75
IRUS Total
Downloads

Cross-subject and cross-modal transfer for generalized abnormal gait pattern recognition

File Description SizeFormat 
TNNLS_19_Final (1).pdfAccepted version12.63 MBAdobe PDFView/Open
TNNLS_19_Supplementary.pdfSupporting information2.9 MBAdobe PDFView/Open
Title: Cross-subject and cross-modal transfer for generalized abnormal gait pattern recognition
Authors: Gu, X
Guo, Y
Deligianni, F
Lo, B
Yang, G-Z
Item Type: Journal Article
Abstract: For abnormal gait recognition, pattern-specific features indicating abnormalities are interleaved with the subject-specific differences representing biometric traits. Deep representations are, therefore, prone to overfitting, and the models derived cannot generalize well to new subjects. Furthermore, there is limited availability of abnormal gait data obtained from precise Motion Capture (Mocap) systems because of regulatory issues and slow adaptation of new technologies in health care. On the other hand, data captured from markerless vision sensors or wearable sensors can be obtained in home environments, but noises from such devices may prevent the effective extraction of relevant features. To address these challenges, we propose a cascade of deep architectures that can encode cross-modal and cross-subject transfer for abnormal gait recognition. Cross-modal transfer maps noisy data obtained from RGBD and wearable sensors to accurate 4-D representations of the lower limb and joints obtained from the Mocap system. Subsequently, cross-subject transfer allows disentangling subject-specific from abnormal pattern-specific gait features based on a multiencoder autoencoder architecture. To validate the proposed methodology, we obtained multimodal gait data based on a multicamera motion capture system along with synchronized recordings of electromyography (EMG) data and 4-D skeleton data extracted from a single RGBD camera. Classification accuracy was improved significantly in both Mocap and noisy modalities.
Issue Date: 1-Feb-2021
Date of Acceptance: 9-Jul-2020
URI: http://hdl.handle.net/10044/1/81388
DOI: 10.1109/TNNLS.2020.3009448
ISSN: 1045-9227
Publisher: Institute of Electrical and Electronics Engineers
Start Page: 546
End Page: 560
Journal / Book Title: IEEE Transactions on Neural Networks and Learning Systems
Volume: 32
Issue: 2
Copyright Statement: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor/Funder: Engineering & Physical Science Research Council (E
British Council (UK)
Funder's Grant Number: EP/K503733/1
330760239
Keywords: Science & Technology
Technology
Computer Science, Artificial Intelligence
Computer Science, Hardware & Architecture
Computer Science, Theory & Methods
Engineering, Electrical & Electronic
Computer Science
Engineering
Feature extraction
Electromyography
Skeleton
Kinematics
Data mining
Gait recognition
Noise measurement
Body sensor network
gait analysis
model generalization
multimodal representation
Artificial Intelligence & Image Processing
Publication Status: Published
Online Publication Date: 2020-07-29
Appears in Collections:Department of Surgery and Cancer
Computing
Faculty of Medicine
Institute of Global Health Innovation
Faculty of Engineering