An Analysis Research for Digitized Features of Epileptic EEG Using SVM

Xu, Xin; Lv, Bin; Song, Jié; Shi, Wei; Hu, Yanrong; Yan, Shan

doi:10.4028/www.scientific.net/amm.239-240.1169

Cited by 3 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wavelet transform method, which inherits and promotes the idea of localized short-time Fourier transform, is a time domain analysis method which can accurately monitor the local information of non-stationary signals with multi-resolution characteristics. Sample entropy is a typical nonlinear analysis method which can reflect non-linear characteristics by measuring complex EEG signals [15]- [18]. Non-negative number, which is calculated from EEG data information, is used to represent the complexity of the time series, and the birth rate of new information in the time series.…”

Section: Introductionmentioning

confidence: 99%

Fatigue EEG Feature Extraction Based on Tasks With Different Physiological States for Ubiquitous Edge Computing

Xu¹,

Gu²,

Yan³

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Mental fatigue is a gradual and cumulative phenomenon that manifests in the weakening of human physiological activities for ubiquitous edge computing in the Internet of Things. In this paper, two groups of Stroop tasks with different difficulty levels are proposed to induce fatigue, which is evaluated via electroencephalogram (EEG). Wavelet packet decomposition and sample entropy algorithm are utilized to analyze the EEG signals in both sober and fatigue state. The experiment results show that compared with the sober state, the fatigue state has a higher α wavelet relative energy and θ wavelet relative energy and significantly lower β wave relative energy (P < 0.05). The ratio of parameters α/β and (α + θ)/β increases with the fatigue degree, and the sample entropy of each brain region shows a decreasing trend. Compared with the more difficult task group, the change of parameters in the low-difficulty task are more obvious. Hence, the suggested parameters α/β and (α + θ)/β can be used as potential indicators to measure mental fatigue, and the appropriate increase in the difficulty of the tasks may be inversely related to the generation of mental fatigue to some extent. INDEX TERMS Stroop tasks, physiological state, fatigue EEG, wavelet packet decomposition, sample entropy, edge computing.

show abstract

Section: Introductionmentioning

confidence: 99%

Fatigue EEG Feature Extraction Based on Tasks With Different Physiological States for Ubiquitous Edge Computing

Xu¹,

Gu²,

Yan³

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…Finally, the instantaneous phase change of the β band under different emotions, the average energy of α band, and β/θ absolute power [18] are fed into the SVM as the eigenvector [19].…”

Section: ) Data Selection and Feature Extractionmentioning

confidence: 99%

Emotion Recognition Based on Double Tree Complex Wavelet Transform and Machine Learning in Internet of Things

Zhang

Tang

et al. 2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

Corresponding to the continual development of human-computer interaction technology, the use of emotional computing (EC) is gradually emerging in the Internet of Things (IoT). Emotion recognition is considered a highly valuable aspect of EC. Numerous studies have examined emotion recognition based on electroencephalogram (EEG) signals, but the recognition rate is unreliable. In this paper, a feature extraction method is proposed that is based on double tree complex wavelet transform (DTCWT) and machine learning. The emotions of 16 subjects are induced under video stimulation, and the original signal is acquired using a Neuroscan device. Both EEG and electromyography (EMG) signal are then eliminated by band-pass filtering, and the reconstructed signal of each frequency band is obtained by DTCWT. Finally, support vector machine (SVM) is utilized to classify three kinds of emotions: calm, happy, and sad, obtaining a classification accuracy of 90.61%. Results show that the proposed algorithm can effectively extract the feature vector and improve the problem of low accuracy in multiple class recognition. INDEX TERMS Emotion recognition, Internet of Things (IoT), double tree complex wavelet transform (DTCWT), machine learning, support vector machine (SVM).

show abstract

“…The distance formula is represents sample feature attributes. In the traditional algorithm, all the feature attributes of the sample are used to determine the distance between neighbors in the KNN algorithm, the dimensional disaster can easily occur [12], and the validity and accuracy of the classification are also affected. We choose support vector machine and the -nearest neighbor classification algorithm to classify the data separately.…”

Section: Feature Extractionmentioning

confidence: 99%

Emotional Recognition of EEG Signals based on Fractal Dimension

Xin¹,

Cao²,

Jiawei³

et al. 2019

Int J Performability Eng

View full text Add to dashboard Cite

A method based on fractal dimension is proposed to identify EEG emotional signals, and fractal dimension is introduced as an eigenvalue into emotion recognition research. The design experiment obtains the EEG raw data of the experimenter and uses the experimental video to locate and capture the effective signal from the original data. After the pre -electron interference and low-pass filtering are applied, the effective signal is subjected to principal component analysis. The dimension reduction dimension is obtained by reducing the dimension. The support vector machine (SVM) and K nearest neighbor (KNN) classification algorithm are used to classify the eigenvalues to obtain their respective accuracy. The results show that the EEG emotion recognition method based on fractal dimension can distinguish different emotions, and the highest accuracy rate is 83.33%. Therefore, fractal dimension i s feasible as the characteristic value of emotion recognition.

show abstract

An Analysis Research for Digitized Features of Epileptic EEG Using SVM

Cited by 3 publications

References 5 publications

Fatigue EEG Feature Extraction Based on Tasks With Different Physiological States for Ubiquitous Edge Computing

Fatigue EEG Feature Extraction Based on Tasks With Different Physiological States for Ubiquitous Edge Computing

Emotion Recognition Based on Double Tree Complex Wavelet Transform and Machine Learning in Internet of Things

Emotional Recognition of EEG Signals based on Fractal Dimension

Contact Info

Product

Resources

About