Efficient Kulczynski EEG feature selection for autism spectrum disorder diagnosis over fog and cloud computing

Abstract This work introduces an efficient feature selection approach based on the Kulczynski Similarity (KS) measure to improve the efficiency and accuracy of machine learning models in Electroencephalogram (EEG)-based autism spectrum disorder (ASD) detection. EEG data are inherently high-dimensional, and using all features increases computational burden while incorporating redundant or irrelevant attributes that may hinder classification performance. The proposed KS method addresses these issues by ranking features according to their similarity, retaining those with high harmony that are most relevant for diagnosis, and discarding non-contributory dimensions. To evaluate the effectiveness of the KS framework, three configurations were compared: the complete EEG feature set, features selected with standard Particle Swarm Optimization (PSO), and features selected with the proposed KS method. While PSO retained 30 out of 47 features (63.83% selection ratio and 36.17% reduction ratio), KS achieved a more compact subset of 28 features (59.57% selection ratio and 40.43% reduction ratio), achieving an additional 4.26% improvement in both selection and reduction ratios over PSO. Despite using fewer inputs, KS consistently delivered higher performance across five classifiers. The best accuracy was obtained by K-Nearest Neighbors (KNN) at 99.20%, followed by eXtreme Gradient Boosting (XGBoost) at 98.12%, Random Forest (RF) at 97.05%, Support Vector Machine (SVM) at 95.36%, and Decision Tree (DT) at 87.95%. The findings demonstrate that KS-based feature selection reduces dimensionality, improves accuracy, and lowers complexity, supporting fog and Cloud computing enabled real-time diagnostics and clinical decision systems for efficient EEG analysis in early ASD detection and better patient care.