The Comparison of Different Dimension Reduction and Classification Methods in Electroencephalogram Signals

Journal Title: Meandros Medical and Dental Journal - Year 2018, Vol 19, Issue 4

Abstract

Objective: Electroencephalogram (EEG) signals have been broadly utilized for the diagnosis of epilepsy. Expert physicians must monitor long-term EEG signals that is sometimes difficult and time consuming process for epilepsy diagnosis. In this study, classification performances of support vector machine (SVM) and linear discriminant analysis (LDA), which are widely used in computer supported epilepsy diagnosis, were compared by using wavelet-based features of extracted from EEG signals which were derived in either normal or inter-ictal periods. In addition, principal component analysis (PCA) and independent component analysis (ICA) were used to determine the effects of dimension reduction on classification success. Materials and Methods: The EEG data were sampled from the EEG laboratory of the Department of Neurology and Clinical Neurophysiology in Adnan Menderes University. Study was approved by Local Ethics Committee with protocol number 2016/873. Ten patients with epilepsy and 10 normal were the study group. EEG signals of patients with epilepsy were contains only seizure free- epochs. EEG signals were first decomposed into frequency sub-bands by using discrete wavelet transform (DWT) and then some statistical features were calculated from those to classify it's as normal or epileptic. Results: In classification of the EEG signals, it's as normal or epileptic, we achieved 88.9% accuracy rate using SVM with radial basis function (RBF) kernel without dimension reduction Conclusion: Results showed that SVM was a powerful tool in classifying EEG signals if it's normal or epileptic.

Authors and Affiliations

Hakan Öztürk, Mevlüt Türe, Nefati Kıylıoğlu, İmran Kurt Ömürlü

Keywords

Related Articles

Congenital Calvarial Lymphangioma: A Case Report

Calvarial cavernous lymphangioma is an extremely rare disease entity with only a few reports. Lymphangiomas are frequently encountered neck and long bone but it may also seen in many part of the body and many tips of the...

Periodic Fever, Aphthous Stomatitis, Pharyngitis and Cervical Adenitis Syndrome: Current Literature Review with a Case Report

Periodic Fever, Aphthous Stomatitis, Pharyngitis and Cervical Adenitis syndrome (PFAPA) is a frequently seen, important medical condition, which must be kept in mind in periodic fever etiology. Although its etiology is n...

Confusion of Insulinoma’s Neuroglycopenic Symptoms with Epilepsy, Two Case Presentation and a Review of Literature

Insulinoma is a pancreatic endocrine tumour which origins from beta cells and characterized by excessive insulin secretion and hypoglycemia due to this. Symptoms seen in hypoglycemia are due to brain’s lack of glucose (n...

Cone Beam Computed Tomographic Analysis of Paranasal Variations, Osteomeatal Complex Disease, Odontogenic Lesion and Their Effect on Maxillary Sinus

Objective: The objective of this study was to establish the prevalence of nasal septal deviation, concha bullosa, and osteomeatal complex disease (obstruction), and odontogenic lesions, along with their potential relatio...

Isolated Zygomatic Arch Fracture: A Case Report

Zygomatic bone is situated at the lateral part of the facial triangle, and is frequently exposed to maxillofacial traumas, since it forms the most prominent region of the facial skeleton. Isolated zygomatic arch fracture...

Download PDF file
  • EP ID EP436718
  • DOI 10.4274/meandros.96168
  • Views 134
  • Downloads 0

How To Cite

Hakan Öztürk, Mevlüt Türe, Nefati Kıylıoğlu, İmran Kurt Ömürlü (2018). The Comparison of Different Dimension Reduction and Classification Methods in Electroencephalogram Signals. Meandros Medical and Dental Journal, 19(4), 336-344. https://europub.co.uk/articles/-A-436718