Classification of human emotion from EEG using discrete wavelet transform

In this paper, we summarize the human emotion recognition using different set of electroencephalogram (EEG) channels using discrete wavelet transform. An audio-visual induction based protocol has been designed with more dynamic emotional content for inducing discrete emotions (disgust, happy, surprise, fear and neutral). EEG signals are collected using 64 electrodes from 20 subjects and are placed over the entire scalp using International 10-10 system. The raw EEG signals are preprocessed using Surface Laplacian (SL) filtering method and decomposed into three different frequency bands (alpha, beta and gamma) using Discrete Wavelet Transform (DWT). We have used “db4” wavelet function for deriving a set of conventional and modified energy based features from the EEG signals for classifying emotions. Two simple pattern classification methods, K Nearest Neighbor (KNN) and Linear Discriminant Analysis (LDA) methods are used and their performances are compared for emotional states classification. The experimental results indicate that, one of the proposed features (ALREE) gives the maximum average classification rate of 83.26% using KNN and 75.21% using LDA compared to those of conventional features. Finally, we present the average classification rate and subsets of emotions classification rate of these two different classifiers for justifying the performance of our emotion recognition system.

A wavelet-approximate entropy method for epileptic activity detection from EEG and its sub-bands

Epilepsy is a common brain disorder that about 1% of world's population suffers from this disorder. EEG signal is summation of brain electrical activities and has a lot of information about brain states and also used in several epilepsy detection methods. In this study, a wavelet-approximate entropy method is ap-plied for epilepsy detection from EEG signal. First wavelet analysis is applied for decomposing the EEG signal to delta, theta, alpha, beta and gamma sub- ands. Then approximate entropy that is a chaotic measure and can be used in estimation complexity of time series applied to EEG and its sub-bands. We used this method for separating 5 group EEG signals (healthy with opened eye, healthy with closed eye, interictal in none focal zone, interictal in focal zone and seizure onset signals). For evaluating separation ability of this method we used t-student statistical analysis. For all pair of groups we have 99.99% separation probability in at least 2 bands of these 6 bands (EEG and its 5 sub-bands). In comparing some groups we have over 99.98% for EEG and all its sub-bands.

Wavelet-based estimation of EEG synchronization associated with native and second language processing in Stroop task

Objective:To examine and compare the synchronization of different brain regions during the Chinese and English Stroop tasks.Methods.Ten native Chinese speakers with a moderate command of English participated in this study,and event-related potentials were recorded while participants performed the Stroop task.Then wavelet-based estimation of instantaneous EEG coherence was applied to investigate the synchronization of different brain regions during Stroop task.Results:A greater negativity for the in- congruent situation than congruent situation appeared from 350ms to 600ms post-stimulus onset over frontal,central,and parietal regions in Chinese Stroop task,while the negativity was absent in English Stroop task.However,not only in Chinese Stroop task but also in English Stroop task was it found signif- icantly higher EEG coherences for the incongruent situation than congruent situation over frontal,pari- etal,and frontoparietal regions before 400ms post stimulus onset atβ(13-30 Hz) frequency band.Conclu- sion:This finding indicated that wavelet-based coherence is more exquisite tool to analyze brain electro- physiological signals associated with complex cognitive task than ERP component,and that functional syn- chronization indexed by EEG coherence is enhanced at the earlier stage while processing the conflicting in- formation for the incongruent stimulus.

The Spatial Equivalence Between Wavelet Decomposition and Phase Space Embedding of EEG

Using both the wavelet decomposition and the phase space embedding, the phase trajectories of electroencephalogram (EEG) is described. It is illustrated based on the present work,that is,the wavelet decomposition of EEG is essentially a projection of EEG chaotic attractor onto the wavelet space opened by wavelet filter vectors, which is in correspondence with the phase space embedding of the same EEG. In other words, wavelet decomposition and phase space embedding are equivalent in methodology. Our experimental results show that in both the wavelet space and the embedded space the structure of phase trajectory of EEG is similar to each other. These results demonstrate that wavelet decomposition is effective on characterizing EEG time series.

