Search

Deep learning has recently made significant progress in semantic segmentation. However, the current methods face critical challenges. The segmentation process often lacks sufficient contextual information and attention mechanisms, low-level features lack semantic richness, and high-level features suffer from poor resolution. These limitations reduce the model's ability to accurately understand and process scene details, particularly in complex scenarios, leading to segmentation outputs that may have inaccuracies in boundary delineation, misclassification of regions, and poor handling of small or overlapping objects. To address these challenges, this paper proposes a Semantic Segmentation Network Based on Adaptive Attention and Deep Fusion with the Multi-Scale Dilated Convolutional Pyramid (SDAMNet). Specifically, the Dilated Convolutional Atrous Spatial Pyramid Pooling (DCASPP) module is developed to enhance contextual information in semantic segmentation. Additionally, a Semantic Channel Space Details Module (SCSDM) is devised to improve the extraction of significant features through multi-scale feature fusion and adaptive feature selection, enhancing the model's perceptual capability for key regions and optimizing semantic understanding and segmentation performance. Furthermore, a Semantic Features Fusion Module (SFFM) is constructed to address the semantic deficiency in low-level features and the low resolution in high-level features. The effectiveness of SDAMNet is demonstrated on two datasets, revealing significant improvements in Mean Intersection over Union (MIOU) by 2.89% and 2.13%, respectively, compared to the Deeplabv3+ network. [ABSTRACT FROM AUTHOR]

The method of acoustic radiation signal detection not only enables contactless measurement but also provides comprehensive state information during equipment operation. This paper proposes an enhanced feature extraction network (EFEN) for fault diagnosis of rolling bearings based on acoustic signal feature learning. The EFEN network comprises four main components: the data preprocessing module, the information feature selection module (IFSM), the channel attention mechanism module (CAMM), and the convolutional neural network module (CNNM). Firstly, the one-dimensional acoustic signal is transformed into a two-dimensional grayscale image. Then, IFSM utilizes three different-sized convolution filters to process input image data and fuse and assign weights to feature information that can attenuate noise while highlighting effective fault information. Next, a channel attention mechanism module is introduced to assign weights to each channel. Finally, the convolutional neural network (CNN) fault diagnosis module is employed for accurate classification of rolling bearing faults. Experimental results demonstrate that the EFEN network achieves high accuracy in fault diagnosis and effectively detects rolling bearing faults based on acoustic signals. The proposed method achieves an accuracy of 98.52%, surpassing other methods in terms of performance. In comparative analysis of antinoise experiments, the average accuracy remains remarkably high at 96.62%, accompanied by a significantly reduced average iteration time of only 0.25 s. Furthermore, comparative analysis confirms that the proposed algorithm exhibits excellent accuracy and resistance against noise. [ABSTRACT FROM AUTHOR]

Effective feature extraction and selection are crucial for the accurate classification and prediction of hand gestures based on electromyographic signals. In this paper, we systematically compare six filter and wrapper feature evaluation methods and investigate their respective impacts on the accuracy of gesture recognition. The investigation is based on several benchmark datasets and one real hand gesture dataset, including 15 hand force exercises collected from 14 healthy subjects using eight commercial sEMG sensors. A total of 37 time- and frequency-domain features were extracted from each sEMG channel. The benchmark dataset revealed that the minimum Redundancy Maximum Relevance (mRMR) feature evaluation method had the poorest performance, resulting in a decrease in classification accuracy. However, the RFE method demonstrated the potential to enhance classification accuracy across most of the datasets. It selected a feature subset comprising 65 features, which led to an accuracy of 97.14%. The Mutual Information (MI) method selected 200 features to reach an accuracy of 97.38%. The Feature Importance (FI) method reached a higher accuracy of 97.62% but selected 140 features. Further investigations have shown that selecting 65 and 75 features with the RFE methods led to an identical accuracy of 97.14%. A thorough examination of the selected features revealed the potential for three additional features from three specific sensors to enhance the classification accuracy to 97.38%. These results highlight the significance of employing an appropriate feature selection method to significantly reduce the number of necessary features while maintaining classification accuracy. They also underscore the necessity for further analysis and refinement to achieve optimal solutions. [ABSTRACT FROM AUTHOR]

During robot-assisted rehabilitation, failure to recognize lower limb movement may efficiently limit the development of exoskeleton robots, especially for individuals with knee pathology. A major challenge encountered with surface electromyography (sEMG) signals generated by lower limb movements is variability between subjects, such as motion patterns and muscle structure. To this end, this paper proposes an sEMG-based lower limb motion recognition using an improved support vector machine (SVM). Firstly, non-negative matrix factorization (NMF) is leveraged to analyze muscle synergy for multi-channel sEMG signals. Secondly, the multi-nonlinear sEMG features are extracted, which reflect the complexity of muscle status change during various lower limb movements. The Fisher discriminant function method is utilized to perform feature selection and reduce feature dimension. Then, a hybrid genetic algorithm-particle swarm optimization (GA-PSO) method is leveraged to determine the best parameters for SVM. Finally, the experiments are carried out to distinguish 11 healthy and 11 knee pathological subjects by performing three different lower limb movements. Results demonstrate the effectiveness and feasibility of the proposed approach in three different lower limb movements with an average accuracy of 96.03% in healthy subjects and 93.65% in knee pathological subjects, respectively. [ABSTRACT FROM AUTHOR]

Click-through rate prediction is a critical task for computational advertising and recommendation systems, where the key challenge is to model feature interactions between different feature domains. At present, the main click-through rate prediction models model feature interactions in an implicit way, which leads to poor interpretation of the model, and the interaction between each pair of features may introduce noise into the model, thus limiting the predictive ability of the model. In response to the above problems, this paper proposes a click-through rate prediction model (GAIAN) based on the graph attention interactive aggregation network, which explicitly obtains cross features on the graph structure. Our specific method is to design a feature interactive selection mechanism to select cross features that are beneficial to model prediction, reducing model noise and reducing the risk of model overfitting. On this basis, the bilinear interaction function is integrated into the aggregation strategy of the graph neural network, and the fine-grained intersection features are extracted in a flexible and explicit way, which makes graph neural networks more suitable for modeling feature interactions and enhances the interpretability of the model. Compared with several other state-of-the-art models on the Criteo and Avazu datasets, the experimental results show the superiority of the model. [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 traditional Transformer model primarily employs a self-attention mechanism to capture global feature relationships, potentially overlooking local relationships within sequences and thus affecting the modeling capability of local features. For Support Vector Machine (SVM), it often requires the joint use of feature selection algorithms or model optimization methods to achieve maximum classification accuracy. Addressing the issues in both models, this paper introduces a novel network framework, CTSF, specifically designed for Industrial Internet intrusion detection. CTSF effectively addresses the limitations of traditional Transformers in extracting local features while compensating for the weaknesses of SVM. The framework comprises a pre-training component and a decision-making component. The pre-training section consists of both CNN and an enhanced Transformer, designed to capture both local and global features from input data while reducing data feature dimensions. The improved Transformer simultaneously decreases certain training parameters within CTSF, making it more suitable for the Industrial Internet environment. The classification section is composed of SVM, which receives initial classification data from the pre-training phase and determines the optimal decision boundary. The proposed framework is evaluated on an imbalanced subset of the X-IIOTID dataset, which represent Industrial Internet data. Experimental results demonstrate that with SVM using both "linear" and "rbf" kernel functions, CTSF achieves an overall accuracy of 0.98875 and effectively discriminates minor classes, showcasing the superiority of this framework. [ABSTRACT FROM AUTHOR]

