Study on Gesture Recognition Method with Two-Stream Residual Network Fusing sEMG Signals and Acceleration Signals.

Currently, surface EMG signals have a wide range of applications in human-computer interaction systems. However, selecting features for gesture recognition models based on traditional machine learning can be challenging and may not yield satisfactory results. Considering the strong nonlinear generalization ability of neural networks, this paper proposes a two-stream residual network model with an attention mechanism for gesture recognition. One branch processes surface EMG signals, while the other processes hand acceleration signals. Segmented networks are utilized to fully extract the physiological and kinematic features of the hand. To enhance the model's capacity to learn crucial information, we introduce an attention mechanism after global average pooling. This mechanism strengthens relevant features and weakens irrelevant ones. Finally, the deep features obtained from the two branches of learning are fused to further improve the accuracy of multi-gesture recognition. The experiments conducted on the NinaPro DB2 public dataset resulted in a recognition accuracy of 88.25% for 49 gestures. This demonstrates that our network model can effectively capture gesture features, enhancing accuracy and robustness across various gestures. This approach to multi-source information fusion is expected to provide more accurate and real-time commands for exoskeleton robots and myoelectric prosthetic control systems, thereby enhancing the user experience and the naturalness of robot operation.

Measuring Surface Electromyography with Textile Electrodes in a Smart Leg Sleeve.

This paper presents the design, development, and validation of a novel e-textile leg sleeve for non-invasive Surface Electromyography (sEMG) monitoring. This wearable device incorporates e-textile sensors for sEMG signal acquisition from the lower limb muscles, specifically the anterior tibialis and lateral gastrocnemius. Validation was conducted by performing a comparative study with eleven healthy volunteers to evaluate the performance of the e-textile sleeve in acquiring sEMG signals compared to traditional Ag/AgCl electrodes. The results demonstrated strong agreement between the e-textile and conventional methods in measuring descriptive metrics of the signals, including area, power, mean, and root mean square. The paired data t-test did not reveal any statistically significant differences, and the Bland-Altman analysis indicated negligible bias between the measures recorded using the two methods. In addition, this study evaluated the wearability and comfort of the e-textile sleeve using the Comfort Rating Scale (CRS). Overall, the scores confirmed that the proposed device is highly wearable and comfortable, highlighting its suitability for everyday use in patient care.

Rectified Latent Variable Model-Based EMG Factorization of Inhibitory Muscle Synergy Components Related to Aging, Expertise and Force-Tempo Variations.

Muscle synergy has been widely acknowledged as a possible strategy of neuromotor control, but current research has ignored the potential inhibitory components in muscle synergies. Our study aims to identify and characterize the inhibitory components within motor modules derived from electromyography (EMG), investigate the impact of aging and motor expertise on these components, and better understand the nervous system's adaptions to varying task demands. We utilized a rectified latent variable model (RLVM) to factorize motor modules with inhibitory components from EMG signals recorded from ten expert pianists when they played scales and pieces at different tempo-force combinations. We found that older participants showed a higher proportion of inhibitory components compared with the younger group. Senior experts had a higher proportion of inhibitory components on the left hand, and most inhibitory components became less negative with increased tempo or decreased force. Our results demonstrated that the inhibitory components in muscle synergies could be shaped by aging and expertise, and also took part in motor control for adapting to different conditions in complex tasks.

Mapping Method of Human Arm Motion Based on Surface Electromyography Signals.

This paper investigates a method for precise mapping of human arm movements using sEMG signals. A multi-channel approach captures the sEMG signals, which, combined with the accurately calculated joint angles from an Inertial Measurement Unit, allows for action recognition and mapping through deep learning algorithms. Firstly, signal acquisition and processing were carried out, which involved acquiring data from various movements (hand gestures, single-degree-of-freedom joint movements, and continuous joint actions) and sensor placement. Then, interference signals were filtered out through filters, and the signals were preprocessed using normalization and moving averages to obtain sEMG signals with obvious features. Additionally, this paper constructs a hybrid network model, combining Convolutional Neural Networks and Artificial Neural Networks, and employs a multi-feature fusion algorithm to enhance the accuracy of gesture recognition. Furthermore, a nonlinear fitting between sEMG signals and joint angles was established based on a backpropagation neural network, incorporating momentum term and adaptive learning rate adjustments. Finally, based on the gesture recognition and joint angle prediction model, prosthetic arm control experiments were conducted, achieving highly accurate arm movement prediction and execution. This paper not only validates the potential application of sEMG signals in the precise control of robotic arms but also lays a solid foundation for the development of more intuitive and responsive prostheses and assistive devices.