EEG Signal Denoising and Feature Extraction Using Wavelet Transform in Brain Computer Interface

Electroencephalogram(EEG) signal preprocessing is one of the most important techniques in brain computer interface(BCI).The target is to increase signal-to-noise ratio and make it more favorable for feature extraction and pattern recognition.Wavelet transform is a method of multi-resolution time-frequency analysis,it can decompose the mixed signals which consist of different frequencies into different frequency band.EEG signal is analyzed and denoised using wavelet transform.Moreover,wavelet transform can be used for EEG feature extraction.The energies of specific sub-bands and corresponding decomposition coefficients which have maximal separability according to the Fisher distance criterion are selected as features.The eigenvector for classification is obtained by combining the effective features from different channels.The performance is evaluated by separability and pattern recognition accuracy using the data set of BCI 2003 Competition,the final classification results have proved the effectiveness of this technology for EEG denoising and feature extraction.

Wavelet Variance Analysis of EEG Based on Window Function

A new wavelet variance analysis method based on window function is proposed to investigate the dynamical features of electroencephalogram(EEG).The exprienmental results show that the wavelet energy of epileptic EEGs are more discrete than normal EEGs, and the variation of wavelet variance is different between epileptic and normal EEGs with the increase of time-window width. Furthermore, it is found that the wavelet subband entropy (WSE) of the epileptic EEGs are lower than the normal EEGs.

Approach for epileptic EEG detection based on gradient boosting

The automatic seizure detection is significant for epilepsy diagnosis and it can alleviate the work intensity of inspecting prolonged electroencephalogram （EEG）. This paper presents and investigates a novel machine learning approach utilizing gradient boosting to detect seizures from long-term EEG. We apply relative fluctuation index to extract features of long-term intracranial EEG data. A classifier trained with the gradient boosting algorithm is adopted to discriminate the seizure and non-seizure EEG signals. Smoothing and collar technique are finally used as post-processing in order to improve the detection accuracy further. The seizure detection method is assessed on Freiburg EEG datasets from 21 patients. The experimental results indicate that the proposed method yields an average sensitivity of 94. 60% with a false detection rate of 0. 18/h.

Synthesized Multi-Method to Detect and Classify Epileptic Waves in EEG

In order to sufficiently exploit the advantages of different signal processing methods, such as wavelet transformation (WT), artificial neural networks (ANN) and expert rules (ER),a synthesized multi-method was introduced to detect and classify the epileptic waves in the EEG data. Using this method, at first, the epileptic waves were detected from pre-processed EEG data at different scales by WT, then the characteristic parameters of the chosen candidates of epileptic waves were extracted and sent into the well-trained ANN to identify and classify the true epileptic waves,and at last, the detected epileptic waves were certificated by ER. The statistic results of detection and classification show that, the synthesized multi-method has a good capacity to extract signal features and to shield the signals from the random noise. This method is especially fit for the analysis of the biomedical signals in biomedical engineering which are usually non-placid and nonlinear.

Revealing True and False Brain States Based on Wavelet Analysis of Electroencephalogram

Statement of the Problem: As you know, there exist two different states in the brain’s mental activity: true and false. In recent years, a progressive method of wavelet transformation of the electroencephalogram (EEG) has been developed, which enabled us to establish the fundamental possibility of direct objective registration of the human brain’s mental activity. Earlier, we created an experimental model and software for recognizing true and false mental responses of a person based on the EEG wavelet transformation and described it in the article. The developed experimental model and information software made it possible to compare the two mental states of brain activity by electroencephalographic indicators, one of which is false and the other is true. The goal is to develop a fundamentally new information technology for recognizing true and false states in the brain’s mental activity based on the wavelet transformation of the electroencephalogram. Results: It was revealed that the true and false states of the brain can be distinguished using the method of continuous wavelet transformation and calculation of the EEG wavelet energy. It is shown that the main differences between true and false mental responses are observed in the delta and alpha ranges of the EEG. In the EEG delta rhythm, the wavelet energy is reliably higher in case of a false answer compared to a true one. In the EEG alpha rhythm, the wavelet energy is significantly higher with a true answer than a false one. Practical significance of the research: The data obtained open up the fundamental possibility of identifying true and false mental states of the brain on the basis of continuous wavelet transformation and calculation of the EEG wavelet energy.

