{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/86770"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/86770","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Fatigue Detection in Human-Robot Collaboration","abstract":"M.S.","abstract_html":"M.S.","abstract_has_math":false,"creators":["Suresh Kumar, Rakesh; 0000-0001-9793-5280"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Esfahani, Ehsan","Mechanical and Aerospace Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02-21T21:44:55Z","date_published":"2025-02-21T21:44:55Z","updated_at":"2026-07-27T19:05:37Z","subjects":["mechanical engineering"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/86770","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Esfahani, Ehsan","Mechanical and Aerospace Engineering"]},{"key":"dc:creator","label":"Author","values":["Suresh Kumar, Rakesh; 0000-0001-9793-5280"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-02-21T21:44:55Z","2020"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["mechanical engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/86770"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["M.S.","In this paper, a method is presented to detect muscle fatigue during Human-Robot Collaboration(HRC) using a low-cost myoelectric sensor. The proposed method uses the concepts of Riemannian geometry to extract simple and useful features from the data collected from muscle activity. A fine motor coordination task is designed and the human is asked to guide the robot along a virtual path. During the experiment, muscle activity from the dominant upper limb of the human is recorded. Then the subject is instructed to perform a muscle curl exercise until it induces fatigue in the muscles. Then the task is repeated with the fatigued muscles and the data is recorded. A total of nine subjects participated in the study and the experiments were labeled as before and after fatigue. At the end of the experiments, the muscle data from all nine subjects are used to extract Riemannian features. Previous studies in HRC have obtained good results by using other methods of extracting features from EMG data like obtaining wavelet coefficients by performing discrete wavelet transform and extracting time-domain features like RMS, MAV from the said coefficients, and Hudgin's set of time-domain features (RMS, MAV, WL, SSC, ZC) directly from the EMG data. These features are used to train classifiers to detect fatigue during human-robot collaboration. The accuracy and robustness of the classifier are compared against the conventional time-domain features and the time domain features extracted from the wavelets. We observe that the Riemannian features provide a better classification of the physical state of the human during an interaction. A classification accuracy of 92% is observed while using the Riemannian features against 86% accuracy with the conventional features and wavelet features. Moreover, other than the superior accuracy, the Riemannian features require fewer computations and can be calculated in real-time.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Fatigue Detection in Human-Robot Collaboration"]}]}],"canonical_facts":{"dc:contributor":["Esfahani, Ehsan","Mechanical and Aerospace Engineering"],"dc:creator":["Suresh Kumar, Rakesh; 0000-0001-9793-5280"],"dc:date":["2025-02-21T21:44:55Z","2020"],"dc:description":["M.S.","In this paper, a method is presented to detect muscle fatigue during Human-Robot Collaboration(HRC) using a low-cost myoelectric sensor. The proposed method uses the concepts of Riemannian geometry to extract simple and useful features from the data collected from muscle activity. A fine motor coordination task is designed and the human is asked to guide the robot along a virtual path. During the experiment, muscle activity from the dominant upper limb of the human is recorded. Then the subject is instructed to perform a muscle curl exercise until it induces fatigue in the muscles. Then the task is repeated with the fatigued muscles and the data is recorded. A total of nine subjects participated in the study and the experiments were labeled as before and after fatigue. At the end of the experiments, the muscle data from all nine subjects are used to extract Riemannian features. Previous studies in HRC have obtained good results by using other methods of extracting features from EMG data like obtaining wavelet coefficients by performing discrete wavelet transform and extracting time-domain features like RMS, MAV from the said coefficients, and Hudgin's set of time-domain features (RMS, MAV, WL, SSC, ZC) directly from the EMG data. These features are used to train classifiers to detect fatigue during human-robot collaboration. The accuracy and robustness of the classifier are compared against the conventional time-domain features and the time domain features extracted from the wavelets. We observe that the Riemannian features provide a better classification of the physical state of the human during an interaction. A classification accuracy of 92% is observed while using the Riemannian features against 86% accuracy with the conventional features and wavelet features. Moreover, other than the superior accuracy, the Riemannian features require fewer computations and can be calculated in real-time.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/86770"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["mechanical engineering"],"dc:title":["Fatigue Detection in Human-Robot Collaboration"],"dc:type":["Text","Thesis"]},"updated_at":"2026-07-27T19:05:37Z"}