Investigation of Heterogeneity Sources for Occupational Task Recognition via Transfer Learning

Details

• Personal Author:
  Cavuoto LA ; Hajifar S ; Lamooki SR ; Megahed FM ; Sun H
• Description:
  Human activity recognition has been extensively used for the classification of occupational tasks. Existing activity recognition approaches perform well when training and testing data follow an identical distribution. However, in the real world, this condition may be violated due to existing heterogeneities among training and testing data, which results in degradation of classification performance. This study aims to investigate the impact of four heterogeneity sources, cross-sensor, cross-subject, joint cross-sensor and cross-subject, and cross-scenario heterogeneities, on classification performance. To that end, two experiments called separate task scenario and mixed task scenario were conducted to simulate tasks of electrical line workers under various heterogeneity sources. Furthermore, a support vector machine classifier equipped with domain adaptation was used to classify the tasks and benchmarked against a standard support vector machine baseline. Our results demonstrated that the support vector machine equipped with domain adaptation outperformed the baseline for cross-sensor, joint cross-subject and cross-sensor, and cross-subject cases, while the performance of support vector machine equipped with domain adaptation was not better than that of the baseline for cross-scenario case. Therefore, it is of great importance to investigate the impact of heterogeneity sources on classification performance and if needed, leverage domain adaptation methods to improve the performance. [Description provided by NIOSH]
• Subjects:
  Electricity Occupational Health Safety Staff Development
• Keywords:
  Author Keywords: Domain Adaptation Electrical Workers Occupational Human Activity Recognition Sensors Task Performance Training Transfer Learning Wearable Sensors Wearable Technologies
• ISSN:
  0746-9462
• Document Type:
  Text
• Funding:
  Grant
• Genre:
  Journal Article
• Place as Subject:
  New York ; Ohio ; OSHA Region 2 ; OSHA Region 5
• CIO:
  National Institute for Occupational Safety and Health (NIOSH)
• Topic:
  Workplace Safety & Health
• Location:
  North America
• Volume:
  21
• Issue:
  19
• NIOSHTIC Number:
  nn:20063723
• Citation:
  Sensors 2021 Oct; 21(19):6677
• Contact Point Address:
  Hongyue Sun, Department of Industrial & Systems Engineering, University at Buffalo, Buffalo, NY 14260
• Email:
  yues@buffalo.edu
• Federal Fiscal Year:
  2022
• NORA Priority Area:
  Transportation, Warehousing and Utilities
• Performing Organization:
  State University of New York at Buffalo
• Peer Reviewed:
  True
• Start Date:
  20200930
• Source Full Name:
  Sensors
• End Date:
  20220929
• Collection(s):
  National Institute for Occupational Safety and Health
• Main Document Checksum:
  urn:sha-512:1e40df40009d394587e33f6368882d28449db7338748b72eb7a265da401dbd75404a3b2db4b58ed7444f2d1d2a88f82944b0d1f0e2e711d2315e9fb0f9514e4a
• Download URL:
  https://stacks.cdc.gov/view/cdc/222284/cdc_222284_DS1.pdf
• File Type:
  [PDF - 1.24 MB ]