Mathematical Modeling Ability of Chemical Engineering Vocational Students based on Improved Deep Residual Network

• Published in: 2024 International Conference on Distributed Systems, Computer Networks and Cybersecurity (ICDSCNC) pp. 1 - 5
• Main Author: Rong, Yayan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 20.09.2024
• Subjects: Accuracy; Analytical models; Chemical engineering; Computational modeling; Deep learning; Education; hawkes process; improved deep residual network; mathematical modeling and vocational students; Mathematical models; Neural networks; Optimization; Residual neural networks
• DOI: 10.1109/ICDSCNC62492.2024.10939899

Mathematics is a fundamental subject in higher vocational education, and mathematical modeling is the specific kind of professional learning that integrates real-world practice. However, the quality of mathematical modeling learning affects the whole vocational professional research efficacy. Hence, this research Improved Deep Residual Network (IDResNet), is proposed to analyze the learning behavior of chemical engineering vocational students in mathematical modeling. The Hawkes approach is initially used to collect behavioral data from students before beginning vocational education instruction. Next Learning impact prediction is a tool used in vocational education instruction to characterize students' learning practices. Statistical modeling is used in higher vocational education to inform decisions based on the number of interested students. Mathematical models are then used to effectively forecast the learning consequences of students receiving vocational education. According to the results, it illustrates that the suggested IDResNet methodology have achieved better performance in accuracy of 99.85% and precision of 99.55% which is comparatively higher than existing models such as Deep Learning Model for Teaching Quality Analysis (DL-TQA), BP Neural Network (BP-NN) and Ideological Political Education Platform IPEP methodology.