Research on a Calculation Model of Ankle-Joint-Torque-Based sEMG.

The purpose of this article is to establish a prediction model of joint movements and realize the prediction of joint movemenst, and the research results are of reference value for the development of the rehabilitation equipment. This will be carried out by analyzing the impact of surface electromyography (sEMG) on ankle movements and using the Hill model as a framework for calculating ankle joint torque. The table and scheme used in the experiments were based on physiological parameters obtained through the model. Data analysis was performed on ankle joint angle signal, movement signal, and sEMG data from nine subjects during dorsiflexion/flexion, varus, and internal/external rotation. The Hill model was employed to determine 16 physiological parameters which were optimized using a genetic algorithm. Three experiments were carried out to identify the optimal model to calculate torque and root mean square error. The optimized model precisely calculated torque and had a root mean square error of under 1.4 in comparison to the measured torque. Ankle movement models predict torque patterns with accuracy, thereby providing a solid theoretical basis for ankle rehabilitation control. The optimized model provides a theoretical foundation for precise ankle torque forecasts, thereby improving the efficacy of rehabilitation robots for the ankle.

Optimizing shoulder elevation assist rate in exoskeletal rehabilitation based on muscular activity indices: a clinical feasibility study.

BACKGROUND: Restoring shoulder function is critical for upper-extremity rehabilitation following a stroke. The complex musculoskeletal anatomy of the shoulder presents a challenge for safely assisting elevation movements through robotic interventions. The level of shoulder elevation assistance in rehabilitation is often based on clinical judgment. There is no standardized method for deriving an optimal level of assistance, underscoring the importance of addressing abnormal movements during shoulder elevation, such as abnormal synergies and compensatory actions. This study aimed to investigate the effectiveness and safety of a newly developed shoulder elevation exoskeleton robot by applying a novel optimization technique derived from the muscle synergy index. METHODS: Twelve chronic stroke participants underwent an intervention consisting of 100 robot-assisted shoulder elevation exercises (10 × 10 times, approximately 40 min) for 10 days (4-5 times/week). The optimal robot assist rate was derived by detecting the change points using the co-contraction index, calculated from electromyogram (EMG) data obtained from the anterior deltoid and biceps brachii muscles during shoulder elevation at the initial evaluation. The primary outcomes were the Fugl-Meyer assessment-upper extremity (FMA-UE) shoulder/elbow/forearm score, kinematic outcomes (maximum angle of voluntary shoulder flexion and elbow flexion ratio during shoulder elevation), and shoulder pain outcomes (pain-free passive shoulder flexion range of motion [ROM] and visual analogue scale for pain severity during shoulder flexion). The effectiveness and safety of robotic therapy were examined using the Wilcoxon signed-rank sum test. RESULTS: All 12 patients completed the procedure without any adverse events. Two participants were excluded from the analysis because the EMG of the biceps brachii was not obtained. Ten participants (five men and five women; mean age: 57.0 [5.5] years; mean FMA-UE total score: 18.7 [10.5] points) showed significant improvement in the FMA-UE shoulder/elbow/forearm score, kinematic outcomes, and pain-free passive shoulder flexion ROM (P < 0.05). The shoulder pain outcomes remained unchanged or improved in all patients. CONCLUSIONS: The study presents a method for deriving the optimal robotic assist rate. Rehabilitation using a shoulder robot based on this derived optimal assist rate showed the possibility of safely improving the upper-extremity function in patients with severe stroke in the chronic phase.

Exploration of a machine learning approach for diagnosing sarcopenia among Chinese community-dwelling older adults using sEMG-based data.

