The Classification of Eye State by Using kNN and MLP Classification Models According to the EEG Signals

Kadir Sabancı, Murat Koklu
  • Murat Koklu
    Selçuk Üniversitesi Teknoloji Fakültesi, Turkey


What is widely used for classification of eye state to detect human’s cognition state is electroencephalography (EEG). In this study, the usage of EEG signals for online eye state detection method was proposed. In this study, EEG eye state dataset that is obtained from UCI machine learning repository database was used. Continuous 14 EEG measurements forms the basic of the dataset. The duration of the measurement is 117 seconds (each measurement has14980 sample). Weka (Waikato Environment for Knowledge Analysis) program is used for classification of eye state. Classification success was calculated by using k-Nearest Neighbors algorithm and multilayer perceptron neural networks models. The obtained success of classification methods were compared. The classification success rates were calculated for various number of neurons in the hidden layer of a multilayer perceptron neural network model. The highest classification success rate have been obtained when the number of neurons in the hidden layer was equal to 7. And it was 56.45%. The classification success rates were calculated with k-nearest neighbors algorithm for different neighbourhood values. The highest success was achieved in the classification made with kNN algorithm.  In kNN models, the success rate for 3 nearest neighbor were calculated as 84.05%.


EEG signals; eye state; weka; multilayer perceptron; kNN classifier

Full Text:

Submitted: 2017-02-21 18:46:25
Published: 2015-12-30 00:00:00
Search for citations in Google Scholar
Related articles: Google Scholar
Abstract views:


Copyright (c) 2017 International Journal of Intelligent Systems and Applications in Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
© Prof.Dr. Ismail SARITAS 2013-2019     -    Address: Selcuk University, Faculty of Technology 42031 Selcuklu, Konya/TURKEY.