After stroke, the most prevalent neurological disorder is epilepsy. The sudden occurrence of the seizures which are unpredictable in nature can cause great harm to epileptic patients thereby leading to a poor quality of lifestyle for them. The transient abnormal behaviour of neurons in the brain is seizures which limits the mental and physical activities of the patient. To measure the electrical potential from the activities of the neurons, Electroencephalography (EEG) is used as it is noninvasive in nature. The recordings are done for a long period of time and so processing the entire data becomes too hectic. Therefore in this paper, Sparse Principal Component Analysis, (SPCA) is utilized to reduce the dimensions of the data and then it is classified with the help of Soft Decision Tree (SDT) Classifier. The results show an average accuracy of 96.83%, an average Performance Index of about 94.69% and an average Time Delay of about 1.99 is obtained.
Sparse PCA and soft decision tree classifiers for epilepsy classification from EEG signals
01.04.2017
232074 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Decision tree classifiers for unmanned aircraft configuration selection
Emerald Group Publishing | 2021
|Bayesian Learning of Sparse Classifiers
British Library Conference Proceedings | 2001
|Bayesian learning of sparse classifiers
IEEE | 2001
|