Evaluation of feature extraction techniques and classifiers for finger movement recognition using surface electromyography signal

Application of a sEMG hand motion recognition method based on variational mode decomposition and ReliefF algorithm in rehabilitation medicine

Hand motion intention recognition has been considered as one of the crucial research fields for prosthetic control and rehabilitation medicine. In recent years, surface electromyogram (sEMG) signals that directly reflect human motion information are ideal input sources for prosthetic control and rehabilitation. However, how to effectively extract components from sEMG signals containing abundant limb movement information to improve the accuracy of hand recognition still is a difficult problem. To achieve this goal, this paper proposes a novel hand motion recognition method based on variational mode decomposition (VMD) and ReliefF. First, VMD is used to decompose the sEMG signal into multiple variational mode functions (VMFs). To efficiently extract the intrinsic components of the sEMG, the recognition performance of different numbers of VMFs is evaluated. Then, four features representing hand motion intentions are extracted from the VMFs to form the initial feature space. Next, the ReliefF algorithm is used to remove redundant features from the feature space. In order to select a feature space that can effectively reflect the intention of hand movements, the hand movement recognition performance of 8 low-dimensional feature spaces is evaluated. Finally, three machine learning methods are used to recognize hand movements. The proposed method was tested on the sEMG for Basic Hand movements Data Set and achieved an average accuracy of 99.14%. Compared with existing research, the proposed method achieves better hand motion recognition performance, indicating the potential for healthcare and rehabilitation applications.

Intelligent classification of major depressive disorder using rs-fMRI of the posterior cingulate cortex

Major Depressive Disorder (MDD) is a widespread psychiatric condition that affects a significant portion of the global population. The classification and diagnosis of MDD is crucial for effective treatment. Traditional methods, based on clinical assessment, are subjective and rely on healthcare professionals' expertise. Recently, there's growing interest in using Resting-State Functional Magnetic Resonance Imaging (rs-fMRI) to objectively understand MDD's neurobiology, complementing traditional diagnostics. The posterior cingulate cortex (PCC) is a pivotal brain region implicated in MDD which could be used to identify MDD from healthy controls. Thus, this study presents an intelligent approach based on rs-fMRI data to enhance the classification of MDD. Original rs-fMRI data were collected from a cohort of 430 participants, comprising 197 patients and 233 healthy controls. Subsequently, the data underwent preprocessing using DPARSF, and the amplitudes of low-frequency fluctuation values were computed to reduce data dimensionality and feature count. Then data associated with the PCC were extracted. After eliminating redundant features, various types of Support Vector Machines (SVMs) were employed as classifiers for intelligent categorization. Ultimately, we compared the performance of each algorithm, along with its respective optimal classifier, based on classification accuracy, true positive rate, and the area under the receiver operating characteristic curve (AUC-ROC). Upon analyzing the comparison results, we determined that the Random Forest (RF) algorithm, in conjunction with a sophisticated Gaussian SVM classifier, demonstrated the highest performance. Remarkably, this combination achieved a classification accuracy of 81.9 % and a true positive rate of 92.9 %. In conclusion, our study improves the classification of MDD by supplementing traditional methods with rs-fMRI and machine learning techniques, offering deeper neurobiological insights and aiding accuracy, while emphasizing its role as an adjunct to clinical assessment.

Loading Recognition for Lumbar Exoskeleton Based on Multi-Channel Surface Electromyography From Low Back Muscles

Lumbar exoskeleton is an assistive robot, which can reduce the risk of injury and pain in low back muscles when lifting heavy objects. An important challenge it faces involves enhancing assistance with minimal muscle energy consumption. One of the viable solutions is to adjust the force or torque of assistance in response to changes in the load on the low back muscles. It requires accurate loading recognition, which has yet to yield satisfactory outcomes due to the limitations of available measurement tools and load classification methods. This study aimed to precisely identify muscle loading using a multi-channel surface electromyographic (sEMG) electrode array on the low back muscles, combined with a participant-specific load classification method. Ten healthy participants performed a stoop lifting task with objects of varying weights, while sEMG data was collected from the low back muscles using a 3x7 electrode array. Nineteen time segments of the lifting phase were identified, and time-domain sEMG features were extracted from each segment. Participant-specific classifiers were built using four classification algorithms to determine the object weight in each time segment, and the classification performance was evaluated using a 5-fold cross-validation method. The artificial neural network classifier achieved an impressive accuracy of up to 96%, consistently improving as the lifting phase progressed, peaking towards the end of the lifting movement. This study successfully achieves accurate recognition of load on low back muscles during the object lifting task. The obtained results hold significant potential in effectively reducing muscle energy consumption when wearing a lumbar exoskeleton.

