Neural network classification of EEG signal for the detection of seizure
Neural network classification of EEG signal for the detection of seizure
复制标题
用于检测癫痫发作的脑电图信号的神经网络分类
DOI：
10.1109/rteict.2017.8256658
复制
发表时间：
2017
期刊：
影响因子：
--
通讯作者：
M. Karki
中科院分区：
文献类型：
--
作者：
S. Yasmeen;M. Karki
大脑是人体最强壮的部分，由大量的神经元组成。脑电活动可以用许多技术来测量，其中脑电图被广泛使用。电信号的任何变化都将定义人类的一种特殊异常。本文提出了一种基于小波变换和统计参数的脑电图信号分析算法。数据集由两种采样率组成，一种是128Hz，另一种是1024Hz。采用离散小波变换进行特征提取。一旦特征提取完成，数据将被提供给神经网络进行分类。采用多层神经网络对癫痫患者和正常人进行分类。该算法在23个数据集上进行了测试。对于采样率为1024的数据，分类准确率达到100%，对于采样率为128的数据，分类准确率达到85%。系统总精度达到92.5%。
Brain is the strongest part of the human body which consists of the number of neurons. Electrical activity of the brain can be measured using many techniques in which EEG is widely used. Any change in electrical signal will define a particular abnormality in human. This paper, suggest a algorithm for the EEG signal analysis for the detection of seizure using wavelet transform and statistical parameters. Data set consists of two sampling rates, one with 128Hz and another with sampling rate of 1024Hz. Feature extraction was done using discrete wavelet transform. Once a feature extraction is done the data will be given to a neural network for the classification. A multilayered neural network was used classify seizure and normal person. The proposed algorithm is tested on 23 data sets. Classification accuracy of 100% has been achieved for the sampling rate of 1024 and 85% for the data with sampling rate of 128. Total system accuracy achieved is 92.5%.