaces or smart bracelets to detect sudden movements of the person wearing the device. The main drawback of these types of systems is that these devices must be placed on a person's body. This is a major drawback because they can be uncomfortable, in addition to the fact that these systems cannot be implemented in open spaces and with unfamiliar people. In contrast, other approaches perform activity recognition from video camera images, which have many advantages over the previous ones since the user is not required to wear the sensors. As a result, these applications can be implemented in open spaces and with unknown people. This paper presents a vision-based algorithm for activity recognition. The main contribution of this work is to use human skeleton pose estimation as a feature extraction method for activity detection in video camera images. The use of this method allows the detection of multiple people's activities in the same scene. The algorithm is also capable of classifying multi-frame activities, precisely for those that need more than one frame to be detected. The method is evaluated with the public UP-FALL dataset and compared to similar algorithms using the same dataset. [ABSTRACT FROM AUTHOR]