Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Mohammad Shahab Shahvazian; Vahid Abootalebi; Mohammad Taghi Sadeghi
Volume 6, Issue 1 , June 2012, , Pages 35-47
Abstract
With the advent of biometric knowledge, conventional methods of authentication are being replaced with biometric based methods. Recently, the use of EEG signal in biometric systems attracted increasing research attention. Only a few works have been done in this emerging of EEG-based biometry mainly focusing ...
Read More
With the advent of biometric knowledge, conventional methods of authentication are being replaced with biometric based methods. Recently, the use of EEG signal in biometric systems attracted increasing research attention. Only a few works have been done in this emerging of EEG-based biometry mainly focusing on person identification not on person authentication. This paper examines the effectiveness of the EEG as a biometric for person authentication. In this study, the EEG signal from fifteen volunteer recorded during imagination of opening and closing fist was used. A set of AR coefficients, power of spectral bands, Energy Spectral Density, Energy Entropy and Sample Entropy were used as extracted features. The authentication system is fused at the sensor module and features to support a system which can meet more challenging and varying requirements. The utility of the sequential search methods is also experimentally studied. In the extensive experimentation on the Shalk and his colleague’s database, we demonstrate that with combination of features when using single channel EEG, the performance of system is improved in two ways of single block and multi block methods compared to other. Result of this study shows a clear vision of commercial and practical use of the brain's electrical signals in the authentication systems of future.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Ramtin Zargari Marandi; Seyed Hojat Sabzpoushan
Volume 6, Issue 4 , June 2012, , Pages 279-285
Abstract
Recent research in pervasive computing field leads to use of novel techniques for human activity recognition. One of these techniques is electrooculography which helps to record eye movements and by analyzing these movements’ patterns it’s possible to recognize daily life activities like ...
Read More
Recent research in pervasive computing field leads to use of novel techniques for human activity recognition. One of these techniques is electrooculography which helps to record eye movements and by analyzing these movements’ patterns it’s possible to recognize daily life activities like reading. Eye movement patterns during reading can be detected using only EOG signals from horizontal channel instead of both horizontal and vertical channels, so only horizontal channel electrode placement on subject’s face set up for hindrance reduction is used in this work. Despite of channels reduction and by using DTW-based string matching algorithm and reading reference template extraction using wavelet transform and encoding of EOG signal, the performance of classification between reading and non-reading data increased, As it shows 4% increase in maximum recognition rate and also low standard deviation in recognition rate in addition to 7% increase in mean of recall which demonstrate that the algorithm is more robust and reliable in comparison with previous algorithms encountering various situations and subjects.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Ali Khadem; Gholam Ali Hossein-Zadeh
Volume 6, Issue 1 , June 2012, , Pages 57-69
Abstract
Exploring the causal (delayed) brain relations is an important topic in the Neuroscience. The traditional estimators of brain causal (delayed) relations are mainly model-based and put restrictive assumptions on the brain dynamics. In the recent years, some nonparametric measures have been introduced ...
Read More
Exploring the causal (delayed) brain relations is an important topic in the Neuroscience. The traditional estimators of brain causal (delayed) relations are mainly model-based and put restrictive assumptions on the brain dynamics. In the recent years, some nonparametric measures have been introduced to solve this problem. Among them, the most important one is Transfer Entropy (TE) which is based on the information theory and Conditional Mutual Information concept. However, in the presence of significant instantaneous relations that are observed extensively in the brain functional datasets, TE may estimate the causal (delayed) relations inaccurately. In this paper, two information theoretic based measures called Instantaneous Interaction (II) and Modified Transfer entropy (MTE) are introduced to estimate the instantaneous and causal (delayed) brain relations, respectively. MTE is used instead of TE whenever II is significant. These measures are evaluated on 3 simulated models and eyes-closed resting state EEG data. The simulation results show high ability of II to estimate the linear and nonlinear instantaneous relations. Also, based on the simulation results MTE outperforms TE to estimate causal (delayed) relations in presence of significant instantaneous relations (significant II). For the real EEG data, II detects a significant instantaneous relation between Posterior and Frontal EEG channels. Also MTE detects the information flow from Posterior EEG channels to Frontal ones more significantly than TE does. So in presence of significant instantaneous relations in the real EEG data, MTE outperforms TE.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Rahele Mohammadi; Ali Mahloojifar
Volume 6, Issue 2 , June 2012, , Pages 141-152
Abstract
Self-paced BCI systems are more natural for real-life applications since these systems allow the user to control the system when desired. Detection of event periods in continuous EEG signal is one of the most important challenges in designing self-paced BCIs. In this paper, the Event related synchronization ...
