RESUMO
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.
Assuntos
Aprendizado de Máquina , Redes Neurais de Computação , Eletroencefalografia/métodos , Carga de Trabalho , Carvão MineralRESUMO
Work stress among coal miners may affect health and well-being, which could have safety implications for their work. The purpose of the present study is to explore the mechanism of how psychosocial safety climate, work stress and job burnout impact on the unsafe behavior of miners. A cross-sectional survey was conducted in Shanxi Province, China during 3 months in 2018. A total of 862 male miners were recruited from 30 coal mines; participants were aged 23-49 years (M = 33.54 yrs), with mining experience of between 4 and 23 years (M = 7.36 yrs). Participants completed a cross-sectional survey which examined psychosocial safety climate, work stress, and burnout of miners. Structural equation modeling and hierarchical linear modeling were used to explore the mechanisms of psychosocial safety climate on unsafe behavior. Findings revealed that psychosocial safety climate can decrease the miners' unsafe behavior through the mediating role of work stress and job burnout. Ultimately these findings guide for coal administrators to avoid miners' unsafe behavior.
Assuntos
Esgotamento Profissional/psicologia , Mineradores/psicologia , Saúde Ocupacional , Cultura Organizacional , Adulto , Esgotamento Profissional/epidemiologia , China/epidemiologia , Estudos Transversais , Humanos , Masculino , Pessoa de Meia-Idade , Mineradores/estatística & dados numéricos , Saúde Ocupacional/estatística & dados numéricos , Adulto JovemRESUMO
Work-family conflict among underground coal miners not only leads their mental disorders but also may cause coal accidents. The purpose of the study is to explore the relationship between Work-family conflict (WFC) and mental health, testing the Psychological capital (PsyCap) plays a moderating role in this relationship. The cross-sectional survey was performed in Shanxi Province, China during the August to October 2017. 986 miners from five coal mines were recruited in this study. Hierarchical linear regression analyses were performed to explore the moderating role of psychological capital. The result showed that Work-family conflict was positively related to Anxiety Symptoms and Depressive Symptoms. Psychological capital (PsyCap) moderated the relationship between WFC and Anxiety, Depressive Symptoms. The findings illustrate that psychological capital was an important way to improve miners' mental health. Managers should promote organization support and investment in PsyCap to improve miners' mental health.
Assuntos
Ansiedade/epidemiologia , Minas de Carvão/estatística & dados numéricos , Depressão/epidemiologia , Mineradores/estatística & dados numéricos , Equilíbrio Trabalho-Vida , Adulto , China/epidemiologia , Estudos Transversais , Humanos , MasculinoRESUMO
Entrusting a third party and implementing a trade-in program are two main ways for manufacturers to collect used products. By establishing two closed-loop supply chain competition models, this study analyses the co-existence conditions of third-party collection and trade-in collection adopted by competitive manufacturers M1 and M2 respectively. Then, based on an analysis of the impact of R&D improvement on the collection decision, the impacts of horizontal cross-shareholding and financing parameters on the collection decision and profit are explored, respectively. The results show that when consumers are low-value customers who prefer cash back over purchasing a new product, competitive manufacturers with different collection channels consider improving their R&D level. The R&D improvement of M1 reduces the trade-in price and the third-party collection price, and shrinks the collection market. However, the R&D improvement of M2 increases the trade-in price and the third-party collection price. In addition, the trade-in collection market shrinks and the third-party collection market increases. In the case of cross-shareholding, the increase of M1's share helps reduce the trade-in price and the third-party collection price, while the increase of M2's share helps increase the trade-in price and the third-party collection price. In factoring financing, the increase in the factoring rate reduces the total collection quantity in the collection market, but helps improve the earnings of M2 from the collection of used products. In the case of equity financing, the increase in equity not only increases the total amount of collection, but also the earning of M1 from the collection of used products.
RESUMO
BACKGROUND: In China, over 80% of all work-related deaths in the mining industry occur in coal mines and human factors constitute 85% of the direct causes of coal mine accidents, which indicates that significant shortcomings currently exist in the safety behavior management of Chinese coal mine workers. We aimed to verify the impact of human psychological behavior in coal mine accidents systematically through experimental study, theoretical analysis and management application. METHODS: Four test instruments (Sensory and cognitive capacity test, Sixteen-Personal Factor Questionnaire, Symptom Checklist 90 Questionnaire and the supervisors' evaluation) were employed from November 2013 to June 2014 to identify unsafe behavior factors, the self-established Questionnaire of Safety Behavior Norms (QSBN) was also used to propose the safety behavior countermeasures of coal mine employees. RESULTS: The mental health of most coal mine workers' is relatively poor. The sensory and cognitive capacity of those in different work posts varies greatly, as does the sense of responsibility. Workers are susceptible to external influences, and score low in site management. When the 16-PF and SCL-90 sensory and cognitive assessments were combined, the psychological index predictive power was greatest for estimating sense of efficiency and degree of satisfaction in internal evaluations, while at the same time lowest for estimating control of introversion-extroversion and stress character. CONCLUSION: The psychological indicators can predict part of employee safety behavior, and assist a coal mine enterprise to recruit staff, develop occupational safety norms and improve the working environment.