sEMG-Based Gesture Recognition Using Sigimg-GADF-MTF and Multi-Stream Convolutional Neural Network

To comprehensively leverage the temporal, static, and dynamic information features of multi-channel surface electromyography (sEMG) signals for gesture recognition, considering the sensitive temporal characteristics of sEMG signals to action amplitude and muscle recruitment patterns, an sEMG-based gesture recognition algorithm is innovatively proposed using Sigimg-GADF-MTF and multi-stream convolutional neural network (MSCNN) by introducing the Sigimg, GADF, and MTF data processing methods and combining them with a multi-stream fusion strategy. Firstly, a sliding window is used to rearrange the multi-channel original sEMG signals through channels to generate a two-dimensional image (named Sigimg method). Meanwhile, each channel signal is respectively transformed into two-dimensional subimages using Gram angular difference field (GADF) and Markov transition field (MTF) methods. Then, the GADF and MTF images are obtained using a horizontal stitching method to splice these subimages, respectively. The Sigimg, GADF, and MTF images are used to construct a training and testing dataset, which is then imported into the constructed MSCNN model for experimental testing. The fully connected layer fusion method is utilized for multi-stream feature fusion, and the gesture recognition results are output. Through comparative experiments, an average accuracy of 88.4% is achieved using the Sigimg-GADF-MTF-MSCNN algorithm on the Ninapro DBl dataset, higher than most mainstream models. At the same time, the effectiveness of the proposed algorithm is fully verified through generalization testing of data obtained from the self-developed sEMG signal acquisition platform with an average accuracy of 82.4%.

• Publication year

  2025

• Venue

  Italian National Conference on Sensors

• Publication date

  2025-06-01

• Fields of study

  Medicine, Computer Science, Engineering

• Identifiers
  DOI 10.3390/s25113506PMID 40969073PMCID 12158361
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar, PubMed

• No claims are published for this paper.

• No concepts are published for this paper.

• An efficient surface electromyography-based gesture recognition algorithm based on multiscale fusion convolution and channel attention

  2024cited by this paper
• A comparative study of advanced technologies and methods in hand gesture analysis and recognition systems

  2024cited by this paper
• Hand gesture recognition using sEMG signals with a multi-stream time-varying feature enhancement approach

  2024cited by this paper
• NKDFF-CNN: A convolutional neural network with narrow kernel and dual-view feature fusion for multitype gesture recognition based on sEMG

  2024cited by this paper
• A survey on hand gesture recognition based on surface electromyography: Fundamentals, methods, applications, challenges and future trends

  2024cited by this paper
• SGRN: SEMG-based gesture recognition network with multi-dimensional feature extraction and multi-branch information fusion

  2024cited by this paper
• Fault diagnosis of a wave energy converter gearbox based on an Adam optimized CNN-LSTM algorithm

  2024cited by this paper
• Improving sEMG-Based Hand Gesture Recognition through Optimizing Parameters and Sliding Voting Classifiers

  2024cited by this paper
• Reliability and validity analysis of MediaPipe-based measurement system for some human rehabilitation motions

  2023cited by this paper
• Gesture recognition of sEMG signal based on GASF-LDA feature enhancement and adaptive ABC optimized SVM

  2023cited by this paper
• Myoelectric Pattern Recognition Using Gramian Angular Field and Convolutional Neural Networks for Muscle–Computer Interface

  2023cited by this paper
• Gesture recognition using dual-stream CNN based on fusion of sEMG energy kernel phase portrait and IMU amplitude image

  2022cited by this paper
• Improved Multi-Stream Convolutional Block Attention Module for sEMG-Based Gesture Recognition

  2022cited by this paper
• Markov Transition Fields and Deep Learning-Based Event-Classification and Vibration-Frequency Measurement for φ-OTDR

  2022cited by this paper
• AI-Driven Human Motion Classification and Analysis Using Laban Movement System

  2022cited by this paper
• Dynamic Gesture Recognition Using Surface EMG Signals Based on Multi-Stream Residual Network

  2021cited by this paper
• Surface-Electromyography-Based Gesture Recognition Using a Multistream Fusion Strategy

  2021cited by this paper
• A Hierarchical View Pooling Network for Multichannel Surface Electromyography-Based Gesture Recognition

  2021cited by this paper
• Gesture recognition based on surface electromyography‐feature image

  2020influential reference
• Hand Gesture Recognition based on Surface Electromyography using Convolutional Neural Network with Transfer Learning Method

  2020cited by this paper
• Surface-Electromyography-Based Gesture Recognition by Multi-View Deep Learning

  2019influential reference
• A multi-stream convolutional neural network for sEMG-based gesture recognition in muscle-computer interface

  2017influential reference
• Gesture recognition by instantaneous surface EMG images

  2016influential reference
• Deep Learning with Convolutional Neural Networks Applied to Electromyography Data: A Resource for the Classification of Movements for Prosthetic Hands

  2016influential reference
• Human Activity Recognition Using Wearable Sensors by Deep Convolutional Neural Networks

  2015cited by this paper
• Electromyography data for non-invasive naturally-controlled robotic hand prostheses

  2014cited by this paper
• A Novel Myoelectric Pattern Recognition Strategy for Hand Function Restoration After Incomplete Cervical Spinal Cord Injury

  2013cited by this paper
• The recognition of multi-finger prehensile postures using LDA

  2013cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Multi-subject/daily-life activity EMG-based control of mechanical hands

  2009cited by this paper
• Support Vector Machine-Based Classification Scheme for Myoelectric Control Applied to Upper Limb

  2008cited by this paper
• A robust, real-time control scheme for multifunction myoelectric control

  2003cited by this paper
• Design

  2001cited by this paper
• A new strategy for multifunction myoelectric control

  1993cited by this paper

• BSCAL: Gesture Recognition Network Based on Dual‐Stream Information Fusion of EMG and IMU Signals

  2025cites this paper