{"id":{"repo_id":"liverpool-jm","oai_identifier":"oai:researchonline.ljmu.ac.uk:10096"},"canonical_url":"https://search.dev.ndltd.org/etd/liverpool-jm/oai:researchonline.ljmu.ac.uk:10096","repository":{"repo_id":"liverpool-jm","name":"Liverpool Jon Moores University","base_url":"https://researchonline.ljmu.ac.uk/cgi/oai2"},"display":{"title":"Physical Activity Recognition and Monitoring for Healthcare in Internet of Things Environment","abstract":"Due to importantly beneficial effects on physical and mental health and strong association with many rehabilitation programs, Physical Activity Recognition and Monitoring (PARM) has been considered as a key paradigm for smart healthcare. The emergence of the Internet of Things (IoT) enabling technology is transferring PARM studies to open and connected uncontrolled environments by connecting heterogeneous cost-effective wearable devices and mobile apps. Little is currently known about whether traditional PARM technologies can tackle the new challenges of IoT environments and how to effectively harness and improve these technologies. Two new challenges exist in the current IoT technologies PARM field. 1) Traditional lifelogging PA measures require relatively high cost and can only be conducted in controlled or semi-controlled environment, though they enjoy remarkable precision of lifelogging PA monitoring outcomes. Recent advancements in commercial wearable devices and smartphones for recording one’s lifelogging PA enable a popularized and uncontrolled environment possible. However, due to diverse life patterns and heterogeneity of connected devices as well as the PA recognition accuracy, lifelogging PA data measured by wearable devices and mobile phone contains much uncertainty so that they are hardly ever adopted for healthcare studies. 2) Traditional PA recognition techniques focus on repeated aerobic exercises or stationary PA. As a crucial indicator in human health, it covers a range of bodily movement from aerobics to anaerobic that may all bring health benefits. However, existing PA recognition approaches are mostly designed for specific scenarios like hospital or smart homes and often lack extensibility for application in other areas, thereby limiting their usefulness. In an effort to tackle the two issues of PARM by using IoT technologies in PARM, this thesis has two main contributions 1) in order to improve the feasibility of the PA tracking datasets from commercial wearable devices, we propose a lifelogging PA intensity pattern decision making approach for life long PA measures. The approach has significantly reduced the uncertainties and incompleteness of datasets from the third party devices. The results indicate that the proposed approach can improve the effectiveness of PA tracking devices or apps for various types of people who frequently use them as a healthcare indicator. 2) More physical activities are detected in addition to traditional PA using acceleration in the gym scenario. A two layer recognition framework is proposed that can classify aerobic, sedentary and free weight activities, count repetitions and sets for the free weight exercises, and in the meantime, measure quantities of repetitions and sets for free weight activities. The results indicate the proposed framework has better performance in recognizing and measuring GPAs than other approaches. The potential of this framework can be extended in supporting more types of PA recognition in complex applications.","abstract_html":"Due to importantly beneficial effects on physical and mental health and strong association with many rehabilitation programs, Physical Activity Recognition and Monitoring (PARM) has been considered as a key paradigm for smart healthcare. The emergence of the Internet of Things (IoT) enabling technology is transferring PARM studies to open and connected uncontrolled environments by connecting heterogeneous cost-effective wearable devices and mobile apps. Little is currently known about whether traditional PARM technologies can tackle the new challenges of IoT environments and how to effectively harness and improve these technologies. Two new challenges exist in the current IoT technologies PARM field. 1) Traditional lifelogging PA measures require relatively high cost and can only be conducted in controlled or semi-controlled environment, though they enjoy remarkable precision of lifelogging PA monitoring outcomes. Recent advancements in commercial wearable devices and smartphones for recording one’s lifelogging PA enable a popularized and uncontrolled environment possible. However, due to diverse life patterns and heterogeneity of connected devices as well as the PA recognition accuracy, lifelogging PA data measured by wearable devices and mobile phone contains much uncertainty so that they are hardly ever adopted for healthcare studies. 