Computer Intelligent Test Paper System Based on Genetic Algorithm

Hongming Wang


The rapid development of the Internet has brought tremendous changes to people’s lives. Through the network function, the online examination is gradually accepted by various educational and teaching institutions. Currently, online exams have become the main method of teaching evaluation. In order to solve the problem of intelligent test paper more effectively, this paper proposes a mufti-threaded intelligent test paper strategy based on genetic algorithm, and designs the computer system structure in the standard test question bank. Convergence simulation and experimental results show that the algorithm is better than simple particle swarm optimization algorithm, simple genetic algorithm and its improved algorithm. Established a mathematical model and objective function for test paper composition, and proposed an intelligent test paper composition strategy based on genetic algorithm. The investigator used overall coding, crossover and mutation operations to improve the global optimization capability and convergence speed. It overcomes the phenomenon of premature and improves the accuracy and speed of convergence. It has the advantages of strong optimization ability and good stability.


Genetic Algorithm; Intelligent Test Paper Generation System; Test Paper Generation Algorithm

Full Text:


Included Database


Hadi M K, Othman M L, Wahab N I A. Special Protection and Control Scheme for Transmission Line Overloading Elimination Based on Hybrid Differential Evolution/Electromagnetism-LikeAlgorithm [J].Journal of Electrical Engineering andTechnology, 2017, 12.

Lobiyal D K, Mansotra V, Singh U. [Advances in Intelligent Systems and Computing] Next-Generation Networks Volume 638 || Genetic Algorithm-Based Routing Protocol for Energy Efficient Routing in MANETs [J]. 2018, 10.1007/978-981-10-6005-2 (Chapter 4): 33–40.

Huaqiang L, Ziyao W,Jinzhu F, et al.Adaptability Planning of Transmission Grid with Integration of High-proportion Renewable Energy[J]. IOP Conference Series: Earth and Environmental ence, 2019, 267(2): 022013 (8pp).

Huang T, Cao Q, Liu J, et al. A multistage depressed collectors design tool for traveling wave tubes based on non-dominated sorting genetic algorithm II [J]. 2018: 175–176.

Liwen Z, Zhuo S, Chao Z, et al. Numerical Investigation of the Dynamic Responses of Long-Span Bridges with Consideration of the Random Traffic Flow Based on the Intelligent ACO-BPNN Model [J]. IEEE Access, 2018, 6: 28520–28529.

Mohammadi M, Lakestani M, Mohamed M H. Intelligent parameter optimization of Savonius rotor using Artificial Neural Network and Genetic Algorithm [J]. Energy, 2018, 143 (jan.15): 56–68. [7] Zhou H, Yanrui L, Yang C, et al. Mixed-Framework-Based Energy Optimization of Chemi-Mechanical Pulping [J]. IEEE Transactions on Industrial Informatics, 2019, PP (99): 1–1.

Bi Y, Kapoor S, Bhatia R. [Studies in Computational Intelligence] Intelligent Systems and Applications Volume 751 || A Multi- objective Genetic Algorithm for Path Planning with Micro Aerial Vehicle Test Bed [J]. 2018, 10.1007/978-3-319-69266-1 (Chapter 4): 59–82.

Subramanyam T C, Ram S S T, Subrahmanyam J B V. Neural network-based allocation and self-improved firefly-based optimal sizing of fuel cells in distributed generation systems [J]. Control and Cybernetics, 2018, 47(4): 357–381.

Huang H, Liu F, Yang Z, et al. Automated Test Case Generation Based on Differential Evolution with Relationship Matrix for iFogSim Toolkit [J]. IEEE Transactions on Industrial Informatics, 2018, PP (11): 1–1.

Jaiswal G C, Ballal M S, Venikar PA, et al. Genetic algorithm–based health index determination of distribution transformer [J]. European transactions on electrical power engineering, 2018, 28(5): e2529.1–e2529.12.

DOI: http://dx.doi.org/10.18282/l-e.v9i3.1599


  • There are currently no refbacks.