As medicinal and technological advances lengthen the average human life span, diseases affecting the elderly such as Alzheimer's disease and Parkinson's disease are seeing increasingly growing numbers, especially in developed countries. As a result, the necessity for an accurate, inexpensive, noninvasive means of diagnosis becomes particularly important, since such a method is not readily available to the general population. One biomarker that has recently showed promise is the analysis of the electroencephalogram (EEG).
Over the course of two studies, more than 130 subjects have been recruited providing information from 16-19 EEG electrodes for each subject. These signals have been decomposed using the wavelet transform to be used in a pattern recognition and classification algorithm to serve as a diagnostic tool for Alzheimer's disease. Through the use of multilayer perceptrons and support vector machines, classifiers were generated on different portions of the EEG. These classifiers are then combined using combination methods such as sum rule, product rule, simple and weighted majority voting.
Classification performance for Cohort A was 88.7%, an increase of more than 5% over previous work in this study. Classification performance for Cohort B was 93.6% and the classification performance for both cohorts combined together was 82.7%. These classification performances exceed the diagnostic accuracy of community clinics (75%) and are close to diagnostic accuracy available at research and university hospitals (90%).
","abstract_html":"<p>As medicinal and technological advances lengthen the average human life span, diseases affecting the elderly such as Alzheimer's disease and Parkinson's disease are seeing increasingly growing numbers, especially in developed countries. As a result, the necessity for an accurate, inexpensive, noninvasive means of diagnosis becomes particularly important, since such a method is not readily available to the general population. One biomarker that has recently showed promise is the analysis of the electroencephalogram (EEG).</p> <p>Over the course of two studies, more than 130 subjects have been recruited providing information from 16-19 EEG electrodes for each subject. These signals have been decomposed using the wavelet transform to be used in a pattern recognition and classification algorithm to serve as a diagnostic tool for Alzheimer's disease. Through the use of multilayer perceptrons and support vector machines, classifiers were generated on different portions of the EEG. These classifiers are then combined using combination methods such as sum rule, product rule, simple and weighted majority voting.</p> <p>Classification performance for Cohort A was 88.7%, an increase of more than 5% over previous work in this study. Classification performance for Cohort B was 93.6% and the classification performance for both cohorts combined together was 82.7%. These classification performances exceed the diagnostic accuracy of community clinics (75%) and are close to diagnostic accuracy available at research and university hospitals (90%).</p>","abstract_has_math":false,"creators":["Balut, Brian"],"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":2008,"date_issued":"2008-12-31T08:00:00Z","date_published":"2008-12-31T08:00:00Z","updated_at":"2026-07-24T04:13:27Z","subjects":["Alzheimer's disease--Diagnosis; Electroencephalography","Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/685","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":["Balut, Brian"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2016-03-20T07:00:00Z"]},{"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","Electrical and Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/685"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["As medicinal and technological advances lengthen the average human life span, diseases affecting the elderly such as Alzheimer's disease and Parkinson's disease are seeing increasingly growing numbers, especially in developed countries. As a result, the necessity for an accurate, inexpensive, noninvasive means of diagnosis becomes particularly important, since such a method is not readily available to the general population. One biomarker that has recently showed promise is the analysis of the electroencephalogram (EEG).
Over the course of two studies, more than 130 subjects have been recruited providing information from 16-19 EEG electrodes for each subject. These signals have been decomposed using the wavelet transform to be used in a pattern recognition and classification algorithm to serve as a diagnostic tool for Alzheimer's disease. Through the use of multilayer perceptrons and support vector machines, classifiers were generated on different portions of the EEG. These classifiers are then combined using combination methods such as sum rule, product rule, simple and weighted majority voting.
Classification performance for Cohort A was 88.7%, an increase of more than 5% over previous work in this study. Classification performance for Cohort B was 93.6% and the classification performance for both cohorts combined together was 82.7%. These classification performances exceed the diagnostic accuracy of community clinics (75%) and are close to diagnostic accuracy available at research and university hospitals (90%).
"]},{"key":"dc:title","label":"Title","values":["Data fusion based optimal EEG electrode selection for early diagnosis of Alzheimer's disease"]}]}],"canonical_facts":{"dc:contributor":["Polikar, Robi"],"dc:creator":["Balut, Brian"],"dc:date.available":["2016-03-20T07:00:00Z"],"dc:description.abstract":["As medicinal and technological advances lengthen the average human life span, diseases affecting the elderly such as Alzheimer's disease and Parkinson's disease are seeing increasingly growing numbers, especially in developed countries. As a result, the necessity for an accurate, inexpensive, noninvasive means of diagnosis becomes particularly important, since such a method is not readily available to the general population. One biomarker that has recently showed promise is the analysis of the electroencephalogram (EEG).
Over the course of two studies, more than 130 subjects have been recruited providing information from 16-19 EEG electrodes for each subject. These signals have been decomposed using the wavelet transform to be used in a pattern recognition and classification algorithm to serve as a diagnostic tool for Alzheimer's disease. Through the use of multilayer perceptrons and support vector machines, classifiers were generated on different portions of the EEG. These classifiers are then combined using combination methods such as sum rule, product rule, simple and weighted majority voting.
Classification performance for Cohort A was 88.7%, an increase of more than 5% over previous work in this study. Classification performance for Cohort B was 93.6% and the classification performance for both cohorts combined together was 82.7%. These classification performances exceed the diagnostic accuracy of community clinics (75%) and are close to diagnostic accuracy available at research and university hospitals (90%).
"],"dc:identifier":["https://rdw.rowan.edu/etd/685"],"dc:subject":["Alzheimer's disease--Diagnosis; Electroencephalography","Electrical and Computer Engineering"],"dc:title":["Data fusion based optimal EEG electrode selection 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":"2026-07-24T04:13:27Z"}