Research on Student Behavior Recognition and its Application based on Machine Learning

DOI

10.2991/978-2-38476-346-7_10How to use a DOI?

Keywords

component; student behavior recognition; machine learning; feature extraction; behavior analysis

Abstract

This exploration aims to study how machine learning technology can identify student behavior and thus strengthen the supervision and management efficiency of educational venues. High-definition monitoring equipment was deployed in a middle school, and advanced sound capture technology was used with the data support of the learning management system to collect and study all the activities of students in detail. Using optical flow, short-time Fourier transform and random forest techniques, data was preprocessed, features were extracted and models were trained. The latest research found that the constructed model performed well in identifying collective activities, with an accuracy rate of up to 95% and an AUC value of 0.97; its performance was slightly insufficient in high-difficulty behavior recognition such as gesture recognition and complex behavior analysis. The research results show that although this model performs well in some specific behavior recognition tasks, it still needs further improvement and enhancement when facing more varied and complex behavior patterns. Future scientific research will focus on improving the model’s wide adaptability and real-time processing efficiency to better meet the requirements of diverse educational environments.

Copyright

© 2024 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Lei Liu
PY  - 2024
DA  - 2024/12/27
TI  - Research on Student Behavior Recognition and its Application based on Machine Learning
BT  - Proceeding of the 2024 International Conference on Diversified Education and Social Development (DESD 2024)
PB  - Atlantis Press
SP  - 70
EP  - 76
SN  - 2352-5398
UR  - https://doi.org/10.2991/978-2-38476-346-7_10
DO  - 10.2991/978-2-38476-346-7_10
ID  - Liu2024
ER  -