general regression neural network

Assessing faculty members involves formal steps in assessing and informing faculty members about how to do the job and the responsibilities assigned to them in different dimensions. In the present study, the evaluation of faculty members has been done from two educational and research perspectives. The statistical population of the present study is 307 faculty members of one of the public universities. Educational performance information has been prepared in collaboration with the Office of Monitoring, Evaluation and Quality Assurance of the University, as well as research performance information in collaboration with the Vice Chancellor for Research. Data analysis was performed using artificial intelligence method and using MATLAB software. In analyzing the results, first, using threshold clustering, faculty members were divided into four clusters. Then, in the second step of the analysis, the potential of the general regression neural network is used. Using the general regression neural network, the degree to which individuals depend on each of the four clusters is determined. The results show that most faculty members have a good educational situation, while the research status of faculty members is not good. Also, in general, research and educational performance between faculties, Faculty of Chemistry (0.99 and 0.60), first rank and physical education faculties (0.34 and 0.99), basic sciences (0.58 and 0.37) and economic and administrative sciences ( 0.40 and 0.47) gained the next ranks. In the final section, by comparing the two methods, while examining the advantages of using the general regression neural network, the necessary suggestions are presented.