The LIBRA NeuroLimb: Hybrid Real-Time Control and Mechatronic Design for Affordable Prosthetics in Developing Regions

Globally, 2.5% of upper limb amputations are transhumeral, and both mechanical and electronic prosthetics are being developed for individuals with this condition. Mechanics often require compensatory movements that can lead to awkward gestures. Electronic types are mainly controlled by superficial electromyography (sEMG). However, in proximal amputations, the residual limb is utilized less frequently in daily activities. Muscle shortening increases with time and results in weakened sEMG readings. Therefore, sEMG-controlled models exhibit a low success rate in executing gestures. The LIBRA NeuroLimb prosthesis is introduced to address this problem. It features three active and four passive degrees of freedom (DOF), offers up to 8 h of operation, and employs a hybrid control system that combines sEMG and electroencephalography (EEG) signal classification. The sEMG and EEG classification models achieve up to 99% and 76% accuracy, respectively, enabling precise real-time control. The prosthesis can perform a grip within as little as 0.3 s, exerting up to 21.26 N of pinch force. Training and validation sessions were conducted with two volunteers. Assessed with the "AM-ULA" test, scores of 222 and 144 demonstrated the prosthesis's potential to improve the user's ability to perform daily activities. Future work will prioritize enhancing the mechanical strength, increasing active DOF, and refining real-world usability.

A Multimodal Multilevel Converged Attention Network for Hand Gesture Recognition With Hybrid sEMG and A-Mode Ultrasound Sensing

Gesture recognition based on surface electromyography (sEMG) has been widely used in the field of human-machine interaction (HMI). However, sEMG has limitations, such as low signal-to-noise ratio and insensitivity to fine finger movements, so we consider adding A-mode ultrasound (AUS) to enhance the recognition impact. To explore the influence of multisource sensing data on gesture recognition and better integrate the features of different modules. We proposed a multimodal multilevel converged attention network (MMCANet) model for multisource signals composed of sEMG and AUS. The proposed model extracts the hidden features of the AUS signal with a convolutional neural network (CNN). Meanwhile, a CNN-LSTM (long-short memory network) hybrid structure extracts some spatial-temporal features from the sEMG signal. Then, two types of CNN features from AUS and sEMG are spliced and transmitted to a transformer encoder to fuse the information and interact with sEMG features to produce hybrid features. Finally, the classification results are output employing fully connected layers. Attention mechanisms are used to adjust the weights of feature channels. We compared MMCANet's feature extraction and classification performance with that of manually extracted sEMG-AUS features using four traditional machine-learning (ML) algorithms. The recognition accuracy increased by at least 5.15%. In addition, we tried deep learning (DL) methods with CNN on single modals. The experimental results showed that the proposed model improved 14.31% and 3.80% over the CNN method with single sEMG and AUS, respectively. Compared with some state-of-the-art fusion techniques, our method also achieved better results.

Automatic identification of schizophrenia employing EEG records analyzed with deep learning algorithms

Electroencephalography is a method of detecting and analyzing electrical activity in the brain. This electrical activity can be recorded and processed to aid in the clinical diagnosis of mental disorders. In this study, a novel system for classifying schizophrenia patients from EEG recordings is presented. The developed algorithm decomposes the EEG signals into a system of radial basis functions using the method of fuzzy means. This decomposition helps to obtain the information from the various electrodes of the EEG and allows separating between healthy controls and patients with schizophrenia. The proposed method has been compared with classical machine learning algorithms, such as, K-Nearest Neighbor, Adaboost, Support Vector Machine, and Bayesian Linear Discriminant Analysis. The results show that the proposed method obtains the highest values in terms of balanced accuracy, recall, precision and F1 score, close to 93 % in all cases. The model developed in this study can be implemented in brain activity analysis systems that help in the prediction of patients with schizophrenia.

