Biology subjects

Atashzar, S. F.

Publications and source records attributed to Atashzar, S. F..

6 recordsLinked to original sources

bioRxiv2022

Deep Augmentation for Electrode Shift Compensation in Transient-phase High-density Electromyographical Neural Interfaces: Towards Application in Neurorobotics

Going beyond the traditional sparse multichannel peripheral human-machine interface that has been used widely in neurorobotics, high-density surface electromyography (HD-sEMG) has shown significant potential for decoding upper-limb motor control. We have recently proposed heterogeneous temporal dilation of LSTM in a deep neural network architecture for a large number of gestures (>60), securing spatial resolution and fast convergence. However, several fundamental questions remain unanswered. One problem targeted explicitly in this paper is the issue of "electrode shift," which can happen specifically for high-density systems and during doffing and donning the sensor grid. Another real-world problem is the question of transient versus plateau classification, which connects to the temporal resolution of neural interfaces and seamless control. In this paper, for the first time, we implement gesture prediction on the transient phase of HD-sEMG data while robustifying the human-machine interface decoder to electrode shift. For this, we propose the concept of deep data augmentation for transient HD-sEMG. We show that without using the proposed augmentation, a slight shift of 10mm may drop the decoders performance to as low as 20%. Combining the proposed data augmentation with a 3D Convolutional Neural Network (CNN), we recovered the performance to 84.6% while securing a high spatiotemporal resolution, robustifying to the electrode shift, and getting closer to large-scale adoption by the end-users, enhancing resiliency.

bioengineering↗

bioRxiv2022

InfoMuNet: Information-theory-based Functional Muscle Network Tracks Sensorimotor Integration Post-stroke

Sensory information is critical for motor coordination. However, understanding sensorimotor integration is complicated, especially in individuals with nervous system impairment. This research presents a novel functional biomarker, based on a nonlinear network graph of muscle connectivity, called InfoMuNet, to quantify the role of sensory information in motor performance. Thirty-two individuals with post-stroke hemiparesis performed a grasp-and-lift task while muscle activities were measured using eight surface electromyography (sEMG) sensors. Subjects performed the task with their affected hand before and after exposure to the sensory stimulation elicited by performing the task with the less-affected hand. For the first time, this work shows that InfoMuNet robustly quantifies functional muscle connectivity improvements in the affected hand after exposure of the less-affected side to sensory information. >90% of the subjects conformed with the improvement resulting from this sensory exposure. InfoMuNet also shows high sensitivity to tactile, kinesthetic, and visual input alterations at the subject level, highlighting the potential use in precision rehabilitation interventions.

neuroscience↗

bioRxiv2021

X-MyoNET: Biometric Identification using Deep Processing of Transient Surface Electromyography

The rapid development of the Internet and various applications such as the Internet of Medical Things (IoMT) has raised substantial concerns about personal information security. Conventional methods (e.g., passwords) and classic biological features (e.g., fingerprints) are security deficient because of potential information leakage and hacking. Biometrics that express behavioral features suggest a robust approach to achieving information security because of the corresponding uniqueness and complexity. In this paper, we consider identifying human subjects based on their transient neurophysiological signature captured using multichannel upper-limb surface electromyography (sEMG). An explainable artificial intelligence (XAI) approach is proposed to process the internal dynamics of temporal sEMG signals. We propose and prove the suitability of "transient sEMG" as a biomarker that can identify individuals. For this, we utilize the Gradient-weighted Class Activation Mapping (Grad-CAM) analysis to explain the networks attention. The outcome not only decodes and makes the unique neurophysiological pattern (i.e., motor unit recruitment during the transient phase of contraction) associated with each individual visualizable but also generates an optimizing two-dimensional (2D) spectrotemporal mask used to significantly reduce the size of the model and the trainable parameters. The resulting mask selectively and systematically samples the spectrotemporal characteristics of the users neurophysiological responses, discarding 40% of the input space while securing the accuracy of about 74% with much shallower neural network architecture. In the systematic comparative study, we find that our proposed model outperforms several state-of-the-art algorithms. For broader impacts, we anticipate our design of a compact, practical, interpretable, and robust identification system that requires only a minimal number of gestures and sensors (only 7% of the entire data set) to be a starting point for small and portable identification hardware.

bioengineering↗

bioRxiv2021

Deep Heterogeneous Dilation of LSTM for Transient-phase Gesture Prediction through High-density Electromyography: Application in Neurorobotics

