Comprehensive Analysis of Hierarchical Aggregation Functions Decision Trees, SVD, K-means Clustering, PCA and Rule Based AI Optimization in the Classification of Fuzzy based Epilepsy Risk Levels from EEG Signals
Keywords:
EEG Signals, Epilepsy Risk Levels, Fuzzy Logic, Hierarchical Decision Trees, SVD, K-means clustering, PCA,AI TechniquesAbstract
A comprehensive analysis for the performance of post classifiers such as Hierarchical Soft Decision Trees, Singular value decomposition(SVD), k-means clustering, Principal Component Analysis (PCA) and Rule based AI techniques in optimization of fuzzy outputs for the classification of epilepsy risk levels from EEG (Electroencephalogram) signals is presented in this paper. The fuzzy pre classifier is used to classify the risk levels of epilepsy based on extracted parameters like energy, variance, peaks, sharp and spike waves, duration, events and covariance from the EEG signals of the patient. Hierarchical Soft decision tree (post classifiers with max-min criteria) four types, SVD, K-means clustering, PCA and AI optimization are applied on the classified data to identify the optimized risk level (singleton) which characterizes the patient’s risk level. The efficacy of the above methods is compared and analyzed based on the bench mark parameters such as Performance Index (PI), and Quality Value (QV).
Downloads
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 International Journal of Computer Information Systems and Industrial Management Applications
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.