Read More
Self-paced BCI systems are more natural for real-life applications since these systems allow the user to control the system when desired. Detection of event periods in continuous EEG signal is one of the most important challenges in designing self-paced BCIs. In this paper, the Event related synchronization (ERS) is extracted from idle EEG signal using fractal dimensions in frequency range from 6 to 36 Hz and sparse representation based classifier. Our proposed method applied on EEG signal recorded during executing foot movement in 7 subjects. The average true positive rate and false positive rate equal to 90% and 5% were achieved.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Adib Keikhosravi; Edmond Zahedi
Volume 6, Issue 4 , June 2012, , Pages 307-317
Abstract
The photoplethysmogram (PPG) is a low cost and ubiquitous signal and has always had a great significance in cardiovascular parameter identification such as arterial dilation due to a stimulus. The PPG is generally recorded from the fingertip which is affected by the auto-regulation mechanism (ARM), preventing ...
Read More
The photoplethysmogram (PPG) is a low cost and ubiquitous signal and has always had a great significance in cardiovascular parameter identification such as arterial dilation due to a stimulus. The PPG is generally recorded from the fingertip which is affected by the auto-regulation mechanism (ARM), preventing the results to be well correlated with standard methods based on imaging the brachial or radial artery. Based on the fact that the ARM has no effect on conduit arteries, the correlation between fingertip and radial artery PPG is investigated in this work. A custom made probe is fabricated using an array of photodiodes and a 960 nm LED for recording the wrist photoplethysmogram (PPG). The design is based on Monte-Carlo simulation of light propagation in tissues. Two series of experiments were carried-out: normal breathing and deep breathing. In both experiments, index finger and wrist PPG were simultaneously recorded. In the first series of experiments, signals from 9 subjects were recorded and the correlation coefficient for the raw signals (AC+DC), the AC and DC components of wrist and finger PPG were 62.5% ± 12.1%, 91.2% ± 6.9% and 61% ± 13.4% respectively. In the second series of experiment (deep breathing), signals from 6 subjects were recorded and the correlation coefficient for the raw signals (AC+DC), the AC and DC components were 89.7% ± 5.9%, 93.7% ± 3.3% and 89.9% ± 5.9% respectively. These results show that under normal breathing conditions, only the AC components of the PPG signals are highly correlated. When respiration becomes the dominant effect, both AC and DC parts become highly correlated.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Reza Soleimani; Seyed Mpjtaba Rouhani
Volume 5, Issue 2 , June 2011, , Pages 89-103
Abstract
in this paper, a novel and effective algorithm for classification of important heart arrhythmia is presented. The proposed algorithm uses heart rate variation (HRV) signal which has better chaotic characteristics. In addition to commonly used linear time domain and frequency domain features, nonlinear ...
Read More
in this paper, a novel and effective algorithm for classification of important heart arrhythmia is presented. The proposed algorithm uses heart rate variation (HRV) signal which has better chaotic characteristics. In addition to commonly used linear time domain and frequency domain features, nonlinear (chaotic) features are examined, too. To increase classification accuracy and facilitate learning, two techniques are used: a) extracted features are reduced by generalized discriminant analysis (GDA) and b) by a self organizing map (SOM), the most informant data are selected. Chaotic features help to improve diagnosis accuracy from 92% up to 97%. The results indicate the importance of GDA and SOM in efficiency of proposed algorithm. MLP, SVM and PNN classifiers are examined and compared. The proposed algorithm was able to diagnose 7 arrhythmias PVC, AFL, AF, CHB, LBBB, VF, VT and normal sinus rhythm (NSR) with 97.4% accuracy.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Faride Ebrahimi; Mohammad Mikaili
Volume 4, Issue 2 , June 2010, , Pages 97-108
Abstract
Different biological signals including EEG, EOG, and EMG are recorded in sleep labs to diagnose sleep disorders. Data recorded during sleep is usually analyzed by sleep specialists visually. Since the sleep data is usually recorded for a long time period- namely a whole night- its visual inspection and ...