BACKGROUND: In the practical application of sarcopenia screening, there is a need for faster, time-saving, and community-friendly detection methods. The primary purpose of this study was to perform sarcopenia screening in community-dwelling older adults and investigate whether surface electromyogram (sEMG) from hand grip could potentially be used to detect sarcopenia using machine learning (ML) methods with reasonable features extracted from sEMG signals. The secondary aim was to provide the interpretability of the obtained ML models using a novel feature importance estimation method. METHODS: A total of 158 community-dwelling older residents (≥ 60 years old) were recruited. After screening through the diagnostic criteria of the Asian Working Group for Sarcopenia in 2019 (AWGS 2019) and data quality check, participants were assigned to the healthy group (n = 45) and the sarcopenic group (n = 48). sEMG signals from six forearm muscles were recorded during the hand grip task at 20% maximal voluntary contraction (MVC) and 50% MVC. After filtering recorded signals, nine representative features were extracted, including six time-domain features plus three time-frequency domain features. Then, a voting classifier ensembled by a support vector machine (SVM), a random forest (RF), and a gradient boosting machine (GBM) was implemented to classify healthy versus sarcopenic participants. Finally, the SHapley Additive exPlanations (SHAP) method was utilized to investigate feature importance during classification. RESULTS: Seven out of the nine features exhibited statistically significant differences between healthy and sarcopenic participants in both 20% and 50% MVC tests. Using these features, the voting classifier achieved 80% sensitivity and 73% accuracy through a five-fold cross-validation. Such performance was better than each of the SVM, RF, and GBM models alone. Lastly, SHAP results revealed that the wavelength (WL) and the kurtosis of continuous wavelet transform coefficients (CWT_kurtosis) had the highest feature impact scores. CONCLUSION: This study proposed a method for community-based sarcopenia screening using sEMG signals of forearm muscles. Using a voting classifier with nine representative features, the accuracy exceeds 70% and the sensitivity exceeds 75%, indicating moderate classification performance. Interpretable results obtained from the SHAP model suggest that motor unit (MU) activation mode may be a key factor affecting sarcopenia.

Clustering index analysis on EMG-Torque relation-based representation of complex neuromuscular changes after spinal cord injury.

Spinal cord injury (SCI) resulting in complex neuromuscular pathology is not sufficiently well understood. To better quantify neuromuscular changes after SCI, this study uses a clustering index (CI) method for surface electromyography (sEMG) clustering representation to investigate the relation between sEMG and torque in SCI survivors. The sEMG signals were recorded from 13 subjects with SCI and 13 gender-age matched able-bodied subjects during isometric contraction of the biceps brachii muscle at different torque levels using a linear electrode array. Two torque representations, maximum voluntary contraction (MVC%) and absolute torque, were used. CI values were calculated for sEMG. Regression analyses were performed on CI values and torque levels of elbow flexion, revealing a strong linear relationship. The slopes of regressions between SCI survivors and control subjects were compared. The findings indicated that the range of distribution of CI values and slopes was greater in subjects with SCI than in control subjects (p < 0.05). The increase or decrease in slope was also observed at the individual level. This suggests that the CI and its sEMG clustering-torque relation may serve as valuable quantitative indicators for determining neuromuscular lesions after SCI, contributing to the development of effective rehabilitation strategies for improving motor performance.

Cross-Subject Lifelong Learning for Continuous Estimation From Surface Electromyographic Signal.

The employment of surface electromyographic (sEMG) signals in the estimation of hand kinematics represents a promising non-invasive methodology for the advancement of human-machine interfaces. However, the limitations of existing subject-specific methods are obvious as they confine the application to individual models that are custom-tailored for specific subjects, thereby reducing the potential for broader applicability. In addition, current cross-subject methods are challenged in their ability to simultaneously cater to the needs of both new and existing users effectively. To overcome these challenges, we propose the Cross-Subject Lifelong Network (CSLN). CSLN incorporates a novel lifelong learning approach, maintaining the patterns of sEMG signals across a varied user population and across different temporal scales. Our method enhances the generalization of acquired patterns, making it applicable to various individuals and temporal contexts. Our experimental investigations, encompassing both joint and sequential training approaches, demonstrate that the CSLN model not only attains enhanced performance in cross-subject scenarios but also effectively addresses the issue of catastrophic forgetting, thereby augmenting training efficacy.

Validity and Impact of Methods for Collecting Training Data for Myoelectric Prosthetic Control Algorithms.

