Levenberg-Marquardt Neural Network for Eye States Detection Based on Electroencephalography Data

Untari Novia Wisesty

Abstract


The eye state detection is one of various task toward Brain Computer Interface system. The eye state can be read in brain signals. In this paper use EEG Eye State dataset (Rosler, 2013) from UCI Machine Learning Repository Database. Dataset is consisting of continuous 14 EEG measurements in 117 seconds. The eye states were marked as “1” or “0”. “1” indicates the eye-closed and “0” the eye-open state. The proposed schemes use Multi Layer Neural Network with Levenberg Marquardt optimization learning algorithm, as classification method.  Levenberg Marquardt method used to optimize the learning algorithm of neural network, because the standard algorithm has a weak convergence rate. It is need many iterations to have minimum error. Based on the analysis towards the experiment on the EEG dataset, it can be concluded that the proposed scheme can be implemented to detect the Eye State. The best accuracy gained from combination variable sigmoid function, data normalization and number of neurons are 31 (95.71%) for one hidden layer, and 98.912% for two hidden layers with number of neurons are 39 and 47 neurons and linear function.

Full Text:

PDF

References


Anderson, Charles W, Zlatko Sijercic. Classification of EEG Signals from Four Subjects during Five Mental Task. Colorado State University.

Rosler, Oliver, David Suendermann. (2013). A First Step Towards Eye State Prediction Using EEG. Proc. of the AIHLS 2013, Istanbul Turkey.

AlZoubi, Omar, Irena Koprinska, Rafael A. Calvo. (2006). Classification of Brain-Computer Interface Data. University of Sydney.

L. Li, L. Xiao, and L. Chen. (2009). Differences of EEG between Eyes-Open and Eyes-Closed States Based on Autoregressive Method. Journal of Electronic Science and Technology of China, vol. 7, no. 2.

B. Chambayil, R. Singla, and R. Jha. (2010). EEG Eye Blink Classification Using Neural Network. Proc. Of the World Congress on Engineering, London, UK.

Sabanci, Kadir, Murat Koklu. (2015). The Classification of Eye State by Using KNN and MLP Classification Model According to the EEG Signal. International Journal of Intelligent System and Applications in Engineering, Vol. 3, pp:127-130. Crossref

Jue Wang, Nan Yan, Hailong Liu, Mingyu Liu, Changfeng Tai. (2008). Brain-Computer Interfaces Based on Attention and Complex Mental Task. HCI-RG Vol. 1 No. 4.

Roesler, Oliver, Lucas Bader, Jan Forster, Yoshikatsu Hayashi, Stefan Hebler, David Suendermann-Oeft. (2014). Comparison of EEG Devices for Eye State Classification. Proc. of the AIHLS 2014, Istanbul Turkey.

Wisesty, Untari Novia, Adiwijaya, Tjokorda Agung B. W. (2012). Algoritma Conjugate Gradient Polak Ribiere untuk Peningkatan Performansi Backpropagation pada Sistem Prediksi Temperatur Udara. Jurnal Penelitian dan Pengembangan Telekomunikasi Vol: 15 no.2

Jain, Neha, Sandeep Bhargava, Savita Shivani, Dinesh Goyal. (2015). International Journal of Science, Engineering and Technology.

Ting Wang, Sheng-Uei Guan, Ka Lok Man, T. O. Ting. (2014). Time Series Classification for EEG Eye State Identification based on Incremental Attribute Learning. 2014 International Symposium on Computer, Consumer and Control. Crossref

Suratgar, Amir Abolfazi, Mohammad Bagher Tavakoli, Abbas Hoseinabadi. (2007). Modified Levenberg-Marquardt Method for Neural Network Training. International Journal of Computer, Electrical, Automation, Control and Information Engineering vol:1, No:6.

AKBEN, Selahaddin Batuhan. (2014). Online EEG Eye State Detection in Time Domain by Using Local Amplitude Increase. Journal of Multidisciplinary Engineering Science and Technology (JMEST) Vol. 1 Issue 4, November-2014.

Rahman, Faridah Abd, Mohd Fauzi Othman. (2015). Eye Blinks Removal in Single-Channel EEG Using Savitzky-Golay Referenced Adaptive Filtering: A Comparison with Independent Component Analysis Method. ARPN Journal of Engineering and Applied Sciences Vol. 10, No. 23.

Sahu, Mridu, N. k. Nagwani, Shrish Verma, Saransh Shirke. (2015). Performance Evaluation of Different Classifier for Eye State Prediction Using EEG Signal. International Journal of Knowledge Engineering, Vol. 1, No.2, September 2015. Crossref

Hondrou, Charline, George Caridakis. (2012). Affective, Natural Interaction Using EEG: Sensors, Application and Future Direction. SETN Hellenic Conference on Artificial Intelligence, LN AI 7297, pp. 331-338.

Crossref




DOI: http://dx.doi.org/10.21108/IJOICT.2016.21.72

Refbacks

  • There are currently no refbacks.


Copyright (c) 2016 Untari Novia Wisesty

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.