The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Automated Health and Safety Recommendations Using LSTM in Hazardous Workplaces
Author(s): Usharani Bhimavarapu (Department of Computer Science and Engineering,)
Copyright: 2025
Pages: 16
EISBN13: 9798337355597
Purchase
View Sample PDF
Abstract
Monitoring of workplace conditions and employee health is crucial to ensuring worker safety and compliance with regulatory standards. In environments where exposure to hazardous factors such as chemicals, noise, or extreme temperatures is common, real-time tracking of exposure levels can help prevent health risks. This study presents a recommendation system based on Long Short-Term Memory (LSTM) networks, designed to monitor and predict workplace exposure risks using sequential data. The system leverages preprocessed exposure data, including environmental conditions and worker-specific health information, to generate personalized safety recommendations. By analyzing historical exposure patterns, the LSTM model identifies potential hazards and suggests timely interventions, such as protective measures or adjustments to work schedules. The system also integrates real-time alerts, which are generated when exposure levels exceed predefined limits, ensuring workers receive immediate safety instructions.
Related Content
|
Zinga Novais, Jorge Vareda Gomes, Mario Romão.
© 2023.
20 pages.
|
|
Shuti Steph Khumalo.
© 2018.
27 pages.
|
|
Charles A.C. Oham, Okeoma John-Paul Okeke.
© 2022.
21 pages.
|
|
Taylor Valore.
© 2011.
21 pages.
|
|
Ruhi Sarangal, Maninder Kaur, Ashok Kumar.
© 2023.
13 pages.
|
|
|