Smart wearable systems for health and wellness in sports, aging, and rehabilitation

Simple item page
dc.availability.bitstreamcontrolled
dc.check.chapterOfThesisNoneen
dc.contributor.advisorO'Flynn, Brendanen
dc.contributor.advisorWalsh, Michaelen
dc.contributor.authorTedesco, Salvatore
dc.contributor.funderScience Foundation Irelanden
dc.contributor.funderEnterprise Irelanden
dc.contributor.funderHorizon 2020 Framework Programmeen
dc.contributor.funderSetanta College Ltden
dc.date.accessioned2022-01-25T14:22:49Z
dc.date.available2022-01-25T14:22:49Z
dc.date.issued2021
dc.date.submitted2021
dc.description.abstractRecent years have witnessed an explosive growth in wearable technology. This area is experiencing a massive expansion thanks to huge technical advances in information and communication technology driven by changes in demography, lifestyle, environment, etc. Wearable sensors are currently popular as personal tracking devices, but wearables can assume a more significant role in multiple applications, such as personalized health, sports, rehabilitation, personal entertainment, etc. In conjunction with technological advances in smart systems, the continuous growth in numbers of connected wearable devices raises major issues in terms of dealing with huge amounts of data originating from heterogeneous devices. Machine learning and artificial intelligence will enable a new capability to provide real-time recognition of patterns in the sensor data which can help to identify events of interest (for example, an elderly person experiencing – or about to experience - a fall) and provide real-time feedback on such events to the wearer or caregiver so appropriate decisions can be made. The work described in this thesis is focused on investigating the integration of wearable technology and developing machine learning models in the application spaces of healthcare, rehabilitation, and fitness monitoring. The key research challenges and developed contributions to the state-of-the-art in this area are identified, addressed, and discussed for specific use cases. These use cases are in the three categories of wearables for geriatric care, wearables for post-injury rehabilitation, and wearables for sports injury prevention. The associated research activities described include: a) An investigation on the accuracy of mainstream wrist-worn activity trackers has been carried out. Currently, wearable mainstream devices show the capability to measure a number of health care related parameters accurately. However, in general the validation studies which analyzed them were typically conducted on young or middle-aged adults. It is important to investigate the use of these devices in different populations, such as older people, both in lab- and free-living environments. To the best of the authors’ knowledge, the studies presented in this thesis were the first, at the time of publication, to investigate the adoption of wearable mainstream devices in older adults in constrained and unconstrained settings beyond simple step-counting. The publications in this thesis highlight how even consumer-level devices show the potential to provide significant health indications. The results obtained in the studies represent a foundation required to prove the benefits of using commercial wearable devices in clinical studies involving older adults. b) An investigation on the use of wearable sensors for lower-limb rehabilitation monitoring post-injury or surgery. The combination of wearable sensors and AI could represent a potential approach for developing an accurate functional assessment tool to curb the ACL injury trend and identify factors that predispose athletes to injury. The system developed enables the objective monitoring of an injured patients’ progress through physiotherapy during the initial rehabilitation phase, and more importantly, also in the 5-10 year period following the injury. To the best of the authors’ knowledge, this is the first time that the combination of a data-driven approach and inertial sensors to classify healthy and ACL-reconstructed subjects on-the-field (with post-ACL athletes returned to sport and with time from surgery between five and 10 years) was explored. The results described in these publications show the feasibility of using body-worn motion sensors and machine learning approaches for the identification of post-ACL gait patterns even a number of years after the injury occurred. c) An investigation on the use of body-mounted inertial sensors and artificial neural networks (ANN) for the estimation of Ground Reaction Forces (GRF) in runners to help prevent injury caused by running style. The research described shows, for the first time, the potential application of ANN modeling for the estimation of all three GRF components (vertical, anteroposterior, and mediolateral) evident in running based on motion kinematic data. This thesis deals with each of these research areas through a selection of nine peer-reviewed publications as senior author (first or last). These publications have furthered the research activities in these areas, contributing to the advancement of the state-of-the-art, and have enabled stakeholders (e.g., clinicians, physiotherapists, coaches, research community) perform activities and field assessments previously unavailable to them. In summary, the thesis describes how machine learning and data science can enhance the practical applications of wearable technology in a number of domains, thus driving the vision for the ubiquitous adoption of wearables in healthcare and fitness accessible to a wider section of society.en
dc.description.statusNot peer revieweden
dc.description.versionAccepted Versionen
dc.format.mimetypeapplication/pdfen
dc.identifier.citationTedesco, S. 2021. Smart wearable systems for health and wellness in sports, aging, and rehabilitation. PhD Thesis, University College Cork.en
dc.identifier.endpage283en
dc.identifier.urihttps://hdl.handle.net/10468/12469
dc.language.isoenen
dc.publisherUniversity College Corken
dc.relation.projectinfo:eu-repo/grantAgreement/EC/H2020::RIA/689996/EU/Integrated Technology Ecosystem for ProACTive Patient Centred Care/ProACTen
dc.rights© 2021, Salvatore Tedesco.en
dc.rights.urihttps://creativecommons.org/licenses/by-nc-nd/4.0/en
dc.subjectWearableen
dc.subjectIMUen
dc.subjectAgeingen
dc.subjectSporten
dc.subjectRehabilitationen
dc.subjectArtificial intelligenceen
dc.subjectDigital healthen
dc.subjectMachine learningen
dc.subjectData scienceen
dc.subjectWearable technologyen
dc.titleSmart wearable systems for health and wellness in sports, aging, and rehabilitationen
dc.typeDoctoral thesisen
dc.type.qualificationlevelDoctoralen
dc.type.qualificationnamePhD - Doctor of Philosophyen
Files
Original bundle
Now showing 1 - 3 of 3
Thumbnail Image
Name:
Revisedthesis_trackedchangesapproved-Final.docx
Size:
9.79 MB
Format:
Microsoft Word XML
Description:
Full Text E-thesis (Word)
Thumbnail Image
Name:
thesis.pdf
Size:
5.51 MB
Format:
Adobe Portable Document Format
Description:
Full Text E-thesis
Thumbnail Image
Name:
3. 117223921 - Salvatore Tedesco - Submission for Examination Form.pdf
Size:
2.46 MB
Format:
Adobe Portable Document Format
Description:
Submission for Examination Form
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
5.2 KB
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Research Theses Submission
College of Science, Engineering and Food Science - Doctoral Theses
Electrical and Electronic Engineering - Doctoral Theses
Tyndall National Institute - Doctoral Theses