Performance improvement and complexity reduction in the classification of EMG signals with mRMR-based CNN-KNN combined model

For real-time applications, the performance in classifying the movement should be as high as possible, and the computational complexity should be low. This paper focuses on the classification of five upper arm movements which can be provided as a control for human-machine interface (HMI) based applications. The conventional machine learning algorithms are used for classification with both time and frequency domain features, and k-nearest neighbor (KNN) outplay others. To further improve the classification accuracy, pretrained CNN architectures are employed which leads to computational complexity and memory requirements. To overcome this, the deep convolutional neural network (CNN) model is introduced with three convolutional layers. To further improve the performance which is the key idea behind real-time applications, a hybrid CNN-KNN model is proposed. Even though the performance is high, the computation costs of the hybrid method are more. Minimum redundancy maximum relevance (mRMR), a feature selection method makes an effort to reduce feature dimensions. As a result, better performance is achieved by our proposed method CNN-KNN with mRMR which reduces computational complexity and memory requirement with a mean prediction accuracy of about 99.05±0.25% with 100 features.

Physical human locomotion prediction using manifold regularization

Human locomotion is an imperative topic to be conversed among researchers. Predicting the human motion using multiple techniques and algorithms has always been a motivating subject matter. For this, different methods have shown the ability of recognizing simple motion patterns. However, predicting the dynamics for complex locomotion patterns is still immature. Therefore, this article proposes unique methods including the calibration-based filter algorithm and kinematic-static patterns identification for predicting those complex activities from fused signals. Different types of signals are extracted from benchmarked datasets and pre-processed using a novel calibration-based filter for inertial signals along with a Bessel filter for physiological signals. Next, sliding overlapped windows are utilized to get motion patterns defined over time. Then, polynomial probability distribution is suggested to decide the motion patterns natures. For features extraction based kinematic-static patterns, time and probability domain features are extracted over physical action dataset (PAD) and growing old together validation (GOTOV) dataset. Further, the features are optimized using quadratic discriminant analysis and orthogonal fuzzy neighborhood discriminant analysis techniques. Manifold regularization algorithms have also been applied to assess the performance of proposed prediction system. For the physical action dataset, we achieved an accuracy rate of 82.50% for patterned signals. While, the GOTOV dataset, we achieved an accuracy rate of 81.90%. As a result, the proposed system outdid when compared to the other state-of-the-art models in literature.

Mechanism of Hyperbaric Oxygen Combined with Astaxanthin Mediating Keap1/Nrf2/HO-1 Pathway to Improve Exercise Fatigue in Mice

Objective

This work aimed to explore the application and optimization of the electrophysiological monitoring system to real-time monitor the exercise-induced fatigue (EIF) animals and investigate the intervention mechanism of hyperbaric oxygen (HBO) combined with natural astaxanthin (NAX) on EIF.

Methods

First, a system was constructed for acquisition, processing, and feature extraction of electrocardiograph (ECG) signal and surface electromyography (EMG) signal for EIF monitoring. The mice were randomly divided into a control group (CG), EIF group (EG), HBO treatment (HBO) group, and HBO combined with NAX treatment (HBO + NAX) group. The effect of the constructed system on classification recognition of EIF was analyzed. The levels of serum antioxidative stress indicators of mice in each group were detected, including malondialdehyde (MDA), catalase (CAT), superoxide dismutase (SOD), glutathione (GSH), glutathione-peroxidation (GSH-Px), and total antioxidant capacity (T-AOC). In addition, the mRNA and protein levels of Keap1/Nrf2/HO-1 pathway related genes in liver tissue were detected.

Results

The results showed that the normalized least mean squares algorithm effectively removed the motion artifact interference of ECG signal and can clearly display the signal peak, and high-pass filtering and power frequency filtering effectively removed the motion and baseline drift interference of surface EMG signal. The recognition sensitivity, specificity, and accuracy of the EIF recognition model based on the long- and short-term memory network were 90.0%, 93.3%, and 92.5%, respectively. Compared with the CG, the characteristics of ECG signal and surface EMG signal of the mice in the EIF group changed greatly (P < 0.05); the serum MDA level was increased obviously; the CAT, SOD, GSH, GSH-Px, and T-AOC levels were observably reduced (P < 0.05); the expressions of Keap1 and HO-1 in the liver were reduced remarkably, while the expression of Nrf2 was increased notably (P < 0.05). Compared with the EIF group, the characteristics of ECG signal and surface EMG signal of the mice in the HBO and HBO + NAX groups were obviously improved (P < 0.05); the serum MDA level was significantly reduced; the CAT, SOD, GSH, GSH-Px, and T-AOC levels were greatly increased (P < 0.05); the expressions of Keap1 and HO-1 in the liver were greatly increased, while the expression of Nrf2 was decreased sharply (P < 0.05).