Seizure detection using earth movers' distance and SVM in intracranial EEG

Seizure detection is extremely essential for long-term monitoring of epileptic patients. This paper investigates the detection of epileptic seizures in multi-channel long-term intracranial electroencephalogram （iEEG）. The algorithm conducts wavelet decomposition of iEEGs with five scales, and transforms the sum of the three frequency bands into histogram for computing the distance. The proposed method combines a novel feature called EMD-L1, which is an efficient algorithm of earth movers＇ distance （EMD）, with support vector machine （SVM） for binary classification between seizures and non-sei- zures. The EMD-LI used in this method is characterized by low time complexity and high processing speed by exploiting the L~ metric structure. The smoothing and collar technique are applied on the raw outputs of SVM classifier to obtain more ac- curate results. Several evaluation criteria are recommended to compare our algorithm with other conventional methods using the same dataset from the Freiburg EEG database. Experiment results show that the proposed method achieves a high sensi- tivity, specificity and low false detection rate, which are 95.73 %, 98.45 % and 0.33/h, respectively. This algorithm is char- acterized by its robustness and high accuracy with the possibility of performing real-time analysis of EEG data, and may serve as a seizure detection tool for monitoring long-term EEG.

Multi-scale phase average waveform of electroencephalogram signals in childhood absence epilepsy using wavelet transformation

BACKGROUND： Recent studies have focused on various methods of wavelet transformation for electroencephalogram （EEG） signals. However, there are very few studies reporting characteristics of multi-scale phase waves during epileptic discharge.OBJECTIVE： To extract multi-scale phase average waveforms from childhood absence epilepsy EEG signals between time and frequency domains using wavelet transformation, and to compare EEG signals of absence seizure with pre-epileptic seizure and normal children, and to quantify multi-scale phase average waveforms from childhood absence epilepsy EEG signals. DESIGN, TIME AND SETTING： The case-comparative experiment was performed at the Department of Neuroelectrophysiology, Tianjin Medical University from August 2002 to May 2005. PARTICIPANTS： A total of 15 patients with childhood absence epilepsy from the General Hospital of Tianjin Medical University were enrolled in the study. The patients were not administered anti-epileptic drugs or sedatives prior to EEG testing. In addition, 12 healthy, age- and gender-matched children were also enrolled.METHODS： EEG signals were tested on 15 patients with childhood absence epilepsy and 12 normal children. Epileptic discharge signals during clinical and subclinical seizures were collected 10 and 20 times, respectively. The collected EEG signals were treated with wavelet transformation to extract multi-scale characteristics during absence epilepsy seizure using a conditional sampling method. Multi-scale phase average waveforms were collected using a conditional phase averaging technique. Amplitude of phase average waveform from EEG signals of epilepsy seizure, subclinical epileptic discharge, and EEG signals of normal children were compared and statistically analyzed in the first half-cycle.MAIN OUTCOME MEASURES： Multi-scale wavelet coefficient and the evolution of EEG signals were observed during childhood absence epilepsy seizures using wavelet transformation. Multi-scale phase average waveforms from EEG signals were observed using a conditional sampling method and phase averaging technique.RESULTS： Multi-scale characteristics of EEG signals demonstrated that 12-scale （3 Hz） rhythmical activity was significantly enhanced during childhood absence epilepsy seizure and co-existed with background structure （〈1 Hz, low frequency discharge）. The phase average wave exhibited opposed phase abnormal rhythm at 3 Hz. Prior to childhood absence epilepsy seizure, EEG detected opposed abnormal a rhythm and 3 Hz composition, which were not detected with traditional EEG. Compared to EEG signals from normal children, epileptic discharges from clinical and subclinical childhood absence epilepsy seizures were positive and amplitude was significantly greater （P〈0.05）.CONCLUSION： Wavelet transformation was used to analyze EEG signals from childhood absence epilepsy to obtain multi-scale quantitative characteristics and phase average waveforms. Multi-scale wavelet coefficients of EEG signals correlated with childhood absence epilepsy seizure, and multi-scale waveforms prior to epilepsy seizure were similar to characteristics during the onset period. Compared to normal children, EEG signals during epilepsy seizure exhibited an opposed phase model.

