Font Size: a A A

Research On System Of Intelligent Test Paper Composition Based On Genetic Simulated Annealing Algorithm

Posted on:2012-01-07Degree:MasterType:Thesis
Country:ChinaCandidate:Y D YuFull Text:PDF
GTID:2178330335972440Subject:Computer technology
Abstract/Summary:PDF Full Text Request
Examination is a most important part of the teaching process, while how to choose topics and organize papers are the key factors in deciding whether the examination is a success or a failure. With the widely use of computer in education, the demand of intelligent test paper composition becomes more and more urgent.Intelligent test paper composition is to compose a test paper with specific total point, type, quantity, knowledge, difficulty and so on, According to a certain requirement from database automatically, the quality and efficiency of composing test paper intelligently is absolutely determined by the design of database and algorithm to extract examination question. For satisfying consumer's variable demands it is very important to compose a paper quickly and reliably by how to design an algorithm.On the basis of analyzing a large quantity of references home and abroad, the writer has made a survey on intelligent test paper composition. The traditional method is using the sole algorithm, like the recollection trial method, the genetic algorithm and the simulation annealing algorithm stochastically and so on. They can finally compose an examination paper, but it has its shortcomings. The synthesis existing algorithm's characteristic and the insufficiency, the writer proposed intelligent test paper composition based on hybrid intelligent algorithm.This article works out a composition system, in which the stochastic algorithm, genetic simulated annealing algorithm, the genetic algorithm and the heredity simulation annealing algorithm are used. Under the same evaluation function as well as the same question bank, the writer makes a comparison among papers. The new method is more efficient and easier to get over immature convergence than the traditional algorithms and meets all the users' requirements only if the quantity of test questions is moderate and reasonable.Delphi 7.0 and Microsoft SQL Server 2000 are used to develop foreground application and background database respectively. Using modular design ideas, the system is a set of the exam-question bank System, including user management, test paper input and maintenance, producing test paper and other major functions.
Keywords/Search Tags:Simulated Annealing Algorithms, Genetic Algorithm, Genetic Simulated Annealing Algorithm, and Intelligent Test Paper Composition
PDF Full Text Request
Related items