Bilateral branch network-based academic performance prediction

Tianci Zheng; Zhurong Zhou; Yi Chen; Zhuang Wang

doi:10.1117/12.3032825

5 July 2024 Bilateral branch network-based academic performance prediction

Tianci Zheng, Zhurong Zhou, Yi Chen, Zhuang Wang

Proceedings Volume 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024); 1318479 (2024) https://doi.org/10.1117/12.3032825
Event: 3rd International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 2024, Kuala Lumpur, Malaysia

Abstract

To address the cold start problem in academic performance prediction with student behavioral sequence, we propose a bilateral branch structured neural network DNN-CBLM. DNN-CBLM combines behavioral sequences and students' personal information covariates for jointly time series analysis. The two network branches are designed for feature extraction of student click behavioral time series data and students' background covariates, respectively. The extract features are finally aggregated for performance prediction. In the comparison experiments, it is demonstrated that DNNCBLM has better prediction performance than other models.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Tianci Zheng, Zhurong Zhou, Yi Chen, and Zhuang Wang "Bilateral branch network-based academic performance prediction", Proc. SPIE 13184, Third International Conference on Electronic Information Engineering and Data Processing (EIEDP 2024), 1318479 (5 July 2024); https://doi.org/10.1117/12.3032825

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