The IRMA Community
Newsletters
Research IRM
Click a keyword to search titles using our InfoSci-OnDemand powered search:
|
Application of Machine Learning Methods to Forecast Potential Dangers in Chemical and Gas Industries
|
|
Author(s): P. Nancy (Department of Computing Technologies, School of Computing, SRM Institute of Science and Technology, Kattankulathur, India), K. Anitha (Department of Computing Technologies, School of Computing, SRM Institute of Science and Technology, Kattankulathur, India), D. Shiny Irene (Department of Computing Technologies, School of Computing, SRM Institute of Science and Technology, Kattankulathur, India)and D. Vinod (Department of Computing Technologies, School of Computing, SRM Institute of Science and Technology, Kattankulathur, India)
Copyright: 2025
Pages: 20
Source title:
Environmental Monitoring Technologies for Improving Global Human Health
Source Author(s)/Editor(s): Olga Anatolievna Pasko (National Open Institute, St. Petersburg, Russia)and Nadezhda Anatolievna Lebedeva (International Personnel Academy, Germany)
DOI: 10.4018/979-8-3693-8532-6.ch011
Purchase
|
Abstract
Employers have a responsibility to prioritize the safety of their workers and should regularly inquire about their well-being to assess their levels of stress and comfort. Through the analysis and comprehension of their workers' requirements, organizations can generate superior quality products. Utilizing predictive analytics to mitigate the frequency and severity of catastrophic events would be advantageous, since Occupational Health and Safety anticipates substantial direct expenses associated with such incidents. If technology can accurately predict the timing and location of accidents, inspection data will be very valuable in directing immediate injury prevention measures and reducing the probability of future incidents. This article presents machine learning techniques for assessing and evaluating risks in the chemical and gas industries using K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Naive Bayes (NB) methods. The support vector machine (SVM) approach demonstrates high performance in criteria such as accuracy, sensitivity, and specificity
Related Content
|
Muhammad Farooq Umer.
© 2026.
28 pages.
|
|
Awesh Khati, Anindita Das, Debajit Karmakar.
© 2026.
26 pages.
|
|
Minhaj Ahmed Qidwai, Mohammad Kabir Gawhari.
© 2026.
20 pages.
|
|
Fozia Asif, Minhaj Ahmed Qidwai.
© 2026.
14 pages.
|
|
Saurabh Chandra, Bhupinder Singh.
© 2026.
20 pages.
|
|
Anshika Tyagi, Vishal Jain.
© 2026.
26 pages.
|
|
Saleema Gulzar, Samina Subzali Vertejee, Tazeen Saeed Ali, Rozina Karmaliani.
© 2026.
16 pages.
|
|
|