Akses terbuka Jurnal SINTA 1
Predicting Occupational Stress Using Environmental and Ergonomic Indicators: A Machine-Learning and Discriminant Analysis Approach
Public Health of Indonesia · Vol. 12 No. 3 (2026) · hlm. 217–228
- ISSN
- 2477-1570, 2528-1542
- Terbit
- 2026-09-15
- Penerbit
- YCAB Publisher
- Bahasa
- eng
Abstrak
Background: Due to increasing work pressures triggered by industrialization, high workloads, and unsafe environmental conditions, occupational stress has now become a major issue impacting worker health and productivity. Physical exposures such as noise, heat, poor air quality, and inadequate ergonomics further exacerbate stress responses, particularly in the manufacturing sectors of developing countries with limited occupational health and safety (OHS) systems. Objective: This study seeks to (1) identify significant environmental factors that affect work stress, (2) develop a discriminative function to group workers into high and low stress categories, and (3) evaluate the accuracy and interpretability of the model. This research is expected to make an empirical contribution to the study of K3 with a data-based multivariate approach, as well as provide a scientific basis for improving occupational health policy and management in the manufacturing industry sector. Methods: This study used an explanatory quantitative approach to examine the relationships between variables and to differentiate groups of workers with different stress levels based on the physical conditions of the work environment and ergonomics. Using a sample of 200 workers in a labor-intensive manufacturing industry, this study developed a predictive model using discriminant analysis to classify workers into high- and low-stress categories. The reliability test was carried out using Cronbach's Alpha coefficient, with a value of ≥0.7 as the minimum limit of internal consistency. Data analysis was performed using JASP 0.18.0.0 (Intel) software. Results: The Tests for Multivariate Normality table shows the results of multivariate normality tests based on two parameters, namely skewness (distribution skewness) and kurtosis (distribution skewness). The p-value for skewness is 0.762 and for kurtosis is 0.547, both greater than the threshold of 0.05. Thus, it can be concluded that the data in this model meets the assumption of multivariate normality, since there is no significant difference between the actual data distribution and the multivariate normal distribution. Conclusion: This study shows that physical environmental factors have a significant effect on the stress level of workers in labour-intensive industries. Through linear discriminant analysis, models with one discriminant function achieved 60% accuracy, demonstrating moderate predictive ability. Ergonomics, air quality (PM2.5), and noise variables had the largest contribution to work stress, while temperature, lighting, and age had a smaller influence. These results confirm the importance of controlling physical factors in creating a healthy and productive work environment. The discriminant model used has met the assumption of multivariate normality, so the results are valid for further analysis. Keywords: Occupational Stress; Environmental; Ergonomic; Discriminant Analysis
Kata kunci
Jaringan kolaborasi para penulis
15 penulis · 39 tautan kepenulisan bersama · 14 lintas organisasi
Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.
- Universitas Respati Yogyakarta
- Universitas Nahdlatul Ulama Surabaya
- Sultan Agung Islamic University
- Muhammadiyah University of Yogyakarta
- Politeknik Kesehatan Kemenkes Surakarta
- Afiliasi tidak diketahui
- Organisasi berbeda
- Organisasi sama
- Afiliasi tidak diketahui
- Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
| Rekan penulis | Organisasi | Artikel bersama |
|---|---|---|
| Siti Fadlilah | Universitas Respati Yogyakarta | 2 |
| Ariyanto Nugroho | Universitas Respati Yogyakarta | 2 |
| Maria Denliana Polnesta Ita | Universitas Respati Yogyakarta | 2 |
| Merita Eka Rahmuniyati | Universitas Respati Yogyakarta | 2 |
| Yelli Yani Rusyani | Universitas Respati Yogyakarta | 2 |
| Ani Farida | Universitas Respati Yogyakarta | 2 |
| Ara’ Afliyatun Nur Sari | Universitas Respati Yogyakarta | 2 |
| Difran Nobel Bistara | Universitas Nahdlatul Ulama Surabaya | 1 |
| Santi Damayanti | Universitas Respati Yogyakarta | 1 |
| Agus Suharto | Muhammadiyah University of Yogyakarta | 1 |
| Sugiyarto Sugiyarto | Politeknik Kesehatan Kemenkes Surakarta | 1 |
| Herry Susanto | Sultan Agung Islamic University | 1 |
Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.