Off-campus UMass Amherst users: To download dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.
Non-UMass Amherst users, please click the view more button below to purchase a copy of this dissertation from Proquest.
(Some titles may also be available free of charge in our Open Access Dissertation Collection, so please check there first.)
Development of novel analytical techniques to classify physical activity mode using accelerometers
Use of accelerometers to assess physical activity (PA) is widespread in public health research, but their utility is often limited by the accuracy of data processing techniques. We hypothesized that more sophisticated approaches to data processing could distinguish between activity types based on accelerometer data, providing a more accurate picture of PA. Using data from MTI Actigraphs worn by 6 subjects during four activities (walking, walking uphill, vacuuming, working at a computer) quadratic discriminant analysis (QDA) was performed, and a hidden Markov model (HMM) was "trained" to recognize the activities. The ability of the new analytic techniques to accurately classify PA was assessed. The mean (SE) percentage of time points for which the QDA correctly identified activity mode was 70.9(1.2)%. Computer work was correctly recognized most frequently (mean (SE) percent correct = 100(0.01)%) followed by vacuuming (67.5(1.5)%), uphill walking (58.2(3.5)%), and walking (53.6(3.3)%). The mean (SE) percentage of time points for which the HMM correctly identified activity mode was 80.8(0.9)%. Vacuuming was correctly recognized most frequently (mean (SE) percent correct = 98.8(0.05)%) followed by computer work (97.3(0.7)%), walking (62.6(2.3)%), and uphill walking (62.5(2.3)%). In contrast to a traditional method of data processing that misidentified the intensity level of 100% of the time spent vacuuming and walking uphill, the QDA and HMM approaches correctly estimated the intensity of activity 99% of the time. In a second study, we applied and HMM to data collected on five subjects doing a variety of activities. The HMM was able to correctly classify sitting most frequently (mean(se) percentage of time points correctly identified was 99.2%(0.8%)) followed by walking on declined treadmill (94.2%(4.6%)), jogging (91.6%(5.6%)), walking on level treadmill at 1.25 m·s-1 (90.8%(6.3%)), walking on level treadmill at 1.70 m·s-1 (81.8%(18.2%)), walking on an inclined treadmill (73.1%(16.6%)), vacuuming (58.6%(14.3%)), walking up stairs (50.3%(17.0%)), walking down stairs (43.3%(17.8%)), and a box loading task (27.8%(9.5%)). The novel approach of estimating activity mode, rather than activity level, may allow for more accurate field-based estimates of physical activity using accelerometer data, which would allow for more accurate public health information regarding the relationship between exercise and a variety of chronic diseases.^
Pober, David M, "Development of novel analytical techniques to classify physical activity mode using accelerometers" (2007). Doctoral Dissertations Available from Proquest. AAI3254942.