Enhanced Recognition of Amputated Wrist and Hand Movements by Deep Learning Method Using Multimodal Fusion of Electromyography and Electroencephalography

Motion classification can be performed using biometric signals recorded by electroencephalography (EEG) or electromyography (EMG) with noninvasive surface electrodes for the control of prosthetic arms. However, current single-modal EEG and EMG based motion classification techniques are limited owing to the complexity and noise of EEG signals, and the electrode placement bias, and low-resolution of EMG signals. We herein propose a novel system of two-dimensional (2D) input image feature multimodal fusion based on an EEG/EMG-signal transfer learning (TL) paradigm for detection of hand movements in transforearm amputees. A feature extraction method in the frequency domain of the EEG and EMG signals was adopted to establish a 2D image. The input images were used for training on a model based on the convolutional neural network algorithm and TL, which requires 2D images as input data. For the purpose of data acquisition, five transforearm amputees and nine healthy controls were recruited. Compared with the conventional single-modal EEG signal trained models, the proposed multimodal fusion method significantly improved classification accuracy in both the control and patient groups. When the two signals were combined and used in the pretrained model for EEG TL, the classification accuracy increased by 4.18–4.35% in the control group, and by 2.51–3.00% in the patient group.

EEG–EMG coupling as a hybrid method for steering detection in car driving settings

Understanding mental processes in complex human behavior is a key issue in driving, representing a milestone for developing user-centered assistive driving devices. Here, we propose a hybrid method based on electroencephalographic (EEG) and electromyographic (EMG) signatures to distinguish left and right steering in driving scenarios. Twenty-four participants took part in the experiment consisting of recordings of 128-channel EEG and EMG activity from deltoids and forearm extensors in non-ecological and ecological steering tasks. Specifically, we identified the EEG mu rhythm modulation correlates with motor preparation of self-paced steering actions in the non-ecological task, while the concurrent EMG activity of the left (right) deltoids correlates with right (left) steering. Consequently, we exploited the mu rhythm de-synchronization resulting from the non-ecological task to detect the steering side using cross-correlation analysis with the ecological EMG signals. Results returned significant cross-correlation values showing the coupling between the non-ecological EEG feature and the muscular activity collected in ecological driving conditions. Moreover, such cross-correlation patterns discriminate the steering side earlier relative to the single EMG signal. This hybrid system overcomes the limitation of the EEG signals collected in ecological settings such as low reliability, accuracy, and adaptability, thus adding to the EMG the characteristic predictive power of the cerebral data. These results prove how it is possible to complement different physiological signals to control the level of assistance needed by the driver.

Light Sleep Detection based on Surface Electromyography Signals for Nap Monitoring

This paper proposes the development of automatic sleep stage detection by using physiological signals. We aim to develop an application to assist drivers after drowsiness or fatigue detection by a commercial driver vigilance system. The proposed method used a low-cost surface electromyography (EMG) device for sleep stage detection. We investigate skeletal muscle location and EMG features from sleep stage 2 to provide an EMG-based nap monitoring system. The results showed that using only one channel of a bipolar EMG signal from an upper trapezius muscle with median power frequency can achieve 84% accuracy. We implement a MyoWare muscle sensor into the proposed nap monitoring device. The results showed that the proposed system is feasible for detecting sleep stages and waking up the napper. A combination of EMG and electroencephalogram (EEG) signals might be yield a high system performance for nap monitoring and alarm system. We will prototype a portable device to connect the application to a smartphone and test with a target group, such as truck drivers and physicians.

Drop jumps versus sled towing and their effects on repeated sprint ability in young basketball players

