Student comprehensive quality evaluation method based on genetic algorithm optimization BP neural network

Abstract

The invention discloses a student comprehensive quality evaluation method based on a genetic algorithm optimization BP neural network. The method comprises following steps: S1. constructing sample data in a manner of acquiring sample data of all quality indexes of a student, wherein the sample data servers as training samples of the BP neural network; S2. determining a network topology structure in a manner of determining the number of BP neural network hidden layers and the number of nerve cells in each layer and initializing weight thresholds of the neural network; S3. optimizing weight thresholds in a manner of optimizing the weight thresholds of the BP neural network through a genetic algorithm; S4. training and testing in a manner of training the BP neural network and performing tests by the use of data which is not trained; and S5. evaluating the comprehensive quality of the student in a manner of inputting the data of all the quality indexes of the student to the trained BP neural network so as to evaluate the comprehensive quality of the student. By employing the method, the efficiency and accuracy of the student comprehensive quality evaluation can be improved.

Description

technical field [0001] The invention relates to a method for measuring quality, in particular to a method for measuring comprehensive quality of students based on genetic algorithm optimization of BP neural network. Background technique [0002] The current educational theory believes that everyone can be fully developed in the day after tomorrow. However, the current evaluation system has many disadvantages, and it has become less and less suitable for the development of students, and has run counter to it. Mainly manifested in: [0003] 1. The evaluation method is single, it only evaluates the score of a test paper, and the score is the only way to evaluate; [0004] 2. The evaluation content is single, mainly based on written examinations, and only pays attention to the knowledge mastery of students, and lacks attention to students' learning attitude and learning innovation ability; [0005] 3. The evaluation method is single. Students are only evaluated through subject...

AI Technical Summary

Problems solved by technology

[0003] 1. The evaluation method is single, it only evaluates the score of a test paper, and the score is the only way to evaluate;

[0004] 2. The evaluation content is single, mainly based on written examinations, and only pays attention to the knowledge mastery of students, and lacks attention to students' learning attitude and learning innovation ability;

[0005] 3. The evaluation method is single. Students are only evaluated through subject examinations, and students are gradually trained to be machines that can cope with examinations, which submerges students' extracurricular practice and interpersonal skills.

[0009] However, the existing technology has the following disadvantages: BP neural network is easy to fall into local minimum points, and the convergence speed is slow, resulting in low efficiency of comprehensive quality measurement; SOFM neural network has problems such as distortion from high-dimensional mapping to low-dimensional, etc. As a result, the accuracy of the comprehensive quality measurement is low; when there are too many indicators in the AHP, the data statistics are large. At this time, it is necessary to compare many indicators, but it is difficult to determine the importance of the indicators. It will even have an impact on the consistency of hierarchical single sorting and total sorting, so that the consistency test cannot pass; at the same time, due to the complexity of objective things or the one-sidedness of understanding of things, the eigenvector (weight value) obtained through the constructed judgment matrix ) is not necessarily reasonable, so there is also the problem that the accuracy of the comprehensive quality measurement is low; the AHP is also used in the evaluation of the students' comprehensive quality based on the genetic algorithm to determine the index weight, which will also lead to the accuracy of the comprehensive quality measurement. The evaluation method of comprehensive quality of college students based on fuzzy evaluation needs to determine the evaluation matrix, and the determination of the evaluation matrix is ​​greatly affected by subjective factors, so there is also the problem of low accuracy of comprehensive quality measurement; although fuzzy analytic hierarchy process The consistency of the judgment matrix of the AHP is improved, but this method is affected by more subjective factors to a certain extent, and the determination of the weight of each index needs to be further improved, so the accuracy of the comprehensive quality measurement is also relatively low. Low

Images