The utilization of multiscale entropy methods to characterize vibration signals has proven to be promising in intelligent diagnosis of mechanical equipment. However, in the current multiscale entropy methods, only the information in the low-frequency range is utilized and the information in the high-frequency range is discarded. In order to take full advantage of the information, in this paper, a fault feature extraction method utilizing the bidirectional composite coarse-graining process with fuzzy dispersion entropy is proposed. To avoid the redundancy of the full frequency range feature information, the Random Forest algorithm combined with the Maximum Relevance Minimum Redundancy algorithm is applied to feature selection. Together with the K-nearest neighbor classifier, a rolling bearing intelligent diagnosis framework is constructed. The effectiveness of the proposed framework is evaluated by a numerical simulation and two experimental examples. The validation results demonstrate that the extracted features by the proposed method are highly sensitive to the bearing health conditions compared with hierarchical fuzzy dispersion entropy, composite multiscale fuzzy dispersion entropy, multiscale fuzzy dispersion entropy, multiscale dispersion entropy, multiscale permutation entropy, and multiscale sample entropy. In addition, the proposed method is able to identify the fault categories and health states of rolling bearings simultaneously. The proposed damage detection methodology provides a new and better framework for intelligent fault diagnosis of rolling bearings in rotating machinery. [ABSTRACT FROM AUTHOR]

Multi-source information fusion technology is a kind of information processing technology which comprehensively processes and utilizes multi-source uncertain information. It is an effective scheme to solve complex pattern recognition and improve classification performance. This study aims to improve the accuracy and robustness of exoskeleton gait pattern transition recognition in complex environments. Based on the theory of multi-source information fusion, this paper explored a multi-source information fusion model for exoskeleton gait pattern transition recognition in terms of two aspects of multi-source information fusion strategy and multi-classifier fusion. For eight common gait pattern transitions (between level and stair walking and between level and ramp walking), we proposed a hybrid fusion strategy of multi-source information at the feature level and decision level. We first selected an optimal feature subset through correlation feature extraction and feature selection algorithm, followed by the feature fusion through the classifier. We then studied the construction of a multi-classifier fusion model with a focus on the selection of base classifier and multi-classifier fusion algorithm. By analyzing the classification performance and robustness of the multi-classifier fusion model integrating multiple classifier combinations with a number of multi-classifier fusion algorithms, we finally constructed a multi-classifier fusion model based on D-S evidence theory and the combination of three SVM classifiers with different kernel functions (linear, RBF, polynomial). Such multi-source information fusion model improved the anti-interference and fault tolerance of the model through the hybrid fusion strategy of feature level and decision level and had higher accuracy and robustness in the gait pattern transition recognition, whose average recognition accuracy for eight gait pattern transitions reached 99.70%, which increased by 0.15% compared with the highest average recognition accuracy of the single classifier. Moreover, the average recognition accuracy in the absence of different feature data reached 97.47% with good robustness. [ABSTRACT FROM AUTHOR]

In order to improve the accuracy of predicting the remaining electrical life of AC circuit breakers, ensure the safe operation of electrical equipment, and reduce economic losses caused by equipment failures, this paper studies a method based on the Savitzky–Golay convolution smoothing long short-term memory neural network for predicting the electrical life of AC circuit breakers. First, a full lifespan test is conducted to obtain degradation data throughout the entire life cycle of the AC circuit breaker, from which feature parameters that effectively reflect its operational state are extracted. Next, principal component analysis and the maximum information coefficient are used to remove redundancy in the feature parameters and choose the best subset of features. Subsequently, the Savitzky–Golay convolutional smoothing algorithm is employed to smooth the feature sequence, reducing the impact of noise and outliers on the feature sequence while preserving its main trends. Then, a secondary feature extraction is performed on the smoothed feature subset to obtain the optimal secondary feature subset. Finally, the remaining electrical lifespan of the AC circuit breaker is treated as a long-term sequence problem and the long short-term memory neural network method is used for precise time-series forecasting. The proposed model outperforms backpropagation neural networks and the gate recurrent unit in terms of prediction precision, achieving an impressive 97.4% accuracy. This demonstrates the feasibility of using time-series forecasting for predicting the residual electrical lifespan of electrical equipment and provides a reference for optimizing the method of predicting remaining electrical life. [ABSTRACT FROM AUTHOR]

Timely preterm labor prediction plays an important role for increasing the chance of neonate survival, the mother's mental health, and reducing financial burdens imposed on the family. The objective of this study is to propose a method for the reliable prediction of preterm labor from the electrohysterogram (EHG) signals based on different pregnancy weeks. In this paper, EHG signals recorded from 300 subjects were split into 2 groups: (I) those with preterm and term labor EHG data that were recorded prior to the 26th week of pregnancy (referred to as the PE-TE group), and (II) those with preterm and term labor EHG data that were recorded after the 26th week of pregnancy (referred to as the PL-TL group). After decomposing each EHG signal into four intrinsic mode functions (IMFs) by empirical mode decomposition (EMD), several linear and nonlinear features were extracted. Then, a self-adaptive synthetic over-sampling method was used to balance the feature vector for each group. Finally, a feature selection method was performed and the prominent ones were fed to different classifiers for discriminating between term and preterm labor. For both groups, the AdaBoost classifier achieved the best results with a mean accuracy, sensitivity, specificity, and area under the curve (AUC) of 95%, 92%, 97%, and 0.99 for the PE-TE group and a mean accuracy, sensitivity, specificity, and AUC of 93%, 90%, 94%, and 0.98 for the PL-TL group. The similarity between the obtained results indicates the feasibility of the proposed method for the prediction of preterm labor based on different pregnancy weeks. [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]

