Workplace Incident and Injuries Prevention Using Machine Learning

DOI

10.2991/978-94-6463-136-4_43How to use a DOI?

Keywords

Machine Learning; Health; and Safety; Injuries and Illnesses; Workplace Safety; Preventive Analytics

Abstract

Today in the area of field operations, there is no systematic way to assess and identify if any of the active or pipeline assignments are prone to mishaps, illness, and injuries. Actionable insights are missing from the leading indicators like concern reports, near-misses, or work-stop events reported by the employees. Illness and Injuries (I&I) incidents result in temporary or permanent loss of valuable human assets that are expensive and difficult to replace. Based on historic statistical analysis, injuries and Illnesses are extreme events in operations. Such a highly unbalanced distribution of data makes these events highly unpredictable. Besides unbalanced distribution, normal and incident cases within operations overlap in their characteristics. Incidents and normal cases share a high level of commonalities and therefore are difficult to be separated by any clear decision boundary.

Deep-learning & AutoML framework-based Machine Learning algorithms bring the required computational power to assess and minutely study the characteristics represented in I&I incident vs normal records and can help identify the root cause and segregate them. Anomaly detection is another Machine Learning technique that allows the identification of unusual patterns that are not expected (also referred to as outliers). Considering I&I incidents as anomalies, this paper has given anomaly detection algorithms to separate such incidents from normal events.

Copyright

© 2023 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Arti Deshpande
AU  - Arya Kumar
PY  - 2023
DA  - 2023/05/01
TI  - Workplace Incident and Injuries Prevention Using Machine Learning
BT  - Proceedings of the International Conference on Applications of Machine Intelligence and Data Analytics (ICAMIDA 2022)
PB  - Atlantis Press
SP  - 499
EP  - 512
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-136-4_43
DO  - 10.2991/978-94-6463-136-4_43
ID  - Deshpande2023
ER  -