SHAP-driven insights into multimodal data: behavior phase prediction for industrial safety applications.
Xiangchun Li1, Shuhao Zhang2, Xiaowei Li1
1School of Emergency Management and Safety Engineering, China University ofMining and Technology-Beijing, Beijing, 100083, China.
Scientific Reports
|October 7, 2025
Summary
This study uses AI and machine learning (ML) to predict unsafe coal miner behaviors using physiological data. XGBoost achieved 97.78% accuracy, showing potential for real-time safety interventions.
Area of Science:
- Occupational Safety and Health
- Artificial Intelligence in Mining
- Biomedical Signal Processing
Background:
- Unsafe behaviors are a leading cause of coal mining accidents, complicating safety management.
- Predicting worker behavior is crucial for proactive safety interventions.
- Physiological characteristics offer potential indicators of behavioral states.
Purpose of the Study:
- To develop an AI/ML framework for predicting coal miner behavior states.
- To identify key physiological features influencing behavior prediction.
- To enhance coal mine safety through early warning systems and real-time interventions.
Main Methods:
- Development of a behavior state prediction framework using AI and ML algorithms.
- Evaluation of eight ML algorithms, including XGBoost, KNN, and LightGBM.
- Identification of significant features using SHAP (Shapley Additive Explanations) analysis.
Main Results:
- XGBoost demonstrated superior performance with 97.78% accuracy, 98.25% recall, and 97.86% F1-score.
- Key predictors identified include heart rate variability (TP/ms²), electromyography median frequency (EMF), respiration range, and RMS.
- SHAP analysis revealed distinct patterns and actionable rules for safety improvements.
Conclusions:
- Physiological features hold significant predictive power for worker behavior in mining.
- AI-driven analysis of wearable sensor data can enable real-time safety management.
- Further validation with actual miners is recommended to confirm generalizability.
Related Concept Videos
01:25Distribution Reliability and Automation
678
Distribution reliability in electrical power systems is critical for ensuring an uninterrupted power supply to consumers at minimal cost. According to IEEE Standard Terms, reliability is the probability that a device will function without failure over a specified time period or amount of usage. For electric power distribution, this translates to maintaining continuous power supply and addressing customer concerns over power outages. Several indices, as defined by IEEE Standard 1366-2012, are...
678
01:21Pilot and Numeric Relaying
589
Pilot relaying is a type of differential protection used in power systems. It compares electrical quantities at the terminals of equipment via a communication channel instead of direct relay interconnection. This method is essential for transmission lines where the terminals are far apart, typically up to 80 km for lines with 69 to 115 kV ratings. Four types of communication channels are used for pilot relaying:
589
01:25Multimachine Stability
698
Multimachine stability analysis is crucial for understanding the dynamics and stability of power systems with multiple synchronous machines. The objective is to solve the swing equations for a network of M machines connected to an N-bus power system.
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
698
01:18Steps in Outbreak Investigation
779
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
779
01:25Interpreting Run Charts
3.2K
Run charts, essentially line graphs plotted over time, serve as fundamental yet effective tools for process analysis. They chronicle data sequentially, facilitating the identification of trends, shifts, or cyclical movements. This graphical representation is instrumental in determining whether a process is stable or exhibits signs of potential instability indicative of special cause variation. In the healthcare domain, run charts depict infection rates over time, enabling hospitals to monitor...
3.2K
01:11Hazard Rate
525
The hazard rate, also known as the hazard function or failure rate, is a statistical measure used to describe the instantaneous rate at which an event occurs, given that the event has not yet happened. From a probabilistic perspective, it represents the likelihood that a subject will experience the event in a very small time interval, conditional on surviving up to the beginning of that interval. In terms of frequency, the hazard rate can be viewed as the ratio of the number of events to the...
525