There are problems associated with facial expression recognition (FER), such as facial occlusion and head pose variations. These two problems lead to incomplete facial information in images, making feature extraction extremely difficult. Most current methods use prior knowledge or fixed-size patches to perform local cropping, thereby enhancing the ability to acquire fine-grained features. However, the former requires extra data processing work and is prone to errors; the latter destroys the integrity of local features. In this paper, we propose a local Sliding Window Attention Network (SWA-Net) for FER. Specifically, we propose a sliding window strategy for feature-level cropping, which preserves the integrity of local features and does not require complex preprocessing. Moreover, the local feature enhancement module mines fine-grained features with intraclass semantics through a multiscale depth network. The adaptive local feature selection module is introduced to prompt the model to find more essential local features. Extensive experiments demonstrate that our SWA-Net model achieves a comparable performance to that of state-of-the-art methods with scores of 90.03% on RAF-DB, 89.22% on FERPlus, 63.97% on AffectNet. [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]

Corn diseases are one of the significant constraints to high–quality corn production, and accurate identification of corn diseases is of great importance for precise disease control. Corn anthracnose and brown spot are typical diseases of corn, and the early symptoms of the two diseases are similar, which can be easily misidentified by the naked eye. In this paper, to address the above problems, a three–dimensional–two–dimensional (3D–2D) hybrid convolutional neural network (CNN) model combining a band selection module is proposed based on hyperspectral image data, which combines band selection, attention mechanism, spatial–spectral feature extraction, and classification into a unified optimization process. The model first inputs hyperspectral images to both the band selection module and the attention mechanism module and then sums the outputs of the two modules as inputs to a 3D–2D hybrid CNN, resulting in a Y–shaped architecture named Y–Net. The results show that the spectral bands selected by the band selection module of Y–Net achieve more reliable classification performance than traditional feature selection methods. Y–Net obtained the best classification accuracy compared to support vector machines, one–dimensional (1D) CNNs, and two–dimensional (2D) CNNs. After the network pruned the trained Y–Net, the model size was reduced to one–third of the original size, and the accuracy rate reached 98.34%. The study results can provide new ideas and references for disease identification of corn and other crops. [ABSTRACT FROM AUTHOR]

Thermal cameras, as opposed to RBG cameras, work effectively in extremely low illumination situations and can record data outside of the human visual spectrum. For surveillance and security applications, thermal images have several benefits. However, due to the little visual information in thermal images and intrinsic similarity of facial heat maps, completing face identification tasks in the thermal realm is particularly difficult. It can be difficult to attempt identification across modalities, such as when trying to identify a face in thermal images using the ground truth database for the matching visible light domain or vice versa. We proposed a method for detecting objects and actions on thermal human face images, based on the classification of five different features (hat, glasses, rotation, normal, and hat with glasses) in this paper. This model is presented in five steps. To improve the results of feature extraction during the pre-processing step, initially, we resize the images and then convert them to grayscale level using a median filter. In addition, features are extracted from pre-processed images using principle component analysis (PCA). Furthermore, the horse herd optimization algorithm (HOA) is employed for feature selection. Then, to detect the human face in thermal images, the LeNet-5 method is used. It is utilized to detect objects and actions in face areas. Finally, we classify the objects and actions on faces using the ANU-Net approach with the Monarch butterfly optimization (MBO) algorithm to achieve higher classification accuracy. According to experiments using the Terravic Facial Infrared Database, the proposed method outperforms "state-of-the-art" methods for face recognition in thermal images. Additionally, the results for several facial recognition tasks demonstrate good precision. [ABSTRACT FROM AUTHOR]

Activity recognition using wearable sensors has become essential for a variety of applications. Tri-axial accelerometers are the most widely used sensor for activity recognition. Although various features have been used to capture patterns and classify the accelerometer signals to recognise activities, there is no consensus on the best features to choose. Reducing the number of features can reduce the computational cost and complexity and enhance the performance of the classifiers. This paper identifies the signal features that have significant discriminative power between different human activities. It also investigates the effect of sensor placement location, the sampling frequency, and activity complexity on the selected features. A comprehensive list of 193 signal features has been extracted from accelerometer signals of four publicly available datasets, including features that have never been used before for activity recognition. Feature significance was measured using the Joint Mutual Information Maximisation (JMIM) method. Common significant features among all the datasets were identified. The results show that the sensor placement location does not significantly affect recognition performance, nor does it affect the significant sub-set of features. The results also showed that with high sampling frequency, features related to signal repeatability and regularity show high discriminative power. [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]

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]

Human emotions are variant with time, non-stationary, complex in nature, and are invoked as a result of human reactions during our daily lives. Continuously detecting human emotions from one-dimensional EEG signals is an arduous task. This paper proposes an advanced signal processing mechanism for emotion detection from EEG signals using continuous wavelet transform. The space and time components of the raw EEG signals are converted into 2D spectrograms followed by feature extraction. A hybrid spatio-temporal deep neural network is implemented to extract rich features. A differential-based entropy feature selection technique adaptively differentiates features based on entropy, based on low and high information regions. Bag of Deep Features (BoDF) is applied to create clusters of similar features and computes the features vocabularies for reduction of feature dimensionality. Extensive experiments are performed on the SEED dataset, which shows the significance of the proposed method compared to state-of-the-art methods. Specifically, the proposed model achieved 96.7%, 96.2%, 95.8%, and 95.3% accuracy with the SJTU SEED dataset, for SVM, ensemble, tree, and KNN classifiers, respectively. [ABSTRACT FROM AUTHOR]

Wi-Fi fingerprint-based indoor localization methods are effective in static environments but encounter challenges in dynamic, real-world scenarios due to evolving fingerprint patterns and feature spaces. This study investigates the temporal variations in signal strength over a 25-month period to enhance adaptive long-term Wi-Fi localization. Key aspects explored include the significance of signal features, the effects of sampling fluctuations, and overall accuracy measured by mean absolute error. Techniques such as mean-based feature selection, principal component analysis (PCA), and functional discriminant analysis (FDA) were employed to analyze signal features. The proposed algorithm, Ada-LT IP, which incorporates data reduction and transfer learning, shows improved accuracy compared to state-of-the-art methods evaluated in the study. Additionally, the study addresses multicollinearity through PCA and covariance analysis, revealing a reduction in computational complexity and enhanced accuracy for the proposed method, thereby providing valuable insights for improving adaptive long-term Wi-Fi indoor localization systems. [ABSTRACT FROM AUTHOR]

