{"id":{"repo_id":"calpoly","oai_identifier":"oai:digitalcommons.calpoly.edu:theses-4191"},"canonical_url":"https://search.ndltd.org/etd/calpoly/oai:digitalcommons.calpoly.edu:theses-4191","repository":{"repo_id":"calpoly","name":"Cal Poly","base_url":"https://digitalcommons.calpoly.edu/do/oai/"},"display":{"title":"Alzheimer’s Detection With The Discrete Wavelet Transform And Convolutional Neural Networks","abstract":"Alzheimer’s disease slowly destroys an individual’s memory, and it is estimated to impact more than 5.5 million Americans. Over time, Alzheimer’s disease can cause behavior and personality changes. Current diagnosis techniques are challenging because individuals may show no clinical signs of the disease in the initial stages. As of today, there is no cure for Alzheimer’s. Therefore, symptom management is key, and it is critical that Alzheimer’s is detected early before major cognitive damage. The approach implemented in this thesis explores the idea of using the Discrete Wavelet Transform (DWT) and Convolutional Neural Networks (CNN) for Alzheimer’s detection. The neural network is trained and tested using Magnetic Resonance Image (MRI) brain scans from the ADNI1 (Alzheimer’s Disease Neuroimaging Initiative) dataset; and various mother wavelets and network hyperparameters are implemented to identify the optimal model. The resulting model can successfully identify patients with mild Alzheimer’s disease (AD) and the ones that are cognitively normal (NL) with an average accuracy of accuracy of 77.53±2.37%, an f1-score of 77.03±3.24%, precision of 80.63±11.03%, recall or sensitivity or 77.90±11.52%, and a specificity of 77.53±2.37%.","abstract_html":"Alzheimer’s disease slowly destroys an individual’s memory, and it is estimated to impact more than 5.5 million Americans. Over time, Alzheimer’s disease can cause behavior and personality changes. Current diagnosis techniques are challenging because individuals may show no clinical signs of the disease in the initial stages. As of today, there is no cure for Alzheimer’s. Therefore, symptom management is key, and it is critical that Alzheimer’s is detected early before major cognitive damage. The approach implemented in this thesis explores the idea of using the Discrete Wavelet Transform (DWT) and Convolutional Neural Networks (CNN) for Alzheimer’s detection. The neural network is trained and tested using Magnetic Resonance Image (MRI) brain scans from the ADNI1 (Alzheimer’s Disease Neuroimaging Initiative) dataset; and various mother wavelets and network hyperparameters are implemented to identify the optimal model. The resulting model can successfully identify patients with mild Alzheimer’s disease (AD) and the ones that are cognitively normal (NL) with an average accuracy of accuracy of 77.53±2.37%, an f1-score of 77.03±3.24%, precision of 80.63±11.03%, recall or sensitivity or 77.90±11.52%, and a specificity of 77.53±2.37%.","abstract_has_math":false,"creators":["Nardone, Melissa N"],"institution":null,"degree_name":"MS in Electrical Engineering","degree_level":null,"degree_discipline":"Electrical Engineering","degree_department":null,"school":null,"contributors":["Xiao-Hua (Helen) Yu","Electrical Engineering","College of Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":null,"date_issued":"","date_published":null,"updated_at":"2026-11-19T07:12:23Z","subjects":["Discrete Wavelet Transform","Convolutional Neural Networks","Alzheimer's Detection"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.calpoly.edu/theses/2904","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.calpoly.edu/theses/2904","record_label":"Repository record","record_kind":"record","record_source":"dc:identifier","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://digitalcommons.calpoly.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.calpoly.edu%3Atheses-4191","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Xiao-Hua (Helen) Yu","Electrical Engineering","College of Engineering"]},{"key":"dc:creator","label":"Author","values":["Nardone, Melissa N"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.available","label":"Dc Date Available","values":["2025-12-07T08:00:00Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2022-12-01T08:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Electrical Engineering"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Discrete Wavelet Transform","Convolutional Neural Networks","Alzheimer's Detection"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.calpoly.edu/theses/2904"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Alzheimer’s disease slowly destroys an individual’s memory, and it is estimated to impact more than 5.5 million Americans. Over time, Alzheimer’s disease can cause behavior and personality changes. Current diagnosis techniques are challenging because individuals may show no clinical signs of the disease in the initial stages. As of today, there is no cure for Alzheimer’s. Therefore, symptom management is key, and it is critical that Alzheimer’s is detected early before major cognitive damage. The approach implemented in this thesis explores the idea of using the Discrete Wavelet Transform (DWT) and Convolutional Neural Networks (CNN) for Alzheimer’s detection. The neural network is trained and tested using Magnetic Resonance Image (MRI) brain scans from the ADNI1 (Alzheimer’s Disease Neuroimaging Initiative) dataset; and various mother wavelets and network hyperparameters are implemented to identify the optimal model. The resulting model can successfully identify patients with mild Alzheimer’s disease (AD) and the ones that are cognitively normal (NL) with an average accuracy of accuracy of 77.53±2.37%, an f1-score of 77.03±3.24%, precision of 80.63±11.03%, recall or sensitivity or 77.90±11.52%, and a specificity of 77.53±2.37%."]},{"key":"dc:title","label":"Title","values":["Alzheimer’s Detection With The Discrete Wavelet Transform And Convolutional Neural Networks"]}]}],"canonical_facts":{"dc:contributor":["Xiao-Hua (Helen) Yu","Electrical Engineering","College of Engineering"],"dc:creator":["Nardone, Melissa N"],"dc:date.available":["2025-12-07T08:00:00Z"],"dc:date.created":["2022-12-01T08:00:00Z"],"dc:description.abstract":["Alzheimer’s disease slowly destroys an individual’s memory, and it is estimated to impact more than 5.5 million Americans. Over time, Alzheimer’s disease can cause behavior and personality changes. Current diagnosis techniques are challenging because individuals may show no clinical signs of the disease in the initial stages. As of today, there is no cure for Alzheimer’s. Therefore, symptom management is key, and it is critical that Alzheimer’s is detected early before major cognitive damage. The approach implemented in this thesis explores the idea of using the Discrete Wavelet Transform (DWT) and Convolutional Neural Networks (CNN) for Alzheimer’s detection. The neural network is trained and tested using Magnetic Resonance Image (MRI) brain scans from the ADNI1 (Alzheimer’s Disease Neuroimaging Initiative) dataset; and various mother wavelets and network hyperparameters are implemented to identify the optimal model. The resulting model can successfully identify patients with mild Alzheimer’s disease (AD) and the ones that are cognitively normal (NL) with an average accuracy of accuracy of 77.53±2.37%, an f1-score of 77.03±3.24%, precision of 80.63±11.03%, recall or sensitivity or 77.90±11.52%, and a specificity of 77.53±2.37%."],"dc:identifier":["https://digitalcommons.calpoly.edu/theses/2904"],"dc:subject":["Discrete Wavelet Transform","Convolutional Neural Networks","Alzheimer's Detection"],"dc:title":["Alzheimer’s Detection With The Discrete Wavelet Transform And Convolutional Neural Networks"],"thesis:degree_discipline":["Electrical Engineering"],"thesis:degree_name":["MS in Electrical Engineering"]},"updated_at":"2026-11-19T07:12:23Z"}