Teaching evaluation on a WebGIS course based on dynamic self-adaptive teaching-learning-based optimization

Teaching evaluation on a WebGIS course is a multi-objective nonlinear high-dimensional NP-hard problem. The index system for the teaching evaluation of a WebGIS course, including teacher- and student-oriented sub-systems, is first established and used for questionnaires from 2013 to 2017. The multi-objective nonlinear high-dimensional evaluation model is constructed and then solved via dynamic self-adaptive teaching-learning-based optimization (DSATLBO). DSATLBO is based on teaching-learning-based optimization with five improvements: dynamic nonlinear self-adaptive teaching factor, extracurricular tutorship factor, dynamic self-adaptive learning factor, multi-way learning factor, and non-dominated sorting factor. WebGIS teaching performance is fully evaluated based on questionnaires and DSATLBO. Optimal weights and weighted scores from DSATLBO are compared with those from the non-dominated sorting genetic algorithm-II using the Pareto front, coverage to two sets, and spacing of the non-dominated solution sets to validate the performance of DSATLBO. The results show that DSATLBO can be uniformly distributed along the Pareto front. Therefore, DSATLBO can efficiently and feasibly solve the multi-objective nonlinear high-dimensional teaching evaluation model of a WebGIS course. The proposed teaching evaluation method can help reflecting the quality of all aspects of classroom teaching and guide the professional development of students.