Application of Structural Equation Modeling (SEM) and an Adaptive Neuro-Fuzzy Inference System (ANFIS) for Assessment of Safety Culture: An Integrated Modeling Approach

Assessing the Mediating Role of Safety Communication Between Safety Culture and Employees Safety Performance

The main purpose of this research was to investigate the mediating role of safety communication (SCO) in the relationship between safety culture (SC) and safety performance (SP) amongst employees in the petrochemical industry. Safety communication methods not only enhance working conditions but also have a positive impact on employee's behaviors and attitudes toward safety leading toward reduced incidents in the workplace environment. A stratified sampling method was followed to collect data in the petrochemical industry in Malaysia. Structural equation modeling (SEM) was utilized to analyze the hypothesized model, using data from 320 participants. The findings reveal that safety communication partially mediates the association between safety culture and safety performance. Further, safety culture was found to have a significant and positive effect on safety performance. This -study makes a significant theoretical contribution by providing empirical evidence on the direct and indirect relationship between safety culture and safety performance in the petrochemical industry.

Ability of neural network cells in learning teacher motivation scale and prediction of motivation with fuzzy logic system

We employed a new approach in the field of social sciences or psychological aspects of teaching besides using a very common software package that is Statistical Package for the Social Sciences (SPSS). Artificial intelligence (AI) is a new domain that the methods of its data analysis could provide the researchers with new insights for their research studies and more innovative ways to analyze their data or verify the data with this method. Also, a very significant element in teaching is teacher motivation that is the trigger that pushes the teachers forward, depending on some internal and external factors. In the current study, seven research questions were designed to explore different aspects of teacher motivation, and they were analyzed via SPSS. The current study also compared the results by using an adaptive neuro-fuzzy inference system (ANFIS). Due to the similarity of ANFIS to humans' brain intelligence, the results of the current study could be similar to humans regarding what happens in reality. To do so, the researchers used the validated teacher motivation scale (TMS) and asked participants to fill the questionnaire, and analyzed the results. When the inputs were added to the ANFIS system, the model indicated a high accuracy and prediction capability. The findings also illustrated the importance of the tuning model parameters for the ANFIS method to build up the AI model with a high repeatability level. The differences between the results and conclusions are discussed in detail in the article.