Conclusion

Therefore, the feature extraction and classification system of ECG signal combined with surface EMG signal could realize real-time monitoring of EIF status. HBO intervention could improve the body's ability to resist oxidative stress through the Keap1/Nrf2/HO-1 pathway and then improve the EIF state. In addition, the improvement effect of HBO + NAX was more obvious.

Study on Intention Recognition and Sensory Feedback: Control of Robotic Prosthetic Hand Through EMG Classification and Proprioceptive Feedback Using Rule-based Haptic Device

In this study, for intention recognition, a convolutional neural network (CNN) classification model using the electromyography (EMG) signals acquired from the subject was developed. For sensory feedback, a rule-based wearable proprioceptive feedback haptic device, a new method for providing feedback on the grip information of a robotic prosthesis was proposed. Then, we constructed a closed-loop integrated system consisting of the CNN-based EMG classification model, the proposed haptic device, and a robotic prosthetic hand. Finally, an experiment was conducted in which the closed-loop integrated system was used to simultaneously evaluate the performance of the intention recognition and sensory feedback for a subject. The trained EMG classification model and the proposed haptic device showed the intention recognition and sensory feedback performance with 97% or higher accuracy in 10 grip states. Although some errors occurred in the intention recognition using the EMG classification model, in general, the grip intention of the subject was grasped relatively accurately, and the grip pattern was also accurately transmitted to the subject by the proposed haptic device. The integrated system which consists of the intention recognition using the CNN-based EMG classification model and the sensory feedback using the proposed haptic device is expected to be utilized for robotic prosthetic hand prosthesis control of limb loss participants.

Evaluation of feature projection techniques in object grasp classification using electromyogram signals from different limb positions

A myoelectric prosthesis is manipulated using electromyogram (EMG) signals from the existing muscles for performing the activities of daily living. A feature vector that is formed by concatenating data from many EMG channels may result in a high dimensional space, which may cause prolonged computation time, redundancy, and irrelevant information. We evaluated feature projection techniques, namely principal component analysis (PCA), linear discriminant analysis (LDA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and spectral regression extreme learning machine (SRELM), applied to object grasp classification. These represent feature projections that are combinations of either linear or nonlinear, and supervised or unsupervised types. All pairs of the four types of feature projection with seven types of classifiers were evaluated, with data from six EMG channels and an IMU sensors for nine upper limb positions in the transverse plane. The results showed that SRELM outperformed LDA with supervised feature projections, and t-SNE was superior to PCA with unsupervised feature projections. The classification errors from SRELM and t-SNE paired with the seven classifiers were from 1.50% to 2.65% and from 1.27% to 17.15%, respectively. A one-way ANOVA test revealed no statistically significant difference by classifier type when using the SRELM projection, which is a nonlinear supervised feature projection (p = 0.334). On the other hand, we have to carefully select an appropriate classifier for use with t-SNE, which is a nonlinear unsupervised feature projection. We achieved the lowest classification error 1.27% using t-SNE paired with a k-nearest neighbors classifier. For SRELM, the lowest 1.50% classification error was obtained when paired with a neural network classifier.

