Dynamic question generation system for web-based testing using particle swarm optimization

Cheng, Shu-Chen; Lin, Yen-Ting; Huang, Yueh‐Min

doi:10.1016/j.eswa.2007.09.064

Cited by 39 publications

(20 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, the obtained test-sheet is displayed in the user's interface. In practical applications, effective test-sheet composition algorithms play a key role in developing online testing systems [2,3].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Online Test-Sheet Composition Approach Using Genetic Algorithm

Wang

Pan

et al. 2009

Advances in Computation and Intelligence

View full text Add to dashboard Cite

Abstract. In e-learning environment, online testing system can help to evaluate students' learning status precisely. To meet the users' multiple assessment requirements, a new test-sheet composition model was put forward. Based on the proposed model, a genetic algorithm with effective coding strategy and problem characteristic mutation operation were designed to generate high quality testsheet in online testing systems. The proposed algorithm was tested using a series of item banks with different scales. Superiority of the proposed algorithm is demonstrated by comparing it with the genetic algorithm with binary coding strategy.

show abstract

Section: Introductionmentioning

confidence: 99%

“…In order to perform online testing successfully, high quality test-sheets must be constructed in short time from item banks using certain test-sheet composition algorithm [1,2].…”

Section: Introductionmentioning

confidence: 99%

A Novel Online Test-Sheet Composition Approach Using Genetic Algorithm

Wang

Pan

et al. 2009

Advances in Computation and Intelligence

View full text Add to dashboard Cite

show abstract

“…In equation (10), when section k is a mastered section, the arithmetic square root of summation of similarity degree between items belongs to section k in section level is not more than ⌈ q m section ⌉. In the concept level, if concept k is a non-mastered concept, item distribution in concept k should satisfy the following constraint:…”

Section: Definition Of Good Item Distribution In Knowledge Hierarchymentioning

confidence: 99%

“…Some test assembling systems use random or manual strategy [5,6]. Some experts use methods in machine learning to solve the test sheet generation problem: Tabu search [7], genetic algorithm (GA) [8], particle swarm optimization [9,10], etc. Hwang et al adopt clustering, dynamic programming, Tabu search and heuristic algorithm to improve the construction procedure of the test sheet in high quality with specified constraints [6,7].…”

Section: Introductionmentioning

confidence: 99%

An Improved Personalized Genetic Algorithm Incorporated Item Distribution for Test Sheet Assembling

Gu¹,

Niu²,

Chen³

et al. 2014

Appl. Math. Inf. Sci.

View full text Add to dashboard Cite

Abstract:In recent years, computer-based testing has become an effective approach to evaluate students' learning level. In our previous work, a personalized genetic algorithm (PGA) for test sheet assembling was proposed. In this paper, an improved personalized genetic algorithm named PGAC which makes an improvement in the crossover process of PGA is presented. Considering item distribution, an improved algorithm incorporated item distribution (IGAID) based on PGAC is presented to assemble simulation test sheets which have good item distribution in knowledge hierarchy for each student. Experiments and comparison with random assembling algorithm and GA are conducted. The results show that PGAC supports effectively assembling a test sheet with more non-mastered items for different students, and IGAID is capable of effectively constructing simulation test sheets with good item distribution in knowledge hierarchy for each student.

show abstract

“…Wong and Looi (2010) published a detailed study about the application of PSO in the content planning and e-assessment domain. They identified the work of Cheng, Lin and Huang (2009) to be the only known study about a PSO used in an adaptive dynamic question generation system for web-based testing: the key element of their work is the fitness function, which selects a different question on each step in the online test. The fitness function has three parameters: the difficulty level of the question (which has to be as closed as possible to the knowledge level of the user), the question item's relevance (as close as possible to the course content that the instructor wishes to assess the learner on) and the number of times a question is chosen (as low as possible).…”

Section: Application Of Evolutionary Algorithmsmentioning

confidence: 99%