DENOISING ELECTROENCEPHALOGRAM (EEG) SIGNALS OF DEAF ADULTS WITH NO EARLY INTERVENTION USING HYBRID Β-HILL CLIMBING ALGORITHM(HΒHC) AND WAVELET TRANSFORM(WT)
Shirly G1, Jerritta S2*
1School of Engineering, Department of Electronics & Communication Engineering, Vels Institute of Science, Technology and Advanced Studies (VISTAS) and National Institute of Speech & Hearing(NISH), India
2School of Engineering, Department of Electronics & Communication Engineering, Vels Institute of Science, Technology and Advanced Studies (VISTAS), India
*Corresponding Author: firstname.lastname@example.org
When dedicated neural structures in the brain that rely on auditory input fail to remember to transmit impulses to remedy the failure of the language processing location of the brain at the age of 17+, a method must be devised. Participants were non early intervened deaf and hard of hearing undergraduates. All of them use Indian Sign Language. Their language skill is dismal and their incidental learning was affected. Electroencephalogram (EEG) is vital in detecting brain activity. Electrical activity reported is often polluted with artifacts which affect the exploration of EEG signals. There are several approaches available to remove artifacts. This study concentrates on muscular artifacts during finger spelling of words and used hybridization between β-hill climbing algorithm and wavelet transform (WT). β-hill climbing is proposed to find optimal wavelet parameters for EEG signal denoising. Performance was calculated by statistical parameters mean square error (MSE), mean absolute error (MAE), peak signal-to-noise ratio (PSNR), signal to noise ratio (SNR), and percentage root mean square difference (PRD). The study proves that ‘db4’ wavelet function gives the better performance than the other wavelet function or hybrid filters.