Intuitive regression control of prostheses relies on training algorithms to correlate biological recordings to motor intent. The quality of the training dataset is critical to run-time regression performance, but accurately labeling intended hand kinematics after hand amputation is challenging. In this study, we quantified the accuracy and precision of labeling hand kinematics using two common training paradigms: 1) mimic training, where participants mimic predetermined motions of a prosthesis, and 2) mirror training, where participants mirror their contralateral intact hand during synchronized bilateral movements. We first explored this question in healthy non-amputee individuals where the ground-truth kinematics could be readily determined using motion capture. Kinematic data showed that mimic training fails to account for biomechanical coupling and temporal changes in hand posture. Additionally, mirror training exhibited significantly higher accuracy and precision in labeling hand kinematics. These findings suggest that the mirror training approach generates a more faithful, albeit more complex, dataset. Accordingly, mirror training resulted in significantly better offline regression performance when using a large amount of training data and a non-linear neural network. Next, we explored these different training paradigms online, with a cohort of unilateral transradial amputees actively controlling a prosthesis in real-time to complete a functional task. Overall, we found that mirror training resulted in significantly faster task completion speeds and similar subjective workload. These results demonstrate that mirror training can potentially provide more dexterous control through the utilization of task-specific, user-selected training data. Consequently, these findings serve as a valuable guide for the next generation of myoelectric and neuroprostheses leveraging machine learning to provide more dexterous and intuitive control.

Understanding the influence of confounding factors in myoelectric control for discrete gesture recognition.

Discrete myoelectric control-based gesture recognition has recently gained interest as a possible input modality for many emerging ubiquitous computing applications. Unlike the continuous control commonly employed in powered prostheses, discrete systems seek to recognize the dynamic sequences associated with gestures to generate event-based inputs. More akin to those used in general-purpose human-computer interaction, these could include, for example, a flick of the wrist to dismiss a phone call or a double tap of the index finger and thumb to silence an alarm. Moelectric control systems have been shown to achieve near-perfect classification accuracy, but in highly constrained offline settings. Real-world, online systems are subject to 'confounding factors' (i.e. factors that hinder the real-world robustness of myoelectric control that are not accounted for during typical offline analyses), which inevitably degrade system performance, limiting their practical use. Although these factors have been widely studied in continuous prosthesis control, there has been little exploration of their impacts on discrete myoelectric control systems for emerging applications and use cases. Correspondingly, this work examines, for the first time, three confounding factors and their effect on the robustness of discrete myoelectric control: (1)limb position variability, (2)cross-day use, and a newly identified confound faced by discrete systems (3)gesture elicitation speed. Results from four different discrete myoelectric control architectures: (1) Majority Vote LDA, (2) Dynamic Time Warping, (3) an LSTM network trained with Cross Entropy, and (4) an LSTM network trained with Contrastive Learning, show that classification accuracy is significantly degraded (p<0.05) as a result of each of these confounds. This work establishes that confounding factors are a critical barrier that must be addressed to enable the real-world adoption of discrete myoelectric control for robust and reliable gesture recognition.

The role of electrodiagnosis in focal neuropathies.

Electrodiagnostic (EDX) testing plays an important role in confirming a mononeuropathy, localizing the site of nerve injury, defining the pathophysiology, and assessing the severity and prognosis. The combination of nerve conduction studies (NCS) and needle electromyography findings provides the necessary information to fully assess a nerve. The pattern of NCS abnormalities reflects the underlying pathophysiology, with focal slowing or conduction block in neuropraxic injuries and reduced amplitudes in axonotmetic injuries. Needle electromyography findings, including spontaneous activity and voluntary motor unit potential changes, complement the NCS findings and further characterize chronicity and degree of axon loss and reinnervation. EDX is used as an objective marker to follow the progression of a mononeuropathy over time.

Combining enhanced spectral resolution of EMG and a deep learning approach for knee pathology diagnosis.

Knee osteoarthritis (OA) is a prevalent, debilitating joint condition primarily affecting the elderly. This investigation aims to develop an electromyography (EMG)-based method for diagnosing knee pathologies. EMG signals of the muscles surrounding the knee joint were examined and recorded. The principal components of the proposed method were preprocessing, high-order spectral analysis (HOSA), and diagnosis/recognition through deep learning. EMG signals from individuals with normal and OA knees while walking were extracted from a publicly available database. This examination focused on the quadriceps femoris, the medial gastrocnemius, the rectus femoris, the semitendinosus, and the vastus medialis. Filtration and rectification were utilized beforehand to eradicate noise and smooth EMG signals. Signals' higher-order spectra were analyzed with HOSA to obtain information about nonlinear interactions and phase coupling. Initially, the bicoherence representation of EMG signals was devised. The resulting images were fed into a deep-learning system for identification and analysis. A deep learning algorithm using adapted ResNet101 CNN model examined the images to determine whether the EMG signals were conventional or indicative of knee osteoarthritis. The validated test results demonstrated high accuracy and robust metrics, indicating that the proposed method is effective. The medial gastrocnemius (MG) muscle was able to distinguish Knee osteoarthritis (KOA) patients from normal with 96.3±1.7% accuracy and 0.994±0.008 AUC. MG has the highest prediction accuracy of KOA and can be used as the muscle of interest in future analysis. Despite the proposed method's superiority, some limitations still require special consideration and will be addressed in future research.

