A Study of Applying Particle Swarm Optimization and Knowledge Structure on Adaptive Testing

• Main Authors: I-CHUN,PAN, 潘逸峻
• Other Authors: Shu-Chen Cheng
• Format: Others
• Language: zh-TW
• Online Access: http://ndltd.ncl.edu.tw/handle/89554627375585954328

碩士 === 南台科技大學 === 資訊工程系 === 99 === The main purpose of adaptive testing is able to provide questions in accordance with learners' competence level, such as deciding the difficulty of the next question according to answering tests. This research is based on Particle Swarm Optimization (PSO), and integrates with knowledge structure to develop a system of adaptive testing. In most system of adaptive testing, an ability value is given to each testee in the approach of evaluating learning ability and it shows the testee’s understanding of a subject, but a subject is usually comprised of many kind of knowledge. Such as English, it contains reading, grammar, vocabularies, writing, listening and etc, and the learners may only excel certain items. Therefore, the method of evaluating learning ability in this system of adaptive testing of the research adopts multiple competency assessment, and each section includes an ability value. Via the approach, the system can set dynamically questions correlated highly with learners' competence level.