<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>According to Malaysia's Department of Occupational Safety and Health (DOSH), workplace accidents have increased dramatically as the country's economy has grown rapidly. The purpose of this study is to identify the trends that lead to fatal workplace accidents in Malaysia. This study investigated 505 fatal accident instances from fifteen industries, using both qualitative and quantitative methodologies. The DOSH discovered and reported these fatalities (2010-2020). Data was organized and coded, then analyzed using Spearman's rank order correlation, frequency analysis, Eta squared, Cramer's V, and Chi-square. Moreover, neurolinguistic programming was used to generate the word cloud and sentiment analysis. Furthermore, light gradient-boosting machine learning was used to better understand the causes of fatalities. The outcomes indicated that fatal falls from heights were the leading cause of fatal accidents (32%). General laborers were the most susceptible to fatal accidents (60%). Contract workers were more likely to die in construction accidents (64%). The findings of this study gave useful insights into workplace fatal accident trends and preventive measures throughout sectors.</p>
</abstract>

According to Malaysia's Department of Occupational Safety and Health (DOSH), workplace accidents have increased dramatically as the country's economy has grown rapidly. The purpose of this study is to identify the trends that lead to fatal workplace accidents in Malaysia. This study investigated 505 fatal accident instances from fifteen industries, using both qualitative and quantitative methodologies. The DOSH discovered and reported these fatalities (2010-2020). Data was organized and coded, then analyzed using Spearman's rank order correlation, frequency analysis, Eta squared, Cramer's V, and Chi-square. Moreover, neurolinguistic programming was used to generate the word cloud and sentiment analysis. Furthermore, light gradient-boosting machine learning was used to better understand the causes of fatalities. The outcomes indicated that fatal falls from heights were the leading cause of fatal accidents (32%). General laborers were the most susceptible to fatal accidents (60%). Contract workers were more likely to die in construction accidents (64%). The findings of this study gave useful insights into workplace fatal accident trends and preventive measures throughout sectors.

Statistical Analysis of Occupational Fatal Accidents for Risk Assessment

Laboratory of Automation and Manufacturing

Department of Chemical and Environmental Engineering

Faculty of Engineering, University Putra Malaysia

Safety Engineering Interest Group, Department of Chemical and Environmental Engineering, Faculty of Engineering

SEEU Review

This work is licensed under the Creative Commons Attribution 4.0 International License.

{"article-title":"Statistical Analysis of Occupational Fatal Accidents for Risk Assessment"}

According to Malaysia's Department of Occupational Safety and Health (DOSH), workplace accidents have increased dramatically as the country's economy has grown...

Statistical Analysis of Occupational Fatal Accidents for Risk Assessment

Online veröffentlicht: 26. Juni 2024

Seitenbereich: 149 - 173

DOI: https://doi.org/10.2478/seeur-2024-0086

Schlüsselwörter
Risk Assessment, Prevention Management, Machine Learning, Neuro-Linguistic Programming, Mixed-Method Analysis

© 2024 Hanane Zermane et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Statistical Analysis of Occupational Fatal Accidents for Risk Assessment

Online veröffentlicht: 26. Juni 2024

Seitenbereich: 149 - 173

DOI: https://doi.org/10.2478/seeur-2024-0086

SchlüsselwörterRisk Assessment, Prevention Management, Machine Learning, Neuro-Linguistic Programming, Mixed-Method Analysis

© 2024 Hanane Zermane et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Schlüsselwörter
Risk Assessment, Prevention Management, Machine Learning, Neuro-Linguistic Programming, Mixed-Method Analysis