Genetic Algorithm Based Feature Selection Technique for Electroencephalography Data

Tariq Ali,Asif Nawaz,Hafiza Ayesha Sadia

doi:10.2478/acss-2019-0015

Abstract

Abstract High dimensionality is a well-known problem that has a huge number of highlights in the data, yet none is helpful for a particular data mining task undertaking, for example, classification and grouping. Therefore, selection of features is used frequently to reduce the data set dimensionality. Feature selection is a multi-target errand, which diminishes dataset dimensionality, decreases the running time, and furthermore enhances the expected precision. In the study, our goal is to diminish the quantity of features of electroencephalography data for eye state classification and achieve the same or even better classification accuracy with the least number of features. We propose a genetic algorithm-based feature selection technique with the KNN classifier. The accuracy is improved with the selected feature subset using the proposed technique as compared to the full feature set. Results prove that the classification precision of the proposed strategy is enhanced by 3 % on average when contrasted with the accuracy without feature selection.

Highlights

In the revolutionary advancement era, there are many technology resources that help develop wearable devices, which are capable of safe use and improve people’s life, especially of those suffering from different types of motor impairment
Some eye tracking systems have developed through image processing techniques, which utilise eye-blink pattern, but in some applications, such as drowsiness detection, the method of eye blink pattern is not sufficient because these methods concentrate just on eye shut state, they cannot be connected to identifying sluggishness with open eyes
For searching and selecting the most optimal attribute set from the original set of attributes, we have proposed the Genetic Algorithm (GA) based technique, and k-Nearest Neighbor (KNN) is used for fitness evaluation

Summary

Introduction

In the revolutionary advancement era, there are many technology resources that help develop wearable devices, which are capable of safe use and improve people’s life, especially of those suffering from different types of motor impairment. The emergence of these technologies with Internet of Things (IOT) can bring evolution in applications of public safety and mobile health. These applications open doors for universal ongoing testing by utilising distinctive data types, for example, Electrocardiography (ECG), Electroencephalography (EEG). The eye-tracking systems can be used for stress feature identification [2], infant sleep-wake state identification [7], drowsiness detection [8], Attention Deficit Hyperactivity Disorder (ADHD) patients [10] and epileptic seizure detection [9]

Objectives

Results

Conclusion