Read More
Different biological signals including EEG, EOG, and EMG are recorded in sleep labs to diagnose sleep disorders. Data recorded during sleep is usually analyzed by sleep specialists visually. Since the sleep data is usually recorded for a long time period- namely a whole night- its visual inspection and classification is a very demanding and time consuming task so automatic analysis can definitely facilitate that. The key to automatic sleep staging is to extract suitable features. In the current study two classes of features are extracted from EEG signal. The first group is the features calculated from the coefficients of wavelet packet transformation (WPT) and the second group consists of a number of frequency features and a time feature, the amplitude of EEG signal itself. These two sets of features were separately mapped on a two dimensional space by SOM neural networks. The mappings indicated that these features are highly discriminative in separating sleep stages automatically. The data extracted from awake and deep sleep EEGs were mapped on two totally different regions. The mapping also indicated that EEG signal is not enough to separate stages thoroughly, as extracted data from EEG during REM and the first stage of NREM are mapped on the same region. Data extracted from EEG signals in the second stage overlapped with other stages which are in agreement with physiological definition of sleep stages.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Mohammad Rashidi; Hamid Behnam; Ali Sheikhani; Mohammad Reza Mohammadi; Maryam Norouzian
Volume 4, Issue 3 , June 2010, , Pages 187-194
Abstract
This paper presents ICA analysis application for detection of autism disorder. In the first step, resources of EEG signals were extracted by ICA and then time domain and frequency domain processing were implemented. EEG signals of ten children with autism and ten healthy children aged 6 to 11 years have ...
Read More
This paper presents ICA analysis application for detection of autism disorder. In the first step, resources of EEG signals were extracted by ICA and then time domain and frequency domain processing were implemented. EEG signals of ten children with autism and ten healthy children aged 6 to 11 years have been obtained. The results have been compared statistically by T-test. Lower correlation levels between resources of the left hemisphere of the brain especially C3 channel region in autistic children compared with healthy subjects have been observed. Also the average energy of theta frequency band in C3 and F3 channels for children with autism were lower than that in healthy people and this criterion was higher in gamma frequency band.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Isar Nejadgholi; Mohammad Hasan Moradi; Fateme Abdol Ali
Volume 4, Issue 4 , June 2010, , Pages 279-292
Abstract
Many methods for automatic heartbeat classification have been applied and reported in literature, but relatively little number of them concerned with patient independent classification because of the less significant results compared to patient dependent ones. In this work, Reconstructed Phase Space ...
Read More
Many methods for automatic heartbeat classification have been applied and reported in literature, but relatively little number of them concerned with patient independent classification because of the less significant results compared to patient dependent ones. In this work, Reconstructed Phase Space (RPS) theory is used to classify five heartbeat types (Normal, PVC, LBBB, RBBB and PB). In the first and second method, RPS is modeled by the Gaussian mixture model (GMM) and bins, respectively and then classified by classic Bayesian classifier. In the third method, RPS is directly used to train predictor time-delayed neural networks (TDNN) and classified based on minimum prediction error. All three methods highly outperform the results reported before for patient independent heartbeat classification. The best result is achieved using GMM-Bayes method with 92.5% accuracy for patient independent classification.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Amin Zare; Reza Boostani; Mansour Zolghadr Jahromi
Volume 4, Issue 3 , June 2010, , Pages 195-208
Abstract
There is a growing interest to improve seizure prediction by online analyzing of electroencephalogram (EEG) signals in epileptic patients. Seizure attack is occurred infrequently and unpredictably; hence, automatic detection of seizure during long-term is highly recommended. In this paper a novel Feature ...
