{"id":{"repo_id":"usf","oai_identifier":"oai:digitalcommons.usf.edu:etd-12308"},"canonical_url":"https://search.ndltd.org/etd/usf/oai:digitalcommons.usf.edu:etd-12308","repository":{"repo_id":"usf","name":"University of South Florida","base_url":"https://digitalcommons.usf.edu/do/oai/"},"display":{"title":"Enhancing State-of-the-Art Motor Imagery Classification with Reinforcement Learning","abstract":"One of the key obstacles to the rapid adoption of non-invasive Brain-Computer Interfaces (BCIs) for Motor Imagery (MI) is the low signal-to-noise ratio, and the substantial data requirements which can be mentally taxing for users. EEGNet, a compact Convolutional Neural Network (CNN), has long been considered the state-of-the-art (SOTA) for MI classification, demonstrating strong performance even with limited data. However, recent studies advocate for integrating Deep Reinforcement Learning (RL) to further enhance classification accuracy by dynamically optimizing feature extraction and decision-making processes. Despite this potential, practical implementations remain scarce due to challenges in stabilizing RL training and adapting it to noisy EEG data. This work addresses these limitations by extending the Shallow Convolutional Network, a SOTA model for EEG classification, with a Stochastic Policy Gradient (SPG) policy. SPG was chosen for its ability to handle continuous action spaces, making it well-suited for working with EEG signal representations. The proposed approach uses reward-driven optimization to adaptively enhance feature selection and classification performance. Using the publicly available BCI Competition IV dataset, the model performs within-subject MI classification, achieving results that are comparable to, and in some cases exceed, existing SOTA approaches.","abstract_html":"One of the key obstacles to the rapid adoption of non-invasive Brain-Computer Interfaces (BCIs) for Motor Imagery (MI) is the low signal-to-noise ratio, and the substantial data requirements which can be mentally taxing for users. EEGNet, a compact Convolutional Neural Network (CNN), has long been considered the state-of-the-art (SOTA) for MI classification, demonstrating strong performance even with limited data. However, recent studies advocate for integrating Deep Reinforcement Learning (RL) to further enhance classification accuracy by dynamically optimizing feature extraction and decision-making processes. Despite this potential, practical implementations remain scarce due to challenges in stabilizing RL training and adapting it to noisy EEG data. This work addresses these limitations by extending the Shallow Convolutional Network, a SOTA model for EEG classification, with a Stochastic Policy Gradient (SPG) policy. SPG was chosen for its ability to handle continuous action spaces, making it well-suited for working with EEG signal representations. The proposed approach uses reward-driven optimization to adaptively enhance feature selection and classification performance. Using the publicly available BCI Competition IV dataset, the model performs within-subject MI classification, achieving results that are comparable to, and in some cases exceed, existing SOTA approaches.","abstract_has_math":false,"creators":["Shepelev, Anton"],"institution":"University of South Florida","degree_name":"MS in Computer Science (M.S.C.S.)","degree_level":"Thesis","degree_discipline":"Computer Science and Engineering","degree_department":null,"school":null,"contributors":["Marvin Andujar, Ph.D.","Shaun Canavan, Ph.D.","Tempestt Neal, Ph.D."],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-04-04T07:00:00Z","date_published":"2025-04-04T07:00:00Z","updated_at":"2026-11-19T08:49:40Z","subjects":["BCI","CNN","Deep Learning","EEG","RL","Bioinformatics","Computer Sciences","Neurosciences"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.usf.edu/etd/11005","outbound_label":"Repository record","outbound_source":"dc:identifier","record_url":"https://digitalcommons.usf.edu/etd/11005","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.usf.edu/do/oai/?verb=GetRecord&metadataPrefix=oai_etdms&identifier=oai%3Adigitalcommons.usf.edu%3Aetd-12308","prefix":"oai_etdms"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Marvin Andujar, Ph.D.","Shaun Canavan, Ph.D.","Tempestt Neal, Ph.D."]