CAJ | 학술논문

分析了小波多分辨分析特征提取的特点,提出了八通道脑电信号癫痫波自动检测的方法.每个通道的信号利用小波变换进行五层分解,以提取小波变换各子带的小波系数和信号偏差组成特征值计算自适应阈值,并将其应用到关键子带,提取出信号中的癫痫波.研究的重点是对脑电信号进行分解选择合适的小波;确定适当的分解层次以及自适应阈值的计算.实验结果表明,方法能够为癫痫脑电的特征提取提供快速而有效的手段.
분석료소파다분변분석특정제취적특점,제출료팔통도뇌전신호전간파자동검측적방법.매개통도적신호이용소파변환진행오층분해,이제취소파변환각자대적소파계수화신호편차조성특정치계산자괄응역치,병장기응용도관건자대,제취출신호중적전간파.연구적중점시대뇌전신호진행분해선택합괄적소파;학정괄당적분해층차이급자괄응역치적계산.실험결과표명,방법능구위전간뇌전적특정제취제공쾌속이유효적수단.
This paper proposed a new scheme for detecting epileptiform activity in 8-channel EEG based on the characteristic of a multi-resolution analysis. The EEG signal on each channel was decomposed to five levels using discrete wavelet transform. Formed wavelet coefficients and standard deviation of all 8-channel raw data to compute adaptive threshold, which applied on sub-bands1, 2 and 3. Then extracted the spike portion of EEG signal extracted from the raw data. The key points of this research work were identification of a suitable wavelet for decomposition of EEG signals, recognition of a proper resolution level, and computation of a dynamic threshold. The experiment results show that the proposed method offers a fast and effective measure for detecting epileptiform activity in human EEG.