Implementation of Subject Specific Model and General Model using Bayesian Algorithm and Compare their Performance

Electromyography (EMG) signals play a pivotal role in numerous applications, offering insights into muscle activity crucial for various fields. However, the challenge lies in mitigating noise interference during transmission, which significantly impacts signal accuracy and reliability. To address th...

Full description

Saved in:
Bibliographic Details
Published in2024 First International Conference on Electronics, Communication and Signal Processing (ICECSP) pp. 1 - 6
Main Authors Jain, Love, Shaklan, Nishant, Kumar, Hemant, Birok, Rajesh
Format Conference Proceeding
LanguageEnglish
Published IEEE 08.08.2024
Subjects
Accuracy
Analytical models
Bayes methods
Bayesian Inference
component
Data models
diverse dataset
Electromyography
Electromyography (EMG)
formatting
general-specific
Inference algorithms
insert
Machine learning algorithms
Signal detection
Signal processing algorithms
Signal to noise ratio
style
styling
subject-specific
Online AccessGet full text

Cover

More Information
Summary:Electromyography (EMG) signals play a pivotal role in numerous applications, offering insights into muscle activity crucial for various fields. However, the challenge lies in mitigating noise interference during transmission, which significantly impacts signal accuracy and reliability. To address this pressing issue, our research delves into the efficacy of subject-specific and general-specific models for EMG signal detection, employing sophisticated Bayesian Inference algorithms. This comprehensive investigation encompasses a diverse dataset representing various demographics, including healthy individuals, older adults, and individuals with specific medical conditions. By leveraging this rich dataset, we aim to conduct a robust evaluation of the proposed models, shedding light on their performance across different population segments and scenarios. The overarching goal of this research is to advance the field of EMG signal detection, with profound implications for neuromuscular diagnosis, prosthetic control systems, and the de-velopment of intuitive human-computer interfaces. By enhancing our understanding of EMG signal processing and modeling, we strive to pave the way for innovative solutions that empower individuals with improved healthcare diagnostics and assistive technologies, ultimately enhancing their quality of life.
DOI:10.1109/ICECSP61809.2024.10698021