2016 IEEE International Conference on Smart Cloud (SMARTCLOUD) (2016)
New York, New York, USA
Nov. 18, 2016 to Nov. 20, 2016
Epilepsy refers to a set of chronic neurologicalsyndromes characterized by transient and unexpected electricaldisturbances of the brain. Scalp Electroencephalogram (EEG) isa common test that measures and records the electrical activityof the brain, and is widely used in the detection and analysisof epileptic seizures. However, it is often difficult to identify thesubtle changes in the EEG waveform by visual inspection. Then, emerge in large numbers of research for biomedical engineersto develop and implement several intelligent algorithms for theidentification of such subtle changes. This paper presents aEEG signal analysis and forecasting technique based on wavelettransform and support vector machine classification method. Themain procedure is a dynamic circulation. The technique firsttrain the given datasets, obtain the value of the parameter, thenautomatically multi-time decompose for a new person's brainsignals, predict whether the person has a characteristic waveof epilepsy, add the person's EEG data into the SVM trainingmodel if the person has epilepsy abnormal signal, combined withabnormal data before retraining and learning. The method has a very large potential uses, such as application for the initial diagnosis of patients, improving the efficiency for doctors.
Electroencephalography, Wavelet transforms, Epilepsy, Time-frequency analysis, Support vector machines
C. Chen, Z. Liu, H. Li, R. Zhou, Y. Zhang and R. Liu, "EEG Detection Based on Wavelet Transform and SVM Method," 2016 IEEE International Conference on Smart Cloud (SMARTCLOUD), New York, New York, USA, 2016, pp. 241-247.