Background The aim of the investigation was to compare the occurrence of post-activation performance enhancement (PAPE) after drop jumps, or heavy sled towing, and the subsequent effect on repeated sprint ability (RSA). Methods Ten young basketball players (17 ± 1 yrs) performed, in randomized order, RSA test with changes of direction after a standardized warm up followed by drop jumps, heavy sled towing, or no exercise (control condition). Neuromuscular assessments composed of two maximal voluntary contractions of the knee extensors, peripheral nerve stimulation, and surface electromyography (EMG), responses were recorded before and immediately after the RSA. The EMG signal of leg muscles during sprinting were also recorded as well as the blood lactate concentration. Results The drop jumps improved the RSA mean time (P = 0.033), total time (P = 0.031), and slowest time (P = 0.029) compared to control condition, while heavy sled towing did not change RSA outcomes (P > 0.05). All conditions exhibited a decrease of doublet high frequency stimulation force (pre-post measurement) (P = 0.023) and voluntary activation (P = 0.041), evidencing the occurrence from peripheral and central components of fatigue after RSA, respectively, but no difference was evident between-conditions. There was a significantly greater EMG activity during sprints for the biceps femoris after drop jumps, only when compared to control condition (P = 0.013). Conclusion Repeated drop jumps were effective to induce PAPE in the form of RSA, while heavy sled towing had no effect on RSA performance in young basketball players. Furthermore, both conditioning activities exhibited similar levels of fatigue following the RSA protocol. Thus, drop jumps may be used as an alternative to induce PAPE and thus improve performance during sprints in young male basketball players.

Semi-automated Detection of the Timing of Respiratory Muscle Activity: Validation and First Application

Background: Respiratory muscle electromyography (EMG) can identify whether a muscle is activated, its activation amplitude, and timing. Most studies have focused on the activation amplitude, while differences in timing and duration of activity have been less investigated. Detection of the timing of respiratory muscle activity is typically based on the visual inspection of the EMG signal. This method is time-consuming and prone to subjective interpretation.Aims: Our main objective was to develop and validate a method to assess the respective timing of different respiratory muscle activity in an objective and semi-automated manner.Method: Seven healthy adults performed an inspiratory threshold loading (ITL) test at 50% of their maximum inspiratory pressure until task failure. Surface EMG recordings of the costal diaphragm/intercostals, scalene, parasternal intercostals, and sternocleidomastoid were obtained during ITL. We developed a semi-automated algorithm to detect the onset (EMG, onset) and offset (EMG, offset) of each muscle’s EMG activity breath-by-breath with millisecond accuracy and compared its performance with manual evaluations from two independent assessors. For each muscle, the Intraclass Coefficient correlation (ICC) of the EMG, onset detection was determined between the two assessors and between the algorithm and each assessor. Additionally, we explored muscle differences in the EMG, onset, and EMG, offset timing, and duration of activity throughout the ITL.Results: More than 2000 EMG, onset s were analyzed for algorithm validation. ICCs ranged from 0.75–0.90 between assessor 1 and 2, 0.68–0.96 between assessor 1 and the algorithm, and 0.75–0.91 between assessor 2 and the algorithm (p < 0.01 for all). The lowest ICC was shown for the diaphragm/intercostal and the highest for the parasternal intercostal (0.68 and 0.96, respectively). During ITL, diaphragm/intercostal EMG, onset occurred later during the inspiratory cycle and its activity duration was shorter than the scalene, parasternal intercostal, and sternocleidomastoid (p < 0.01). EMG, offset occurred synchronously across all muscles (p ≥ 0.98). EMG, onset, and EMG, offset timing, and activity duration was consistent throughout the ITL for all muscles (p > 0.63).Conclusion: We developed an algorithm to detect EMG, onset of several respiratory muscles with millisecond accuracy that is time-efficient and validated against manual measures. Compared to the inherent bias of manual measures, the algorithm enhances objectivity and provides a strong standard for determining the respiratory muscle EMG, onset.

Human Muscle Synergy Analysis to Approach the Understanding of Brain Control Algorithm

Purpose: Muscle synergy is a functional unit that coordinates the activity of a number of muscles. In this study, the extraction of muscle synergies in three types of hand movements in the horizontal plane is investigated. Materials and Methods: So, after constructing the tracking pattern of three signals, by LabVIEW, the Electromyography (EMG) signal from six muscles of hand was recorded. Then time-constant muscle synergies and their activity curves from the recorded EMG signals were extracted using Non-negative Matrix Factorization (NMF) method. Results: Comparison of these patterns showed that the non-random motions’ synergies were more similar than the random motions among different individuals. It was observed that in all movements, the similarity of the synergies in one cluster was greater than the similarity of their corresponding activation curves. Conclusion: The results showed that the complexity of the recurrence plot in random movement is greater than that of the other movements.