Read More
There is a growing interest to improve seizure prediction by online analyzing of electroencephalogram (EEG) signals in epileptic patients. Seizure attack is occurred infrequently and unpredictably; hence, automatic detection of seizure during long-term is highly recommended. In this paper a novel Feature Reduction method namely AIS-RCA which adopted from the immunity system is proposed to improve the seizure detection rate. The automatic seizure detection can be performed in two successive stages: 1) The feature extraction/selection stage from EEG signals and 2) classifying the feature vectors by an efficient classifier. In this study, first, pseudo-Wigner-Ville distribution was applied to each window of the EEG signals and then the extracted features were transformed by AIS-RCA transform to represent the features in a more separable space. The AIS-RCA transformation matrix is estimated by using chunklets (a chunklet is defined as a subset of points that are known to be same). AIS-RCA using the proposed Artificial Immune System algorithm named Adaptive Distance-AIRS to discover the chunklets in the data space. Finally KNN classifier was applied to the transformed features to classify the seizure and non-seizure windows. The experimental results show that the proposed method yields epileptic detection accuracy rate up to 99.9% which is better than the results achieved by other types of features such as FFT, Wavelet transform, entropy and chaotic measures.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Mohammad Mehdi Ramezani; Ahmad Reza Sharafat
Volume 4, Issue 2 , June 2010, , Pages 123-134
Abstract
In this paper, we propose a novel approach for classification of surface electromyogram (sEMG) signal with a view to controlling myoelectric prosthetic devices. The sEMG signal generated during isometric contraction is modeled by a stochastic process whose probability density function (PDF) is non- Gaussian ...
Read More
In this paper, we propose a novel approach for classification of surface electromyogram (sEMG) signal with a view to controlling myoelectric prosthetic devices. The sEMG signal generated during isometric contraction is modeled by a stochastic process whose probability density function (PDF) is non- Gaussian for low levels of applied force. Since the PDF of ambient noise is assumed to be Gaussian, we extract correntropy features, as they contain information on non-Gaussian components (the sEMG signal) only; and utilize the linear discriminant analysis (LDA) to classify the sEMG signal using correntropy features. Our proposed method has lower classification error and requires much less computations as compared to other existing advanced methods.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Sorour Behbahani; Ali Motie Nasrabadi
Volume 4, Issue 1 , June 2010, , Pages 53-64
Abstract
The analysis of EEG signals plays an important role in a wide range of applications, such as psychotropic drug research, sleep studies, seizure detection and hypnosis processing. From years ago hypnosis was known as a method to help the patients in different fields such as reduction of stress, leaving ...
Read More
The analysis of EEG signals plays an important role in a wide range of applications, such as psychotropic drug research, sleep studies, seizure detection and hypnosis processing. From years ago hypnosis was known as a method to help the patients in different fields such as reduction of stress, leaving bad habits, pain control and etc. EEG signals during pure hypnosis would differ from those recorded in the normal no hypnotic conditions. There are several methods for analyzing the EEG signal and similarity index method is one of the famous methods in this branch. In this paper the features of EEG signal of three groups of people with different hypnotizability during hypnosis (Fractal, Wavelet Entropy, Frequency Bands) from left-right and frontal-back lobes were extracted and analyzed using Fuzzy Similarity Index Method to find whether there are any significant relations between the function of these hemispheres and hypnotizability degree. Finally after detecting the significancy, we used the selected features were used to classify the subjects into three groups of hypnotizability. The best classification accuracy was obtained 94% (for two classes of features 1. entropy, Higuchi, high frequency, 2. energy and entropy) and the lowest was 87.5% (for entropy, Higuchi and low frequency features).
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Hosna Ghandeharion; Abbas Erfanian Omidvar
Volume 3, Issue 3 , June 2009, , Pages 199-211
Abstract
Contamination of Electroencephalographic (EEG) recordings with different kinds of artifacts is the main obstacle to the analysis of EEG data. Independent Component Analysis (ICA) is now a widely accepted tool for detection of artifact in EEG data. This component-based method segregates artifactual activities ...
Read More
Contamination of Electroencephalographic (EEG) recordings with different kinds of artifacts is the main obstacle to the analysis of EEG data. Independent Component Analysis (ICA) is now a widely accepted tool for detection of artifact in EEG data. This component-based method segregates artifactual activities in separate sources hence, the reconstruction of EEG recordings without these sources leads to artifact reduction. Identification of the artifactual components is a major challenge to artifact removal using ICA is the. Although, during past several years, it has been proposed for automatic detecting the artifactual component, there is still little consensus on criteria for automatic rejection of undesired components. In this paper we present a new identification procedure based on statistics and time-frequency properties of independent components for fully automatic ocular artifact suppression. By comparing the statistics and time-frequency properties of independent components, the artifactual components were identified and removed. The results on 2000 4-s EEG epochs indicate that the artifact components can be identified with an accuracy of 92.8%. Moreover, statistical test indicates that the statistics and time-frequency properties of artifactual components are significantly different from that of non-artifactual components.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Mohammad Hasan Moradi; Bahador Makki Abadi
Volume 2, Issue 2 , June 2008, , Pages 141-154
Abstract
Hish rate classification of Electromyogram (EMG) signals for controlling of prosthetic hands is still a hot topic among the rehabilitation research titles. Specially, when the degree of freedom in artificial hands increases, the classification rate decreases dramatically. In this paper, a new five layer ...