The accuracy of classifying motor imagery (MI) activities is a significant challenge when using brain–computer interfaces (BCIs). BCIs allow people with motor impairments to control external devices directly with their brains using electroencephalogram (EEG) patterns that translate brain activity into control signals. Many researchers have been working to develop MI-based BCI recognition systems using various time-frequency feature extraction and classification approaches. However, the existing systems still face challenges in achieving satisfactory performance due to large amount of non-discriminative and ineffective features. To get around these problems, we suggested a multiband decomposition-based feature extraction and classification method that works well, along with a strong feature selection method for MI tasks. Our method starts by splitting the preprocessed EEG signal into four sub-bands. In each sub-band, we then used a common spatial pattern (CSP) technique to pull out narrowband-oriented useful features, which gives us a high-dimensional feature vector. Subsequently, we utilized an effective feature selection method, Relief-F, which reduces the dimensionality of the final features. Finally, incorporating advanced classification techniques, we classified the final reduced feature vector. To evaluate the proposed model, we used the three different EEG-based MI benchmark datasets, and our proposed model achieved better performance accuracy than existing systems. Our model's strong points include its ability to effectively reduce feature dimensionality and improve classification accuracy through advanced feature extraction and selection methods. [ABSTRACT FROM AUTHOR]

Drowsiness is a main factor for various costly defects, even fatal accidents in areas such as construction, transportation, industry and medicine, due to the lack of monitoring vigilance in the mentioned areas. The implementation of a drowsiness detection system can greatly help to reduce the defects and accident rates by alerting individuals when they enter a drowsy state. This research proposes an electroencephalography (EEG)-based approach for detecting drowsiness. EEG signals are passed through a preprocessing chain composed of artifact removal and segmentation to ensure accurate detection followed by different feature extraction methods to extract the different features related to drowsiness. This work explores the use of various machine learning algorithms such as Support Vector Machine (SVM), the K nearest neighbor (KNN), the Naive Bayes (NB), the Decision Tree (DT), and the Multilayer Perceptron (MLP) to analyze EEG signals sourced from the DROZY database, carefully labeled into two distinct states of alertness (awake and drowsy). Segmentation into 10 s intervals ensures precise detection, while a relevant feature selection layer enhances accuracy and generalizability. The proposed approach achieves high accuracy rates of 99.84% and 96.4% for intra (subject by subject) and inter (cross-subject) modes, respectively. SVM emerges as the most effective model for drowsiness detection in the intra mode, while MLP demonstrates superior accuracy in the inter mode. This research offers a promising avenue for implementing proactive drowsiness detection systems to enhance occupational safety across various industries. [ABSTRACT FROM AUTHOR]

A motor imagery brain–computer interface connects the human brain and computers via electroencephalography (EEG). However, individual differences in the frequency ranges of brain activity during motor imagery tasks pose a challenge, limiting the manual feature extraction for motor imagery classification. To extract features that match specific subjects, we proposed a novel motor imagery classification model using distinctive feature fusion with adaptive structural LASSO. Specifically, we extracted spatial domain features from overlapping and multi-scale sub-bands of EEG signals and mined discriminative features by fusing the task relevance of features with spatial information into the adaptive LASSO-based feature selection. We evaluated the proposed model on public motor imagery EEG datasets, demonstrating that the model has excellent performance. Meanwhile, ablation studies and feature selection visualization of the proposed model further verified the great potential of EEG analysis. [ABSTRACT FROM AUTHOR]

The machines of WF Maschinenbau process metal blanks into various workpieces using so-called flow-forming processes. The quality of these workpieces depends largely on the quality of the blanks and the condition of the machine. This creates an urgent need for automated monitoring of the forming processes and the condition of the machine. Since the complexity of the flow-forming processes makes physical modeling impossible, the present work deals with data-driven modeling using machine learning algorithms. The main contributions of this work lie in showcasing the feasibility of utilizing machine learning and sensor data to monitor flow-forming processes, along with developing a practical approach for this purpose. The approach includes an experimental design capable of providing the necessary data, as well as a procedure for preprocessing the data and extracting features that capture the information needed by the machine learning models to detect defects in the blank and the machine. To make efficient use of the small number of experiments available, the experimental design is generated using Design of Experiments methods. They consist of two parts. In the first part, a pre-selection of influencing variables relevant to the forming process is performed. In the second part of the design, the selected variables are investigated in more detail. The preprocessing procedure consists of feature engineering, feature extraction and feature selection. In the feature engineering step, the data set is augmented with time series variables that are meaningful in the domain. For feature extraction, an algorithm was developed based on the mechanisms of the r-STSF, a state-of-the-art algorithm for time series classification, extending them for multivariate time series and metric target variables. This feature extraction algorithm itself can be seen as an additional contribution of this work, because it is not tied to the application domain of monitoring flow-forming processes, but can be used as a feature extraction algorithm for multivariate time series classification in general. For feature selection, a Recursive Feature Elimination is employed. With the resulting features, random forests are trained to detect several quality features of the blank and defects of the machine. The trained models achieve good prediction accuracy for most of the target variables. This shows that the application of machine learning is a promising approach for the monitoring of flow-forming processes, which requires further investigation for confirmation. [ABSTRACT FROM AUTHOR]

Japanese Sign Language (JSL) is vital for communication in Japan's deaf and hard-of-hearing community. But probably because of the large number of patterns, 46 types, there is a mixture of static and dynamic, and the dynamic ones have been excluded in most studies. Few researchers have been working to develop a dynamic JSL alphabet, and their performance accuracy is unsatisfactory. We proposed a dynamic JSL recognition system using effective feature extraction and feature selection approaches to overcome the challenges. In the procedure, we follow the hand pose estimation, effective feature extraction, and machine learning techniques. We collected a video dataset capturing JSL gestures through standard RGB cameras and employed MediaPipe for hand pose estimation. Four types of features were proposed. The significance of these features is that the same feature generation method can be used regardless of the number of frames or whether the features are dynamic or static. We employed a Random forest (RF) based feature selection approach to select the potential feature. Finally, we fed the reduced features into the kernels-based Support Vector Machine (SVM) algorithm classification. Evaluations conducted on our proprietary newly created dynamic Japanese sign language alphabet dataset and LSA64 dynamic dataset yielded recognition accuracies of 97.20% and 98.40%, respectively. This innovative approach not only addresses the complexities of JSL but also holds the potential to bridge communication gaps, offering effective communication for the deaf and hard-of-hearing, and has broader implications for sign language recognition systems globally. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) based on wearable sensors has emerged as a low-cost key-enabling technology for applications such as human–computer interaction and healthcare. In wearable sensor-based HAR, deep learning is desired for extracting human active features. Due to the spatiotemporal dynamic of human activity, a special deep learning network for recognizing the temporal continuous activities of humans is required to improve the recognition accuracy for supporting advanced HAR applications. To this end, a residual multifeature fusion shrinkage network (RMFSN) is proposed. The RMFSN is an improved residual network which consists of a multi-branch framework, a channel attention shrinkage block (CASB), and a classifier network. The special multi-branch framework utilizes a 1D-CNN, a lightweight temporal attention mechanism, and a multi-scale feature extraction method to capture diverse activity features via multiple branches. The CASB is proposed to automatically select key features from the diverse features for each activity, and the classifier network outputs the final recognition results. Experimental results have shown that the accuracy of the proposed RMFSN for the public datasets UCI-HAR, WISDM, and OPPORTUNITY are 98.13%, 98.35%, and 93.89%, respectively. In comparison with existing advanced methods, the proposed RMFSN could achieve higher accuracy while requiring fewer model parameters. [ABSTRACT FROM AUTHOR]

