One of the long lasting neurological disorders which are categorized by continuos and gratuitous seizures is epilepsy. Epilepsy is witnessed by electrophysiological disturbances occurring in the human brain ranging from short period of attention to severe and prolonged seizures. For the purpose of analyzing and diagnosing epileptic seizures, Electroencephalography (EEG) signals are used. The EEG signal is a representative signal that contains essential data about the activities of the brain. As the recordings of the EEG signal are quite long in nature, processing the entire amount of data as such is extremely difficult and hence dimensionality reduction has to be preferred. In this paper, Variational Bayesian Matrix Factorization (VBMF) is utilized as a dimensionality reduction technique and then it is classified with the help of Adaboost Variant Classifier. The type of Adaboost Variant Classifier used here is Real Adaboost Classifier. The results show that when VBMF is utilized with Real Adaboost Classifier, an average classification accuracy of about 95.52 % is reported.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Matrix Factorization with Adaboost Variant Classifier for Epilepsy Classification from EEG Signals


    Contributors:


    Publication date :

    2018-03-01


    Size :

    2127636 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English






    VEHICLE DETECTION FOR AUTONOMOUS PARKING USING A SOFT-CASCADE ADABOOST CLASSIFIER

    Broggi, A. / Cardarelli, E. / Cattani, S. et al. | British Library Conference Proceedings | 2014


    Traffic Signs Detection Based on Haar-Like Features and Adaboost Classifier

    Li, Zhijiang / Dong, Chuan / Zheng, Ling et al. | ASCE | 2013