},{"key":"dc:creator","label":"Author","values":["Shepelev, Anton"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-04-04T07:00:00Z"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science and Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis","M.S.C.S."]},{"key":"thesis:degree_name","label":"Degree Name","values":["MS in Computer Science (M.S.C.S.)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of South Florida"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["BCI","CNN","Deep Learning","EEG","RL","Bioinformatics","Computer Sciences","Neurosciences"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.usf.edu/etd/11005"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["One of the key obstacles to the rapid adoption of non-invasive Brain-Computer Interfaces (BCIs) for Motor Imagery (MI) is the low signal-to-noise ratio, and the substantial data requirements which can be mentally taxing for users. EEGNet, a compact Convolutional Neural Network (CNN), has long been considered the state-of-the-art (SOTA) for MI classification, demonstrating strong performance even with limited data. However, recent studies advocate for integrating Deep Reinforcement Learning (RL) to further enhance classification accuracy by dynamically optimizing feature extraction and decision-making processes. Despite this potential, practical implementations remain scarce due to challenges in stabilizing RL training and adapting it to noisy EEG data. This work addresses these limitations by extending the Shallow Convolutional Network, a SOTA model for EEG classification, with a Stochastic Policy Gradient (SPG) policy. SPG was chosen for its ability to handle continuous action spaces, making it well-suited for working with EEG signal representations. The proposed approach uses reward-driven optimization to adaptively enhance feature selection and classification performance. Using the publicly available BCI Competition IV dataset, the model performs within-subject MI classification, achieving results that are comparable to, and in some cases exceed, existing SOTA approaches."]},{"key":"dc:title","label":"Title","values":["Enhancing State-of-the-Art Motor Imagery Classification with Reinforcement Learning"]}]}],"canonical_facts":{"dc:contributor":["Marvin Andujar, Ph.D.","Shaun Canavan, Ph.D.","Tempestt Neal, Ph.D."],"dc:creator":["Shepelev, Anton"],"dc:date":["2025-04-04T07:00:00Z"],"dc:description":["One of the key obstacles to the rapid adoption of non-invasive Brain-Computer Interfaces (BCIs) for Motor Imagery (MI) is the low signal-to-noise ratio, and the substantial data requirements which can be mentally taxing for users. EEGNet, a compact Convolutional Neural Network (CNN), has long been considered the state-of-the-art (SOTA) for MI classification, demonstrating strong performance even with limited data. However, recent studies advocate for integrating Deep Reinforcement Learning (RL) to further enhance classification accuracy by dynamically optimizing feature extraction and decision-making processes. Despite this potential, practical implementations remain scarce due to challenges in stabilizing RL training and adapting it to noisy EEG data. This work addresses these limitations by extending the Shallow Convolutional Network, a SOTA model for EEG classification, with a Stochastic Policy Gradient (SPG) policy. SPG was chosen for its ability to handle continuous action spaces, making it well-suited for working with EEG signal representations. The proposed approach uses reward-driven optimization to adaptively enhance feature selection and classification performance. Using the publicly available BCI Competition IV dataset, the model performs within-subject MI classification, achieving results that are comparable to, and in some cases exceed, existing SOTA approaches."],"dc:identifier":["https://digitalcommons.usf.edu/etd/11005"],"dc:subject":["BCI","CNN","Deep Learning","EEG","RL","Bioinformatics","Computer Sciences","Neurosciences"],"dc:title":["Enhancing State-of-the-Art Motor Imagery Classification with Reinforcement Learning"],"thesis:degree_discipline":["Computer Science and Engineering"],"thesis:degree_level":["Thesis","M.S.C.S."],"thesis:degree_name":["MS in Computer Science (M.S.C.S.)"],"thesis:institution_name":["University of South Florida"]},"updated_at":"2026-11-19T08:49:40Z"}