Hydraulic multi-way valves as core components are widely applied in engineering machinery, mining machinery, and metallurgical industries. Due to the harsh working environment, faults in hydraulic multi-way valves are prone to occur, and the faults that occur are hidden. Moreover, hydraulic multi-way valves are expensive, and multiple experiments are difficult to replicate to obtain true fault data. Therefore, it is not easy to achieve fault diagnosis of hydraulic multi-way valves. To address this problem, an effective intelligent fault diagnosis method is proposed using an improved Squeeze-Excitation Convolution Neural Network and Gated Recurrent Unit (SECNN-GRU). The effectiveness of the method is verified by designing a simulation model for a hydraulic multi-way valve to generate fault data, as well as the actual data obtained by establishing an experimental platform for a directional valve. In this method, shallow statistical features are first extracted from data containing fault information, and then fault features with high correlation with fault types are selected using the Maximum Relevance Minimum Redundancy algorithm (mRMR). Next, spatial dimension features are extracted through CNN. By adding the Squeeze-Excitation Block, different weights are assigned to features to obtain weighted feature vectors. Finally, the time-dimension features of the weighted feature vectors are extracted and fused through GRU, and the fused features are classified using a classifier. The fault data obtained from the simulation model verifies that the average diagnostic accuracy of this method can reach 98.94%. The average accuracy of this method can reach 92.10% (A1 sensor as an example) through experimental data validation of the directional valve. Compared with other intelligent diagnostic algorithms, the proposed method has better stationarity and higher diagnostic accuracy, providing a feasible solution for fault diagnosis of the hydraulic multi-way valve. [ABSTRACT FROM AUTHOR]

Recently, deep models have been very popular because they achieve excellent performance with many classification problems. Deep networks have high computational complexities and require specific hardware. To overcome this problem (without decreasing classification ability), a hand-modeled feature selection method is proposed in this paper. A new shape-based local feature extractor is presented which uses the geometric shape of the frustum. By using a frustum pattern, textural features are generated. Moreover, statistical features have been extracted in this model. Textures and statistics features are fused, and a hybrid feature extraction phase is obtained; these features are low-level. To generate high level features, tunable Q factor wavelet transform (TQWT) is used. The presented hybrid feature generator creates 154 feature vectors; hence, it is named Frustum154. In the multilevel feature creation phase, this model can select the appropriate feature vectors automatically and create the final feature vector by merging the appropriate feature vectors. Iterative neighborhood component analysis (INCA) chooses the best feature vector, and shallow classifiers are then used. Frustum154 has been tested on three basic hand-movement sEMG datasets. Hand-movement sEMG datasets are commonly used in biomedical engineering, but there are some problems in this area. The presented models generally required one dataset to achieve high classification ability. In this work, three sEMG datasets have been used to test the performance of Frustum154. The presented model is self-organized and selects the most informative subbands and features automatically. It achieved 98.89%, 94.94%, and 95.30% classification accuracies using shallow classifiers, indicating that Frustum154 can improve classification accuracy. [ABSTRACT FROM AUTHOR]

After lung cancer, breast cancer is the second leading cause of death in women. If breast cancer is detected early, mortality rates in women can be reduced. Because manual breast cancer diagnosis takes a long time, an automated system is required for early cancer detection. This paper proposes a new framework for breast cancer classification from ultrasound images that employs deep learning and the fusion of the best selected features. The proposed framework is divided into five major steps: (i) data augmentation is performed to increase the size of the original dataset for better learning of Convolutional Neural Network (CNN) models; (ii) a pre-trained DarkNet-53 model is considered and the output layer is modified based on the augmented dataset classes; (iii) the modified model is trained using transfer learning and features are extracted from the global average pooling layer; (iv) the best features are selected using two improved optimization algorithms known as reformed differential evaluation (RDE) and reformed gray wolf (RGW); and (v) the best selected features are fused using a new probability-based serial approach and classified using machine learning algorithms. The experiment was conducted on an augmented Breast Ultrasound Images (BUSI) dataset, and the best accuracy was 99.1%. When compared with recent techniques, the proposed framework outperforms them. [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]

Epileptic seizures are temporary episodes of convulsions, where approximately 70 percent of the diagnosed population can successfully manage their condition with proper medication and lead a normal life. Over 50 million people worldwide are affected by some form of epileptic seizures, and their accurate detection can help millions in the proper management of this condition. Increasing research in machine learning has made a great impact on biomedical signal processing and especially in electroencephalogram (EEG) data analysis. The availability of various feature extraction techniques and classification methods makes it difficult to choose the most suitable combination for resource-efficient and correct detection. This paper intends to review the relevant studies of wavelet and empirical mode decomposition-based feature extraction techniques used for seizure detection in epileptic EEG data. The articles were chosen for review based on their Journal Citation Report, feature selection methods, and classifiers used. The high-dimensional EEG data falls under the category of '3N' biosignals—nonstationary, nonlinear, and noisy; hence, two popular classifiers, namely random forest and support vector machine, were taken for review, as they are capable of handling high-dimensional data and have a low risk of over-fitting. The main metrics used are sensitivity, specificity, and accuracy; hence, some papers reviewed were excluded due to insufficient metrics. To evaluate the overall performances of the reviewed papers, a simple mean value of all metrics was used. This review indicates that the system that used a Stockwell transform wavelet variant as a feature extractor and SVM classifiers led to a potentially better result. [ABSTRACT FROM AUTHOR]

This paper proposes a Gaussian mixture model-based (GMM) bearing fault band selection (GMM-WBBS) method for signal processing. The proposed method benefits reliable feature extraction using fault frequency oriented Gaussian mixture model (GMM) window series. Selecting exclusively bearing fault frequency harmonics, it eliminates the interference of bearing normal vibrations in the lower frequencies, bearing natural frequencies, and the higher frequency contents that prove to be useful only for anomaly detection but do not provide any insight into the bearing fault location. The features are extracted from time- and frequency- domain signals that exclusively contain the bearing fault frequency harmonics. Classification is done using the Weighted KNN algorithm. The experiments performed with the data containing the vibrations recorded from artificially damaged bearings show the positive effect of utilizing the proposed GMM-WBBS signal processing to filter out the discriminative data of uncertain origin. All comparison methods retrofitted with the proposed method demonstrated classification performance improvements when provided with vibration data with suppressed bearing natural frequencies and higher frequency contents. [ABSTRACT FROM AUTHOR]

