EEG Signal Classification Using Power Spectral Features and linear Discriminant Analysis: A Brain Computer Interface Application
01 Jan 2010-
TL;DR: The design of a set of algorithms capable to classify brain signals related to imaginary motor activities ( left and right hand imaginary) is shown and it is shown that the use of parametrical methods for Spectral Power Density estimation can improve the accuracy of the Brain Computer Interface.
Abstract: Biological signal processing offers an alternative to improve life quality in handicapped patients. In this sense is possible, to control devices as wheel chairs or computer systems. The signals that are usually used are EMG, EOG and EEG. When the lost of ability is severe the use of EMG signals is not possible because the person had lost, as in the case of ALS patients, the ability to control his body. EOG offers low resolution because the technique depends of many external and uncontrollable variables of the environment. This work shows the design of a set of algorithms capable to classify brain signals related to imaginary motor activities ( left and right hand imaginary). First, digital signal processing is used to select and extract discriminant features, using parametrical methods for the estimation of the power spectral density and the Fisher criterion for separability. The signal is then classified, using linear discriminant analysis. The results show that is possible to obtain good performance with error rates as low as 13% and that the use of parametrical methods for Spectral Power Density estimation can improve the accuracy of the Brain Computer Interface.
Citations
More filters
TL;DR: The proposed method for multi-channel EEG-based emotion recognition using deep forest can eliminate the need for feature extraction in traditional methods and the classification model is insensitive to hyperparameter settings, which greatly reduce the complexity of emotion recognition.
Abstract: Recently, deep neural networks (DNNs) have been applied to emotion recognition tasks based on electroencephalography (EEG), and have achieved better performance than traditional algorithms. However, DNNs still have the disadvantages of too many hyperparameters and lots of training data. To overcome these shortcomings, in this article, we propose a method for multi-channel EEG-based emotion recognition using deep forest. First, we consider the effect of baseline signal to preprocess the raw artifact-eliminated EEG signal with baseline removal. Secondly, we construct 2 $D$ frame sequences by taking the spatial position relationship across channels into account. Finally, 2 $D$ frame sequences are input into the classification model constructed by deep forest that can mine the spatial and temporal information of EEG signals to classify EEG emotions. The proposed method can eliminate the need for feature extraction in traditional methods and the classification model is insensitive to hyperparameter settings, which greatly reduce the complexity of emotion recognition. To verify the feasibility of the proposed model, experiments were conducted on two public DEAP and DREAMER databases. On the DEAP database, the average accuracies reach to 97.69% and 97.53% for valence and arousal, respectively; on the DREAMER database, the average accuracies reach to 89.03%, 90.41%, and 89.89% for valence, arousal and dominance, respectively. These results show that the proposed method exhibits higher accuracy than the state-of-art methods.
114 citations
Cites methods from "EEG Signal Classification Using Pow..."
...Duan et al. [24] proposed the differential entropy (DE) to represent the state related to emotions, which proved to be more suitable for emotional classification than PSD [25]....
[...]
...Usually, fast Fourier transform (FFT) [22] is utilized to transform the time-domain EEG signals into the frequency-domain, and Welch method is used to estimate corresponding power spectral density (PSD) [23]....
[...]
27 Apr 2015
TL;DR: The present work employs Independent Component Analysis and Machine Learning techniques to classify EEG signals into seven different emotions and is able to recognize seven emotions using the two algorithms, SVM and LDA with an average overall accuracy of 74.13% and 66.50% respectively.
Abstract: Emotion Detection has been a topic of great research in the last few decades. It plays a very important role in establishing human computer interface. We as humans are able to understand the emotions of other person but it is literally impossible for the computer to do so. The present work is to achieve the same as accurately as possible. Emotion detection can be done either through text, speech, facial expression or gesture. In the present work the emotions are detected using Electroencephalography (EEG) signals. EEG records the electrical activity within the neurons of the brain. The main advantage of using EEG signals is that it detects real emotions arising straight from our mind and ignores external features like facial expressions or gesture. Hence EEG can act as real indicator of the emotion depicted by the subject. We have employed Independent Component Analysis (ICA) and Machine Learning techniques such as Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) to classify EEG signals into seven different emotions. The accuracy achieved with both the algorithms is computed and compared. We are able to recognize seven emotions using the two algorithms, SVM and LDA with an average overall accuracy of 74.13% and 66.50% respectively. This accuracy was achieved after performing a 4-fold cross-validation. Future applications of emotion detection includes neuro-marketing, market survey, EEG based music therapy and music player.
91 citations
Cites methods from "EEG Signal Classification Using Pow..."
