Effective Approach for Classifying EMG Signals Through Reconstruction Using Autoencoders

Amyotrophic Lateral Sclerosis (ALS) is one of the most common neuromuscular diseases which affects both lower and upper motor neurons. In this paper, a dilated one dimensional convolutional neural network, named ALSNet, is proposed for identifying ALS from raw EMG signal. No hand-crafted feature extraction is required, rather, ALSNet is able to take raw EMG signal as input and detect EMG signals of ALS subjects. This makes the method more feasible for practical implementation by reducing the computational cost required for extracting features. To our best knowledge, no research work for identification of ALS from raw EMG signal has been conducted yet. The performance of the ALSNet was evaluated using popular metrics such as overall accuracy, sensitivity, specificity and balanced accuracy and compared with other existing methods. The proposed method showed a better performance than the other existing methods with an overall accuracy of 97.74%.

Considering the vast variety of EMG signal applications such as rehabilitation of people suffering from some mobility limitations, scientists have done much research on EMG control system. In this regard, feature extraction of EMG signal has been highly valued as a significant technique to extract the desired information of EMG signal and remove unnecessary parts. This proposed method is based on discrete wavelet transform (DWT). This method consists of 2 main processes; feature extraction and classification. Feature extraction is implemented from the EMG signals, and different level of wavelet decomposition (cA3, cD3, cD2 and cDl) using root mean square (RMS) and cepstrum coefficient (CC). Then, the feature vector is classified based on decision functions obtained by PCA. Experimental results showed that our method using DWT can improve motion recognition accuracy compared to when using raw EMG signals.

Although multi-view learning has made significant progress over the past few decades, it is still challenging due to the difficulty in modeling complex correlations among different views, especially under the context of view missing. To address the challenge, we propose a novel framework termed Cross Partial Multi-View Networks (CPM-Nets), which aims to fully and flexibly take advantage of multiple partial views. We first provide a formal definition of completeness and versatility for multi-view representation and then theoretically prove the versatility of the learned latent representations. For completeness, the task of learning latent multi-view representation is specifically translated to a degradation process by mimicking data transmission, such that the optimal tradeoff between consistency and complementarity across different views can be implicitly achieved. Equipped with adversarial strategy, our model stably imputes missing views, encoding information from all views for each sample to be encoded into latent representation to further enhance the completeness. Furthermore, a nonparametric classification loss is introduced to produce structured representations and prevent overfitting, which endows the algorithm with promising generalization under view-missing cases. Extensive experimental results validate the effectiveness of our algorithm over existing state of the arts for classification, representation learning and data imputation.

