{"id":{"repo_id":"njit","oai_identifier":"oai:digitalcommons.njit.edu:theses-1344"},"canonical_url":"https://search.dev.ndltd.org/etd/njit/oai:digitalcommons.njit.edu:theses-1344","repository":{"repo_id":"njit","name":"NJIT","base_url":"https://digitalcommons.njit.edu/do/oai/"},"display":{"title":"Using wavelet and template analysis to classify hand postures in unsupervised daily activities","abstract":"This project's goal was to identify determinants that characterize different types of activities an individual do in daily life, knowing the quality of hand function is essential to plan more effective rehabilitation therapies and treatments for upper limb movement disorders. The first part of the project was Jebsen-Taylor study where healthy individuals and individuals with brain injury performed seven activities classified as precision grasp, cylindrical grasp, and palmar grasp while metacarpal joint angles were measured in real time. The data from those seven activities was used to determine parameters that characterize each type of activity and which might be used as evaluation parameters after treatment. The determinants studied were the mean and variance of joints' angles, range of motion, flexion and extension speed, and range of motion. A glove was used to record hand activity of an individual for 24 hours. Characteristics of these hand activities produce signals that are localized in both time and frequency, thus wavelet transform was used to detect the instance of change in the type of activity. Three clusters built after analyzing the seven activities were used to scan the 24 hr data and summarize the types of activity that had been performed by the subject in addition to reporting multiple parameters of the hand as range of motion and speed. The result was that the subject did no activity for 8 hours, precision grasp activities for 2 hours, palmar grasp activities for 12 hours and cylindrical grasp activities for 1 hour.","abstract_html":"This project's goal was to identify determinants that characterize different types of activities an individual do in daily life, knowing the quality of hand function is essential to plan more effective rehabilitation therapies and treatments for upper limb movement disorders. The first part of the project was Jebsen-Taylor study where healthy individuals and individuals with brain injury performed seven activities classified as precision grasp, cylindrical grasp, and palmar grasp while metacarpal joint angles were measured in real time. The data from those seven activities was used to determine parameters that characterize each type of activity and which might be used as evaluation parameters after treatment. The determinants studied were the mean and variance of joints' angles, range of motion, flexion and extension speed, and range of motion. A glove was used to record hand activity of an individual for 24 hours. Characteristics of these hand activities produce signals that are localized in both time and frequency, thus wavelet transform was used to detect the instance of change in the type of activity. Three clusters built after analyzing the seven activities were used to scan the 24 hr data and summarize the types of activity that had been performed by the subject in addition to reporting multiple parameters of the hand as range of motion and speed. The result was that the subject did no activity for 8 hours, precision grasp activities for 2 hours, palmar grasp activities for 12 hours and cylindrical grasp activities for 1 hour.","abstract_has_math":false,"creators":["Saleh, Soha Hassan"],"institution":null,"degree_name":"Master of Science in Biomedical Engineering - (M.S.)","degree_level":null,"degree_discipline":"Biomedical Engineering","degree_department":null,"school":null,"contributors":["Lisa K. Simone","Richard A. Foulds","Ali N. Akansu"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2008,"date_issued":"2008-01-27T08:00:00Z","date_published":"2008-01-27T08:00:00Z","updated_at":"2026-07-24T03:23:16Z","subjects":["Hand function","Wavelet transform","Biomedical Engineering and Bioengineering"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://digitalcommons.njit.edu/theses/345","outbound_label":"Repository record","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Lisa K. Simone","Richard A. Foulds","Ali N. Akansu"]},{"key":"dc:creator","label":"Author","values":["Saleh, Soha Hassan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Biomedical Engineering"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science in Biomedical Engineering - (M.S.)"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Hand function","Wavelet transform","Biomedical Engineering and Bioengineering"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["https://digitalcommons.njit.edu/theses/345"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This project's goal was to identify determinants that characterize different types of activities an individual do in daily life, knowing the quality of hand function is essential to plan more effective rehabilitation therapies and treatments for upper limb movement disorders. The first part of the project was Jebsen-Taylor study where healthy individuals and individuals with brain injury performed seven activities classified as precision grasp, cylindrical grasp, and palmar grasp while metacarpal joint angles were measured in real time. The data from those seven activities was used to determine parameters that characterize each type of activity and which might be used as evaluation parameters after treatment. The determinants studied were the mean and variance of joints' angles, range of motion, flexion and extension speed, and range of motion. A glove was used to record hand activity of an individual for 24 hours. Characteristics of these hand activities produce signals that are localized in both time and frequency, thus wavelet transform was used to detect the instance of change in the type of activity. Three clusters built after analyzing the seven activities were used to scan the 24 hr data and summarize the types of activity that had been performed by the subject in addition to reporting multiple parameters of the hand as range of motion and speed. The result was that the subject did no activity for 8 hours, precision grasp activities for 2 hours, palmar grasp activities for 12 hours and cylindrical grasp activities for 1 hour."]},{"key":"dc:title","label":"Title","values":["Using wavelet and template analysis to classify hand postures in unsupervised daily activities"]}]}],"canonical_facts":{"dc:contributor":["Lisa K. Simone","Richard A. Foulds","Ali N. Akansu"],"dc:creator":["Saleh, Soha Hassan"],"dc:description.abstract":["This project's goal was to identify determinants that characterize different types of activities an individual do in daily life, knowing the quality of hand function is essential to plan more effective rehabilitation therapies and treatments for upper limb movement disorders. The first part of the project was Jebsen-Taylor study where healthy individuals and individuals with brain injury performed seven activities classified as precision grasp, cylindrical grasp, and palmar grasp while metacarpal joint angles were measured in real time. The data from those seven activities was used to determine parameters that characterize each type of activity and which might be used as evaluation parameters after treatment. The determinants studied were the mean and variance of joints' angles, range of motion, flexion and extension speed, and range of motion. A glove was used to record hand activity of an individual for 24 hours. Characteristics of these hand activities produce signals that are localized in both time and frequency, thus wavelet transform was used to detect the instance of change in the type of activity. Three clusters built after analyzing the seven activities were used to scan the 24 hr data and summarize the types of activity that had been performed by the subject in addition to reporting multiple parameters of the hand as range of motion and speed. The result was that the subject did no activity for 8 hours, precision grasp activities for 2 hours, palmar grasp activities for 12 hours and cylindrical grasp activities for 1 hour."],"dc:identifier":["https://digitalcommons.njit.edu/theses/345"],"dc:subject":["Hand function","Wavelet transform","Biomedical Engineering and Bioengineering"],"dc:title":["Using wavelet and template analysis to classify hand postures in unsupervised daily activities"],"dc:type":["Thesis"],"thesis:degree_discipline":["Biomedical Engineering"],"thesis:degree_name":["Master of Science in Biomedical Engineering - (M.S.)"]},"updated_at":"2026-07-24T03:23:16Z"}