Genetic Programming-Based Feature Selection for Emotion Classification Using EEG Signal.

Aditi Sakalle,Maneesha Sakalle,Harshit Bhardwaj,Asif Iqbal,Wubshet Ibrahim,Pradeep Tomar,Arpit Bhardwaj,Enas Abdulhay

doi:10.1155/2022/8362091

Aditi Sakalle, Maneesha Sakalle + Show 6 more

Open Access

https://doi.org/10.1155/2022/8362091

Copy DOI

Abstract

The COVID-19 has resulted in one of the world's most significant worldwide lock-downs, affecting human mental health. Therefore, emotion recognition is becoming one of the essential research areas among various world researchers. Treatment that is efficacious and diagnosed early for negative emotions is the only way to save people from mental health problems. Genetic programming, a very important research area of artificial intelligence, proves its potential in almost every field. Therefore, in this study, a genetic program-based feature selection (FSGP) technique is proposed. A fourteen-channel EEG device gives 70 features for the input brain signal; with the help of GP, all the irrelevant and redundant features are separated, and 32 relevant features are selected. The proposed model achieves a classification accuracy of 85% that outmatches other prior works.

Highlights

Due to the COVID-19 epidemic, all the governments in the world have to impose a lockdown. is strictness, affects the emotions of the people, and lots of people are feeling emotional imbalance [1]. e people are experiencing negative emotions, and their health and performance are degrading day by day
A fourteen-channel EEG device gives 70 features for the input brain signal; with the help of GP, all the irrelevant and redundant features are separated, and 32 relevant features are selected. e proposed model achieves a classification accuracy of 85% that outmatches other prior works
The FSGP model results are examined. e computer configuration consists of 64 GB RAM-based Python (3.8) for incorporating FSGP, GPmtfs, and another existing approaches, i.e., neural network, genetic programming, random forest, and SVM. ese algorithms were applied to the EEG dataset for emotion recognition

Summary

Introduction

Due to the COVID-19 epidemic, all the governments in the world have to impose a lockdown. is strictness, affects the emotions of the people, and lots of people are feeling emotional imbalance [1]. e people are experiencing negative emotions, and their health and performance are degrading day by day. To address the challenge as mentioned above, lots of researchers are applying classification algorithms to understand the emotion of the people [3]. Humans cannot classify these types of emotions; whereas, these classifiers can do this task very efficiently [4]. Ere are few evolutionary algorithms, but genetic programming has shown good results on classification problems. Another advantage of using GP is that the classifier of GP has a tree structure [16], so we can recognize the features present in the best classifier. Another advantage of using GP is that the classifier of GP has a tree structure [16], so we can recognize the features present in the best classifier. is will help, especially in the case of medical diagnosis, because

Methods

Results

Conclusion