<abstract xmlns="http://www.w3.org/1999/xhtml">

<p>In this paper, the feature increment can be regarded as a learning mapping function, and a non-equilibrium incremental learning (WILS) method for the academic warning is proposed, and the academic warning model of the non-equilibrium incremental learning method is constructed. The learning factor is regulated by introducing the Focal loss function, and the learned knowledge is integrated into the Focal loss as the final loss function. Finally, the three-dimensional indicators of social characteristics, personal characteristics, and student behavior were used to explore the influencing factors of academic performance and academic support strategies were explored in this way. The results show that the average value of the accuracy of the academic early warning model is 0.857, and the F1-Measure is 0.891, which indicates that the model can reasonably and efficiently provide prior warning of students’ learning situations and behavioral performance. This paper proposes countermeasure suggestions for managing academic early warning and academic support work, which enhances the purpose of talent cultivation quality.</p>
</abstract>

In this paper, the feature increment can be regarded as a learning mapping function, and a non-equilibrium incremental learning (WILS) method for the academic warning is proposed, and the academic warning model of the non-equilibrium incremental learning method is constructed. The learning factor is regulated by introducing the Focal loss function, and the learned knowledge is integrated into the Focal loss as the final loss function. Finally, the three-dimensional indicators of social characteristics, personal characteristics, and student behavior were used to explore the influencing factors of academic performance and academic support strategies were explored in this way. The results show that the average value of the accuracy of the academic early warning model is 0.857, and the F1-Measure is 0.891, which indicates that the model can reasonably and efficiently provide prior warning of students’ learning situations and behavioral performance. This paper proposes countermeasure suggestions for managing academic early warning and academic support work, which enhances the purpose of talent cultivation quality.

Reflections on and Exploration of Academic Early Warning Management and Support for Students in Colleges and Universities

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution 4.0 International License.

In this paper, the feature increment can be regarded as a learning mapping function, and a non-equilibrium incremental learning (WILS) method for the academic...

Reflections on and Exploration of Academic Early Warning Management and Support for Students in Colleges and Universities

Pubblicato online: 02 dic 2023

Pagine: -

Ricevuto: 07 mar 2023

Accettato: 12 giu 2023

DOI: https://doi.org/10.2478/amns.2023.2.01327

Parole chiave
Characteristic increment, Mapping function, Unbalanced incremental, Academic warning model, Academic support

© 2023 Junli Feng et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Reflections on and Exploration of Academic Early Warning Management and Support for Students in Colleges and Universities

Pubblicato online: 02 dic 2023

Pagine: -

Ricevuto: 07 mar 2023

Accettato: 12 giu 2023

DOI: https://doi.org/10.2478/amns.2023.2.01327

Parole chiaveCharacteristic increment, Mapping function, Unbalanced incremental, Academic warning model, Academic support

© 2023 Junli Feng et al., published by Sciendo

This work is licensed under the Creative Commons Attribution 4.0 International License.

Parole chiave
Characteristic increment, Mapping function, Unbalanced incremental, Academic warning model, Academic support