Comparison of ICA and WT with S-transform based method for removal of ocular artifact from EEG signals

Ocular artifacts are most unwanted disturbance in electroencephalograph (EEG) signals. These are characterized by high amplitude but have overlap-ping frequency band with the useful signal. Hence, it is difficult to remove the ocular artifacts by traditional filtering methods. This paper proposes a new approach of artifact removal using S-transform (ST). It provides an instantaneous time-frequency repre-sentation of a time-varying signal and generates high magnitude S-coefficients at the instances of abrupt changes in the signal. A threshold function has been defined in S-domain to detect the artifact zone in the signal. The artifact has been attenuated by a suitable multiplying factor. The major advantage of ST-fil- tering is that the artifacts may be removed within a narrow time-window, while preserving the frequency information at all other time points. It also preserves the absolutely referenced phase information of the signal after the removal of artifacts. Finally, a com-parative study with wavelet transform (WT) and in-dependent component analysis (ICA) demonstrates the effectiveness of the proposed approach.

The Coherence Cube Computing Method with Self-adaptive Time Window Based on Wavelet Transform

The coherence cube technology has become an important technology for the seismic attribute interpretation, which extracts the discontinuities of the events through analyzing the similarities of adjacent seismic channels to identify the fault form. The coherence cube technology which uses constant time window lengths can not balance the shallow layers and the deep layers, because the frequency band of seismic data varies with time. When analyzing the shallow layers, the time window will crossover a lot of events, which will lead to weak focusing ability and failure to delineate the details. While the time window will not be long enough for analyzing deep layers, which will lead to low accuracy because the coherences near the zero points of the events are heavily influenced by noise. For solving the problem, we should make a research on the coherence cube technology with self-adaptive time window. This paper determines the sample points＆#39; time window lengths in real time by computing the instantaneous frequency bands with Wavelet Transformation, which gives a coherence computing method with the self-adaptive time window lengths. The result shows that the coherence cube technology with self-adaptive time window based on Wavelet Transformation improves the accuracy of fault identification, and supresses the noise effectively. The method combines the advantages of long time window method and short time window method.

Automatic Detection and Classification of Epileptiform waves in EEG──A Hierarchical Multi-Method Approach

A hierarchical multi-method integrated approach is proposed in this paper to detect and classify the epileptic waves in EEG automatically. The initial clinical results are encouraging.

Study on Singularity of Chaotic Signal Based on Wavelet Transform

Based on the variations of wavelet transform modulus maxima at multi-scales, the singularity of chaotic signals are studied, and the singularity of these signals are measured by the Lipschitz exponent.In the meantime, a nonlinear method is proposed based on the higher order statistics, on the other aspect, which characterizes the higher order singular spectrum (HOSS) of chaotic signals. All computations are done with Lorenz attractor, Rossler attractor and EEG(electroencephalogram) time series and the comparisions among these results are made. The experimental results show that the Lipschitz exponents and the higher order singular spectra of these signals are significantly different from each other, which indicates these methods are effective for studing the singularity of chaotic signals.

Classification of Imagined Speech EEG Signals with DWT and SVM

With the development of human-computer interaction technology,brain-computer interface(BCI)has been widely used in medical,entertainment,military,and other fields.Imagined speech is the latest paradigm of BCI and represents the mental process of imagining a word without making a sound or making clear facial movements.Imagined speech allows patients with physical disabilities to communicate with the outside world and use smart devices through imagination.Imagined speech can meet the needs of more complex manipulative tasks considering its more intuitive features.This study proposes a classification method of imagined speech Electroencephalogram(EEG)signals with discrete wavelet transform(DWT)and support vector machine(SVM).An open dataset that consists of 15 subjects imagining speaking six different words,namely,up,down,left,right,backward,and forward,is used.The objective is to improve the classification accuracy of imagined speech BCI system.The features of EEG signals are first extracted by DWT,and the imagined words are clas-sified by SVM with the above features.Experimental results show that the proposed method achieves an average accuracy of 61.69%,which is better than those of existing methods for classifying imagined speech tasks.