2) Traditional PA recognition techniques focus on repeated aerobic exercises or stationary PA. As a crucial indicator in human health, it covers a range of bodily movement from aerobics to anaerobic that may all bring health benefits. However, existing PA recognition approaches are mostly designed for specific scenarios like hospital or smart homes and often lack extensibility for application in other areas, thereby limiting their usefulness. In an effort to tackle the two issues of PARM by using IoT technologies in PARM, this thesis has two main contributions 1) in order to improve the feasibility of the PA tracking datasets from commercial wearable devices, we propose a lifelogging PA intensity pattern decision making approach for life long PA measures. The approach has significantly reduced the uncertainties and incompleteness of datasets from the third party devices. The results indicate that the proposed approach can improve the effectiveness of PA tracking devices or apps for various types of people who frequently use them as a healthcare indicator. 2) More physical activities are detected in addition to traditional PA using acceleration in the gym scenario. A two layer recognition framework is proposed that can classify aerobic, sedentary and free weight activities, count repetitions and sets for the free weight exercises, and in the meantime, measure quantities of repetitions and sets for free weight activities. The results indicate the proposed framework has better performance in recognizing and measuring GPAs than other approaches. The potential of this framework can be extended in supporting more types of PA recognition in complex applications.","abstract_has_math":false,"creators":["Qi, J"],"institution":"Liverpool John Moores University","degree_name":"phd","degree_level":"doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":["Yang, P","Hanneghan, M","Stephen, T"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2019,"date_issued":"2019-02","date_published":"2019-02","updated_at":"2026-07-24T06:30:25Z","subjects":["QA76 Computer software","RA0421 Public health. Hygiene. Preventive Medicine","RC1200 Sports Medicine"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://doi.org/10.24377/LJMU.t.00010096","outbound_label":"DOI","outbound_source":"dc:identifier.doi"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Yang, P","Hanneghan, M","Stephen, T"]},{"key":"dc:creator","label":"Author","values":["Qi, J"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2019-02-11"]},{"key":"dc:date.issued","label":"Date","values":["2019-02"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Computer Science and Mathematics"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["Liverpool John Moores University"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["https://researchonline.ljmu.ac.uk/id/eprint/10096/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["phd"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["QA76 Computer software","RA0421 Public health. Hygiene. Preventive Medicine","RC1200 Sports Medicine"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.24377/LJMU.t.00010096"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://researchonline.ljmu.ac.uk/id/eprint/10096/1/LJMU%20Jun%20Qi%20-%20thesis%20final.docx"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Due to importantly beneficial effects on physical and mental health and strong association with many rehabilitation programs, Physical Activity Recognition and Monitoring (PARM) has been considered as a key paradigm for smart healthcare. The emergence of the Internet of Things (IoT) enabling technology is transferring PARM studies to open and connected uncontrolled environments by connecting heterogeneous cost-effective wearable devices and mobile apps. Little is currently known about whether traditional PARM technologies can tackle the new challenges of IoT environments and how to effectively harness and improve these technologies. Two new challenges exist in the current IoT technologies PARM field. 1) Traditional lifelogging PA measures require relatively high cost and can only be conducted in controlled or semi-controlled environment, though they enjoy remarkable precision of lifelogging PA monitoring outcomes. Recent advancements in commercial wearable devices and smartphones for recording one’s lifelogging PA enable a popularized and uncontrolled environment possible. However, due to diverse life patterns and heterogeneity of connected devices as well as the PA recognition accuracy, lifelogging PA data measured by wearable devices and mobile phone contains much uncertainty so that they are hardly ever adopted for healthcare studies. 2) Traditional PA recognition techniques focus on repeated aerobic exercises or stationary PA. As a crucial indicator in human health, it covers a range of bodily movement from aerobics to anaerobic that may all bring health benefits. However, existing PA recognition approaches are mostly designed for specific scenarios like hospital or smart homes and often lack extensibility for application in other areas, thereby limiting their usefulness. In an effort to tackle the two issues of PARM by using IoT technologies in PARM, this thesis has two main contributions 1) in order to improve the feasibility of the PA tracking datasets from commercial wearable devices, we propose a lifelogging PA intensity pattern decision making approach for life long PA measures. The approach has significantly reduced the uncertainties and incompleteness of datasets from the third party devices. The results indicate that the proposed approach can improve the effectiveness of PA tracking devices or apps for various types of people who frequently use them as a healthcare indicator. 