Deep Learning Models for Health and Safety Risk Prediction in Power Infrastructure Projects

Inappropriate management of health and safety (H&S) risk in power infrastructure projects can result in occupational accidents and equipment damage. Accidents at work have detrimental effects on workers, company, and the general public. Despite the availability of H&S incident data, utilizing them to mitigate accident occurrence effectively is challenging due to inherent limitations of existing data logging methods. In this study, we used a text-mining approach for retrieving meaningful terms from data and develop six deep learning (DL) models for H&S risks management in power infrastructure. The DL models include DNN_classify (risk or no risk), DNN_reg1 (loss time), DNN_reg2 (body injury), DNN_reg3 (plant and fleet), DNN_reg4 (equipment), and DNN_reg5 (environment). An H&S risk database obtained from a leading UK power infrastructure construction company was used in developing the models using the H2O framework of the R language. Performances of DL models were assessed and benchmarked with existing models using test data and appropriate performance metrics. The overall accuracy of the classification model was 0.93. The average R² value for the five regression models was 0.92, with mean absolute error between 0.91 and 0.94. The presented results, in addition to the developed user-interface module, will help practitioners obtain a better understanding of H&S challenges, minimize project costs (such as third-party insurance and equipment repairs), and offer effective strategies to mitigate H&S risk.     

Uncovering peer effects mechanisms with weight outcomes using spatial econometrics

Research about how peers influence weight outcomes among adolescents has yielded mixed findings. This paper seeks to not only estimate these peer effects, but also to distinguish between two mechanisms: social multiplier effects and social norm effects. After estimating an augmented spatial autoregressive model using data from the National Longitudinal Study of Adolescent to Adult Health Survey, this study finds significant peer interactions in body mass index, which can be explained by both mechanisms of peer influence; the social norm effect is much larger than the social multiplier effect. The estimated peer effects for overweight and obesity statuses suggest that peer effects are important for overweight status but not for obesity status, and peer influence for overweight status appears to operate solely through social multiplier effect. These findings provide important information for the design of obesity-prevention interventions in schools.     

Can Marriage Reduce Risky Health Behavior for African-Americans?

This paper estimates whether marriage can improve health outcomes for African-Americans through changes in risky health behaviors like smoking, drinking, and drug use. Using data from the National Longitudinal Study on Adolescent Health and propensity score matching methodology to account for the potential selection bias, the results show that marriage does lead to a reduction in risky health behaviors, specifically drinking and drug use. This question has important policy implications because if marriage has the same benefits for African-Americans as it does for the general population, social welfare programs can be re-evaluated to incorporate marriage promotion, and further support can be given to programs that decrease adverse health behaviors.