Deep networks have been recently proposed to estimate motor intention using conventional bipolar surface electromyography (sEMG) signals for myoelectric control of neurorobots. In this regard, Deepnets are generally challenged by long training times (affecting practicality and calibration), complex model architectures (affecting the predictability of the outcomes), and a large number of trainable parameters (increasing the need for big data). Capitalizing on our recent work on homogeneous temporal dilation in a Recurrent Neural Network (RNN) model, this paper proposes, for the first time, heterogeneous temporal dilation in an LSTM model and applies that to high-density surface electromyography (HD-sEMG), allowing for the decoding of dynamic temporal dependencies with tunable temporal foci. In this paper, a 128-channel HD-sEMG signal space is considered due to the potential for enhancing the spatiotemporal resolution of human-robot interfaces. Accordingly, this paper addresses a challenging motor intention decoding problem of neurorobots, namely, transient intention identification. Our approach uses only the dynamic and transient phase of gesture movements when the signals are not stabilized or plateaued, which can significantly enhance the temporal resolution of human-robot interfaces. This would eventually enhance seamless real-time implementations. Additionally, this paper introduces the concept of "dilation foci" to modulate the modeling of temporal variation in transient phases. In this work a high number (e.g., 65) of gestures is included, which adds to the complexity and significance of the understudied problem. Our results show state-of-the-art performance for gesture prediction in terms of accuracy, training time, and model convergence.

bioengineering↗

bioRxiv2021

Non-parametric Functional Muscle Network as a Robust Biomarker of Fatigue

The possibility of muscle fatigue detection using surface electromyography has been explored and multiple biomarkers, such as median frequency, have been suggested. However, there are contradictory reports in the literature which results in an inconsistent understanding of the biomarkers of fatigue. Thus, there is an unmet need for a statistically robust sEMG-based biomarker for fatigue detection. This paper, for the first time, demonstrates the superior capability of a non-parametric muscle network to reliably detect fatigue-related changes. Seven healthy volunteers completed a lower limb exercise protocol, which consisted of 30s of a sit-to-stand exercise before and after the completion of fatiguing leg press sets. A non-parametric muscle network was constructed, using Spearmans power correlation and showed a very reliable decrease in network metrics associated with fatigue (degree, weighted clustering coefficient (WCC)). The network metrics displayed a significant decrease at the group level (degree, WCC: p < 0.001), individual subject level (degree: p < 0.035 WCC: p < 0.004) and particular muscle level (degree: p < 0.017). Regarding the decrease in mean degree connectivity at particular muscles, all seven subjects followed the group trend. In contrast to the robust results achieved by the proposed non-parametric muscle network, classical spectrotemporal measurements showed heterogeneous trends at the particular muscle and individual subject levels. Thus, this paper for the first time shows that non-parametric muscle network is a reliable biomarker of fatigue and could be used in a broad range of applications.

neuroscience↗

bioRxiv2021

Characterization of Cervical-Cranial Muscle Network in Correlation with Vocal Features

Objective evaluation of physiological responses using non-invasive methods has attracted great interest regarding the assessment of vocal performance and disorders. This paper, for the first time, demonstrates that the topographical features of the cervical-cranial intermuscular coherence network generated using surface electromyography (sEMG) have a strong potential for detecting subtle changes in vocal performance. For this purpose, in this paper, 12 sEMG signals were collected from six cervical and cranial muscles bilaterally. Data were collected from four subjects without a history of a voice disorder performing a series of vocal tasks. The vocal tasks were varied phonation (an /a/ sustained for the maximal duration with combinations of two levels of loudness and two levels of pitch), a pitch glide from low to high, singing a familiar song, spontaneous speech, and reading with different loudness levels. The varied phonation tasks showed the median degree, and weighted clustering coefficient of the coherence-based intermuscular network ascends monotonically, with a high effect size (|rrb| = 0.52). The set of tasks, including pitch glide, singing, and speech, was significantly distinguishable using the network features as both degree and weighted clustering coefficient had a very high effect size (|rrb| > 0.83) across these tasks. Also, pitch glide has the highest degree and weighted clustering coefficient among all tasks (degree > 0.6, weighted clustering coefficient > 0.6). Spectrotemporal features performed far less effective than the proposed functional muscle network metrics to differentiate the vocal tasks. The highest effect size for spectrotemporal features was only |rrb| = 0.19. In this paper, for the first time, the power of a cervical-cranial muscle network has been demonstrated as a neurophysiological window to vocal performance. The results also shed light on the tasks with the highest network involvement, which may be potentially used in monitoring vocal disorders and tracking rehabilitation progress.

neuroscience↗