Search

Electroencephalography (EEG)--based turn intention prediction for lower limb movement is important to build an efficient brain-computer interface (BCI) system. This study investigates the feasibility of intention detection of left-turn, right-turn, and straight walk by utilizing EEG signals obtained before the event occurrence. Synchronous data was collected using 31-channel EEG and IMU-based motion capture systems for nine healthy participants while performing left-turn, right-turn, and straight walk movements. EEG data was preprocessed with steps including Artifact Subspace Reconstruction (ASR), re-referencing, and Independent Component Analysis (ICA) to remove data noise. Feature extraction from the preprocessed EEG data involved computing various statistical measures (mean, median, standard deviation, skew, and kurtosis), and Hjorth parameters (activity, mobility, and complexity). Further, the feature selection was performed using the Random forest algorithm for the dimensionality reduction. The feature set obtained was utilized for 3-class classification using XG boost, gradient boosting, and support vector machine (SVM) with RBF kernel classifiers in a five-fold cross-validation scheme. Using the proposed intention detection methodology, the SVM classifier using an EEG window of 1.5 s and 0 s time-lag has the best decoding performance with mean accuracy, precision, and recall of 81.23%, 85.35%, and 83.92%, respectively, across the nine participants. The decoding analysis shows the feasibility of turn intention prediction for lower limb movement using the EEG signal before the event onset., Comment: *Equal contributions by the authors

Exoskeletons and rehabilitation systems offer great potential for enhancing human strength and recovery through advanced human-machine interfaces (HMIs) that adapt to movement dynamics. However, the real-time application of physics-informed neural networks (PINNs) is limited by their reliance on fixed input lengths and surrogate models. This study introduces a novel physics-informed Gated Recurrent Network (PiGRN) designed to predict multi-joint torques using surface electromyography (sEMG) data. The PiGRN model employs a Gated Recurrent Unit (GRU) to convert time-series sEMG inputs into multi-joint kinematics and external loads, which are then integrated into an equation of motion to ensure consistency with physical laws. Experimental validation with sEMG data from five participants performing elbow flexion-extension tasks showed that the PiGRN model accurately predicted joint torques for 10 unfamiliar movements, with RMSE values between 4.02\% and 11.40\% and correlation coefficients ranging from 0.87 to 0.98. These findings highlight the PiGRN's potential for real-time exoskeleton and rehabilitation applications. Future research will explore more diverse datasets, improve musculoskeletal models, and investigate unsupervised learning methods.

In this research, we present an innovative method known as a physics-informed neural network (PINN) model to predict multi-joint kinematics using electromyography (EMG) signals recorded from the muscles surrounding these joints across various loads. The primary aim is to simultaneously predict both the shoulder and elbow joint angles while executing elbow flexion-extension (FE) movements, especially under varying load conditions. The PINN model is constructed by combining a feed-forward Artificial Neural Network (ANN) with a joint torque computation model. During the training process, the model utilizes a custom loss function derived from an inverse dynamics joint torque musculoskeletal model, along with a mean square angle loss. The training dataset for the PINN model comprises EMG and time data collected from four different subjects. To assess the model's performance, we conducted a comparison between the predicted joint angles and experimental data using a testing data set. The results demonstrated strong correlations of 58% to 83% in joint angle prediction. The findings highlight the potential of incorporating physical principles into the model, not only increasing its versatility but also enhancing its accuracy. The findings could have significant implications for the precise estimation of multi-joint kinematics in dynamic scenarios, particularly concerning the advancement of human-machine interfaces (HMIs) for exoskeletons and prosthetic control systems.

Airwriting recognition is a task that involves identifying letters written in free space using finger movement. It is a special case of gesture recognition, where gestures correspond to letters in a specific language. Electroencephalography (EEG) is a non-invasive technique for recording brain activity and has been widely used in brain-computer interface applications. Leveraging EEG signals for airwriting recognition offers a promising alternative input method for Human-Computer Interaction. One key advantage of airwriting recognition is that users don't need to learn new gestures. By concatenating recognized letters, a wide range of words can be formed, making it applicable to a broader population. However, there has been limited research in the recognition of airwriting using EEG signals, which forms the core focus of this study. The NeuroAiR dataset comprising EEG signals recorded during writing English uppercase alphabets is first constructed. Various features are then explored in conjunction with different deep learning models to achieve accurate airwriting recognition. These features include processed EEG data, Independent Component Analysis components, source-domain-based scout time series, and spherical and head harmonic decomposition-based features. Furthermore, the impact of different EEG frequency bands on system performance is comprehensively investigated. The highest accuracy achieved in this study is 44.04% using Independent Component Analysis components and the EEGNet classification model. The results highlight the potential of EEG-based airwriting recognition as a user-friendly modality for alternative input methods in Human-Computer Interaction applications. This research sets a strong baseline for future advancements and demonstrates the viability and utility of EEG-based airwriting recognition.