Read More
Hish rate classification of Electromyogram (EMG) signals for controlling of prosthetic hands is still a hot topic among the rehabilitation research titles. Specially, when the degree of freedom in artificial hands increases, the classification rate decreases dramatically. In this paper, a new five layer classifier based on Neuro-Fuzzy-Genetic structure was introduced to increase the classification accuracy of EMG signals. The proposed classifier has a self- organized structure, which adaptively creates new rules according to the input features and trains the fuzzy rule weights based on the back propagation method. Finally, the genetic algorithm (GA) was employed for the final tuning stage. In this study, six subjects were asked to perform 9 different movements and their EMG signals were caught during the tasks from the six different forearm muscles. In order to remove the noises, the signals were filtered. Then the integral absolute average (IAV), Cepstrum coefficients and Wavelet Packet Coefficients with entropy pruning were extracted from the filtered signals as features. We used principal components analysis (PCA) for dimensionality reduction (234 to 10). The dimensionality reduction by PCA simplifies the structure of the classifier and reduces the processing time for the pattern recognition. The proposed classifier was applied on the features and the results were led to higher than 96.7% classification rate for the 9 classes of movement. To make a comparison, support vector machine (SVM) was employed (76% classification rate for 9 classes) and the results showed a drastic supremacy of the proposed method.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Kianoush Nazarpour; Ahmad Reza Sharafat; Seyed Mohammad Firouzabadi
Volume 1, Issue 3 , June 2007, , Pages 189-199
Abstract
A novel approach to surface electromyogram (sEMG) signal classification using its higher order statistics (HOS) is presented in this study. As the probability density function of the sEMG during isometric contraction in some cases is very close to the Gaussian distribution, it is frequently assumed to ...
Read More
A novel approach to surface electromyogram (sEMG) signal classification using its higher order statistics (HOS) is presented in this study. As the probability density function of the sEMG during isometric contraction in some cases is very close to the Gaussian distribution, it is frequently assumed to be Gaussian. As this assumption is not valid when the force is small, in this paper, we consider the non-Gaussian characteristics of the sEMG, and compute the second-, the third- and the fourth order statistics of the sEMG as its features. These features are used to classify four upper limb primitive motions, i.e., elbow flexion (EF), elbow extension (EE), forearm supination (FS), and forearm pronation (FP). We used the sequential forward selection (SFS) method to reduce the number of HOS features to a sufficient minimum while retaining their discriminatory information, and apply the Knearest neighbor method for classification. Our approach is robust against statistical variations in noise, and does not require additional computations compared to existing methods for providing high rates of correct classification of the sEMG, which makes it useful in devising real-time sEMG controlled prostheses.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Masoud Reza Aghabozorgi Sahaf
Volume 1, Issue 4 , June 2007, , Pages 301-310
Abstract
The extraction of the fetal electrocardiogram (FECG) from the skin electrode signals recorded of the mother's body is a problem of concern to signal processing. Blind signal separation (BSS) technique that separates some signals from their combinations without acknowledgments about transmission channel, ...
