sEMG signal classification with novel feature extraction using different machine learning approaches

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.

Extreme Gradient Boosting for Surface Electromyography Classification on Time-Domain Features

Surface electromyography (sEMG) signals play an essential role in disease diagnosis and rehabilitation. This study applied a powerful machine learning algorithm called extreme gradient boosting (XGBoost) to classify sEMG signals acquired from muscles around the knee for distinguishing patients with knee osteoarthritis (KOA) from healthy subjects. First, to improve data quality, we preprocessed the data via interpolation and normalization. Next, to ensure the description integrity of model input, we extracted nine time-domain features based on the statistical characteristics of sEMG signals over time. Finally, we classified the samples using XGBoost and cross-validation (CV) and compared the results to those produced by the support vector machine (SVM) and the deep neural network (DNN). Experimental results illustrate that the presented method effectively improves classification performance. Moreover, compared with the SVM and the DNN, XGBoost has higher accuracy and better classification performance, which indicates its advantages in the classification of patients with KOA based on sEMG signals.

An sEMG-Based Human-Exoskeleton Interface Fusing Convolutional Neural Networks With Hand-Crafted Features

In recent years, the human-robot interfaces (HRIs) based on surface electromyography (sEMG) have been widely used in lower-limb exoskeleton robots for movement prediction during rehabilitation training for patients with hemiplegia. However, accurate and efficient lower-limb movement prediction for patients with hemiplegia remains a challenge due to complex movement information and individual differences. Traditional movement prediction methods usually use hand-crafted features, which are computationally cheap but can only extract some shallow heuristic information. Deep learning-based methods have a stronger feature expression ability, but it is easy to fall into the dilemma of local features, resulting in poor generalization performance of the method. In this article, a human-exoskeleton interface fusing convolutional neural networks with hand-crafted features is proposed. On the basis of our previous study, a lower-limb movement prediction framework (HCSNet) in patients with hemiplegia is constructed by fusing time and frequency domain hand-crafted features and channel synergy learning-based features. An sEMG data acquisition experiment is designed to compare and analyze the effectiveness of HCSNet. Experimental results show that the method can achieve 95.93 and 90.37% prediction accuracy in both within-subject and cross-subject cases, respectively. Compared with related lower-limb movement prediction methods, the proposed method has better prediction performance.

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.