Purpose:There has been burgeoning interest in applying machine learning methods for predicting radiotherapy outcomes. However, the imbalanced ratio of a large number of variables to a limited sample size in radiation oncology constitutes a major challenge. Therefore, dimensionality reduction methods can be a key to success. The study investigates and contrasts the application of traditional machine learning methods and deep learning approaches for outcome modeling in radiotherapy. In particular, new joint architectures based on variational autoencoder (VAE) for dimensionality reduction are presented and their application is demonstrated for the prediction of lung radiation pneumonitis (RP) from a large-scale heterogeneous dataset.Methods:A large-scale heterogeneous dataset containing a pool of 230 variables including clinical factors (e.g., dose, KPS, stage) and biomarkers (e.g., single nucleotide polymorphisms (SNPs), cytokines and micro-RNAs) in a population of 106 non-small cell lung cancer (NSCLC) patients who received radiotherapy was used for modeling RP. 22 patients had grade 2 or higher RP. Four methods were investigated, including feature selection (case A) and feature extraction (case B) with traditional machine learning methods, a VAE-MLP joint architecture (case C) with deep learning and lastly, the combination of feature selection and joint-architecture (case D). For feature selection, Random forest (RF), Support Vector Machine (SVM) and multi-layer perceptron (MLP) were implemented to select relevant features. Specifically, each method was run for multiple times to rank features within several cross-validated (CV) resampled sets. A collection of ranking lists were then aggregated by top 5% and Kemeny graph methods to identify the final ranking for prediction. A synthetic minority oversampling technique (SMOTE) was applied to correct for class imbalance during this process. For deep learning, a VAE-MLP joint architecture where a VAE aimed for dimensionality reduction and an MLP aimed for classification was developed. In this architecture, reconstruction loss and prediction loss were combined into a single loss function to realize simultaneous training and weights were assigned to different classes to mitigate class imbalance. To evaluate the prediction performance and conduct comparisons, the area under receiver operating characteristic (ROC) curves (AUCs) were performed for nested CVs for both handcrafted feature selections and the deep learning approach. The significance of differences in AUCs was assessed using the DeLong test of U-statistics.Results:An MLP-based method using weight pruning (WP) feature selection yielded the best performance among the different hand-crafted feature selection methods (case A), reaching an AUC of 0.804 (95% CI: 0.761–0.823) with 29 top features. A VAE-MLP joint architecture (case C) achieved a comparable but slightly lower AUC of 0.781 (95% CI: 0.737–0.808) with the size of latent dimension being 2. The combination of handcrafted features (case A) and latent representation (case D) achieved a significant AUC improvement of 0.831 (95% CI: 0.805–0.863) with 22 features (p-value = 0.000642 compared with handcrafted features only (Case A) and p-value=0.000453 compared to VAE alone (Case C)) with an MLP classifier.Conclusion:The potential for combination of traditional machine learning methods and deep learning VAE techniques has been demonstrated for dealing with limited datasets in modeling radiotherapy toxicities. Specifically, latent variables from a VAE-MLP joint architecture are able to complement handcrafted features for the prediction of RP and improve prediction over either method alone.

Wavelet denoising algorithms have been received considerable attention in the removal of noises of surface electromyography (sEMG) signal. Wavelet denoising algorithms proposed by Donoho's method is more often used in sEMG signal. However, Donoho's method is limited especially for multifunction myoelectric control. It does not only remove noises but it also removes some important part of sEMG signals. This study proposes an improved threshold estimation method. Six modified threshold estimation methods associated with the selected thresholding rescaling are evaluated. SEMG signal from six hand motions with additive WGN at various signal-to-noise ratios (SNRs) were applied to evaluate the efficient of method. Features of the estimated signal are sent to classification task. Evaluations of the performance of these algorithms are mean squared error (MSE) and classification rate. The results show that Global Scale Modified Universal (GSMU) method provides better performance than traditional Donoho's method. It produces sEMG signals that remain important information of the original sEMG signal and can eliminate lots of noises. The average MSE are 0.0024 at 20 dB SNR, low noise, and 0.074 at 0 dB, high noise. The accuracy of hand movement recognition of sEMG signal that estimates from GSMU is improved. It improves 1 to 4% of the classification accuracy depend on level of noise. In addition, performance of level dependent method is better than the others rescaling method. In the experiment, GSMU threshold estimation method is an efficient method for producing useful sEMG signal without noise and improving the application of hand movement recognition.

Posterior collapse is a pervasive issue in Variational Autoencoders (VAEs) that leads to the learned latent representations becoming trivial and devoid of meaningful information. To address this problem, this paper presents a novel β-VAE approach, which incorporates a hyperparameter β to strike an optimal balance between the reconstruction loss and the KL divergence loss. By conducting a comprehensive series of experiments and drawing comparisons with existing methods, robust evidence is provided that the proposed β-VAE method effectively mitigates posterior collapse and yields more expressive and informative latent representations.The experimental setup involves various architectures and datasets to demonstrate the versatility and efficacy of the β-VAE approach in diverse settings. Additionally, ablation studies are performed to investigate the impact of different β values on the model's performance, elucidating the role of this hyperparameter in controlling the trade-off between reconstruction quality and latent representation expressiveness. Furthermore, the disentanglement properties of the learned latent space are analyzed, which is a crucial aspect of VAEs, especially when applied to complex, real-world data.In-depth analysis of the results offers valuable insights into the underlying mechanisms of β-VAE, thereby contributing to a more profound understanding of VAEs and their inherent limitations. The findings not only establish the effectiveness of the β-VAE method in preventing posterior collapse but also pave the way for future research on improving VAEs' performance in various applications. Potential future work could explore alternative techniques for balancing the competing objectives of reconstruction and latent representation learning or delve into the theoretical properties of β-VAE, providing a more rigorous foundation for this approach.

