Muscle force estimation from lower limb EMG signals using novel optimised machine learning techniques

Human motor performance assessment with lower limb exoskeletons as a potential strategy to support healthy aging-a perspective article

With increasing age, motor performance declines. This decline is associated with less favorable health outcomes such as impaired activities of daily living, reduced quality of life, or increased mortality. Through regular assessment of motor performance, changes over time can be monitored, and targeted therapeutic programs and interventions may be informed. This can ensure better individualization of any intervention approach (e.g. by considering the current motor performance status of a person) and thus potentially increase its effectiveness with regard to maintaining current performance status or delaying further decline. However, in older adults, motor performance assessment is time consuming and requires experienced examiners and specific equipment, amongst others. This is particularly not feasible in care facility/nursing home settings. Wearable robotic devices, such as exoskeletons, have the potential of being used to assess motor performance and provide assistance during physical activities and exercise training for older adults or individuals with mobility impairments, thereby potentially enhancing motor performance. In this manuscript, we aim to (1) provide a brief overview of age-related changes of motor performance, (2) summarize established clinical and laboratory test procedures for the assessment of motor performance, (3) discuss the possibilities of translating established test procedures into exoskeleton-based procedures, and (4) highlight the feasibility, technological requirements and prerequisites for the assessment of human motor performance using lower limb exoskeletons.

Hand gestures classification of sEMG signals based on BiLSTM-metaheuristic optimization and hybrid U-Net-MobileNetV2 encoder architecture

Surface electromyography (sEMG) data has been extensively utilized in deep learning algorithms for hand movement classification. This paper aims to introduce a novel method for hand gesture classification using sEMG data, addressing accuracy challenges seen in previous studies. We propose a U-Net architecture incorporating a MobileNetV2 encoder, enhanced by a novel Bidirectional Long Short-Term Memory (BiLSTM) and metaheuristic optimization for spatial feature extraction in hand gesture and motion recognition. Bayesian optimization is employed as the metaheuristic approach to optimize the BiLSTM model's architecture. To address the non-stationarity of sEMG signals, we employ a windowing strategy for signal augmentation within deep learning architectures. The MobileNetV2 encoder and U-Net architecture extract relevant features from sEMG spectrogram images. Edge computing integration is leveraged to further enhance innovation by enabling real-time processing and decision-making closer to the data source. Six standard databases were utilized, achieving an average accuracy of 90.23% with our proposed model, showcasing a 3-4% average accuracy improvement and a 10% variance reduction. Notably, Mendeley Data, BioPatRec DB3, and BioPatRec DB1 surpassed advanced models in their respective domains with classification accuracies of 88.71%, 90.2%, and 88.6%, respectively. Experimental results underscore the significant enhancement in generalizability and gesture recognition robustness. This approach offers a fresh perspective on prosthetic management and human-machine interaction, emphasizing its efficacy in improving accuracy and reducing variance for enhanced prosthetic control and interaction with machines through edge computing integration.

Multivariable analysis for predicting lower limb muscular strength with a hip-joint exoskeleton

Introduction

Advancements in exercise science have highlighted the importance of accurate muscular strength assessments for optimizing performance and preventing injuries.

Methods

We propose a novel approach to measuring muscular strength in young, healthy individuals using Bot Fit, a hip-joint exoskeleton, during resistance exercises. In this study, we introduced performance metrics to evaluate exercise performance during both short and extended durations of three resistance exercises: squats, knee-ups, and reverse lunges. These metrics, derived from the robot's motor signals and sEMG data, include initial exercise speed, the number of repetitions, and muscle engagement. We compared these metrics against baseline muscular strength, measured using standard fitness equipment such as one-repetition maximum (1RM) and isometric contraction tests, conducted with 30 participants aged 23 to 30 years.

Results

Our results revealed that initial exercise speed and the number of repetitions were significant predictors of baseline muscular strength. Using statistical multivariable analysis, we developed a highly accurate model ( R = 0.884 , adj.R 2 = 0.753 , p-value < 0.001 ) and an efficient model (with all models achieving R > 0.87 ) with strong explanatory power.