The study of human activity recognition (HAR) plays an important role in many areas such as healthcare, entertainment, sports, and smart homes. With the development of wearable electronics and wireless communication technologies, activity recognition using inertial sensors from ubiquitous smart mobile devices has drawn wide attention and become a research hotspot. Before recognition, the sensor signals are typically preprocessed and segmented, and then representative features are extracted and selected based on them. Considering the issues of limited resources of wearable devices and the curse of dimensionality, it is vital to generate the best feature combination which maximizes the performance and efficiency of the following mapping from feature subsets to activities. In this paper, we propose to integrate bee swarm optimization (BSO) with a deep Q-network to perform feature selection and present a hybrid feature selection methodology, BAROQUE, on basis of these two schemes. Following the wrapper approach, BAROQUE leverages the appealing properties from BSO and the multi-agent deep Q-network (DQN) to determine feature subsets and adopts a classifier to evaluate these solutions. In BAROQUE, the BSO is employed to strike a balance between exploitation and exploration for the search of feature space, while the DQN takes advantage of the merits of reinforcement learning to make the local search process more adaptive and more efficient. Extensive experiments were conducted on some benchmark datasets collected by smartphones or smartwatches, and the metrics were compared with those of BSO, DQN, and some other previously published methods. The results show that BAROQUE achieves an accuracy of 98.41% for the UCI-HAR dataset and takes less time to converge to a good solution than other methods, such as CFS, SFFS, and Relief-F, yielding quite promising results in terms of accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Ubiquitous computing has been a green research area that has managed to attract and sustain the attention of researchers for some time now. As ubiquitous computing applications, human activity recognition and localization have also been popularly worked on. These applications are used in healthcare monitoring, behavior analysis, personal safety, and entertainment. A robust model has been proposed in this article that works over IoT data extracted from smartphone and smartwatch sensors to recognize the activities performed by the user and, in the meantime, classify the location at which the human performed that particular activity. The system starts by denoising the input signal using a second-order Butterworth filter and then uses a hamming window to divide the signal into small data chunks. Multiple stacked windows are generated using three windows per stack, which, in turn, prove helpful in producing more reliable features. The stacked data are then transferred to two parallel feature extraction blocks, i.e., human activity recognition and human localization. The respective features are extracted for both modules that reinforce the system's accuracy. A recursive feature elimination is applied to the features of both categories independently to select the most informative ones among them. After the feature selection, a genetic algorithm is used to generate ten different generations of each feature vector for data augmentation purposes, which directly impacts the system's performance. Finally, a deep neural decision forest is trained for classifying the activity and the subject's location while working on both of these attributes in parallel. For the evaluation and testing of the proposed system, two openly accessible benchmark datasets, the ExtraSensory dataset and the Sussex-Huawei Locomotion dataset, were used. The system outperformed the available state-of-the-art systems by recognizing human activities with an accuracy of 88.25% and classifying the location with an accuracy of 90.63% over the ExtraSensory dataset, while, for the Sussex-Huawei Locomotion dataset, the respective results were 96.00% and 90.50% accurate. [ABSTRACT FROM AUTHOR]

Contemporary advancements in wearable equipment have generated interest in continuously observing stress utilizing various physiological indicators. Early stress detection can improve healthcare by lessening the negative effects of chronic stress. Machine learning (ML) methodologies have been modified for healthcare equipment to monitor user health situations utilizing sufficient user information. Nevertheless, more data are needed to make applying Artificial Intelligence (AI) methodologies in the medical field easier. This research aimed to detect stress using a stacking model based on machine learning algorithms using chest-based features from the Wearable Stress and Affect Detection (WESAD) dataset. We converted this natural dataset into a convenient format for the suggested model by performing data visualization and preprocessing using the RESP feature and feature analysis using the Z-score, SelectKBest feature, the Synthetic Minority Over-Sampling Technique (SMOTE), and normalization. The efficiency of the proposed model was estimated regarding accuracy, precision, recall, and F1-score. The experimental outcome illustrated the efficacy of the proposed stacking technique, achieving 0.99% accuracy. The results revealed that the proposed stacking methodology performed better than traditional methodologies and previous studies. [ABSTRACT FROM AUTHOR]

Heart sounds have been extensively studied for heart disease diagnosis for several decades. Traditional machine learning algorithms applied in the literature have typically partitioned heart sounds into small windows and employed feature extraction methods to classify samples. However, as there is no optimal window length that can effectively represent the entire signal, windows may not provide a sufficient representation of the underlying data. To address this issue, this study proposes a novel approach that integrates window-based features with features extracted from the entire signal, thereby improving the overall accuracy of traditional machine learning algorithms. Specifically, feature extraction is carried out using two different time scales. Short-term features are computed from five-second fragments of heart sound instances, whereas long-term features are extracted from the entire signal. The long-term features are combined with the short-term features to create a feature pool known as long short-term features, which is then employed for classification. To evaluate the performance of the proposed method, various traditional machine learning algorithms with various models are applied to the PhysioNet/CinC Challenge 2016 dataset, which is a collection of diverse heart sound data. The experimental results demonstrate that the proposed feature extraction approach increases the accuracy of heart disease diagnosis by nearly 10%. [ABSTRACT FROM AUTHOR]

Software Defect Prediction (SDP) is an integral aspect of the Software Development Life-Cycle (SDLC). As the prevalence of software systems increases and becomes more integrated into our daily lives, so the complexity of these systems increases the risks of widespread defects. With reliance on these systems increasing, the ability to accurately identify a defective model using Machine Learning (ML) has been overlooked and less addressed. Thus, this article contributes an investigation of various ML techniques for SDP. An investigation, comparative analysis and recommendation of appropriate Feature Extraction (FE) techniques, Principal Component Analysis (PCA), Partial Least Squares Regression (PLS), Feature Selection (FS) techniques, Fisher score, Recursive Feature Elimination (RFE), and Elastic Net are presented. Validation of the following techniques, both separately and in combination with ML algorithms, is performed: Support Vector Machine (SVM), Logistic Regression (LR), Naïve Bayes (NB), K-Nearest Neighbour (KNN), Multilayer Perceptron (MLP), Decision Tree (DT), and ensemble learning methods Bootstrap Aggregation (Bagging), Adaptive Boosting (AdaBoost), Extreme Gradient Boosting (XGBoost), Random Forest(RF), and Generalized Stacking (Stacking). Extensive experimental setup was built and the results of the experiments revealed that FE and FS can both positively and negatively affect performance over the base model or Baseline. PLS, both separately and in combination with FS techniques, provides impressive, and the most consistent, improvements, while PCA, in combination with Elastic-Net, shows acceptable improvement. [ABSTRACT FROM AUTHOR]