Highly stretchable and customizable microneedle electrode arrays for intramuscular electromyography.

Stretchable three-dimensional (3D) penetrating microelectrode arrays have potential utility in various fields, including neuroscience, tissue engineering, and wearable bioelectronics. These 3D microelectrode arrays can penetrate and conform to dynamically deforming tissues, thereby facilitating targeted sensing and stimulation of interior regions in a minimally invasive manner. However, fabricating custom stretchable 3D microelectrode arrays presents material integration and patterning challenges. In this study, we present the design, fabrication, and applications of stretchable microneedle electrode arrays (SMNEAs) for sensing local intramuscular electromyography signals ex vivo. We use a unique hybrid fabrication scheme based on laser micromachining, microfabrication, and transfer printing to enable scalable fabrication of individually addressable SMNEA with high device stretchability (60 to 90%). The electrode geometries and recording regions, impedance, array layout, and length distribution are highly customizable. We demonstrate the use of SMNEAs as bioelectronic interfaces in recording intramuscular electromyography from various muscle groups in the buccal mass of Aplysia.

Effects of static exercises on hip muscle fatigue and knee wobble assessed by surface electromyography and inertial measurement unit data.

Hip muscle weakness can be a precursor to or a result of lower limb injuries. Assessment of hip muscle strength and muscle motor fatigue in the clinic is important for diagnosing and treating hip-related impairments. Muscle motor fatigue can be assessed with surface electromyography (sEMG), however sEMG requires specialized equipment and training. Inertial measurement units (IMUs) are wearable devices used to measure human motion, yet it remains unclear if they can be used as a low-cost alternative method to measure hip muscle fatigue. The goals of this work were to (1) identify which of five pre-selected exercises most consistently and effectively elicited muscle fatigue in the gluteus maximus, gluteus medius, and rectus femoris muscles and (2) determine the relationship between muscle fatigue using sEMG sensors and knee wobble using an IMU device. This work suggests that a wall sit and single leg knee raise activity fatigue the gluteus medius, gluteus maximus, and rectus femoris muscles most reliably (p < 0.05) and that the gluteus medius and gluteus maximus muscles were fatigued to a greater extent than the rectus femoris (p = 0.031 and p = 0.0023, respectively). Additionally, while acceleration data from a single IMU placed on the knee suggested that more knee wobble may be an indicator of muscle fatigue, this single IMU is not capable of reliably assessing fatigue level. These results suggest the wall sit activity could be used as simple, static exercise to elicit hip muscle fatigue in the clinic, and that assessment of knee wobble in addition to other IMU measures could potentially be used to infer muscle fatigue under controlled conditions. Future work examining the relationship between IMU data, muscle fatigue, and multi-limb dynamics should be explored to develop an accessible, low-cost, fast and standardized method to measure fatiguability of the hip muscles in the clinic.

Utility of single fibre electromyography (SFEMG)and motor unit number estimation technique (MUNE) in the diagnosis and differentiation of polyneuropathies of different aetiology.

OBJECTIVE: To determine whether single fibre electromyography and motor unit number index can distinguish between axonal and myelin lesions in polyneuropathies. METHODS: This case-control study was conducted at the Department of Medical Physiology, School of Medicine, University of Duhok, Iraq, and the Neurophysiology Department, Hawler Teaching Hospital, Erbil, Iraq, from January 2021 to March 2022. Group A had patients diagnosed with polyneuropathy regardless of the aetiology, while group B had age-matched healthy controls. Both groups were subjected to single fibre electromyography and motor unit number index as well as conventional nerve conduction study and concentric needle electromyography. Data was analysed using SPSS 26. RESULTS: Of the 140 subjects, 60(43%) were patients in group A; 40(67%) males and 20(33%) females with mean age 55.3±7.2 years. There were 80(57%) controls in group B; 43(54%) females and 37(46%) males with mean age 53.81±7.15. Group A had significantly higher single fibre electromyography jitter, and mean consecutive difference (MCD) values than group B (p<0.05). Group A patients with axonal polyneuropathy had a higher mean jitter (MCD) value (36.476.7ms) than those with demyelinating polyneuropathy (23.262.31 ms) (P <0.05). Patients in group A had a motor unit number index value with a significantly lower mean value (p<0.05) when compared to the controls. Axonal polyneuropathy patients had a lower MUNIX value (99.612.8) than demyelinating polyneuropathy patients (149.845.7) (P< 0.05). CONCLUSIONS: Single fibre electromyography and motor unit number index could help differentiate between the pathophysiology of axonal and demyelinating polyneuropathy.

