ONLY HAND SOLUTION

ONLY HAND SOLUTION

ONLY HAND SOLUTION

ONLY HAND SOLUTION

ONLY HAND SOLUTION

ONLY HAND SOLUTION

ONLY HAND SOLUTION

ONLY HAND SOLUTION

ONLY HAND SOLUTION

ONLY HAND SOLUTION

HEURISTIC MINIMIZATION, GENETIC ALGORITHM DESIGN:

${?}^{***}$ Denoise EEG Signals Using Deep Learning Regression with GPU Acceleration. This example shows how to remove electro$-$oculogram $($EOG$)$ noise from electroencephalogram $($EEG$)$ signals using the EEGdenoiseNet benchmark dataset $[1]$ and deep learning regression. The EEGdenoiseNet dataset contains $4514$ clean EEG segments and $3400$ ocular artifact segments that can be used to synthesize noisy EEG segments with the ground$-$truth clean EEG $($the dataset also contains muscular artifact segments, but these will not be used in this example$).$

This example uses clean and EOG$-$contaminated EEG signals to train a long short$-$term memory $($LSTM$)$ model to remove the EOG artifacts. The regression model was trained with raw input signals and with signals transformed by the short$-$time Fourier transform $($STFT$).$ The STFT model improves performance especially at degraded SNR values.

To enable GPU acceleration for STFT computations, you must have Parallel Computing Toolbox ${?}^{Tw.}.$ To see which GPUs are supported, see GPU Computing Requirements $($Parallel Comoutine Toolbox$)."$

Design a GA algorithm to find the minimum of the EEG with the colored EOG artifact noise. Show your design steps and hand calculations $(7$ marks$).$

Write a GA using $($python$,$ c$+$t$,$ or mat$/$ab$)$ to perform this heuristic minimization. $(3$ marks$).$