Related Experiment Video
Updated: Oct 12, 2025
10:04
A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes
Published on: March 3, 2018
6.8K
Analysis of College Student Registration Management and Change Prediction Based on Mutated Fuzzy Neural Network
Yao Wang1,2, Lie Jiao3, Chunzhi Liu2
1Management Science and Engineering, Liaoning Technical University, Fuxin 123000, Liaoning, China.
Computational Intelligence and Neuroscience
|November 26, 2021
Summary
Predicting student registration changes is crucial for universities. A new mutated fuzzy neural network (MFNN) model, enhanced with principal component analysis (PCA), accurately forecasts these changes, improving university management.
Area of Science:
- Educational Data Mining
- Artificial Intelligence in Education
- Higher Education Management
Background:
- Student registration changes are common in universities, posing management challenges.
- Current statistical methods for analyzing these changes are often cumbersome and lack predictive power.
- There's a need for advanced technical methods, like data mining, for effective student registration management.
Purpose of the Study:
- To develop an accurate prediction model for student academic registration changes in universities.
- To provide university management with a tool for early warning and informed decision-making regarding student registration.
- To explore the application of data mining techniques in managing student academic trajectories.
Main Methods:
- Development of a mutated fuzzy neural network (MFNN) prediction model for student registration variations.
- Integration of principal component analysis (PCA) to optimize the MFNN model's training efficiency and prediction accuracy.
- Defining prediction model parameters, formulating an optimization problem, and proposing an objective optimization function.
Main Results:
- The proposed MFNN model, enhanced with PCA, demonstrated significant effectiveness in predicting individual student registration changes.
- The model achieved a high prediction accuracy of approximately 92.91%.
- Optimization through PCA improved both the efficiency of model training and the overall correct prediction rate.
Conclusions:
- The mutated fuzzy neural network (MFNN) model offers a powerful and accurate solution for predicting student registration changes in higher education.
- The integration of PCA significantly enhances the model's performance, making it a valuable tool for university administration.
- This data-driven approach provides a supplementary decision-making reference for school teaching managers, improving registration management.