Statistical analysis of Epileptic activities based on Histogram and Wavelet-Spectral entropy

Epilepsy is a chronic neurological disorder which is identified by successive unexpected seizures. Electroencephalogram (EEG) is the electrical signal of brain which contains valuable information about its normal or epileptic activity. In this work EEG and its frequency sub-bands have been analysed to detect epileptic seizures. A discrete wavelet transform (DWT) has been applied to decompose the EEG into its sub-bands. Applying histogram and Spectral entropy approaches to the EEG sub-bands, normal and abnormal states of brain can be distinguished with more than 99% probability.

Effects of subject’s wakefulness state and health status on approximated entropy during eye opening and closure test of routine EEG examination

This study tested a novel method designed to provide useful information for medical diagnosis and treatment. We measured electroencephalography (EEG) during a test of eye opening and closing, a common test in routine EEG examination. This test is mainly used for measuring the degree of alpha blocking and sensitivity during eyes opening and closing. However, because these factors depend on the subject’s awareness, drowsiness can interfere with accurate diagnosis. We sought to determine the optimal EEG frequency band and optimal brain region for distinguishing healthy individuals from patients suffering from several neurophysiological diseases (including dementia, cerebrovascular disorder, schizophrenia, alcoholism, and epilepsy) while fully awake, and while in an early drowsy state. We tested four groups of subjects (awake healthy subjects, drowsy healthy subjects, awake patients and drowsy patients). The complexity of EEG band frequencies over five lobes in the human brain was analyzed using wavelet-based approximate entropy (ApEn). Two-way analysis of variance tested the effects of the two factors of interest (subjects’ health state, and subjects’ wakefulness state) on five different lobes of the brain during eyes opening and closing. The complexity of the theta and delta bands over frontal and central regions, respectively, was significantly greater in the healthy state during eyes opening. In contrast, patients exhibited increased complexity of gamma band activity over the temporal region only, during eyes-close. The early drowsy state and wakefulness state increased the complexity of theta band activity over the temporal region only during eyes-close and eyes-open states respectively, and this change was significantly greater in control subjects compared with patients. We propose that this method may be useful in routine EEG examination, to aid medical doctors and clinicians in distinguishing healthy individuals from patients, regardless of whether the subject is fully awake or in the early stages of drowsiness.

Performance comparison of neural network training methods based on wavelet packet transform for classification of five mental tasks

In this study, performances comparison to discriminate five mental states of five artificial neural network (ANN) training methods were investigated. Wavelet Packet Transform (WPT) was used for feature extraction of the relevant frequency bands from raw electroencephalogram (EEG) signals. The five ANN training methods used were (a) Gradient Descent Back Propagation (b) Levenberg-Marquardt (c) Resilient Back Propagation (d) Conjugate Learning Gradient Back Propagation and (e) Gradient Descent Back Propagation with movementum.

Wavelet diagnosis of ECG signals with kaiser based noise diminution

The evaluation of distortion diagnosis using Wavelet function for Electrocardiogram (ECG), Electroencephalogram (EEG) and Phonocardiography (PCG) is not novel. However, some of the technological and economic issues remain challenging. The work in this paper is focusing on the reduction of the noise interferences and analyzes different kinds of ECG signals. Furthermore, a physiological monitoring system with a programming model for the filtration of ECG is presented. Kaiser based Finite Impulse Response (FIR) filter is used for noise reduction and identification of R peaks based on Peak Detection Algorithm (PDA). Two approaches are implemented for detecting the R peaks;Amplitude Threshold Value (ATV) and Peak Prediction Technique (PPT). Daubechies wavelet transform is applied to analyze the ECG of driver under stress, arrhythmia and sudden cardiac arrest signals. From the obtained results, it was found that the PPT is an effective and efficient technique in detecting the R peaks compared to ATV.