TY - GEN
T1 - Unveiling Multivariate EEG Features
T2 - 2023 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2023
AU - Fan, Zuo Cian
AU - Lin, Ro Wei
AU - Tsai, Ching Shu
AU - Chou, Wen Jiun
AU - Li, Chia Jung
AU - Huang, Zih Jun
AU - Shih, Bin Yu
AU - Wang, Liang Jen
AU - Ko, Li Wei
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - We sought to revolutionize the classification of Attention-Deficit/Hyperactivity Disorder (ADHD) by pioneering an innovative approach that seamlessly integrated auditory and visual tests with electroencephalogram (EEG) coherence analysis, forming the foundation for our Support Vector Machine (SVM) models. Our primary objective was to achieve precise differentiation between individuals with ADHD and those without, aiming to reshape the landscape of ADHD diagnosis and early intervention. We constructed an SVM model based on CATA coherence, incorporating a carefully selected set of 180 features, and another grounded in CPT coherence with 70 features. Astonishingly, our exploration uncovered that a model incorporating CATA's coherence and Power Spectral Density (PSD) as features achieved an astounding accuracy rate of 97.7%, using only half the number of features. This revelation hints at untapped potential for multivariate advancements in the realm of ADHD classification. The landscape of ADHD diagnosis and intervention is perpetually evolving, most notably with the FDA's approval of game therapy for ADHD. Leveraging the transformative power of our findings, we envision the development of user-friendly game therapies for in-home use, empowering both clinicians and parents alike. This marks a paradigm shift in the realm of ADHD intervention, offering objective, data-driven tools for the early management of ADHD. Gamified therapy not only enhances accessibility but also fosters engagement and compliance, all of which are pivotal in the long-term care of individuals with ADHD. In summary, our study represents a significant advancement in our comprehension and classification of ADHD. By fusing auditory and visual tests with EEG coherence analysis, fortified by state-of-the-art machine learning techniques, we have achieved an unprecedented level of accuracy in identifying individuals with ADHD. Our findings, aligned with the FDA-approved game therapy, offer a glimpse into a future where technology and neuroscience collaborate synergistically to enrich the lives of those affected by ADHD.
AB - We sought to revolutionize the classification of Attention-Deficit/Hyperactivity Disorder (ADHD) by pioneering an innovative approach that seamlessly integrated auditory and visual tests with electroencephalogram (EEG) coherence analysis, forming the foundation for our Support Vector Machine (SVM) models. Our primary objective was to achieve precise differentiation between individuals with ADHD and those without, aiming to reshape the landscape of ADHD diagnosis and early intervention. We constructed an SVM model based on CATA coherence, incorporating a carefully selected set of 180 features, and another grounded in CPT coherence with 70 features. Astonishingly, our exploration uncovered that a model incorporating CATA's coherence and Power Spectral Density (PSD) as features achieved an astounding accuracy rate of 97.7%, using only half the number of features. This revelation hints at untapped potential for multivariate advancements in the realm of ADHD classification. The landscape of ADHD diagnosis and intervention is perpetually evolving, most notably with the FDA's approval of game therapy for ADHD. Leveraging the transformative power of our findings, we envision the development of user-friendly game therapies for in-home use, empowering both clinicians and parents alike. This marks a paradigm shift in the realm of ADHD intervention, offering objective, data-driven tools for the early management of ADHD. Gamified therapy not only enhances accessibility but also fosters engagement and compliance, all of which are pivotal in the long-term care of individuals with ADHD. In summary, our study represents a significant advancement in our comprehension and classification of ADHD. By fusing auditory and visual tests with EEG coherence analysis, fortified by state-of-the-art machine learning techniques, we have achieved an unprecedented level of accuracy in identifying individuals with ADHD. Our findings, aligned with the FDA-approved game therapy, offer a glimpse into a future where technology and neuroscience collaborate synergistically to enrich the lives of those affected by ADHD.
KW - ADHD
KW - BCI
KW - EEG
KW - auditory task
KW - visual task
UR - http://www.scopus.com/inward/record.url?scp=85179586133&partnerID=8YFLogxK
U2 - 10.1109/iFUZZY60076.2023.10324282
DO - 10.1109/iFUZZY60076.2023.10324282
M3 - Conference contribution
AN - SCOPUS:85179586133
T3 - 2023 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2023
BT - 2023 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2023
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 26 October 2023 through 29 October 2023
ER -