Skip to content
DraconiticResearch
Search Sources API
190,839 studies31 sourcesUpdated 36 min ago
Peer-reviewedCC BYJournal of NeuroEngineering and Rehabilitation

Gait environments recognition via synaptic convolutional neural network with memory autapses

  • Jirou Feng1
  • Shuai Hao2
  • Junhwan Choi1
  • Junhwi Cho1
  • Wenyue Cui3
  • Jung Kim1
  1. 1Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology
  2. 2Inner Mongolia Autonomous Region Key Laboratory for Ecological Environment Collaborative Intelligence, Inner Mongolia Normal University
  3. 3School of Control Science and Engineering, Dalian University of Technology
Read full textDOICite

Abstract

Exoskeleton systems face significant challenges in maintaining reliable gait prediction under dynamically changing walking environments. Conventional learning-based methods often suffer from limited adaptability and high computational latency, especially when deployed on low-power embedded hardware. A neuromorphic computing framework based on a synaptic convolutional neural network with memory autapses (SCN-MA) is introduced for real-time gait environment recognition. A structured gait experiment was conducted to collect pneumatic mechanomyography (pMMG) and stretch signals under multiple walking conditions, forming a multimodal dataset for training and evaluation. The framework adopts multiple binary gait classification models trained in parallel, which enhances modularity and scalability. A reinforcement learning based ensemble policy is then trained to integrate the outputs of these models for final decision-making. The complete system is implemented on the Zynq-based FPGA platform, enabling end-to-end prediction with low latency and high energy efficiency. Experimental results confirm improved accuracy and adaptability over baseline models, supporting the use of neuromorphic architectures in exoskeleton systems.

Related

  1. Feature-aware attention convolutional neural network for efficient pulmonary fibrosis classification from chest CT images with FPGA deployment
    K. Mahapackialakshmi, G. Jaffino
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  2. Interpretable attention-deficit hyperactivity disorder diagnosis from functional magnetic resonance imaging via hybrid convolutional neural network–transformer learning and multi-level graph-based comprehensibility
    R. Harini, O. Uma Maheswari, K. Lakshmi Priya
    Scientific ReportsPeer-reviewedCC BY-NC-ND 4.0Full textPsychiatry & mental healthCrossref
  3. Evaluating Pedestrian Crossing Safety: Implementing and Evaluating a Convolutional Neural Network Model Trained on Paired Aerial and Subjective Perspective Images (Vol 11, E42428, 2025)
    Dylan Russon, Antoine Guennec, Juan Naredo-Turrado +5
    HeliyonPeer-reviewedLicence not statedFull textGeneral biologyEpidemiology & public healthHAL
  4. Rapid estimation of photon measurement density functions using a deep convolutional neural network for functional near-infrared spectroscopy
    Yang Zhao, Xue-Ting Sun, Wen-Di Shi +2
    NeuroImage: ReportsPeer-reviewedCC BY-NC-NDFull textMedical imaging & radiologyDOAJEurope PMCPMC
  5. Predicting clonal mutations from tumour spatial transcriptomics data using a graph convolutional neural network
    T. Luijts, S. Hoogstoel, S. Wen +9
    bioRxivPreprintCC BY-NC-NDFull textOncologybioRxiv

Cite

BibTeXRIS
BibTeX
@article{feng2026gait,
  title = {{Gait environments recognition via synaptic convolutional neural network with memory autapses}},
  author = {Jirou Feng and Shuai Hao and Junhwan Choi and Junhwi Cho and Wenyue Cui and Jung Kim},
  journal = {Journal of NeuroEngineering and Rehabilitation},
  year = {2026},
  month = jul,
  doi = {10.1186/s12984-026-02071-x},
  url = {https://doi.org/10.1186/s12984-026-02071-x},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Gait environments recognition via synaptic convolutional neural network with memory autapses
AU  - Jirou Feng
AU  - Shuai Hao
AU  - Junhwan Choi
AU  - Junhwi Cho
AU  - Wenyue Cui
AU  - Jung Kim
PY  - 2026
DA  - 2026/07/01
JO  - Journal of NeuroEngineering and Rehabilitation
DO  - 10.1186/s12984-026-02071-x
UR  - https://doi.org/10.1186/s12984-026-02071-x
AB  - Exoskeleton systems face significant challenges in maintaining reliable gait prediction under dynamically changing walking environments. Conventional learning-based methods often suffer from limited adaptability and high computational latency, especially when deployed on low-power embedded hardware. A neuromorphic computing framework based on a synaptic convolutional neural network with memory autapses (SCN-MA) is introduced for real-time gait environment recognition. A structured gait experiment was conducted to collect pneumatic mechanomyography (pMMG) and stretch signals under multiple walking conditions, forming a multimodal dataset for training and evaluation. The framework adopts multiple binary gait classification models trained in parallel, which enhances modularity and scalability. A reinforcement learning based ensemble policy is then trained to integrate the outputs of these models for final decision-making. The complete system is implemented on the Zynq-based FPGA platform, enabling end-to-end prediction with low latency and high energy efficiency. Experimental results confirm improved accuracy and adaptability over baseline models, supporting the use of neuromorphic architectures in exoskeleton systems.
SN  - 1743-0003
ER  -