The Application of Modified BP Neural Network Method to the Evaluation of the Quality of Teaching

Abstract:

Modified BP neural network method was used to solve the problem of teaching quality evaluation. The neural network was built to fit the function relationship between the second-floor indicator and teaching quality evaluation. So quality teaching evaluation could be implemented. At first, the theory of BP neural network method was introduced, then, students` evaluation of the secondary indicators was taken as inputs, and scores from the Steering Group as output, and 20 lessons scores as researched data, and then, calculating characters of BP method were analyzed. The calculating result showed that the calculation results of the method have the stability, its feasibility was proved. After that, the optimized calculating method was used to optimize result. The calculation results showed that the method had high accuracy, and predictive value calculation error was less than 2.02%, and it verified the feasibility of the method.

• Periodical: Advanced Materials Research (Volume 710)
• Pages: 628-632
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.710.628
• Online since: June 2013
• Authors: Rong Song, Tao Liu
• Keywords: BP Neural Network (BPNN), Evaluation Results, Nonlinear Relationship, Quality of Teaching, Teaching Quality Evaluation System

References

[1] Huang Min, He Zhong-shi. Application of classified technology in higher vocational teaching quality evaluation[J]. Computer Engineering and Design. 2012, 33(3):1257-1261.

[2] Wang Jiaxin, Wang Xuhui. Teaching Evaluation System through Network Based on Data Mining[J]. Journal of Henan Textile College. 2009, 21(3):50—53.

[3] Fu Hai-yan,Fu Mou-song,Zhang Cheng-yi. Application of rough set theory to instruction quality evaluation and analysis[J]. Computer Engineering and Applications. 2007,43(36):214-216.

[4] Fu Hai-yan,Fu Mou-song,Zhang Cheng-yi. Comprehensive evaluation system based on FCM and rough sets theory[J]. Computer Engineering and Applications. 2006, 26(6):1479—1481.

[5] Liu Yan-eheng, Wang Chuan, Wei Yi. Practical calculation of CUEP based on BP neural network[J]. Electronic system protection and control. 2011,39(22):144-149.

[6] Luo Zhi-gao, Zhang Bao-gang, He Xin. On-line crack monitoring of metal deep drawing parts based on BP neural network[J]. Journal of Vibration and Shock. 2012,31(10):102-105.