The fusion tracking of RGB and thermal infrared image (RGBT) is paid wide attention to due to their complementary advantages. Currently, most algorithms obtain modality weights through attention mechanisms to integrate multi-modalities information. They do not fully exploit the multi-scale information and ignore the rich contextual information among features, which limits the tracking performance to some extent. To solve this problem, this work proposes a new multi-scale feature interactive fusion network (MSIFNet) for RGBT tracking. Specifically, we use different convolution branches for multi-scale feature extraction and aggregate them through the feature selection module adaptively. At the same time, a Transformer interactive fusion module is proposed to build long-distance dependencies and enhance semantic representation further. Finally, a global feature fusion module is designed to adjust the global information adaptively. Numerous experiments on publicly available GTOT, RGBT234, and LasHeR datasets show that our algorithm outperforms the current mainstream tracking algorithms. [ABSTRACT FROM AUTHOR]

Driver identification refers to the process whose primary purpose is identifying the person behind the steering wheel using collected information about the driver him/herself. The constant monitoring of drivers through sensors generates great benefits in advanced driver assistance systems (ADAS), to learn more about the behavior of road users. Currently, there are many research works that address the subject in search of creating intelligent models that help to identify vehicle users in an efficient and objective way. However, the different methodologies proposed to create these models are based on data generated from sensors that include different vehicle brands on routes established in real environments, which, although they provide very important information for different purposes, in the case of driver identification, there may be a certain degree of bias due to the different situations in which the route environment may change. The proposed method seeks to intelligently and objectively select the most outstanding statistical features from motor activity generated in the main elements of the vehicle with genetic algorithms for driver identification, this process being newer than those established by the state-of-the-art. The results obtained from the proposal were an accuracy of 90.74% to identify two drivers and 62% for four, using a Random Forest Classifier (RFC). With this, it can be concluded that a comprehensive selection of features can greatly optimize the identification of drivers. [ABSTRACT FROM AUTHOR]

In view of the limited number of extracted sound features, the lack of in-depth analysis of applicable sound features, and the lack of in-depth study of the selection basis and optimization process of classification models in the existing broiler sound classification or recognition research, the author proposes a recognition method for broiler sound signals based on multi-domain sound features and classification models. The implementation process is divided into the training stage and the testing stage. In the training stage, the experimental area is built, and multiple segments of broiler sound signals are collected and filtered. Through sub-frame processing and endpoint detection, the combinations of start frames and end frames of multiple sound types in broiler sound signals are obtained. A total of sixty sound features from four aspects of time domain, frequency domain, Mel-Frequency Cepstral Coefficients (MFCC), and sparse representation are extracted from each frame signal to form multiple feature vectors. These feature vectors are labeled manually to build the data set. The min-max standardization method is used to process the data set, and the random forest is used to calculate the importance of sound features. Then, thirty sound features that contribute more to the classification effect of the classification model are retained. On this basis, the classification models based on seven classification algorithms are trained, the best-performing classification model based on k-Nearest Neighbor (kNN) is obtained, and its inherent parameters are optimized. Then, the optimal classification model is obtained. The test results show that the average classification accuracy achieved by the decision-tree-based classifier (abbreviated as DT classifier) on the data set before and after min–max standardization processing is improved by 0.6%, the average classification accuracy achieved by the DT classifier on the data set before and after feature selection is improved by 3.1%, the average classification accuracy achieved by the kNN-based classification model before and after parameter optimization is improved by 1.2%, and the highest classification accuracy is 94.16%. In the testing stage, for a segment of the broiler sound signal collected in the broiler captivity area, the combinations of the start frames and end frames of multiple sound types in the broiler sound signal are obtained through signal filtering, sub-frame processing, endpoint detection, and other steps. Thirty sound features are extracted from each frame signal to form the data set to be predicted. The optimal classification model is used to predict the labels of each piece of data in the data set to be predicted. By performing majority voting processing on the predicted labels of the data combination corresponding to each sound type, the common labels are obtained; that is, the predicted types are obtained. On this basis, the definition of recognition accuracy for broiler sound signals is proposed. The test results show that the classification accuracy achieved by the optimal classification model on the data set to be predicted is 93.57%, and the recognition accuracy achieved on the multiple segments of the broiler sound signals is 99.12%. [ABSTRACT FROM AUTHOR]

Epilepsy is a chronic neurological disorder caused by abnormal neuronal activity that is diagnosed visually by analyzing electroencephalography (EEG) signals. Background: Surgical operations are the only option for epilepsy treatment when patients are refractory to treatment, which highlights the role of classifying focal and generalized epilepsy syndrome. Therefore, developing a model to be used for diagnosing focal and generalized epilepsy automatically is important. Methods: A classification model based on longitudinal bipolar montage (LB), discrete wavelet transform (DWT), feature extraction techniques, and statistical analysis in feature selection for RNN combined with long short-term memory (LSTM) is proposed in this work for identifying epilepsy. Initially, normal and epileptic LB channels were decomposed into three levels, and 15 various features were extracted. The selected features were extracted from each segment of the signals and fed into LSTM for the classification approach. Results: The proposed algorithm achieved a 96.1% accuracy, a 96.8% sensitivity, and a 97.4% specificity in distinguishing normal subjects from subjects with epilepsy. This optimal model was used to analyze the channels of subjects with focal and generalized epilepsy for diagnosing purposes, relying on statistical parameters. Conclusions: The proposed approach is promising, as it can be used to detect epilepsy with satisfactory classification performance and diagnose focal and generalized epilepsy. [ABSTRACT FROM AUTHOR]