Conclusion

This model, focusing on a single exercise (squat) and a key performance metric (initial speed), accurately represents the muscular strength of Bot Fit users across all three exercises. This study expands the application of hip-joint exoskeleton robots, enabling efficient estimation of lower limb muscle strength through resistance exercises with Bot Fit.

A Surface Electromyography (sEMG) System Applied for Grip Force Monitoring

Muscles play an indispensable role in human life. Surface electromyography (sEMG), as a non-invasive method, is crucial for monitoring muscle status. It is characterized by its real-time, portable nature and is extensively utilized in sports and rehabilitation sciences. This study proposed a wireless acquisition system based on multi-channel sEMG for objective monitoring of grip force. The system consists of an sEMG acquisition module containing four-channel discrete terminals and a host computer receiver module, using Bluetooth wireless transmission. The system is portable, wearable, low-cost, and easy to operate. Leveraging the system, an experiment for grip force prediction was designed, employing the bald eagle search (BES) algorithm to enhance the Random Forest (RF) algorithm. This approach established a grip force prediction model based on dual-channel sEMG signals. As tested, the performance of acquisition terminal proceeded as follows: the gain was up to 1125 times, and the common mode rejection ratio (CMRR) remained high in the sEMG signal band range (96.94 dB (100 Hz), 84.12 dB (500 Hz)), while the performance of the grip force prediction algorithm had an R2 of 0.9215, an MAE of 1.0637, and an MSE of 1.7479. The proposed system demonstrates excellent performance in real-time signal acquisition and grip force prediction, proving to be an effective muscle status monitoring tool for rehabilitation, training, disease condition surveillance and scientific fitness applications.

Exploratory analysis using machine learning algorithms to predict pinch strength by anthropometric and socio-demographic features

Objectives. This study examines the role of different machine learning (ML) algorithms to determine which socio-demographic factors and hand-forearm anthropometric dimensions can be used to accurately predict hand function. Methods. The cross-sectional study was conducted with 7119 healthy Iranian participants (3525 males and 3594 females) aged 10-89 years. Seventeen hand-forearm anthropometric dimensions were measured by JEGS digital caliper and a measuring tape. Tip-to-tip, key and three-jaw chuck pinches were measured using a calibrated pinch gauge. Subsequently, 21 features pertinent to socio-demographic factors and hand-forearm anthropometric dimensions were used for classification. Furthermore, 12 well-known classifiers were implemented and evaluated to predict pinches. Results. Among the 21 features considered in this study, hand length, stature, age, thumb length and index finger length were found to be the most relevant and effective components for each of the three pinch predictions. The k-nearest neighbor, adaptive boosting (AdaBoost) and random forest classifiers achieved the highest classification accuracy of 96.75, 86.49 and 84.66% to predict three pinches, respectively. Conclusions. Predicting pinch strength and determining the predictive hand-forearm anthropometric and socio-demographic characteristics using ML may pave the way to designing an enhanced tool handle and reduce common musculoskeletal disorders of the hand.

An Optimized Stimulation Control System for Upper Limb Exoskeleton Robot-Assisted Rehabilitation Using a Fuzzy Logic-Based Pain Detection Approach

The utilization of robotic systems in upper limb rehabilitation has shown promising results in aiding individuals with motor impairments. This research introduces an innovative approach to enhance the efficiency and adaptability of upper limb exoskeleton robot-assisted rehabilitation through the development of an optimized stimulation control system (OSCS). The proposed OSCS integrates a fuzzy logic-based pain detection approach designed to accurately assess and respond to the patient's pain threshold during rehabilitation sessions. By employing fuzzy logic algorithms, the system dynamically adjusts the stimulation levels and control parameters of the exoskeleton, ensuring personalized and optimized rehabilitation protocols. This research conducts comprehensive evaluations, including simulation studies and clinical trials, to validate the OSCS's efficacy in improving rehabilitation outcomes while prioritizing patient comfort and safety. The findings demonstrate the potential of the OSCS to revolutionize upper limb exoskeleton-assisted rehabilitation by offering a customizable and adaptive framework tailored to individual patient needs, thereby advancing the field of robotic-assisted rehabilitation.

