2026-09-19T00:38:52Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1558652024-08-02T03:38:43Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Anthony, Brian W. Copeland, Daniel Ilan Massachusetts Institute of Technology. Department of Mechanical Engineering 2024-08-01T19:02:13Z 2024-08-01T19:02:13Z 2024-05 2024-06-13T16:46:16.813Z https://hdl.handle.net/1721.1/155865 Falls represent a significant health risk, especially for the elderly. Fortunately, interventions have been shown to decrease falls when clinicians identify at-risk patients. However, factors such as medication changes, illness, and injuries can rapidly increase fall risk, making timely clinical identification and subsequent interventions challenging to implement. Our study introduces a comprehensive approach to assessing fall risk using a frequency-modulated continuous-wave (FMCW) radar system, addressing the need for frequent, low-cost, longterm balance monitoring solutions. This technology is compared with ground-truth contactbased lab sensors like force plates and motion capture systems, establishing a foundation for accurate balance assessments in home settings. In our cross-sectional analysis, participants performed the one-legged stand test (OLST) with simultaneous data collection from FMCW radar, force plates, and motion capture systems. By integrating the FMCW radar with machine learning algorithms, we achieved a 98.4% accuracy in identifying OLST foot movements and an R-squared of 0.70 in predicting force plate patterns, demonstrating the system’s nuanced capability for balance performance evaluation. Additionally, we examine the efficacy of combining radar technology with machine learning to identify movements similar to those performed in fitness, clinical, and rehabilitation settings. We also explore the use of simulations for optimizing radar system configurations. This thesis demonstrates the effectiveness of FMCW radar technology in laboratory settings and its potential for home-based health monitoring. The study highlights the transformative potential of integrating radar technology with machine learning through detailed experimentation and analysis, offering a versatile tool for health monitoring and fall risk assessment. S.M. Massachusetts Institute of Technology In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ Frequency Modulated Continuous Wave Radar Based Fall Risk Monitoring System Thesis application/pdf Master Master of Science in Mechanical Engineering Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="5f64e45f-584d-4579-b32a-8c6481160b0a"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Title>Frequency Modulated Continuous Wave Radar Based Fall Risk Monitoring System</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2024-05</PublicationDate> <Authors> <Author> <DisplayName>Copeland, Daniel Ilan</DisplayName> <Affiliation> <OrgUnit> </OrgUnit> </Affiliation> </Author> </Authors> <Editors> </Editors> <Publishers> <Publisher> <DisplayName>Massachusetts Institute of Technology</DisplayName> <OrgUnit /> </Publisher> </Publishers> <License>https://rightsstatements.org/page/InC-EDU/1.0/</License> <Abstract>Falls represent a significant health risk, especially for the elderly. Fortunately, interventions have been shown to decrease falls when clinicians identify at-risk patients. However, factors such as medication changes, illness, and injuries can rapidly increase fall risk, making timely clinical identification and subsequent interventions challenging to implement. Our study introduces a comprehensive approach to assessing fall risk using a frequency-modulated continuous-wave (FMCW) radar system, addressing the need for frequent, low-cost, longterm balance monitoring solutions. This technology is compared with ground-truth contactbased lab sensors like force plates and motion capture systems, establishing a foundation for accurate balance assessments in home settings. In our cross-sectional analysis, participants performed the one-legged stand test (OLST) with simultaneous data collection from FMCW radar, force plates, and motion capture systems. By integrating the FMCW radar with machine learning algorithms, we achieved a 98.4% accuracy in identifying OLST foot movements and an R-squared of 0.70 in predicting force plate patterns, demonstrating the system’s nuanced capability for balance performance evaluation. Additionally, we examine the efficacy of combining radar technology with machine learning to identify movements similar to those performed in fitness, clinical, and rehabilitation settings. We also explore the use of simulations for optimizing radar system configurations. This thesis demonstrates the effectiveness of FMCW radar technology in laboratory settings and its potential for home-based health monitoring. The study highlights the transformative potential of integrating radar technology with machine learning through detailed experimentation and analysis, offering a versatile tool for health monitoring and fall risk assessment.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>