2) More physical activities are detected in addition to traditional PA using acceleration in the gym scenario. A two layer recognition framework is proposed that can classify aerobic, sedentary and free weight activities, count repetitions and sets for the free weight exercises, and in the meantime, measure quantities of repetitions and sets for free weight activities. The results indicate the proposed framework has better performance in recognizing and measuring GPAs than other approaches. The potential of this framework can be extended in supporting more types of PA recognition in complex applications."]},{"key":"dc:format","label":"Dc Format","values":["text"]},{"key":"dc:title","label":"Title","values":["Physical Activity Recognition and Monitoring for Healthcare in Internet of Things Environment"]}]}],"canonical_facts":{"dc:contributor":["Yang, P","Hanneghan, M","Stephen, T"],"dc:creator":["Qi, J"],"dc:date":["2019-02-11"],"dc:date.issued":["2019-02"],"dc:description.abstract":["Due to importantly beneficial effects on physical and mental health and strong association with many rehabilitation programs, Physical Activity Recognition and Monitoring (PARM) has been considered as a key paradigm for smart healthcare. The emergence of the Internet of Things (IoT) enabling technology is transferring PARM studies to open and connected uncontrolled environments by connecting heterogeneous cost-effective wearable devices and mobile apps. Little is currently known about whether traditional PARM technologies can tackle the new challenges of IoT environments and how to effectively harness and improve these technologies. Two new challenges exist in the current IoT technologies PARM field. 1) Traditional lifelogging PA measures require relatively high cost and can only be conducted in controlled or semi-controlled environment, though they enjoy remarkable precision of lifelogging PA monitoring outcomes. Recent advancements in commercial wearable devices and smartphones for recording one’s lifelogging PA enable a popularized and uncontrolled environment possible. However, due to diverse life patterns and heterogeneity of connected devices as well as the PA recognition accuracy, lifelogging PA data measured by wearable devices and mobile phone contains much uncertainty so that they are hardly ever adopted for healthcare studies. 2) Traditional PA recognition techniques focus on repeated aerobic exercises or stationary PA. As a crucial indicator in human health, it covers a range of bodily movement from aerobics to anaerobic that may all bring health benefits. However, existing PA recognition approaches are mostly designed for specific scenarios like hospital or smart homes and often lack extensibility for application in other areas, thereby limiting their usefulness. In an effort to tackle the two issues of PARM by using IoT technologies in PARM, this thesis has two main contributions 1) in order to improve the feasibility of the PA tracking datasets from commercial wearable devices, we propose a lifelogging PA intensity pattern decision making approach for life long PA measures. The approach has significantly reduced the uncertainties and incompleteness of datasets from the third party devices. The results indicate that the proposed approach can improve the effectiveness of PA tracking devices or apps for various types of people who frequently use them as a healthcare indicator. 2) More physical activities are detected in addition to traditional PA using acceleration in the gym scenario. A two layer recognition framework is proposed that can classify aerobic, sedentary and free weight activities, count repetitions and sets for the free weight exercises, and in the meantime, measure quantities of repetitions and sets for free weight activities. The results indicate the proposed framework has better performance in recognizing and measuring GPAs than other approaches. The potential of this framework can be extended in supporting more types of PA recognition in complex applications."],"dc:format":["text"],"dc:identifier.doi":["10.24377/LJMU.t.00010096"],"dc:identifier.uri":["https://researchonline.ljmu.ac.uk/id/eprint/10096/1/LJMU%20Jun%20Qi%20-%20thesis%20final.docx"],"dc:publisher.department":["Computer Science and Mathematics"],"dc:publisher.institution":["Liverpool John Moores University"],"dc:relation.isreferencedby":["https://researchonline.ljmu.ac.uk/id/eprint/10096/"],"dc:subject":["QA76 Computer software","RA0421 Public health. Hygiene. Preventive Medicine","RC1200 Sports Medicine"],"dc:title":["Physical Activity Recognition and Monitoring for Healthcare in Internet of Things Environment"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["doctoral"],"dc:type.qualificationname":["phd"]},"updated_at":"2026-07-24T06:30:25Z"}