Rebello Bruna Carolina, Ramirez Alejandro Rafael Garcia, Heredia-Negron Frances, Roche-Lima Abiel
Engenharia da Computação, Universidade Do Vale Do Itajaí, Santa Catarina, Brasil.
Center for Collaborative Research in Health Disparities - RCMI Program University of Puerto Rico Medical Sciences Campus, San Juan, Puerto Rico.
J Eng Res (Ponta Grossa). 2022;2(8). doi: 10.22533/at.ed.317282219056.
The brain is made up of billions of neurons, which control all actions performed by us. In epilepsy, the pattern order of brain signals is altered, causing epileptiform discharges in an individual's brain. Approximately 1% of the world population has epilepsy and, therefore, there is a need for studies that can help in the diagnosis and treatment of this disorder. The objective of this work is to develop a machine learning-based approach to predict epileptic seizures using non-invasive electroencephalography (EEG). Therefore, the classification of interictal and preictal states was performed using the CHB-MIT database. The algorithm was developed to predict epileptic seizures in multiple subjects using a patient-independent approach. The Discrete Wavelet Transform was used to perform the decomposition of the EEG signals in 5 levels and, as characteristics, the Spectral Power, the Mean and the Standard Deviation were studied, in order to analyze which one would present the best result and as a classifier, the Supported Vector Machine (SVM). The study achieved an accuracy of 92.30%, 84.60% and 76.92% for the Power, Standard Deviation and Mean characteristics, respectively.
大脑由数十亿个神经元组成，这些神经元控制着我们所执行的所有动作。在癫痫中，大脑信号的模式顺序会发生改变，导致个体大脑中出现癫痫样放电。全球约1%的人口患有癫痫，因此，需要开展有助于诊断和治疗这种疾病的研究。这项工作的目的是开发一种基于机器学习的方法，使用非侵入性脑电图（EEG）来预测癫痫发作。因此，使用CHB - MIT数据库对发作间期和发作前期状态进行了分类。该算法采用独立于患者的方法开发，用于预测多个受试者的癫痫发作。使用离散小波变换对EEG信号进行5级分解，并研究了谱功率、均值和标准差等特征，以分析哪一个会呈现出最佳结果，同时使用支持向量机（SVM）作为分类器。该研究对于功率、标准差和均值特征分别实现了92.30%、84.60%和76.92%的准确率。