Introduction: Obstructive sleep apnea (OSA) can cause serious health problems such as hypertension or cardiovascular disease. The manual detection of apnea is a time-consuming task, and automatic diagnosis is much more desirable. The contribution of this work is to detect OSA using a multi-error-reduction (MER) classification system with multi-domain features from bio-signals. Methods: Time-domain, frequency-domain, and non-linear analysis features are extracted from oxygen saturation (SaO 2 ), ECG, airflow, thoracic, and abdominal signals. To analyse the significance of each feature, we design a two-stage feature selection. Stage 1 is the statistical analysis stage, and Stage 2 is the final feature subset selection stage using machine learning methods. In Stage 1, two statistical analyses (the one-way analysis of variance (ANOVA) and the rank-sum test) provide a list of the significance level of each kind of feature. Then, in Stage 2, the support vector machine (SVM) algorithm is used to select a final feature subset based on the significance list. Next, an MER classification system is constructed, which applies a stacking with a structure that consists of base learners and an artificial neural network (ANN) meta-learner. Results: The Sleep Heart Health Study (SHHS) database is used to provide bio-signals. A total of 66 features are extracted. In the experiment that involves a duration parameter, 19 features are selected as the final feature subset because they provide a better and more stable performance. The SVM model shows good performance (accuracy = 81.68%, sensitivity = 97.05%, and specificity = 66.54%). It is also found that classifiers have poor performance when they predict normal events in less than 60 s. In the next experiment stage, the time-window segmentation method with a length of 60 s is used. After the above two-stage feature selection procedure, 48 features are selected as the final feature subset that give good performance (accuracy = 90.80%, sensitivity = 93.95%, and specificity = 83.82%). To conduct the classification, Gradient Boosting, CatBoost, Light GBM, and XGBoost are used as base learners, and the ANN is used as the meta-learner. The performance of this MER classification system has the accuracy of 94.66%, the sensitivity of 96.37%, and the specificity of 90.83%. [ABSTRACT FROM AUTHOR]

Background: Current telemedicine approaches lack standardised procedures for the remote assessment of axial impairment in Parkinson's disease (PD). Unobtrusive wearable sensors may be a feasible tool to provide clinicians with practical medical indices reflecting axial dysfunction in PD. This study aims to predict the postural instability/gait difficulty (PIGD) score in PD patients by monitoring gait through a single inertial measurement unit (IMU) and machine-learning algorithms. Methods: Thirty-one PD patients underwent a 7-m timed-up-and-go test while monitored through an IMU placed on the thigh, both under (ON) and not under (OFF) dopaminergic therapy. After pre-processing procedures and feature selection, a support vector regression model was implemented to predict PIGD scores and to investigate the impact of L-Dopa and freezing of gait (FOG) on regression models. Results: Specific time- and frequency-domain features correlated with PIGD scores. After optimizing the dimensionality reduction methods and the model parameters, regression algorithms demonstrated different performance in the PIGD prediction in patients OFF and ON therapy (r = 0.79 and 0.75 and RMSE = 0.19 and 0.20, respectively). Similarly, regression models showed different performances in the PIGD prediction, in patients with FOG, ON and OFF therapy (r = 0.71 and RMSE = 0.27; r = 0.83 and RMSE = 0.22, respectively) and in those without FOG, ON and OFF therapy (r = 0.85 and RMSE = 0.19; r = 0.79 and RMSE = 0.21, respectively). Conclusions: Optimized support vector regression models have high feasibility in predicting PIGD scores in PD. L-Dopa and FOG affect regression model performances. Overall, a single inertial sensor may help to remotely assess axial motor impairment in PD patients. [ABSTRACT FROM AUTHOR]

Data-driven analysis for damage assessment has a large potential in structural health monitoring (SHM) systems, where sensors are permanently attached to the structure, enabling continuous and frequent measurements. In this contribution, we propose a machine learning (ML) approach for automated damage detection, based on an ML toolbox for industrial condition monitoring. The toolbox combines multiple complementary algorithms for feature extraction and selection and automatically chooses the best combination of methods for the dataset at hand. Here, this toolbox is applied to a guided wave-based SHM dataset for varying temperatures and damage locations, which is freely available on the Open Guided Waves platform. A classification rate of 96.2% is achieved, demonstrating reliable and automated damage detection. Moreover, the ability of the ML model to identify a damaged structure at untrained damage locations and temperatures is demonstrated. [ABSTRACT FROM AUTHOR]

Developing cyber security is very necessary and has attracted considerable attention from academy and industry organizations worldwide. It is also very necessary to provide sustainable computing for the the Internet of Things (IoT). Machine learning techniques play a vital role in the cybersecurity of the IoT for intrusion detection and malicious identification. Thus, in this study, we develop new feature extraction and selection methods and for the IDS system using the advantages of the swarm intelligence (SI) algorithms. We design a feature extraction mechanism depending on the conventional neural networks (CNN). After that, we present an alternative feature selection (FS) approach using the recently developed SI algorithm, Aquila optimizer (AQU). Moreover, to assess the quality of the developed IDS approach, four well-known public datasets, CIC2017, NSL-KDD, BoT-IoT, and KDD99, were used. We also considered extensive comparisons to other optimization methods to verify the competitive performance of the developed method. The results show the high performance of the developed approach using different evaluation indicators. [ABSTRACT FROM AUTHOR]

To achieve the real-time application of a dynamic programming (DP) control strategy, we propose a predictive energy management strategy (PEMS) based on full-factor trip information, including vehicle speed, slip ratio and slope. Firstly, the prediction model of the full-factor trip information is proposed, which provides an information basis for global optimization energy management. To improve the prediction's accuracy, the vehicle speed is predicted based on the state transition probability matrix generated in the same driving scene. The characteristic parameters are extracted by a feature selection method taken as the basis for the driving condition's identification. Similar to speed prediction, regarding the uncertain route at an intersection, the slope prediction is modelled as a Markov model. On the basis of the predicted speed and the identified maximum adhesion coefficient, the slip ratio is predicted based on a neural network. Then, a predictive energy management strategy is developed based on the predictive full-factor trip information. According to the statistical rules of DP results under multiple standard driving cycles, the reference SOC trajectory is generated to ensure global sub-optimality, which determines the feasible state domain at each prediction horizon. Simulations are performed under different types of driving conditions (Urban Dynamometer Driving Schedule, UDDS and World Light Vehicle Test Cycle, WLTC) to verify the effectiveness of the proposed strategy. [ABSTRACT FROM AUTHOR]

The aim of this study was to find an efficient method to determine features that characterize octave illusion data. Specifically, this study compared the efficiency of several automatic feature selection methods for automatic feature extraction of the auditory steady-state responses (ASSR) data in brain activities to distinguish auditory octave illusion and nonillusion groups by the difference in ASSR amplitudes using machine learning. We compared univariate selection, recursive feature elimination, principal component analysis, and feature importance by testifying the results of feature selection methods by using several machine learning algorithms: linear regression, random forest, and support vector machine. The univariate selection with the SVM as the classification method showed the highest accuracy result, 75%, compared to 66.6% without using feature selection. The received results will be used for future work on the explanation of the mechanism behind the octave illusion phenomenon and creating an algorithm for automatic octave illusion classification. [ABSTRACT FROM AUTHOR]