Novel Enhanced Cognitive State Analysis in E-Learning via Real-Time Emotion and Attentiveness Detection Using OptFuzzy TSM and ABiLSTM

The emotional state of an online learner has drawn a lot of attention. Accurately predicting a student's emotional state can improve learning outcomes through designated mediation. Still, keeping an eye on and sustaining students attention in online classes is challenging because there isn't any immediate supervision. To identify these challenges based on the learner's emotional states, this paper presents a novel, efficient, Optimized Fuzzy approach and signifies solutions to inspire the learner. The Improved Multi-Task Cascaded Convolutional Networks (IMTCNN) are used to identify the face region in real time. Different emotions are classified by analyzing extracted facial expressions using an Optimized Takagi-Sugeno and Mamdani fuzzy systems (Fuzzy TSM) approach. With the Enhanced Mother Optimization Algorithm (EMO), the hyperparameters in the classification approach are optimized. The proposed method determines whether learners are attentive or inattentive during online learning sessions by computing an Attention-based bi-directional long-short term memory (ABiLSTM) to predict cognitive states. To improve learning efficiency and productivity, users receive real-time feedback. The proposed approach can give instructors ongoing feedback, allowing them to modify the way they teach and keep students interested and engaged. With recognition rates of over ۹۸.۲۱% accuracy on the proposed datasets, the study's results are encouraging and outperforming those of other approaches.

کلیدواژه ها:

E-learning ، cognitive state ، dual Mamdani and neuro-fuzzy inference system ، Archerfish Hunting Optimization Algorithm (AHOA) ، Improved Position Enhancement Faster Network (IPEFNet)