Minimum Mapping from EMG Signals at Human Elbow and Shoulder Movements into Two DoF Upper-Limb Robot with Machine Learning

Analysis of the Hanging Actions and Operating Heights of Storage Furniture Suitable for the Elderly

The current functional scale design of storage furniture which the elderly use does not meet their needs, and unsuitable storage furniture may bring many physiological and psychological problems to their daily lives. The purpose of this study is to start with the hanging operation, to study the factors influencing the hanging operation heights of elderly people undergoing self-care in a standing posture and to determine the research methods to be used to study the appropriate hanging operation height of the elderly so as to provide data and theoretical support for the functional design scale of storage furniture suitable for the elderly. This study quantifies the situations of elderly people's hanging operation through an sEMG test performed on 18 elderly people at different hanging heights combined with a subjective evaluation before and after the operation and a curve fitting between the integrated sEMG indexes and the test heights. The test results show that the height of the elderly subjects had a significant effect on the hanging operation, and the main power muscles of the suspension operation were the anterior deltoid, upper trapezius and brachioradialis. Elderly people in different height groups had their own performance of the most comfortable hanging operation ranges. The suitable range for the hanging operation was 1536-1728 mm for seniors aged 60 or above whose heights were within the range of 1500-1799 mm, which could obtain a better action view and ensure the comfort of the operation. External hanging products, such as wardrobe hangers and hanging hooks, could also be determined according to this result.

Predicting postural control adaptation measuring EEG, EMG, and center of pressure changes: BioVRSea paradigm

Introduction: Postural control is a sensorimotor mechanism that can reveal neurophysiological disorder. The present work studies the quantitative response to a complex postural control task. Methods: We measure electroencephalography (EEG), electromyography (EMG), and center of pressure (CoP) signals during a virtual reality (VR) experience called BioVRSea with the aim of classifying different postural control responses. The BioVRSea paradigm is based on six different phases where motion and visual stimulation are modulated throughout the experiment, inducing subjects to a different adaptive postural control strategy. The goal of the study is to assess the predictability of those responses. During the experiment, brain activity was recorded from a 64-channel EEG, muscle activity was determined with six wireless EMG sensors placed on lower leg muscles, and individual movement measured by the CoP. One-hundred and seventy-two healthy individuals underwent the BioVRSea paradigm and 318 features were extracted from each phase of the experiment. Machine learning techniques were employed to: (1) classify the phases of the experiment; (2) assess the most notable features; and (3) identify a quantitative pattern for healthy responses. Results: The results show that the EEG features are not sufficient to predict the distinct phases of the experiment, but they can distinguish visual and motion onset stimulation. EMG features and CoP features, when used jointly, can predict five out of six phases with a mean accuracy of 74.4% (±8%) and an AUC of 0.92. The most important feature to identify the different adaptive strategies is the Squared Root Mean Distance of points on Medio-Lateral axis (RDIST_ML). Discussion: This work shows the importance and the feasibility of a quantitative evaluation in a complex postural control task and demonstrates the potential of EEG, CoP, and EMG for assessing pathological conditions. These predictive systems pave the way for developing an objective assessment of pathological behavior PC responses. This will be a first step in identifying individual disorders and treatment options.

Sliding-Window Normalization to Improve the Performance of Machine-Learning Models for Real-Time Motion Prediction Using Electromyography

Many researchers have used machine learning models to control artificial hands, walking aids, assistance suits, etc., using the biological signal of electromyography (EMG). The use of such devices requires high classification accuracy. One method for improving the classification performance of machine learning models is normalization, such as z-score. However, normalization is not used in most EMG-based motion prediction studies because of the need for calibration and fluctuation of reference value for calibration (cannot re-use). Therefore, in this study, we proposed a normalization method that combines sliding-window and z-score normalization that can be implemented in real-time processing without need for calibration. The effectiveness of this normalization method was confirmed by conducting a single-joint movement experiment of the elbow and predicting its rest, flexion, and extension movements from the EMG signal. The proposed method achieved 77.7% accuracy, an improvement of 21.5% compared to the non-normalization (56.2%). Furthermore, when using a model trained by other people’s data for application without calibration, the proposed method achieved 63.1% accuracy, an improvement of 8.8% compared to the z-score (54.4%). These results showed the effectiveness of the simple and easy-to-implement method, and that the classification performance of the machine learning model could be improved.

