Ensemble Deep Learning with Chimp Optimization Based Medical Data Classification

Eye state classification acts as a vital part of the biomedical sector, for instance, smart home device control, drowsy driving recognition, and so on. The modifications in cognitive levels can be reflected via transforming electroencephalogram (EEG) signals. deep learning (DL) models automated extract features often showcased improved outcomes over conventional model recognition processes. This paper presents an Ensemble Deep Learning with Chimp Optimization Algorithm EEG State Classification (EDLCOA-ESC). proposed EDLCOA-ESC technique involves min-max normalization approach pre-processing step. Besides, wavelet packet decomposition (WPD) is employed extraction useful from In addition, ensemble sparse autoencoder (DSAE) kernel ridge regression (KRR) are classification. Finally, hyperparameters tuning DSAE takes place using COA thereby boost results to maximum extent. An extensive range simulation analysis on benchmark dataset carried out reported promising performance recent approaches accuracy 98.50%.