RESUMEN
Fatigue of miners is caused by intensive workloads, long working hours, and shift-work schedules. It is one of the major factors increasing the risk of safety problems and work mistakes. Examining the detection of miner fatigue is important because it can potentially prevent work accidents and improve working efficiency in underground coal mines. Many previous studies have introduced feature-based machine-learning methods to estimate miner fatigue. This work proposes a method that uses electroencephalogram (EEG) signals to generate topographic maps containing frequency and spatial information. It utilizes a convolutional neural network (CNN) to classify the normal state, critical state, and fatigue state of miners. The topographic maps are generated from the EEG signals and contrasted using power spectral density (PSD) and relative power spectral density (RPSD). These two feature extraction methods were applied to feature recognition and four representative deep-learning methods. The results showthat RPSD achieves better performance than PSD in classification accuracy with all deep-learning methods. The CNN achieved superior results to the other deep-learning methods, with an accuracy of 94.5%, precision of 97.0%, sensitivity of 94.8%, and F1 score of 96.3%. Our results also show that the RPSD-CNN method outperforms the current state of the art. Thus, this method might be a useful and effective miner fatigue detection tool for coal companies in the near future.
Asunto(s)
Aprendizaje Automático , Redes Neurales de la Computación , Electroencefalografía/métodos , Carga de Trabajo , Carbón MineralRESUMEN
BACKGROUND: Exposure to small confined spaces evokes physiological responses such as increased heart rate in claustrophobic patients. However, little is known about electrocortical activity while these people are functionally exposed to such phobic situations. The aim of this study was to examine possible changes in electrocortical activity in this population. METHOD: Two highly affected patients with claustrophobia and two healthy controls participated in this in vivo study during which electroencephalographic (EEG) activity was continuously recorded. Relative power spectral density (rPSD) was compared between two situations of being relaxed in a well-lit open area, and sitting in a relaxed chair in a small (90 cm × 180 cm × 155 cm) chamber with a dim light. This comparison of rPSDs in five frequency bands of EEG was intended to investigate possible patterns of change in electrical activity during fear-related situation. This possible change was also compared between claustrophobic patients and healthy controls in all cortical areas. RESULTS: Statistical models showed that there is a significant interaction between groups of participants and experimental situations in all frequency bands (P < 0.01). In other words, claustrophobic patients showed significantly different changes in electrical activity while going from rest to the test situation. Clear differences were observed in alpha and theta bands. In the theta band, while healthy controls showed an increase in rPSD, claustrophobic patients showed an opposite decrease in the power of electrical activity when entering the confined chamber. In alpha band, both groups showed an increase in rPSD, though this increase was significantly higher for claustrophobic patients. CONCLUSION: The effect of in vivo exposure to confined environments on EEG activity is different in claustrophobic patients than in healthy controls. Most of this contrast is observed in central and parietal areas of the cortex, and in the alpha and theta bands.