EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A data-driven approach to coal mine safety performance using swarm intelligence and ensemble learning

Yejiao Liu, Jinliang Li, Ting Teng, Wenjie Yan, Huixin Wang, Dongqiang Cao, Fu Gao, Fengyi Jiang

Advances in Differential Equations and Control Processes · 05.06.2026

DOI: 10.59400/adecp4235 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advances in Differential Equations and Control Processes, online erschienen am 05.06.2026. Verfasst von Yejiao Liu und 7 weiteren Autor:innen. Die Arbeit nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

At present, there are some shortcomings in the dynamic adaptability and subjectivity of coal mine safety performance evaluation, and it is difficult to realize the short-term safety performance evaluation with full staff participation. In this study, based on the Analytic Network Process-Technique for Order Preference by Similarity to an Ideal Solution (ANP-TOPSIS), a coal mine safety performance evaluation index system was constructed, and the evaluation index was optimized by a particle swarm optimization algorithm to improve the accuracy of dynamic index weight allocation. Emotional processing analysis technology is introduced, and the survey evaluation form is designed to quantify the subjective emotional tendency. Statistical methods such as the intra-group correlation coefficient, consistency test and regression model are used to improve the reliability of expert scoring data and quantitatively analyze individual subjective differences. Using the random forest classification method, combined with the term frequency-inverse document frequency (TF-IDF) to vectorize the text data, a bottom-up dynamic evaluation method of employee safety performance based on machine learning is established. The random forest model achieved an average F1-score of 0.929, with all six safety dimensions scoring above 0.8. The example shows that the short-process long-period safety performance evaluation based on ANP-TOPSIS-PSO, and a random forest model can accurately describe the coal mine safety appearance and provide scientific decision support for improving the coal mine safety performance level.

Zitieren

APA

Liu, Y., Li, J., Teng, T., Yan, W., Wang, H., Cao, D., Gao, F., & Jiang, F. (2026). A data-driven approach to coal mine safety performance using swarm intelligence and ensemble learning. Advances in Differential Equations and Control Processes. https://doi.org/10.59400/adecp4235

Vancouver

Liu Y, Li J, Teng T, Yan W, Wang H, Cao D, et al. A data-driven approach to coal mine safety performance using swarm intelligence and ensemble learning. Advances in Differential Equations and Control Processes. 2026. doi:10.59400/adecp4235

BibTeX
@article{Liu2026,
  author = {Liu, Yejiao and Li, Jinliang and Teng, Ting and Yan, Wenjie and Wang, Huixin and Cao, Dongqiang and Gao, Fu and Jiang, Fengyi},
  title = {A data-driven approach to coal mine safety performance using swarm intelligence and ensemble learning},
  journal = {Advances in Differential Equations and Control Processes},
  year = {2026},
  doi = {10.59400/adecp4235}
}
Kostenlos starten →