...[6] used power spectral features to classify EEG signals into two classes using LDA with accuracy as high as 86%....
[...]
TL;DR: The proposed approach that uses WPT and LDA results in high accuracy, sensitivity, and specificity for deceit identification for EEG based BCI provided better results in comparison with the other existing methods.
30 citations
TL;DR: In this article, the authors proposed an automatic seizure classification system based on extracting the most significant EEG features for seizure diagnosis, which consists of five steps: channel selection to minimize dimensionality by selecting the most affected channels using the variance parameter, feature extraction to extract the most relevant features, 11 features, from the selected channels.
Abstract: Seizure is an abnormal electrical activity of the brain. Neurologists can diagnose the seizure using several methods such as neurological examination, blood tests, computerized tomography (CT), magnetic resonance imaging (MRI) and electroencephalogram (EEG). Medical data, such as the EEG signal, usually includes a number of features and attributes that do not contains important information. This paper proposes an automatic seizure classification system based on extracting the most significant EEG features for seizure diagnosis. The proposed algorithm consists of five steps. The first step is the channel selection to minimize dimensionality by selecting the most affected channels using the variance parameter. The second step is the feature extraction to extract the most relevant features, 11 features, from the selected channels. The third step is to average the 11 features extracted from each channel. Next, the fourth step is the classification of the average features using the classification step. Finally, cross-validation and testing the proposed algorithm by dividing the dataset into training and testing sets. This paper presents a comparative study of seven classifiers. These classifiers were tested using two different methods: random case testing and continuous case testing. In the random case process, the KNN classifier had greater precision, specificity, positive predictability than the other classifiers. Still, the ensemble classifier had a higher sensitivity and a lower miss-rate (2.3%) than the other classifiers. For the continuous case test method, the ensemble classifier had higher metric parameters than the other classifiers. In addition, the ensemble classifier was able to detect all seizure cases without any mistake.
27 citations
25 Jan 2019
TL;DR: This work proposes a new paradigm of walking imagery (WI) in a virtual environment (VE) and designs a multi-view multi-level deep polynomial network (MMDPN) to explore the complementarity among the features so as to improve the detection of walking from an idle state.
Abstract: Brain–computer interfaces based on motor imagery (MI) have been widely used to support the rehabilitation of motor functions of the upper limbs rather than lower limbs. This is probably because it is more difficult to detect the brain activities of lower limb MI. In order to reliably detect the brain activities of lower limbs to restore or improve the walking ability of the disabled, we propose a new paradigm of walking imagery (WI) in a virtual environment (VE), in order to elicit the reliable brain activities and achieve a significant training effect. First, we extract and fuse both the spatial and time-frequency features as a multi-view feature to represent the patterns in the brain activity. Second, we design a multi-view multi-level deep polynomial network (MMDPN) to explore the complementarity among the features so as to improve the detection of walking from an idle state. Our extensive experimental results show that the VE-based paradigm significantly performs better than the traditional text-based paradigm. In addition, the VE-based paradigm can effectively help users to modulate the brain activities and improve the quality of electroencephalography signals. We also observe that the MMDPN outperforms other deep learning methods in terms of classification performance.
25 citations
Cites methods from "EEG Signal Classification Using Pow..."
...[24] employed power spectral density (PSD) to represent the frequency feature....
[...]
References
More filters
Book•
01 Jan 1997
TL;DR: This chapter presents a meta-analyses of the nonparametric methods used in the construction of the Cramer-Rao Bound Tools, which were developed in the second half of the 1990s to address the problem of boundedness in the discrete-time model.
Abstract: 1. Basic Concepts. 2. Nonparametric Methods. 3. Parametric Methods for Rational Spectra. 4. Parametric Methods for Line Spectra. 5. Filter Bank Methods. 6. Spatial Methods. Appendix A: Linear Algebra and Matrix Analysis Tools. Appendix B: Cramer-Rao Bound Tools. Bibliography. References Grouped by Subject. Subject Index.
2,154 citations
Book•
11 Sep 2007
TL;DR: This book discusses their applications to medical data, using graphs and topographic images to show simulation results that assess the efficacy of the methods, and provides expansive coverage of algorithms and tools from the field of digital signal processing.
