JCAI

In recent year, artificial intelligence is significantly evolving model for the estimation of the vast range of advanced model. This paper introduces a novel approach for predicting learning styles in the realm of education through the application of a Hidden Chain Fuzzy Model (HCFM). Learning styles, encompassing auditory, visual, and kinesthetic preferences, play a pivotal role in shaping effective teaching strategies and personalized educational experiences. The HCFM, an innovative extension of traditional fuzzy models, is designed to capture the intricate relationships and dependencies inherent in learning behaviors. The model’s learning process is rigorously examined, evaluating its ability to discern diverse learning styles through a dataset of instances characterized by varying aptitudes and preferences. Comprehensive classification metrics, including accuracy, precision, recall, F1 Score, AUC-ROC, and Mean Squared Error (MSE), are employed to assess the model’s performance across distinct learning styles. The HCFM’s predictive capabilities are further demonstrated through a detailed analysis of individual instances, highlighting its effectiveness in tailoring predictions to the unique characteristics of learners. The results suggest that the HCFM holds promise as a powerful tool for personalized education, paving the way for more adaptive and tailored learning environments. The paper concludes by discussing potential avenues for future research, emphasizing the importance of further validation and exploration of the model’s applicability in diverse educational settings.
Keywords : Artificial Intelligence; Hidden Chain Fuzzy Model; Mean Squared Error;education; hiddenmarkov model.
Citation : G. Li, “E-Learning Intelligence Model with Artificial Intelligence to Improve Learning Performance of Students”, Journal of Computer Allied Intelligence (JCAI) , vol.01, no.01, pp.14-26,2023.