Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients

Judul Paper: Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients
Inan Guler (Department of Electronics and Computer Education, Faculty of Technical Education, Gazi University, 06500 Teknikokullar, Ankara, Turkey), Elif Derya Ubeyli (Department of Electrical and Electronics Engineering, Faculty of Engineering, TOBB Ekonomi ve Teknoloji Universitesi) - Sogutozu, Ankara, Turkey
Journal of Neuroscience Methods(2005),0165-0270, doi:10.1016/j.jneumeth.2005.04.013

Abstract: This paper describes the application of adaptive neuro-fuzzy inference system (ANFIS) model for classification of electroencephalogram (EEG) signals. Decision making was performed in two stages: feature extraction using the wavelet transform (WT) and the ANFIS trained with the backpropagation gradient descent method in combination with the least squaresmethod. Five types of EEG signals were used as input patterns of the five ANFIS classifiers. To improve diagnostic accuracy, the sixth ANFIS classifier (combining ANFIS) was trained using the outputs of the five ANFIS classifiers as input data. The proposed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. Some conclusions concerning the saliency of features on classification of the EEG signals were obtained through analysis of the ANFIS. The performance of the ANFIS model was evaluated in terms of training performance and classification accuracies and the results confirmed that the proposed ANFIS model has potential in classifying the EEG signals.

Makalah ini menggambarkan bagaimana aplikasi model sistem inferensi adaptif neuro-fuzzy (ANFIS) untuk klasifikasi elektroensefalogram (EEG) sinyal. Pengambilan keputusan dilakukan dalam dua tahap: ekstraksi ciri menggunakan wavelet transform (WT) dan ANFIS dilatih dengan metode backpropagation keturunan gradien dalam kombinasi dengan metode kuadrat terkecil. Lima jenis sinyal EEG digunakan sebagai pola masukan dari lima pengklasifikasi ANFIS. Untuk meningkatkan akurasi diagnostik, classifier ANFIS keenam (ANFIS menggabungkan) telah dilatih menggunakan output dari lima pengklasifikasi ANFIS sebagai data masukan. Model ANFIS diusulkan menggabungkan kemampuan jaringan saraf adaptif dan logika fuzzy pendekatan kualitatif. Beberapa kesimpulan tentang kemenonjolan fitur pada klasifikasi sinyal EEG diperoleh melalui analisa dari ANFIS. Kinerja model ANFIS dievaluasi dalam hal kinerja pelatihan dan keakuratan klasifikasi dan hasilnya menyatakan bahwa model ANFIS yang diusulkan memiliki potensi dalam mengklasifikasikan sinyal EEG.
Readmore: Adaptive neuro-fuzzy inference system for classification of EEG signals using wavelet coefficients

Calibration-Free Eye Gaze Direction Detection With Gaussian Processes

Judul Paper: Calibration-Free Eye Gaze Direction Detection With Gaussian Processes
Basilio Noris, Karim Benmachiche, Aude G. Billard
LASA Laboratory - EPFL, Station 9, CH-1015 Lausanne, Switzerland

Abstract: In this paper we present a solution for eye gaze detection from a wireless head mounted camera designed for children aged between 6 months and 18 months. Due to the constraints of working with very young children, the system does not seek to be as accurate as other state-of-the-art eye trackers, however it requires no calibration process from the wearer. Gaussian Process Regression and Support Vector Machines are used to analyse the raw pixel data from the video input and return an estimate of the child’s gaze direction. A confidence map is used to determine the accuracy the system can expect for each coordinate on the image. The best accuracy so far obtained by the system is 2.34 on adult subjects, tests with children remain to be done.

Dalam makalah ini, disajikan sebuah sistem deteksi dari pandangan mata dengan kepala dipasang kamera nirkabel yang dirancang untuk anak usia antara 6 bulan dan 18 bulan. Karena keterbatasan bekerja dengan anak-anak yang sangat muda, sistem tidak berusaha seakurat dengan sistem deteksi lain, namun sistem ini tidak memerlukan proses kalibrasi dari pemakainya. Proses Gaussian Vector Regresi dan Dukungan Mesin digunakan untuk menganalisis data pixel mentah dari input video dan mengsetimasi arah tatapan mata. Peta tingkar ketepatan digunakan untuk menentukan akurasi sistem untuk setiap koordinat pada gambar. Akurasi terbaik sejauh ini diperoleh sistem ini 2,34 pada mata orang dewasa, dan dilakukan tes pada anak-anak.
Readmore: Calibration-Free Eye Gaze Direction Detection With Gaussian Processes
 

| © 2009. All Rights Reserved | Designed by BloggerStop.Net |