Related Experiment Video
Updated: Oct 5, 2025

Project-Based Learning Guidelines for Health Sciences Students: An Analysis with Data Mining and Qualitative Techniques
Published on: December 9, 2022
Research on Teaching Practice of Blended Higher Education Based on Deep Learning Route
Yang Li1, Lijing Zhang1, Yuan Tian1
1Aviation University of Air Force, Changchun, Jilin 130022, China.
This study introduces a hybrid education teaching quality evaluation system using a deep belief network (DBN) model. The DBN model demonstrates effective learning and low fitting errors, ensuring accurate hybrid teaching quality assessments in colleges.
Area of Science:
- Educational Technology
- Artificial Intelligence in Education
- Higher Education Pedagogy
Background:
- Traditional teaching quality evaluation methods often lack the sophistication to capture the nuances of hybrid educational models.
- The integration of online and in-person learning necessitates advanced evaluation systems.
- Deep learning approaches offer potential for more accurate and adaptive educational assessments.
Purpose of the Study:
- To establish a robust hybrid education teaching practice quality evaluation system for colleges.
- To develop and validate a hybrid teaching quality evaluation model utilizing a deep belief network (DBN).
- To assess the accuracy and reliability of the proposed DBN model in evaluating hybrid teaching quality.
Main Methods:
- Construction of a hybrid teaching quality evaluation model based on a deep belief network (DBN).
- Utilization of Karl Pearson correlation coefficient and root mean square error (RMSE) to measure evaluation accuracy and fluctuation.
- Experimental validation of the DBN model's learning and training performance through iterative testing.
Main Results:
- The DBN model exhibited significant decreases in fitting error with increased iterations, stabilizing below 0.01 after 20 iterations.
- Evaluation correlation coefficients consistently exceeded 0.85, indicating strong agreement with actual teaching quality.
- Root mean square error (RMSE) values remained below 0.45, demonstrating minimal fluctuation and high precision in evaluations.
Conclusions:
- The developed DBN model demonstrates excellent learning and training performance with low fitting errors for hybrid teaching quality evaluation.
- The proposed evaluation system achieves high accuracy and reliability, closely mirroring actual teaching quality assessments.
- The DBN-based hybrid teaching quality evaluation system is effective and suitable for application in colleges and universities.
More Related Videos
Related Concept Videos
Cognitive Learning
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
Introduction to Learning
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
Purposive Learning
Higher Mental Functions of Brain: Learning and Memory
Observational Learning
Associative Learning
Classical conditioning, also known...