Effects of prolonged vibration to the flexor carpi radialis muscle on intracortical excitability.

Prolonged local vibration (LV) can induce neurophysiological adaptations thought to be related to long-term potentiation or depression. Yet, how changes in intracortical excitability may be involved remains to be further investigated as previous studies reported equivocal results. We therefore investigated the effects of 30 min of LV applied to the right flexor carpi radialis muscle (FCR) on both short-interval intracortical inhibition (SICI) and intracortical facilitation (ICF). SICI and ICF were measured through transcranial magnetic stimulation before and immediately after 30 min of FCR LV (vibration condition) or 30 min of rest (control condition). Measurements were performed during a low-intensity contraction (n = 17) or at rest (n = 7). No significant SICI nor ICF modulations were observed, whether measured during isometric contractions or at rest (p = 0.2). Yet, we observed an increase in inter-individual variability for post measurements after LV. In conclusion, while intracortical excitability was not significantly modulated after LV, increased inter-variability observed after LV may suggest the possibility of divergent responses to prolonged LV exposure.

Estimation of electrical muscle activity during gait using inertial measurement units with convolution attention neural network and small-scale dataset.

In general, muscle activity can be directly measured using Electromyography (EMG) or calculated with musculoskeletal models. However, both methods are not suitable for non-technical users and unstructured environments. It is desired to establish more portable and easy-to-use muscle activity estimation methods. Deep learning (DL) models combined with inertial measurement units (IMUs) have shown great potential to estimate muscle activity. However, it frequently occurs in clinical scenarios that a very small amount of data is available and leads to limited performance of the DL models, while the augmentation techniques to efficiently expand a small sample size for DL model training are rarely used. The primary aim of the present study was to develop a novel DL model to estimate the EMG envelope during gait using IMUs with high accuracy. A secondary aim was to develop a novel model-based data augmentation method to improve the performance of the estimation model with small-scale dataset. Therefore, in the present study, a time convolutional network-based generative adversarial network, namely MuscleGAN, was proposed for data augmentation. Moreover, a subject-independent regression DL model was developed to estimate EMG envelope. Results suggested that the proposed two-stage method has better generalization and estimation performance than the commonly used existing methods. Pearson correlation coefficient and normalized root-mean-square errors derived from the proposed method reached up to 0.72 and 0.13, respectively. It was indicated that the MuscleGAN indeed improved the estimation accuracy of lower limb EMG envelope from 70% to 72%. Thus, even using only two IMUs and a very small-scale dataset, the proposed model is still capable of accurately estimating lower limb EMG envelope, demonstrating considerable potential for its application in clinical and daily life scenarios.

Validity of muscle activation estimated with predicted ground reaction force in inverse dynamics based musculoskeletal simulation during gait.

The inverse dynamics based musculoskeletal simulation needs ground reaction forces (GRF) as an external force input. GRF can be predicted from kinematic data. However, the validity of estimated muscle activation using the predicted GRF has remained unclear. Therefore, the purpose of this study was to determine the validity of estimated muscle activation with predicted GRF in the inverse dynamics based musculoskeletal simulation. To perform musculoskeletal simulations, an open-source motion capture dataset that contains gait data from 50 healthy subjects was used. CusToM was used for the musculoskeletal simulations. Two sets of inverse dynamics and static optimization were performed, one used predicted GRF (PRED) and another used experimentally measured GRF (EXP). Pearson's correlation was calculated to evaluate the similarity between EMG and estimated muscle activations for both PRED and EXP. To compare PRED and EXP, paired t-tests were used to compare the trial-wise muscle activation similarity and residuals. Relationships between joint moments and residuals were also tested. The overall muscle activation similarity was comparable in PRED (R = 0.477) and EXP (R = 0.475). The residuals were 2-4 times higher in EXP compared to PRED (P < 0.001). The hip flexion-extension moment was correlated to sagittal plane residual moment (R = 0.467). The muscle activations estimated using predicted GRF were comparable to that with measured GRF in the inverse dynamics based musculoskeletal simulation. Prediction of GRF helps to perform musculoskeletal simulations where the force plates are not available.