Attendance data based on BP neural network model

Jiacheng Wu

doi:10.1117/12.2639487

17 May 2022 Attendance data based on BP neural network model

Jiacheng Wu

Proceedings Volume 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022); 122595G (2022) https://doi.org/10.1117/12.2639487
Event: 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing, 2022, Kunming, China

Abstract

Neural networks have better classification and memory capabilities, so the corresponding learning algorithms have become the focus of research. The purpose of this paper is to analysis of attendance data based on BP neural network model. The basic theory and technology are introduced, and the attendance rate of M University students is predicted by model, and compared with the actual number. In the process of solving and drawing conclusions, there is such a relationship between the predefined parameters of the neural network model and the required quantities, after selecting the initial value, the whole algorithm will solve the optimal value in a specific direction. In order to avoid errors caused by the selection of initial values and the creation of local minima, the verification data is used after microprocessing and continuous debugging of the program. The overall error of 10 students' attendance prediction fluctuates between 3 and 11. The parameters of training volume, training number, and learning rate in this paper are suitable for the prediction model of attendance.

Citation Download Citation

Jiacheng Wu "Attendance data based on BP neural network model", Proc. SPIE 12259, 2nd International Conference on Applied Mathematics, Modelling, and Intelligent Computing (CAMMIC 2022), 122595G (17 May 2022); https://doi.org/10.1117/12.2639487

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available