Seizure Detection in EEG signals: A Comparison of Different approaches

Abstract. In this article, we investigate the performance of a seizure detection module for online monitoring of epileptic patients. The module is using as input data streams from electroencephalographic and electrocardiographic recordings. The architecture of the module consists of time and frequency domain feature extraction followed by classification. Four classification algorithms were evaluated on three epileptic subjects. The best performance was achieved by the support vector machine algorithm, with more than 90% for two of the subjects and slightly lower than 90% for the third subject.

Over recent years, due to the increase in the epileptic patient population, issues of diagnosing and treatment of epilepsy have become more and more prominent and much research has been done in this field in consequence. However, there are still many gaps and lack of knowledge in interpreting Electroencephalograph (EEG) signals in order to solve the problem.Particular problems in this area include difficulties in detecting the seizure events (due to the different seizure types and their variability from patient to patient or even in an individual over time), and dealing with long-term EEG recordings, which is an onerous and time consuming task for electroencephalographers.The thesis discusses the two problem areas using EEG data from four subjects with overall 21 hours of recording from the CHB-MIT scalp benchmark EEG dataset. We propose a patient specific seizure detection technique, which selects the optimal feature subsets, and train a dedicated classifier for each patient in order to maximize the classification performance. To exploit the characteristics of a patient's EEG pattern as much as possible, we used a large set of features in the proposed framework, namely time domain, frequency domain, time-frequency domain and nonlinear features, and selected the most crucial features among them by using Conditional Mutual Information Maximization (CMIM) technique. We further performed extensive comparative evaluations against 6 other feature selection methods to demonstrate the superiority of the CMIM.Support Vector Machine (SVM) with the linear kernel is used as the classifier. The experimental results show a delicate classification performance over the test set, i.e. an average of 90.62% sensitivity and 99.32% specificity are acquired when all channels and recordings are used to form a composite feature vector. In addition, an average sensitivity and specificity rates of 93.78% and 99.05% are obtained using CMIM, respectively. PREFACEThis master thesis was carried out in the MUVIS group at the signal processing department of Tampere University of Technology. It was funded by the Academy of Finland.I wish to express my sincere gratitude to Professor Serkan Kiranyaz, whose inspiring guidance and inexhaustible patience have helped me cultivate a systematic approach towards the research. I am indebted to him for the freedom he gave me in implementing my ideas. I have also acquired valuable insights through his instruction in academic approach.I am very much grateful to Professor Turker Ince for his warm support and his valuable suggestions. Besides, I would also like to thank Professor Moncef Gabbouj for providing me with the opportunity for the thesis work. He gave me a lot of trust and flexibility in the project.I have been extremely fortunate in having valuable friends who have made a homely atmosphere for me during my stay in Tampere

Problem statement: Electroencepharogram (EEG) is an extremely complex signal with very low signal to noise ratio and these attributed to difficulty in analyzing the signal. Hence for detecting abnormal segment, a distinctive method is required to train the technologist to distinguish the anomalous in EEG data. The objective of this study was to create a framework to analyze EEG signals recorded from epileptic patients by evaluating the potential of UMACE filter to detect changes in single-channel EEG data during routine epilepsy monitoring. Approach: Normally, the peak to side lobe ratio (PSR) of a UMACE filter was employed as an indicator if a test data is similar to an authentic class or vice versa, however in this study, the consistent changes of the correlation output known as Region Of Interest (ROI) was plotted and monitored. Based on this approach, a novel method to analyze and distinguish variances in scalp EEG as well as comparing both normal and abnormal regions of the patient's EEG was assessed. The performance of the novelty detection was examined based on the onset and end time of each seizure in the ROI plot. Results: Results showed that using ROI plot of variances one can distinguish irregularities in the EEG data. The advantage of the proposed technique was that it did not require large amount of data for training. Conclusion: As such, it was feasible to perform seizure analysis as well as localizing seizure onsets. In short, the technique can be used as a guideline for faster diagnosis in a lengthy EEG recording.