This paper presents an analysis of parametric characterization of a motor driven tendon-sheath actuator system for use in upper limb augmentation for applications such as rehabilitation, therapy, and industrial automation. The double tendon sheath system, which uses two sets of cables (agonist and antagonist side) guided through a sheath, is considered to produce smooth and natural-looking movements of the arm. The exoskeleton is equipped with a single motor capable of controlling both the flexion and extension motions. One of the key challenges in the implementation of a double tendon sheath system is the possibility of slack in the tendon, which can impact the overall performance of the system. To address this issue, a robust mathematical model is developed and a comprehensive parametric study is carried out to determine the most effective strategies for overcoming the problem of slack and improving the transmission. The study suggests that incorporating a series spring into the system's tendon leads to a universally applicable design, eliminating the need for individual customization. The results also show that the slack in the tendon can be effectively controlled by changing the pretension, spring constant, and size and geometry of spool mounted on the axle of motor.

This paper proposes an adaptive gravity compensation (AGC) control strategy for a cable-driven upper-limb exosuit intended to assist the wearer with lifting tasks. Unlike most model-based control techniques used for this human-robot interaction task, the proposed control design does not assume knowledge of the anthropometric parameters of the wearer's arm and the payload. Instead, the uncertainties in human arm parameters, such as mass, length, and payload, are estimated online using an indirect adaptive control law that compensates for the gravity moment about the elbow joint. Additionally, the AGC controller is agnostic to the desired joint trajectory followed by the human arm. For the purpose of controller design, the human arm is modeled using a 1-DOF manipulator model. Further, a cable-driven actuator model is proposed that maps the assistive elbow torque to the actuator torque. The performance of the proposed method is verified through a co-simulation, wherein the control input realized in MATLAB is applied to the human bio-mechanical model in OpenSim under varying payload conditions. Significant reductions in human effort in terms of human muscle torque and metabolic cost are observed with the proposed control strategy. Further, simulation results show that the performance of the AGC controller converges to that of the gravity compensation (GC) controller, demonstrating the efficacy of AGC-based online parameter learning.

Kinematic parameter (KP) estimation from early electroencephalogram (EEG) signals is essential for positive augmentation using wearable robot. However, work related to early estimation of KPs from surface EEG is sparse. In this work, a deep learning-based model, BiCurNet, is presented for early estimation of biceps curl using collected EEG signal. The model utilizes light-weight architecture with depth-wise separable convolution layers and customized attention module. The feasibility of early estimation of KPs is demonstrated using brain source imaging. Computationally efficient EEG features in spherical and head harmonics domain is utilized for the first time for KP prediction. The best Pearson correlation coefficient (PCC) between estimated and actual trajectory of $0.7$ is achieved when combined EEG features (spatial and harmonics domain) in delta band is utilized. Robustness of the proposed network is demonstrated for subject-dependent and subject-independent training, using EEG signals with artifacts.

Airwriting Recognition refers to the problem of identification of letters written in space with movement of the finger. It can be seen as a special case of dynamic gesture recognition wherein the set of gestures are letters in a particular language. Surface Electromyography (sEMG) is a non-invasive approach used to capture electrical signals generated as a result of contraction and relaxation of the muscles. sEMG has been widely adopted for gesture recognition applications. Unlike static gestures, dynamic gestures are user-friendly and can be used as a method for input with applications in Human Computer Interaction. There has been limited work in recognition of dynamic gestures such as airwriting, using sEMG signals and forms the core of the current work. In this work, a multi-loss minimization framework for sEMG based airwriting recognition is proposed. The proposed framework aims at learning a feature embedding vector that minimizes the triplet loss, while simultaneously learning the parameters of a classifier head to recognize corresponding alphabets. The proposed method is validated on a dataset recorded in the lab comprising of sEMG signals from 50 participants writing English uppercase alphabets. The effect of different variations of triplet loss, triplet mining strategies and feature embedding dimension is also presented. The best-achieved accuracy was 81.26% and 65.62% in user-dependent and independent scenarios respectively by using semihard positive and hard negative triplet mining. The code for our implementation will be made available at https://github.com/ayushayt/TripCEAiR.

Airwriting Recognition is the task of identifying letters written in free space with finger movement. Electromyography (EMG) is a technique used to record electrical activity during muscle contraction and relaxation as a result of movement and is widely used for gesture recognition. Most of the current research in gesture recognition is focused on identifying static gestures. However, dynamic gestures are natural and user-friendly for being used as alternate input methods in Human-Computer Interaction applications. Airwriting recognition using EMG signals recorded from forearm muscles is therefore a viable solution. Since the user does not need to learn any new gestures and a large range of words can be formed by concatenating these letters, it is generalizable to a wider population. There has been limited work in recognition of airwriting using EMG signals and forms the core idea of the current work. The SurfMyoAiR dataset comprising of EMG signals recorded during writing English uppercase alphabets is constructed. Several different time-domain features to construct EMG envelope and two different time-frequency image representations: Short-Time Fourier Transform and Continuous Wavelet Transform were explored to form the input to a deep learning model for airwriting recognition. Several different deep learning architectures were exploited for this task. Additionally, the effect of various parameters such as signal length, window length and interpolation techniques on the recognition performance is comprehensively explored. The best-achieved accuracy was 78.50% and 62.19% in user-dependent and independent scenarios respectively by using Short-Time Fourier Transform in conjunction with a 2D Convolutional Neural Network based classifier. Airwriting has great potential as a user-friendly modality to be used as an alternate input method in Human-Computer Interaction applications.