Stacking classifier to improve the classification of shoulder motion in transhumeral amputees

In recent years surface electromyography signals-based machine learning models are rapidly establishing. The efficacy of prosthetic arm growth for transhumeral amputees is aided by efficient classifiers. The paper aims to propose a stacking classifier-based classification system for sEMG shoulder movements. It presents the possibility of various shoulder motions classification of transhumeral amputees. To improve the system performance, adaptive threshold method and wavelet transformation have been applied for features extraction. Six different classifiers Support Vector Machines (SVM), Tree, Random Forest (RF), K-Nearest Neighbour (KNN), AdaBoost and Naïve Bayes (NB) are designed to extract the sEMG data classification accuracy. With cross-validation, the accuracy of RF, Tree and Ada Boost is 97%, 92% and 92% respectively. Stacking classifiers provides an accuracy as 99.4% after combining the best predicted multiple classifiers.

Development of Surface EMG Game Control Interface for Persons with Upper Limb Functional Impairments

In recent years, surface Electromyography (sEMG) signals have been effectively applied in various fields such as control interfaces, prosthetics, and rehabilitation. We propose a neck rotation estimation from EMG and apply the signal estimate as a game control interface that can be used by people with disabilities or patients with functional impairment of the upper limb. This paper utilizes an equation estimation and a machine learning model to translate the signals into corresponding neck rotations. For testing, we designed two custom-made game scenes, a dynamic 1D object interception and a 2D maze scenery, in Unity 3D to be controlled by sEMG signal in real-time. Twenty-two (22) test subjects (mean age 27.95, std 13.24) participated in the experiment to verify the usability of the interface. From object interception, subjects reported stable control inferred from intercepted objects more than 73% accurately. In a 2D maze, a comparison of male and female subjects reported a completion time of 98.84 s. ± 50.2 and 112.75 s. ± 44.2, respectively, without a significant difference in the mean of the one-way ANOVA (p = 0.519). The results confirmed the usefulness of neck sEMG of sternocleidomastoid (SCM) as a control interface with little or no calibration required. Control models using equations indicate intuitive direction and speed control, while machine learning schemes offer a more stable directional control. Control interfaces can be applied in several areas that involve neck activities, e.g., robot control and rehabilitation, as well as game interfaces, to enable entertainment for people with disabilities.

Biosignal-Based Human-Machine Interfaces for Assistance and Rehabilitation: A Survey

As a definition, Human–Machine Interface (HMI) enables a person to interact with a device. Starting from elementary equipment, the recent development of novel techniques and unobtrusive devices for biosignals monitoring paved the way for a new class of HMIs, which take such biosignals as inputs to control various applications. The current survey aims to review the large literature of the last two decades regarding biosignal-based HMIs for assistance and rehabilitation to outline state-of-the-art and identify emerging technologies and potential future research trends. PubMed and other databases were surveyed by using specific keywords. The found studies were further screened in three levels (title, abstract, full-text), and eventually, 144 journal papers and 37 conference papers were included. Four macrocategories were considered to classify the different biosignals used for HMI control: biopotential, muscle mechanical motion, body motion, and their combinations (hybrid systems). The HMIs were also classified according to their target application by considering six categories: prosthetic control, robotic control, virtual reality control, gesture recognition, communication, and smart environment control. An ever-growing number of publications has been observed over the last years. Most of the studies (about 67%) pertain to the assistive field, while 20% relate to rehabilitation and 13% to assistance and rehabilitation. A moderate increase can be observed in studies focusing on robotic control, prosthetic control, and gesture recognition in the last decade. In contrast, studies on the other targets experienced only a small increase. Biopotentials are no longer the leading control signals, and the use of muscle mechanical motion signals has experienced a considerable rise, especially in prosthetic control. Hybrid technologies are promising, as they could lead to higher performances. However, they also increase HMIs’ complexity, so their usefulness should be carefully evaluated for the specific application.