A Real-Time Wearable Physiological Monitoring System for Home-Based Healthcare Applications

The acquisition of physiological data are essential to efficiently predict and treat cardiac patients before a heart attack occurs and effectively expedite motor recovery after a stroke. This goal can be achieved by using wearable wireless sensor network platforms for real-time healthcare monitoring. In this paper, we present a wireless physiological signal acquisition device and a smartphone-based software platform for real-time data processing and monitor and cloud server access for everyday ECG/EMG signal monitoring. The device is implemented in a compact size (diameter: 30 mm, thickness: 4.5 mm) where the biopotential is measured and wirelessly transmitted to a smartphone or a laptop for real-time monitoring, data recording and analysis. Adaptive digital filtering is applied to eliminate any interference noise that can occur during a regular at-home environment, while minimizing the data process time. The accuracy of ECG and EMG signal coverage is assessed using Bland–Altman analysis by comparing with a reference physiological signal acquisition instrument (RHS2116 Stim/Recording System, Intan). Signal coverage of R-R peak intervals showed almost identical outcome between this proposed work and the RHS2116, showing a mean difference in heart rate of 0.15 4.65 bpm and a Wilcoxon’s p value of 0.133. A 24 h continuous recording session of ECG and EMG is conducted to demonstrate the robustness and stability of the device based on extended time wearability on a daily routine.

Construction and Simulation of Athlete’s Wrong Action Recognition Model in Sports Training Based on Embedded Wireless Communication and Computer Vision

Embedded networking has a broad prospect. Because of the Internet and the rapid development of PC skills, computer vision technology has a wide range of applications in many fields, especially the importance of identifying wrong movements in sports training. To study the computer vision technology to identify the wrong movement of athletes in sports training, in this paper, a hidden Markov model based on computer vision technology is constructed to collect video and identify the landing and take-off movements and badminton serving movements of a team of athletes under the condition of sports training, Bayesian classification algorithm to analyze the acquired sports training action data, obtain the error frequency, and the number of errors of the landing jump action, and the three characteristic data of the displacement, velocity, and acceleration of the body’s center of gravity of the athlete in the two cases of successful and incorrect badminton serve actions and compared and analyzed the accuracy of the action recognition method used in this article, the action recognition method based on deep learning and the action recognition method based on EMG signal under 30 experiments. The training process of deep learning is specifically split into two stages: 1st, a monolayer neuron is built layer by layer so that the network is trained one layer at a time; when all layers are fully trained, a tuning is performed using a wake-sleep operation. The final result shows that the frequency of the wrong actions of the athletes on the landing jump is concentrated in the knee valgus, the total frequency of error has reached 58%, and the frequency of personal error has reached 45%; the problem of the landing distance of the two feet of the team athletes also appeared more frequently, the total frequency reached 50%, and the personal frequency reached 30%. Therefore, athletes should pay more attention to the problems of knee valgus and the distance between feet when performing landing jumps; the difference in the displacement, speed, and acceleration of the body’s center of gravity during the badminton serve will affect the error of the action. And the action recognition method used in this study has certain advantages compared with the other two action recognition methods, and the accuracy of action recognition is higher.

Novel approaches to the treatment of cervical dystonia. The concept of dual navigation control

Сervical dystonia (CD) is the most common type of focal dystonia (up to 50% of all dystonia cases). Botulinum neurotoxin (BoNT) injections is the treatment choice for CD. However, the effectiveness and tolerability of botulinum therapy in CD depends on the correct choice of target muscles and the accuracy of the BoNT injection. The publication presents literature data and our own clinical experience regarding the use of navigation in BoNT injections in CD.According to the majority of authors, the use of navigation equipment, such as ultrasound (US) and electromyography (EMG), definitely increases the effectiveness of CD treatment and reduces the likelihood of adverse events. For the first time, an algorithm for the diagnosis and treatment of CD is proposed, based on the use of the method of «double- (EMG and US) guided navigation», a variant for determining the comparative activity of muscles by the intensity of the EMG signal and the design of an individual «passport» of the CD. The possibilities of analyzing the US of muscles, drawing up an accurate treatment regimen, targeted administration of BoNT, and using a non-injectable EMG electrode are shown. We present 4 clinical cases demonstrating the advantages of the double- (EMG+US) guided navigation method over the EMG-guided navigation for injection. The proposed algorithm for the diagnosis and treatment of CD makes it possible to increase the effectiveness of treatment, optimize the costs of BoNT and diagnostic equipment (injection EMG needle).