Alzheimer's disease (AD) is a neurological disorder characterized by nerve degeneration and neuronal death. The diagnosis of AD at an early stage is a major concern due to growing number of elderly people affected by the disease, as well as the lack of a standard diagnosis procedure available to community clinics. A biomarker that will allow early diagnosis of the disease would be beneficial. Such biomarker should be noninvasive, simple to obtain, safe, inexpensive, accurate, and most importantly, must be made available to local health clinics for maximum effectiveness.
Recent studies have used wavelets and other signal processing methods to analyze EEG signals in an attempt to find a noninvasive biomarker for AD. In this study, multiresolution wavelet analysis was performed on event related potentials (ERPs) of electroencephalogram (EEG) signals. Extracted feature sets were then used to train the ensemble system, based on stacked generalization algorithm, and individual decisions were calculated and compared. The ensemble decisions from individual data sources (specific electrode - stimuli - frequency band combinations) were combined using different data fusion techniques for further analyses. Particular emphasis was made for the value of procedure in the diagnosis of the disease at its earliest stage.
","abstract_html":"<p>Alzheimer's disease (AD) is a neurological disorder characterized by nerve degeneration and neuronal death. The diagnosis of AD at an early stage is a major concern due to growing number of elderly people affected by the disease, as well as the lack of a standard diagnosis procedure available to community clinics. A biomarker that will allow early diagnosis of the disease would be beneficial. Such biomarker should be noninvasive, simple to obtain, safe, inexpensive, accurate, and most importantly, must be made available to local health clinics for maximum effectiveness.</p> <p>Recent studies have used wavelets and other signal processing methods to analyze EEG signals in an attempt to find a noninvasive biomarker for AD. In this study, multiresolution wavelet analysis was performed on event related potentials (ERPs) of electroencephalogram (EEG) signals. Extracted feature sets were then used to train the ensemble system, based on stacked generalization algorithm, and individual decisions were calculated and compared. The ensemble decisions from individual data sources (specific electrode - stimuli - frequency band combinations) were combined using different data fusion techniques for further analyses. Particular emphasis was made for the value of procedure in the diagnosis of the disease at its earliest stage.</p>","abstract_has_math":false,"creators":["Gandhi, Hardik P."],"institution":null,"degree_name":"M.S. in Electrical Engineering","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engineering","degree_department":null,"school":null,"contributors":["Polikar, Robi"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2007,"date_issued":"2007-04-25T07:00:00Z","date_published":"2007-04-25T07:00:00Z","updated_at":"2026-07-24T04:13:40Z","subjects":["Alzheimer's disease--Diagnosis; Electroencephalography; Signal processing","Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/780","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Polikar, Robi"]},{"key":"dc:creator","label":"Author","values":["Gandhi, Hardik P."]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2016-03-28T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S. in Electrical Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Alzheimer's disease--Diagnosis; Electroencephalography; Signal processing","Electrical and Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/780"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Alzheimer's disease (AD) is a neurological disorder characterized by nerve degeneration and neuronal death. The diagnosis of AD at an early stage is a major concern due to growing number of elderly people affected by the disease, as well as the lack of a standard diagnosis procedure available to community clinics. A biomarker that will allow early diagnosis of the disease would be beneficial. Such biomarker should be noninvasive, simple to obtain, safe, inexpensive, accurate, and most importantly, must be made available to local health clinics for maximum effectiveness.
Recent studies have used wavelets and other signal processing methods to analyze EEG signals in an attempt to find a noninvasive biomarker for AD. In this study, multiresolution wavelet analysis was performed on event related potentials (ERPs) of electroencephalogram (EEG) signals. Extracted feature sets were then used to train the ensemble system, based on stacked generalization algorithm, and individual decisions were calculated and compared. The ensemble decisions from individual data sources (specific electrode - stimuli - frequency band combinations) were combined using different data fusion techniques for further analyses. Particular emphasis was made for the value of procedure in the diagnosis of the disease at its earliest stage.
"]},{"key":"dc:title","label":"Title","values":["Stacked generalization for early diagnosis of Alzheimer's disease"]}]}],"canonical_facts":{"dc:contributor":["Polikar, Robi"],"dc:creator":["Gandhi, Hardik P."],"dc:date.available":["2016-03-28T07:00:00Z"],"dc:description.abstract":["Alzheimer's disease (AD) is a neurological disorder characterized by nerve degeneration and neuronal death. The diagnosis of AD at an early stage is a major concern due to growing number of elderly people affected by the disease, as well as the lack of a standard diagnosis procedure available to community clinics. A biomarker that will allow early diagnosis of the disease would be beneficial. Such biomarker should be noninvasive, simple to obtain, safe, inexpensive, accurate, and most importantly, must be made available to local health clinics for maximum effectiveness.
Recent studies have used wavelets and other signal processing methods to analyze EEG signals in an attempt to find a noninvasive biomarker for AD. In this study, multiresolution wavelet analysis was performed on event related potentials (ERPs) of electroencephalogram (EEG) signals. Extracted feature sets were then used to train the ensemble system, based on stacked generalization algorithm, and individual decisions were calculated and compared. The ensemble decisions from individual data sources (specific electrode - stimuli - frequency band combinations) were combined using different data fusion techniques for further analyses. Particular emphasis was made for the value of procedure in the diagnosis of the disease at its earliest stage.
"],"dc:identifier":["https://rdw.rowan.edu/etd/780"],"dc:subject":["Alzheimer's disease--Diagnosis; Electroencephalography; Signal processing","Electrical and Computer Engineering"],"dc:title":["Stacked generalization for early diagnosis of Alzheimer's disease"],"thesis:degree_discipline":["Electrical & Computer Engineering"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S. in Electrical Engineering"]},"updated_at":"2026-07-24T04:13:40Z"}