A Self-Adaptive Monitoring and Analysis System for Students´ Behaviors in Laboratory Course

Recently, there are many problems in software laboratory course management. It is, particularly, widespread that student play video games or do other things which are unrelated to the course. However, most of present monitoring software are all based on the operation of teachers, rather than a real-time system, which is very inconvenient. In order to carry out the laboratory course management better and help teachers to monitor and analyze students´ behaviors of operating computer, we design and implement a model of Self-adaptive Monitoring and Analysis System (SMAS) for students´ behaviors in laboratory course. For monitoring, we implement a module which uses the technology neural-network-based expert system, with which we can monitor the students´ behavior real-time and self-adaptively. For analysis, with the methodologies such as Factor Analysis, Cluster Analysis, and Discriminant Analysis, we propose and implement an evaluation algorithm, which can evaluate the students´ performance in a course quantificationally and obviously.