JoWUA

Abstract

College students often face obstacles in achieving optimal cognitive performance due to the demands of academic stress during workload and the side effects of cutting-edge media that destroy the students’ attention and cognitive skills. This study aimed to investigate the effectiveness of the adaptive moment estimation (Adam), an optimization algorithm designed for training deep learning (DL) models, assisted with brain biofeedback to enhance students’ brain synapse transportation by boosting the cognitive performance of college students. The contribution of the study is to improve the academic cognitive skills of college students by processing input data (text, and videos). The study used an electroencephalogram (EEG) headset to read attention signals as brain biofeedback combined with the Adam optimization algorithm that trained on the student attention dataset to improve cognitive performance parameters. Adam’s optimization algorithm represents the suggested deep learning model. Results improved the attention accuracy (97.51%), mental fatigue and drowsiness (3%), and precision at predicting learning performance improved by (20%) for college students trained on the Adam optimization algorithm-assisted brain biofeedback system compared with state-of-the-art models concerning the same attention dataset. The study provides evidence that combining Adam and brain biofeedback effectively boosts college students’ performance, cognitive skills and synapse transportation system.