{"id":{"repo_id":"york","oai_identifier":"oai:yorkspace.library.yorku.ca:10315/43590"},"canonical_url":"https://search.dev.ndltd.org/etd/york/oai:yorkspace.library.yorku.ca:10315/43590","repository":{"repo_id":"york","name":"York University","base_url":"https://yorkspace.library.yorku.ca/oai/request"},"display":{"title":"\"Towards Closed-Loop Sleep Monitoring in Parkinson’s Disease: Self-Supervised Learning Strategies for Sleep Stage Classification\"","abstract":"Parkinson’s disease (PD) involves severe sleep disturbances that may accelerate neurodegeneration. Closed-loop deep brain stimulation (DBS) is a promising therapeutic solution but requires accurate, real-time sleep-stage classification from subthalamic nucleus signals, a task where conventional models generalize poorly. To address pronounced class imbalance and improve cross-patient generalization, this work introduces a self-supervised transformer framework. The model employs a masked autoencoder strategy, pretrained on large public EEG/ECoG datasets from healthy subjects to learn balanced representations of all sleep stages, thereby improving discrimination of rare classes. While pretraining yielded limited overall improvement, it specifically enhanced N3 stage identification and next-sleep-stage prediction. Contrastive self-supervision (70%) significantly outperformed a reconstruction-based approach (62%). Furthermore, spectral feature extraction proved more effective than temporal CNN features for distinguishing commonly mispredicted stages. Future work will focus on hybrid reconstruction-contrastive losses, incorporating spectral feature usage to forecasting and extending the forecasting horizon to predict multiple subsequent stages for proactive neuromodulation.","abstract_html":"Parkinson’s disease (PD) involves severe sleep disturbances that may accelerate neurodegeneration. Closed-loop deep brain stimulation (DBS) is a promising therapeutic solution but requires accurate, real-time sleep-stage classification from subthalamic nucleus signals, a task where conventional models generalize poorly. To address pronounced class imbalance and improve cross-patient generalization, this work introduces a self-supervised transformer framework. The model employs a masked autoencoder strategy, pretrained on large public EEG/ECoG datasets from healthy subjects to learn balanced representations of all sleep stages, thereby improving discrimination of rare classes. While pretraining yielded limited overall improvement, it specifically enhanced N3 stage identification and next-sleep-stage prediction. Contrastive self-supervision (70%) significantly outperformed a reconstruction-based approach (62%). Furthermore, spectral feature extraction proved more effective than temporal CNN features for distinguishing commonly mispredicted stages. Future work will focus on hybrid reconstruction-contrastive losses, incorporating spectral feature usage to forecasting and extending the forecasting horizon to predict multiple subsequent stages for proactive neuromodulation.","abstract_has_math":false,"creators":["Menguc, Kristal Doga"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":["Zylberberg, Joel"],"committee_chairs":[],"committee_members":[],"year":2026,"date_issued":"2026-03-10","date_published":"2026-03-10","updated_at":"2026-07-24T06:33:46Z","subjects":["Computer science"],"languages":["en"],"rights":["Author owns copyright, except where explicitly noted. Please contact the author directly with licensing requests."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10315/43590","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Zylberberg, Joel"]},{"key":"dc:creator","label":"Author","values":["Menguc, Kristal Doga"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-03-10T16:11:56Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-03-10T16:11:56Z"]},{"key":"dc:date.issued","label":"Date","values":["2026-03-10"]},{"key":"dc:type","label":"Dc Type","values":["Electronic Thesis or Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Computer science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Author owns copyright, except where explicitly noted. Please contact the author directly with licensing requests."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10315/43590"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Parkinson’s disease (PD) involves severe sleep disturbances that may accelerate neurodegeneration. Closed-loop deep brain stimulation (DBS) is a promising therapeutic solution but requires accurate, real-time sleep-stage classification from subthalamic nucleus signals, a task where conventional models generalize poorly. To address pronounced class imbalance and improve cross-patient generalization, this work introduces a self-supervised transformer framework. The model employs a masked autoencoder strategy, pretrained on large public EEG/ECoG datasets from healthy subjects to learn balanced representations of all sleep stages, thereby improving discrimination of rare classes. While pretraining yielded limited overall improvement, it specifically enhanced N3 stage identification and next-sleep-stage prediction. Contrastive self-supervision (70%) significantly outperformed a reconstruction-based approach (62%). Furthermore, spectral feature extraction proved more effective than temporal CNN features for distinguishing commonly mispredicted stages. Future work will focus on hybrid reconstruction-contrastive losses, incorporating spectral feature usage to forecasting and extending the forecasting horizon to predict multiple subsequent stages for proactive neuromodulation."]},{"key":"dc:title","label":"Title","values":["\"Towards Closed-Loop Sleep Monitoring in Parkinson’s Disease: Self-Supervised Learning Strategies for Sleep Stage Classification\""]}]}],"canonical_facts":{"dc:contributor.advisor":["Zylberberg, Joel"],"dc:creator":["Menguc, Kristal Doga"],"dc:date.accessioned":["2026-03-10T16:11:56Z"],"dc:date.available":["2026-03-10T16:11:56Z"],"dc:date.issued":["2026-03-10"],"dc:description.abstract":["Parkinson’s disease (PD) involves severe sleep disturbances that may accelerate neurodegeneration. Closed-loop deep brain stimulation (DBS) is a promising therapeutic solution but requires accurate, real-time sleep-stage classification from subthalamic nucleus signals, a task where conventional models generalize poorly. To address pronounced class imbalance and improve cross-patient generalization, this work introduces a self-supervised transformer framework. The model employs a masked autoencoder strategy, pretrained on large public EEG/ECoG datasets from healthy subjects to learn balanced representations of all sleep stages, thereby improving discrimination of rare classes. While pretraining yielded limited overall improvement, it specifically enhanced N3 stage identification and next-sleep-stage prediction. Contrastive self-supervision (70%) significantly outperformed a reconstruction-based approach (62%). Furthermore, spectral feature extraction proved more effective than temporal CNN features for distinguishing commonly mispredicted stages. Future work will focus on hybrid reconstruction-contrastive losses, incorporating spectral feature usage to forecasting and extending the forecasting horizon to predict multiple subsequent stages for proactive neuromodulation."],"dc:identifier.uri":["https://hdl.handle.net/10315/43590"],"dc:language":["en"],"dc:rights":["Author owns copyright, except where explicitly noted. Please contact the author directly with licensing requests."],"dc:subject":["Computer science"],"dc:title":["\"Towards Closed-Loop Sleep Monitoring in Parkinson’s Disease: Self-Supervised Learning Strategies for Sleep Stage Classification\""],"dc:type":["Electronic Thesis or Dissertation"]},"updated_at":"2026-07-24T06:33:46Z"}