Human Gait Recognition Based on Multiple Feature Combination and Parameter Optimization Algorithms

Accuracy is a key index of human gait recognition. In this paper, we propose an improved gait recognition algorithm, which combines multiple feature combination and artificial bee colony for optimizing the support vector machine (ABC-SVM). Firstly, considering the complexity characteristics of surface electromyography (sEMG) signals, four types of features are extracted from the denoised sEMG signals, including the time-domain features of integral of absolute value (IAV), variance (VAR), and number of zero-crossing (ZC) points, frequency-domain features of mean power frequency (MPF) and median frequency (MF), and wavelet features and fuzzy entropy features. Secondly, the classifiers of SVM, linear discriminant analysis (LDA), and extreme learning machine (ELM) are employed to recognize the gait with obtained features, including singe-class features, multiple combination features, and optimized features of dimension reduction by principal component analysis (PCA). Thirdly, the penalty coefficient and kernel function parameter of the SVM classifier are optimized by the ABC algorithm, and the influence of different features and classifiers on the recognition results is studied. Finally, the feature samples selected to construct the SVM classifier are trained and recognized. Results show that the classification performance of the ABC-SVM classifier is significantly better than that of the nonoptimized SVM classifier, and the average recognition rate is increased by 3.18%. In addition, the combined feature samples (time-domain, frequency-domain, wavelet, and fuzzy entropy features) not only improve the gait classification accuracy but also enhance the recognition stability.

Improving Human Activity Recognition Performance by Data Fusion and Feature Engineering

Human activity recognition (HAR) is essential in many health-related fields. A variety of technologies based on different sensors have been developed for HAR. Among them, fusion from heterogeneous wearable sensors has been developed as it is portable, non-interventional and accurate for HAR. To be applied in real-time use with limited resources, the activity recognition system must be compact and reliable. This requirement can be achieved by feature selection (FS). By eliminating irrelevant and redundant features, the system burden is reduced with good classification performance (CP). This manuscript proposes a two-stage genetic algorithm-based feature selection algorithm with a fixed activation number (GFSFAN), which is implemented on the datasets with a variety of time, frequency and time-frequency domain features extracted from the collected raw time series of nine activities of daily living (ADL). Six classifiers are used to evaluate the effects of selected feature subsets from different FS algorithms on HAR performance. The results indicate that GFSFAN can achieve good CP with a small size. A sensor-to-segment coordinate calibration algorithm and lower-limb joint angle estimation algorithm are introduced. Experiments on the effect of the calibration and the introduction of joint angle on HAR shows that both of them can improve the CP.

A new detection method for EMG activity monitoring

This paper introduces a new approach for electromyography (EMG) activity monitoring based on an improved version of the adaptive linear energy detector (ALED), a widely used technique in voice activity detection. More precisely, we propose a modified ALED technique (named M-ALED) to improve the method's robustness with respect to noise. To achieve this objective, M-ALED relies on the Teager-Kaiser operator for signal pre-conditioning to increase the SNR and uses the order statistics to gain robustness against the signal's impulsiveness. We propose again to exploit the order statistics for the initial signal baseline estimation to deal with the cases where such information is unavailable. Finally, since M-ALED detects the signal's activity at the frame level, we propose in a second stage to refine this detection (at the sample level) by using a constant false alarm rate (CFAR) approach leading to the fine M-ALED (FM-ALED) solution. The performance of FM-ALED is assessed via real and synthetic EMG signal recordings and the obtained results highlight its effectiveness as compared with the state-of-the-art methods (it reduces the mean error probability by a factor close to 2).

EMG Feature Selection and Classification Using a Pbest-Guide Binary Particle Swarm Optimization

Due to the increment in hand motion types, electromyography (EMG) features are increasingly required for accurate EMG signals classification. However, increasing in the number of EMG features not only degrades classification performance, but also increases the complexity of the classifier. Feature selection is an effective process for eliminating redundant and irrelevant features. In this paper, we propose a new personal best (Pbest) guide binary particle swarm optimization (PBPSO) to solve the feature selection problem for EMG signal classification. First, the discrete wavelet transform (DWT) decomposes the signal into multiresolution coefficients. The features are then extracted from each coefficient to form the feature vector. After which pbest-guide binary particle swarm optimization (PBPSO) is used to evaluate the most informative features from the original feature set. In order to measure the effectiveness of PBPSO, binary particle swarm optimization (BPSO), genetic algorithm (GA), modified binary tree growth algorithm (MBTGA), and binary differential evolution (BDE) were used for performance comparison. Our experimental results show the superiority of PBPSO over other methods, especially in feature reduction; where it can reduce more than 90% of features while keeping a very high classification accuracy. Hence, PBPSO is more appropriate for application in clinical and rehabilitation applications.