It is very important for epilepsy treatment to distinguish epileptic seizure and non-seizure. In this study, an automatic seizure detection algorithm based on dual density dual tree complex wavelet transform (DD-DT CWT) for intracranial electroencephalogram (iEEG) was proposed. The experimental data were collected from 15 719 competition data set up by the National Institutes of Health (NINDS) in Kaggle. The processed database consisted of 55 023 seizure epochs and 501 990 non-seizure epochs. Each epoch was 1 second long and contained 174 sampling points. Firstly, the signal was resampled. Then, DD-DT CWT was used for EEG signal processing. Four kinds of features include wavelet entropy, variance, energy and mean value were extracted from the signal. Finally, these features were sent to least squares-support vector machine (LS-SVM) for learning and classification. The appropriate decomposition level was selected by comparing the experimental results under different wavelet decomposition levels. The experimental results showed that the features selected in this paper were different between seizure and non-seizure. Among the eight patients, the average accuracy of three-level decomposition classification was 91.98%, the sensitivity was 90.15%, and the specificity was 93.81%. The work of this paper shows that our algorithm has excellent performance in the two classification of EEG signals of epileptic patients, and can detect the seizure period automatically and efficiently.
Algorithms ; Electroencephalography ; Epilepsy/diagnosis* ; Humans ; Seizures/diagnosis* ; Signal Processing, Computer-Assisted ; Support Vector Machine ; Wavelet Analysis

OBJECTIVE: To explore mechanism of health beliefs by application of health belief model (HBM) and structural equation modeling (SEM) with regard to recreational physical activity (PA), to identify the differences of among population with high risk of chronic diseases and healthy people, and to provide the specific interventions of recreational physical activity and reference for health relevant policy-making in the future. METHODS: A total of 2 736 residents with high risk of chronic diseases and 1 514 healthy people were involved. A questionnaire survey, physical examination and biochemical examination were conducted. The questionnaire based on HBM had acceptable validity and reliability. The proposed model based on the total sample size of the two groups was developed using the structural equation modeling and multi-comparison in the ways of appearance and parameters were also validated. RESULTS: The median amount of recreational (PA) among population with high risk of chronic diseases and healthy people were 0.0 thousand-step equivalent with quartile of (0.0, 4.6) and 0.0 thousand-step equivalent with quartile of (0.0, 4.0) respectively. The results of SEM suggested that the direct effects of perceived objective barriers (β=-0.245), perceived subjective barriers (β=-0.057), cues to action (β=-0.043) and self-efficacy (β=0.117) on recreational (PA) were significant. Self-efficacy was the most important mediator. The multi-group comparisons indicated that the models of the two groups had the same appearance but the parameters between them were significant (δ χ²=27.4, P<0.05). The multi-group structural equation model (MSEM) indicated that two paths from cues to action and from perceived subjective barriers to recreational (PA) were not statistically significant among the population with high-risk of chronic diseases. In the two groups, one path coefficient from perceived objective barriers to subjective barriers (P=0.007) was statistically significant (P<0.05). CONCLUSION The recreational (PA) levels of both groups were lower. Health beliefs on recreational (PA) of the two groups played different roles and some paths were also different. Therefore, specific interventions and strategies should be developed for different people. For residents with high risk of chronic diseases, much more attention should be paid to reduce the objective and subjective barriers of recreational physical activity and to improve self-efficacy so as to delay or prevent the occurrence of chronic diseases and then to improve the quality of life of this kind of population.
Chronic Disease ; Exercise ; Health Status ; Humans ; Quality of Life ; Reproducibility of Results ; Surveys and Questionnaires