An analytical framework for enhancing brain signal classification through hybrid filtering and dimensionality reduction

Accurate classification of focal and non-focal epilepsy is a critical healthcare analytics challenge that requires robust data preprocessing and feature optimization. This work develops an integrated analytics framework that combines hybrid filtering with hybrid dimensionality reduction to improve both signal quality and predictive performance. A multi-criteria ranking strategy based on the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) is employed, incorporating conventional signal measures alongside distance and divergence metrics to identify optimal preprocessing pipelines. Statistical validation is performed using the Friedman test with Nemenyi post-hoc analysis to establish the significance of competing filter–dimensionality reduction combinations. The validated framework is benchmarked across conventional, hybrid, and deep learning classifiers, with the most effective configuration—Butterworth–Wavelet Packet Decomposition (BW + WPD) filtering followed by Principal Component Analysis–Linear Discriminant Analysis (PCA + LDA)—achieving 95.63% accuracy using an Adaboost classifier on the Bern–Barcelona dataset. Evaluation on the independent Bonn dataset confirms robustness and cross-subject generalizability. These findings demonstrate the value of a multi-metric, statistically validated analytics strategy for reliable epilepsy detection, with potential applicability to broader healthcare signal classification tasks.