Majority Vote of Ensemble Machine Learning Methods for Real-Time Epilepsy Prediction Applied on EEG Pediatric Data
Journal: TEM JOURNAL - Technology, Education, Management, Informatics (Vol.7, No. 2)Publication Date: 2018-05-25
Authors : Samed Jukić Dino Кеčo Jasmin Kevrić;
Page : 313-318
Keywords : Majority Vote; Rotation Forest; Real-Time Prediction; Epilepsy;
Abstract
The main aim of the study is to develop a real-time epilepsy prediction approach by using the ensemble machine learning techniques that might predict offline seizure paradigms. The proposed seizure prediction algorithm is patient-specific since generalization showed no satisfactory results in our previous studies. The algorithm is tested on CHB-MIT database comprised of EEG data from pediatric epileptic patients. Based on relations to number of seizures and number of files, gender and age, three patients have been chosen for this study. The special majority voting algorithm is proposed and used for raising an alarm of upcoming seizure. EEG signals are denoised using MSPCA (Multiscale PCA), the features were extracted by WPD (wavelet packet decomposition), and EEG signals were classified using Rotation Forest. The significance of the study lies in the fact that the proposed seizure prediction algorithm could be used in novel diagnostic and therapeutic applications for pediatric patients.
Other Latest Articles
- Effect of IN-OVO injection with Nano Iron -Particles on Physiological Responses and Performance of Broiler Chickens under Saini Conditions
- Possibilities of Carrying out Quality Control of Solder Joints Using the Burst test in the Practice
- Ex Vitro Propagation of Rubber Tree (Hevea Brasiliensis) using Stem Cuttings
- Effects of Organic Turmeric on Liver Integrity and Oxidative Stress of the Brain in Rabbits Exposed to Ultraviolet Radiation
- Identifying the Key Factors of Service Quality in a Traditional Chinese Medicine Clinic-based Kano-IPA Model and Case Study
Last modified: 2018-06-01 22:41:18