Selection of suitable features plays a pivotal role in Electromyography pattern recognition (EMG-PR) based system designing. Time-domain features are widely used in EMG-PR based application and show improved proficiency in the development of rehabilitation robotics. Even though, the performance of existing features is not satisfactory. In this study, we proposed four novel time-domain features obtained by using first-order differentiation of original surface electromyogram (sEMG) signals feature. Here, sEMG signals were acquired from ten healthy volunteers with the help of myotrace400 device for six different arm movements. The data acquisition and pre-processing stage were carried out followed by the feature extraction process for better classification results. Four different classifiers namely, k-nearest neighbors (KNN), Linear discriminant analysis (LDA), Quadratic discriminant analysis (QDA) and Medium tree (MT) classifiers were utilized for the performance evaluation of proposed and conventional features. Experimental results demonstrate that proposed features extracted by using first-order differentiation of sEMG signals feature attained better classification accuracy with MT classifier as compared to the feature extracted from original sEMG signals with the conventional features. The accuracy of proposed feature based on first-order differentiation improved up to 6%. The results indicate that proposed features may be considered for developing the EMG-PR based system designing.

Deep learning based on lung cancer classification has been used increasingly for the early diagnosis for several reasons such as lack of robust deep learning-based system, complexity of nodule structure, lack of proper lung segmentation technique, high false positive result, lack of best feature extraction and less amount of medical imaging data for training deep learning model, it has been difficult to get high classification performance. The aim of this paper getting high lung cancer classification performance. We introduce the Data, Classification technique and View (DCV) as main components of the system that concern for the better lung cancer classification results, along with them different intermediate components such as Lung nodule segmentation, Feature extraction, Feature reduction are also defined. These components are key for providing better classification performance result which helps radiologist for early diagnosis of lung cancer. We have proposed uses image data having different dimensionality as input to the deep learning based classifier which provides lung cancer classification to be viewed by radiologists for the early diagnosis of lung cancer.We evaluated the proposed DCV system by classifying 30 state-of-art research papers in the field of deep learning based lung cancer classification system. Through this paper, readers will get the result of deep learning based lung cancer classification system. Also, readers will understand the classification groups, validation criteria, future gaps of the 30 literature.

Comparative analysis of SVM and Naive Bayes classifier for the SEMG signal classification

The objective of this work is to study the EMG signals based on hand motions for specified tasks, and different gripping conditions so as to identify patterns of EMG signals. This will allow therapists to identify weak muscles of patients with motor weakness, such as spinal cord injury (SCI) and post-stroke and concentrate on rehabilitation activities which can strengthen these specific muscles. At the same time, it is hoped that the analysis is able to provide useful data for objective and quantitative assessment towards control applications on the hand rehabilitation device, which is being developed. The analysis of the EMG signals for various hand muscles during functional motions and prehensile tasks has been carried out. The method to identify individual hand motions from EMG signals is described. The EMG signals associated to physical parameters are also illustrated in this paper. Finally, the preliminary works and future research are concluded.

GLEAM: A multimodal deep learning framework for chronic lower back pain detection using EEG and sEMG signals.

In recent times, the topic of human facial age estimation attracted much attention. This is due to its ability to improve biometrics systems. Recently, several applications that are based on the demographic attributes estimation have been developed. These include law enforcement, re-identification in videos, planed marketing, intelligent advertising, social media, and human-computer interaction. The main contributions of the paper are as follows. Firstly, it extends some handcrafted models that are based on the Pyramid Multi Level (PML) face representation. Secondly, it evaluates the performance of two different kinds of features that are handcrafted and deep features. It compares handcrafted and deep features in terms of accuracy and computational complexity. The proposed scheme of study includes the following three main steps: 1) face preprocessing; 2) feature extraction (two different kinds of features are studied: handcrafted and deep features); 3) feeding the obtained features to a linear regressor. In addition, we investigate the strengths and weaknesses of handcrafted and deep features when used in facial age estimation. Experiments are run on three public databases (FG-NET, PAL and FACES). These experiments show that both handcrafted and deep features are effective for facial age estimation.