Abstract: Electroencephalograms (EEGs) are becoming increasingly important measurements of brain activity and they have great potential for the diagnosis and treatment of mental and brain diseases and abnormalities. With appropriate interpretation methods they are emerging as a key methodology to satisfy the increasing global demand for more affordable and effective clinical and healthcare services. Developing and understanding advanced signal processing techniques for the analysis of EEG signals is crucial in the area of biomedical research. This book focuses on these techniques, providing expansive coverage of algorithms and tools from the field of digital signal processing. It discusses their applications to medical data, using graphs and topographic images to show simulation results that assess the efficacy of the methods. Additionally, expect to find: explanations of the significance of EEG signal analysis and processing (with examples) and a useful theoretical and mathematical background for the analysis and processing of EEG signals; an exploration of normal and abnormal EEGs, neurological symptoms and diagnostic information, and representations of the EEGs; reviews of theoretical approaches in EEG modelling, such as restoration, enhancement, segmentation, and the removal of different internal and external artefacts from the EEG and ERP (event-related potential) signals; coverage of major abnormalities such as seizure, and mental illnesses such as dementia, schizophrenia, and Alzheimer's disease, together with their mathematical interpretations from the EEG and ERP signals and sleep phenomenon; descriptions of nonlinear and adaptive digital signal processing techniques for abnormality detection, source localization and brain-computer interfacing using multi-channel EEG data with emphasis on non-invasive techniques, together with future topics for research in the area of EEG signal processing. © 2007 by John Wiley & Sons Ltd,. All Rights Reserved.
1,115 citations
Book•
01 Jan 2007
TL;DR: This book was set in LaTex by the authors and was printed and bound in the United States of America Library of Congress Cataloging-in-Publication Data Towards Brain-Computer Interfacing.
Abstract: © 2007 Massachusetts Institute of Technology All rights reserved. No part of this book may be reproduced in any form by any electronic or mechanical means(including photocopying, recording, or information storage and retrieval) without permission in writing from thepublisher. This book was set in LaTex by the authors and was printed and bound in the United States of America Library of Congress Cataloging-in-Publication Data Towards Brain-Computer Interfacing / edited by Guido Dornhege, Jose del R. Millan, Thilo Hinterberger, Dennis McFarland, Klaus-Robert Muller. p.; cm. (Neural information processing series) “A Bradford book.” Includes bibliographical references and index. ISBN 978-0-262-04244
608 citations
TL;DR: An approach to analyze data from the P300 speller paradigm using the machine-learning technique support vector machines, which is fast, requires only 10 electrode positions and demands only a small amount of preprocessing.
Abstract: We propose an approach to analyze data from the P300 speller paradigm using the machine-learning technique support vector machines. In a conservative classification scheme, we found the correct solution after five repetitions. While the classification within the competition is designed for offline analysis, our approach is also well-suited for a real-world online solution: It is fast, requires only 10 electrode positions and demands only a small amount of preprocessing.
499 citations
"EEG Signal Classification Using Pow..." refers background in this paper
...8th Latin American and Caribbean Conference for Engineering and Technology Arequipa, Perú WE1-1 June 1-4, 2010 Keywords: Brain Computer Interface, EEG, Linear Discriminant Analysis, AR modeling, Oscillatory Brain Activity....
[...]
TL;DR: The merits of three alternative methods for estimating spectral features are compared to the fast Fourier transform (FFT), based on autoregressive (AR) modeling, and it is demonstrated that a fifth-order filter is sufficient to estimate EEG characteristics in 90 percent of the cases.
Abstract: The hypothesis that an electroencephalogram (EEG) can be analyzed by computer using a series of basic descriptive elements of short duration (1-5 s) has prompted the development of methods to extract the best possible features from very short (1 s) time intervals. In this paper, the merits of three alternative methods for estimating spectral features are compared to the fast Fourier transform (FFT). These procedures, based on autoregressive (AR) modeling are: 1) Kalman filtering, 2) the Burg algorithm, and 3) the Yule-Walker (YW) approach. The methods are reportedly able to provide high resolution spectal estimates from short EEG intervals, even in cases where intervals contain less than a ful period of a cyclic waveform. The first method is adaptive, the other two are not. Using Akaike's final prediction error (FPE) criterion, it was demonstrated that a fifth-order filter is sufficient to estimate EEG characteristics in 90 percent of the cases. However, visual inspection of the resulting spectra revealed that the order indicated by the FPE criterion is generally too low and better spectra can be obtained using a tenth-order AR model. The Yule-Walker method resulted in many unstable models and should not be used. Of two remaining methods, i.e., Burg and Kalman, the first provides spectra with peaks having a smaller bandwidth than the Kalman-flter method. Additional experiments with the Burg method revealed that, on the average, the same results were obtained using the FFT.
172 citations
"EEG Signal Classification Using Pow..." refers background in this paper
...In [8] was found that the order of this model is very important to obtain an accurate estimation of the spectrum....
[...]