The number of the elderly population affected by Alzheimer's disease is rapidly rising. The need to find an accurate, inexpensive, and non-intrusive procedure that can be made available to community healthcare providers for the early diagnosis of Alzheimer's disease is becoming an increasingly urgent public health concern. Several recent studies have looked at analyzing electroencephalogram signals through the use of many signal processing techniques. While their methods show great promise, the final outcome of these studies has been largely inconclusive. The inherent difficulty of the problem may be the cause of this outcome, but most likely it is due to the inefficient use of the available information, as many of these studies have used only a single EEG source for the analysis. In this contribution, data from the event related potentials of 19 available electrodes of the EEG are analyzed. These signals are decomposed into different frequency bands using multiresolution wavelet analysis. Two data fusion approaches are then investigated: i.) concatenating features before presenting them to a classification algorithm with the expectation of creating a more informative feature space, and ii.) generating multiple classifiers each trained with a different combination of features obtained from various stimuli, electrode, and frequency bands. The classifiers are then combined through the weighted majority vote, product and sum rule combination schemes. The results indicate that a correct diagnosis performance of over 80% can be obtained by combining data primarily from parietal and occipital lobe electrodes. The performance significantly exceeds that reported from community clinic physicians, despite their access to the outcomes of longitudinal monitoring of the patients.
","abstract_html":"<p>The number of the elderly population affected by Alzheimer's disease is rapidly rising. The need to find an accurate, inexpensive, and non-intrusive procedure that can be made available to community healthcare providers for the early diagnosis of Alzheimer's disease is becoming an increasingly urgent public health concern. Several recent studies have looked at analyzing electroencephalogram signals through the use of many signal processing techniques. While their methods show great promise, the final outcome of these studies has been largely inconclusive. The inherent difficulty of the problem may be the cause of this outcome, but most likely it is due to the inefficient use of the available information, as many of these studies have used only a single EEG source for the analysis. In this contribution, data from the event related potentials of 19 available electrodes of the EEG are analyzed. These signals are decomposed into different frequency bands using multiresolution wavelet analysis. Two data fusion approaches are then investigated: i.) concatenating features before presenting them to a classification algorithm with the expectation of creating a more informative feature space, and ii.) generating multiple classifiers each trained with a different combination of features obtained from various stimuli, electrode, and frequency bands. The classifiers are then combined through the weighted majority vote, product and sum rule combination schemes. The results indicate that a correct diagnosis performance of over 80% can be obtained by combining data primarily from parietal and occipital lobe electrodes. The performance significantly exceeds that reported from community clinic physicians, despite their access to the outcomes of longitudinal monitoring of the patients.</p>","abstract_has_math":false,"creators":["Stepenosky, Nicholas"],"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":2006,"date_issued":"2006-12-31T08:00:00Z","date_published":"2006-12-31T08:00:00Z","updated_at":"2026-07-24T04:13:52Z","subjects":["Alzheimer's disease--Diagnosis; Multisensor data fusion","Electrical and Computer Engineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://rdw.rowan.edu/etd/938","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":["Stepenosky, Nicholas"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2016-04-07T07:00:00Z"]},{"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; Multisensor data fusion","Electrical and Computer Engineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://rdw.rowan.edu/etd/938"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["The number of the elderly population affected by Alzheimer's disease is rapidly rising. The need to find an accurate, inexpensive, and non-intrusive procedure that can be made available to community healthcare providers for the early diagnosis of Alzheimer's disease is becoming an increasingly urgent public health concern. Several recent studies have looked at analyzing electroencephalogram signals through the use of many signal processing techniques. While their methods show great promise, the final outcome of these studies has been largely inconclusive. The inherent difficulty of the problem may be the cause of this outcome, but most likely it is due to the inefficient use of the available information, as many of these studies have used only a single EEG source for the analysis. In this contribution, data from the event related potentials of 19 available electrodes of the EEG are analyzed. These signals are decomposed into different frequency bands using multiresolution wavelet analysis. Two data fusion approaches are then investigated: i.) concatenating features before presenting them to a classification algorithm with the expectation of creating a more informative feature space, and ii.) generating multiple classifiers each trained with a different combination of features obtained from various stimuli, electrode, and frequency bands. The classifiers are then combined through the weighted majority vote, product and sum rule combination schemes. The results indicate that a correct diagnosis performance of over 80% can be obtained by combining data primarily from parietal and occipital lobe electrodes. The performance significantly exceeds that reported from community clinic physicians, despite their access to the outcomes of longitudinal monitoring of the patients.
"]},{"key":"dc:title","label":"Title","values":["Data fusion of complementary information from parietal and occipital event related potentials for early diagnosis of Alzheimer's disease"]}]}],"canonical_facts":{"dc:contributor":["Polikar, Robi"],"dc:creator":["Stepenosky, Nicholas"],"dc:date.available":["2016-04-07T07:00:00Z"],"dc:description.abstract":["The number of the elderly population affected by Alzheimer's disease is rapidly rising. The need to find an accurate, inexpensive, and non-intrusive procedure that can be made available to community healthcare providers for the early diagnosis of Alzheimer's disease is becoming an increasingly urgent public health concern. Several recent studies have looked at analyzing electroencephalogram signals through the use of many signal processing techniques. While their methods show great promise, the final outcome of these studies has been largely inconclusive. The inherent difficulty of the problem may be the cause of this outcome, but most likely it is due to the inefficient use of the available information, as many of these studies have used only a single EEG source for the analysis. In this contribution, data from the event related potentials of 19 available electrodes of the EEG are analyzed. These signals are decomposed into different frequency bands using multiresolution wavelet analysis. Two data fusion approaches are then investigated: i.) concatenating features before presenting them to a classification algorithm with the expectation of creating a more informative feature space, and ii.) generating multiple classifiers each trained with a different combination of features obtained from various stimuli, electrode, and frequency bands. The classifiers are then combined through the weighted majority vote, product and sum rule combination schemes. The results indicate that a correct diagnosis performance of over 80% can be obtained by combining data primarily from parietal and occipital lobe electrodes. The performance significantly exceeds that reported from community clinic physicians, despite their access to the outcomes of longitudinal monitoring of the patients.
"],"dc:identifier":["https://rdw.rowan.edu/etd/938"],"dc:subject":["Alzheimer's disease--Diagnosis; Multisensor data fusion","Electrical and Computer Engineering"],"dc:title":["Data fusion of complementary information from parietal and occipital event related potentials 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":"2026-07-24T04:13:52Z"}