Explore the latest scholarly publications.
ID: IJRIM-V02I07ART001 📥 Download
Abstract: Convolutional Neural Networks (CNNs) have revolutionized the field of deep learning, offering exceptional performance in tasks involving pattern recognition and feature extraction from complex data. This study explores the application of CNN-based models for hand gesture recognition using electromyography (EMG) signals. EMG signals, generated by muscle contractions, provide a rich source of information for understanding voluntary movements and have become a key modality in developing robust gesture recognition systems. By leveraging the powerful feature extraction capabilities of CNNs, this approach seeks to overcome the limitations of traditional machine learning methods, such as reliance on handcrafted features and sensitivity to noise. This paper presents a comprehensive review of CNN architectures tailored for EMG-based gesture recognition, focusing on signal preprocessing, model training, and optimization techniques.