Estimation of Knee Assistive Moment in a Gait Cycle Using Knee Angle and Knee Angular Velocity through Machine Learning and Artificial Stiffness Control Strategy (MLASCS)

Nowadays, many people around the world cannot walk perfectly because of their knee problems. A knee-assistive device is one option to support walking for those with low or not enough knee muscle forces. Many research studies have created knee devices with control systems implementing different techniques and sensors. This study proposes an alternative version of the knee device control system without using too many actuators and sensors. It applies the machine learning and artificial stiffness control strategy (MLASCS) that uses one actuator combined with an encoder for estimating the amount of assistive support in a walking gait from the recorded gait data. The study recorded several gait data and analyzed knee moments, and then trained a k-nearest neighbor model using the knee angle and the angular velocity to classify a state in a gait cycle. This control strategy also implements instantaneous artificial stiffness (IAS), a control system that requires only knee angle in each state to determine the amount of supporting moment. After validating the model via simulation, the accuracy of the machine learning model is around 99.9% with the speed of 165 observers/s, and the walking effort is reduced by up to 60% in a single gait cycle.

A real-time and convex model for the estimation of muscle force from surface electromyographic signals in the upper and lower limbs

Surface electromyography (sEMG) is a signal consisting of different motor unit action potential trains and records from the surface of the muscles. One of the applications of sEMG is the estimation of muscle force. We proposed a new real-time convex and interpretable model for solving the sEMG-force estimation. We validated it on the upper limb during isometric voluntary flexions-extensions at 30%, 50%, and 70% Maximum Voluntary Contraction in five subjects, and lower limbs during standing tasks in thirty-three volunteers, without a history of neuromuscular disorders. Moreover, the performance of the proposed method was statistically compared with that of the state-of-the-art (13 methods, including linear-in-the-parameter models, Artificial Neural Networks and Supported Vector Machines, and non-linear models). The envelope of the sEMG signals was estimated, and the representative envelope of each muscle was used in our analysis. The convex form of an exponential EMG-force model was derived, and each muscle's coefficient was estimated using the Least Square method. The goodness-of-fit indices, the residual signal analysis (bias and Bland-Altman plot), and the running time analysis were provided. For the entire model, 30% of the data was used for estimation, while the remaining 20% and 50% were used for validation and testing, respectively. The average R-square (%) of the proposed method was 96.77 ± 1.67 [94.38, 98.06] for the test sets of the upper limb and 91.08 ± 6.84 [62.22, 96.62] for the lower-limb dataset (MEAN ± SD [min, max]). The proposed method was not significantly different from the recorded force signal (p-value = 0.610); that was not the case for the other tested models. The proposed method significantly outperformed the other methods (adj. p-value < 0.05). The average running time of each 250 ms signal of the training and testing of the proposed method was 25.7 ± 4.0 [22.3, 40.8] and 11.0 ± 2.9 [4.7, 17.8] in microseconds for the entire dataset. The proposed convex model is thus a promising method for estimating the force from the joints of the upper and lower limbs, with applications in load sharing, robotics, rehabilitation, and prosthesis control for the upper and lower limbs.

Study on Flexible sEMG Acquisition System and Its Application in Muscle Strength Evaluation and Hand Rehabilitation

Wearable devices based on surface electromyography (sEMG) to detect muscle activity can be used to assess muscle strength with the development of hand rehabilitation applications. However, conventional acquisition devices are usually complicated to operate and poorly comfortable for more medical and scientific application scenarios. Here, we report a flexible sEMG acquisition system that combines a graphene-based flexible electrode with a signal acquisition flexible printed circuit (FPC) board. Our system utilizes a polydimethylsiloxane (PDMS) substrate combined with graphene transfer technology to develop a flexible sEMG sensor. The single-lead sEMG acquisition system was designed and the FPC board was fabricated considering the requirements of flexible bending and twisting. We demonstrate the above design approach and extend this flexible sEMG acquisition system to applications for assessing muscle strength and hand rehabilitation training using a long- and short-term memory network training model trained to predict muscle strength, with 98.81% accuracy in the test set. The device exhibited good flexion and comfort characteristics. In general, the ability to accurately and imperceptibly monitor surface electromyography (EMG) signals is critical for medical professionals and patients.