Robust Alzheimer’s disease Severity Classification in Compressed EEG Signal

Abstract: Alzheimer's disease (AD) is considered to be the most common and the fastest growing neurological disease in the world. Biomarker tools for early diagnosis and disease progression in AD remain key issues for clinical applications, sanitary systems and pharmaceutical companies. Electroencephalogram (EEG) yields, a powerful and relatively cheap way for screening of dementia and AD in their early stages. Portable EEG systems based on wireless sensors can be used for unobtrusive long term monitoring provided they can solve technological problems. Clinical applications require intensive recording of massive EEG data, raising the need for efficient and flexible compression techniques. Early diagnosis of Alzheimer's disease and its prodromal stage is very important for possible delay of the disease, and there is thus a great deal of interest in the development of new methods for earlier detection. In this thesis, a novel approach to the diagnosis of Alzheimer's disease from EEG is proposed with the use of decision tree classification algorithm combined with empirically determined regions of interest as attributes. In addition to this a model based Greedy search algorithm is used to allocate the weight value. Keywords: Alzheimer's disease, Compressive Sensing, Greedy search algorithm, Decision tree classification.