Read More
The extraction of the fetal electrocardiogram (FECG) from the skin electrode signals recorded of the mother's body is a problem of concern to signal processing. Blind signal separation (BSS) technique that separates some signals from their combinations without acknowledgments about transmission channel, is a fundamental method for solving this problem. The most proposed BSS algorithm for separation of fetal electrocardiogram (FECG) and mother electrocardiogram (MECG) relies on the independence of these signals (ICA). This paper introduces a novel technique for the cases that signals are correlated with each other, i.e. considering a real assumption. The method uses Wold decomposition principle for extracting the desired and proper information from the predictable part of the measured data, and exploits approaches based on the second-order statistics to estimate source signals. Simulation results are showed the effectiveness of the method for separation of electrocardiogram signals.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Mohammad Reza Nourouzi; Mohammad Javad Yazdanpanah
Volume 1, Issue 1 , June 2007, , Pages 53-62
Abstract
Ventricular Fibrillation (VF) is a dangerous abnormality in the heart activity. During the VF, well known shape of electrocardiogram (ECG) signal changes to a pseudo-noise waveform. Recent researches have depicted that VF is not a noisy signal. The characteristics of VF and chaotic signals are the same. ...
Read More
Ventricular Fibrillation (VF) is a dangerous abnormality in the heart activity. During the VF, well known shape of electrocardiogram (ECG) signal changes to a pseudo-noise waveform. Recent researches have depicted that VF is not a noisy signal. The characteristics of VF and chaotic signals are the same. In this research, these characteristics were studied and used for discriminating the VF signal from the other electrocardiogram signals. Three types of electrocardiogram signals including VF, Tachycardia and Normal ECG were used for training and testing a back propagation neural network. We used these signals in three stages. At the first stage, the power spectrum of signals was used for training and testing the neural network. Time Series signals were used in the second stage. The result of the first experience was better than the second. At the third stage, we used surrogate technique to enrich the training signals in the time domain. The surrogate technique is a method which has been used in the chaotic systems. By using these new generated signals for training the neural network, the results of classification were extremely improved. Furthermore, the results of simulations showed that the chaotic dynamic of VF signal is a time dependant one.
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Nader Jafarnia Dabanloo; Ahmad Ayatollahi; Vahid Jouhari Majd; Desmond Mclernon
Volume -2, Issue 1 , July 2005, , Pages 71-80
Abstract
The generation of electrocardiogram (ECG) signals by using a mathematical model has recently been investigated. One of the applications of a dynamical model which can artificially produces an ECG signal is the easy assessment of diagnostic ECG signal processing devices. In addition, the model may be ...
Read More
The generation of electrocardiogram (ECG) signals by using a mathematical model has recently been investigated. One of the applications of a dynamical model which can artificially produces an ECG signal is the easy assessment of diagnostic ECG signal processing devices. In addition, the model may be also used in compression and telemedicine applications. It is also required that the model has capability to produce both normal and abnormal ECG signals. In this study, it is introduced a new method using radial basis function neural networks in a dynamical model based on McSharry model, to produce artificially the ECG signals. This new method has the advantage of capability to simulate a wider class of physiological signals (both normal and abnormal), compared to McSharry model. The simulation results are presented for normal ECG and three abnormal ones. The accuracy of the model has evaluated by using the error functions. The average of this error for a period of 100 seconds using 20 neurons is less than 2.5 percent for the four modeled cases (one normal and three abnormal).
Biomedical Signal Processing / Medical Signal Processing / Biosignal Processing
Vahid Abootalebi; Mohammad Hasan Moradi; Mohammad Ali Khalilzadeh
Volume -1, Issue 1 , June 2004, , Pages 25-45
Abstract
P300 is the most predominant cognitive component of the brain signals. In this study, the single trial event related potentials recorded from the scalp, were decomposed to their time-frequency components using discrete wavelet transform. These quantities were later analyzed as the features related to ...
Read More
P300 is the most predominant cognitive component of the brain signals. In this study, the single trial event related potentials recorded from the scalp, were decomposed to their time-frequency components using discrete wavelet transform. These quantities were later analyzed as the features related to the cognitive activities of brain. Study on these features showed that cognitive processes of the brain of ten reflected in the feature of δ and θ bands. The aim of this study, as a primary step for "lie detection using brain signals (EEG - Polygraphy)", was to design a system for discriminating between single trials involved P300 and those without it. In the first approach, an optimal discriminant function based on 9 features was designed using "Stepwise Linear Discriminant Analysis". Detection accuracy was 75% in training data and 71% in test data. More study on this method showed that almost similar accuracy could be obtained from the features of Pz channel alone. In the second approach, the modular learning strategy - based on principal component analysis and neural networks - was used. After training the systems, the maximum classification accuracy was 76% in train data and 72% in test data.