Modeling important factors on occupational accident severity factor in the construction industry using a combination of artificial neural network and genetic algorithm.

BACKGROUND: Many occupational accidents annually occur worldwide. The construction industry injury is greater than the average injury to other industries. The severity of occupational accidents and the resulting injuries in these industries is very high and severe and several factors are involved in their occurrence. OBJECTIVE: Modeling important factors on occupational accident severity factor in the construction industry using a combination of artificial neural network and genetic algorithm. METHODS: In this study, occupational accidents were analyzed and modeled during five years at construction sites of 5 major projects affiliated with a gas turbine manufacturing company based on census sampling. 712 accidents with all the studied variables were selected for the study. The process was implemented in MATLAB software version 2018a using combined artificial neural network and genetic algorithm. Additional information was also collected through checklists and interviews. RESULTS: Mean and standard deviation of accident severity rate (ASR) were obtained 283.08±102.55 days. The structure of the model is 21, 42, 42, 2, indicating that the model consists of 21 inputs (selected feature), 42 neurons in the first hidden layer, 42 neurons in the second hidden layer, and 2 output neurons. The two methods of genetic algorithm and artificial neural network showed that the severity rate of accidents and occupational injuries in this industry follows a systemic flow and has different causes. CONCLUSION: The model created based on the selected parameters is able to predict the accident occurrence based on working conditions, which can help decision makers in developing preventive strategies.

Risk assessment of the work-related musculoskeletal disorders based on individual characteristics using path analysis models.

BACKGROUND: This study aimed to assess the risk of work-related musculoskeletal disorders (WMSDs) using the path analysis models. METHODS: This study was carried out on 350 office employees with good general health. All variables were collected using a questionnaire. Personality traits and mental workload of employees were evaluated using the NEO Personality Inventory and the NASA-task load index software, respectively. The individual and personality traits were used as predictor variables, and mental workload (MWL) and body posture scores as mediating variables of the musculoskeletal discomforts. The role of predictor and mediating variables on discomforts was explained based on the path analysis models. RESULTS: The impact coefficient of MWL and posture on WMSDs was significant. The coefficient of the direct effect of body mass index (BMI) and gender on musculoskeletal disorders was significant and positive and the women have reported a higher rate of discomforts. The strongest positive impact of personality traits on MWL and posture was conscientiousness, followed by neuroticism and agreeableness. In return, the strongest negative impact was extroversion, followed by openness. The strongest positive impact of individual factors on MWL and posture was BMI, followed by work experience. CONCLUSION: Gender, BMI, neuroticism, extraversion, and conscientiousness can be strong predictors for musculoskeletal discomforts which can mediate the impact of body posture and mental workload (mediating factors) on musculoskeletal discomfort. Therefore, personality and individual traits can be strong alarming and indicators for risk identification and preventing musculoskeletal disorders when choosing people for a job or task.