Enhanced teaching team evaluation system for vocational colleges.

Area of Science:

• Artificial Intelligence
• Optimization Algorithms
• Educational Technology

Background:

• Effective teaching team evaluation is crucial for vocational college reforms.
• Existing AI systems lack accuracy in predicting teaching evaluations.
• The artemisinin optimization (AO) algorithm shows promise but struggles with local optima.

Purpose of the Study:

• To develop an enhanced AI algorithm for accurate teaching team evaluation.
• To improve the global optimization capabilities of the AO algorithm.
• To identify key factors for constructing a comprehensive teaching evaluation system.

Main Methods:

• Enhanced the AO algorithm with comprehensive learning and dispersed foraging mechanisms, creating CLDMAO.
• Benchmarked CLDMAO against state-of-the-art algorithms using CEC 2017 test functions.
• Developed a binary CLDMAO-KNN model for the teaching team evaluation system.

Main Results:

• CLDMAO demonstrated superior performance, ranking first in most CEC 2017 test functions.
• The binary CLDMAO-KNN model achieved excellent results in error rate, fitness, and feature selection.
• The model successfully identified factors for building a complete evaluation system.

Conclusions:

• The CLDMAO algorithm offers a significant advancement in AI-based optimization.
• The CLDMAO-KNN model provides an effective solution for predicting teaching team evaluations.
• This research facilitates the development of more accurate and insightful educational evaluation systems.