EPSPatNet86: eight-pointed star pattern learning network for detection ADHD disorder using EEG signals. (31st March 2022)

• Record Type: Journal Article
• Authors: Tanko, Dahiru; Barua, Prabal Datta; Dogan, Sengul; Tuncer, Turker; Palmer, Elizabeth; Ciaccio, Edward J; Acharya, U Rajendra
• Is Part Of: Physiological measurement. Volume 43:Number 3(2022)
• Publication Date: 2022-03-31
• Subjects: EPSPatNet86 -- ADHD -- EEG signal classification -- hand-modeled learning network -- feature engineering; Physiology -- Measurement -- Periodicals; Patient monitoring -- Periodicals; 612
• DOI: 10.1088/1361-6579/ac59dc
• Languages: English
• ISSNs: 0967-3334

Abstract

Abstract: Objective. The main objective of this work is to present a hand-modelled one-dimensional signal classification system to detect Attention-Deficit Hyperactivity Disorder (ADHD) disorder using electroencephalography (EEG) signals. Approach. A novel handcrafted feature extraction method is presented in this research. Our proposed method uses a directed graph and an eight-pointed star pattern (EPSPat). Also, tunable q wavelet transforms (TQWT), wavelet packet decomposition (WPD), statistical extractor, iterative Chi2 (IChi2) selector, and the k-nearest neighbors (kNN) classifier have been utilized to develop the EPSPat based learning model. This network uses two wavelet decomposition methods (TQWT and WPD), and 85 wavelet coefficient bands are extracted. The proposed EPSPat and statistical feature creator generate features from the 85 wavelet coefficient bands and the original EEG signal. The learning network is termed EPSPatNet86. The main purpose of the presented EPSPatNet86 is to detect abnormalities of the EEG signals. Therefore, 85 wavelet subbands have been generated to extract features. The created 86 feature vectors have been evaluated using the Chi2 selector and the kNN classifier in the loss value calculation phase. The final features vector is created by employing a minimum loss-valued eight feature vectors. The IChi2 selector selects the best feature vector, which is fed to the kNN classifier. An EEG signal dataset has been used to demonstrate the presented model's EEG signal classification ability. We have used an ADHD EEG dataset since ADHD is a commonly seen brain-related ailment. Main results. Our developed EPSPatNet86 model can detect the ADHD EEG signals with 97.19% and 87.60% accuracy using 10-fold cross and subject-wise validations, respectively. Significance. The calculated results demonstrate that the presented EPSPatNet86 attained satisfactory EEG classification ability. Results show that we can apply our developed EPSPatNet86 model to other EEG signal datasets to detect abnormalities.