Mental Fatigue Classification Aided by Machine Learning-Driven Model Under the Influence of Foot and Auditory Binaural Beats Brain Massages via fNIRS

Fatigue is a feeling of constant exhaustion, burnout, or lack of energy. A very particular state of fatigue, cognitive fatigue, drastically influences sustained attention and focus. To date, there remains a significant gap in classifying cognitive fatigue while learning under the influence of mechan...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE access 2024, Vol.12, p.187160-187191
Hauptverfasser: Haroon, Nazo, Jabbar, Hamid, Shahbaz Khan, Umar, Ted. Jeong, Taikyeong, Naseer, Noman
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Fatigue is a feeling of constant exhaustion, burnout, or lack of energy. A very particular state of fatigue, cognitive fatigue, drastically influences sustained attention and focus. To date, there remains a significant gap in classifying cognitive fatigue while learning under the influence of mechanical foot and binaural beat brain massages aided by functional Near-Infrared Spectroscopy. We aim to evaluate the effects of mechanical massage under the influence of binaural beats brain massage on mental fatigue recovery aided by an ensemble Machine Learning model. The experimental paradigm employed to induce cognitive fatigue includes digital lessons such as picture recognition, digit span, Stroop color and word, sustained attention to response, and N-back test. After extensive features extraction, Ridge, Gaussian Naïve Bayes, and Support Vector Machine (SVM) with linear, quadratic, Radial Basis Function (RBF), and sigmoid kernel, K-Nearest Neighbor (k-NN), Random Forest (RF), Linear Discriminant Analysis (LDA), and Quadratic Discriminant Analysis (QDA) classifiers are employed. An ensemble algorithm, particularly using the hard voting method is employed that combines the forecasts of multiple classifiers to make a final decision, where each classifier casts one vote for a given input, and the class with the majority of votes is selected as the final prediction. This approach leverages the strength of each classifier, resulting in better overall performance than any single model alone. The Random Forest classifier aligns with the ensemble's final decision 94.6% of the time, which indicates its significant contribution to the ensemble model out of all classifiers. Receiving binaural beats brain massage along with mechanical massage helps to recover mental fatigue. Mechanical massage inculcation with binaural beats brain massage significantly reinforces to relieve cognitive fatigue along with enhancing mental vigilance, short and long-term verbal, and working memory.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2024.3508875