Surface electromyography (sEMG) signals are an indirect measurement of muscle activity, and their applications range from biomechanics to control and rehabilitation. Hand movement recognition is a very difficult endeavor due to forearm anatomy. Hence, a multichannel approach for signal acquisition and processing is required. Conventional electrodes can limit the ease-of-use and repeatability of multi-channel sEMG recordings. New techniques have been proposed in this regard, with dry electrodes being one of them. Dry electrode technology has enabled the design of better donning and doffing procedures for multichannel sEMG recording, particularly for rehabilitation and prosthetic applications. However, there is a debate about the quality of the signals recorded with them and their usefulness for the recognition of multiple hand movements. To mitigate these quality issues, this work proposes an array of reusable stainless steel dry electrodes for multichannel sEMG recording with a design that facilitates its positioning on the forearm. The dry electrodes were characterized through electrical impedance measures and a Bland-Altman test. They were found to have similar characteristics to standard, disposable sEMG pre-gelled electrodes. For placement repeatability and application feasibility, an anatomy-based electrode positioning protocol was implemented with 17 healthy subjects and six hand movements. To evaluate the application feasibility of the electrode array, a feed-forward artificial neural network was trained to classify signals from the six movements, with a 97,86±0,58% accuracy. The amplitude of the sEMG signals for two antagonist movements was compared, finding a 24,81% variation. The dry electrode array showed feasibility in acquiring and classifying sEMG signals of hand movements with high accuracy.

Surface electromyogram (sEMG) signals have been used to control multifunctional prosthetic hands. Researchers usually focused on the use of several channels with sEMG signals to identify more hand motions without limiting the number of sEMG sensors. However, the residual muscles of an amputee are limited. Therefore, the point of a successful recognition system is to decrease the channels of sEMG signals to classify more hand motions. To achieve this goal, we proposed a hand motion recognition system, in which three channels of sEMG signals can classify nine hand motions. In this recognition system, the time domain features, root mean square ratio (RMSR) and autoregressive (AR) model, were selected to extract the features of the sEMG signals as compared with the time-frequency domain features. Furthermore, the linear discriminant analysis (LDA) was adopted as the classifier. Consequently, the average accuracy rate of the presented system was 91.46%. Therefore, the proposed algorithms in this paper can be reasonably feasible for prosthetic hands.

This study aimed to investigate the muscle synergy for hand motions of both the left and right hands based on surface electromyography (sEMG) signals. Six hand motions, including hand grasp (HG), four fingers flexion (FFF), index finger extension (IFE), thumb internal rotation (TIR), thumb opposition (TO), key pinch (KP), were examined in the experiment. The sEMG signals were recorded from brachioradialis (BRA), flexor carpi ulnaris (FCU), flexor carpi radialis (FCR), extensor digitorum communis (EDC), flexor digitorum superficialis (FDS), abductor pollicis brevis (APB), first dorsal interosseous (FDI) and abductor digiti minimi (ADM) of both the left and right hands. A co-contraction index (CI) followed by a correlation coefficients (CC) was applied to quantify the muscle synergy during the hand motions and to compare the synergistic patterns across hands. Results shown that the left and right hands had similar muscle synergy (CC (CC>0.9) for any of the motions. For both hands, there were strong correlations between the synergistic matrix of different motions (CC (CC>0.85), including the correlations between HG and FFF, between FFF and IFE, and between TO and KP. By contrast, weak correlations between the synergistic matrix for IFE and that for TIR (CC (CC<0.1), suggesting a low similarity of the muscle synergy for the two motions. This study shed light on how the muscles of the left and right hands are involved and co-contracted for the dexterous hand motions.