Filtering by
Human activity recognition is the task of identifying a person’s movement from sensors in a wearable device, such as a smartphone, smartwatch, or a medical-grade device. A great method for this task is machine learning, which is the study of algorithms that learn and improve on their own with the help of massive amounts of useful data. These classification models can accurately classify activities with the time-series data from accelerometers and gyroscopes. A significant way to improve the accuracy of these machine learning models is preprocessing the data, essentially augmenting data to make the identification of each activity, or class, easier for the model. <br/>On this topic, this paper explains the design of SigNorm, a new web application which lets users conveniently transform time-series data and view the effects of those transformations in a code-free, browser-based user interface. The second and final section explains my take on a human activity recognition problem, which involves comparing a preprocessed dataset to an un-augmented one, and comparing the differences in accuracy using a one-dimensional convolutional neural network to make classifications.
protocols, including within sleep-focused studies. This study seeks to address accuracy of
accelerometer data in detection of the beginnings and ends of sleep bouts in young adults with
polysomnography (PSG) corroboration. An existing algorithm used to differentiate valid/invalid wear
time and detect bouts of sleep has been modified with the goal of maximizing accuracy of sleep bout
detection. Methods: Three key decisions and thresholds of the algorithm have been modified with three
experimental values each being tested. The main experimental variable Sleepwindow controls the
amount of time before and after a determined bout of sleep that is searched for additional sedentary
time to incorporate and consider part of the same sleep bout. Results were compared to PSG and sleep
diary data for absolute agreement of sleep bout start time (START), end time (END) and time in bed
(TIB). Adjustments were made for outliers as well as sleep latency, snooze time, and the sum of both.
Results: Only adjustments made to a sleep window variable yielded altered results. Between a 5-, 15-,
and 30-minute window, a 15-minute window incurred the least error and most agreement to
comparisons for START, while a 5-minute window was best for END and TIB. Discussion: Contrary
to expectation, corrections for snooze, latency, and both did not substantially improve agreement to
PSG. Algorithm-derived estimates of START and END always fell after sleep diary and PSG both,
suggesting either participants’ sedentary behavior beginning and ends were at a delay from sleep and
wake times, or the algorithm estimates consistently later times than appropriate. The inclusion of a
sleep window variable yields substantial variety in results. A 15-minute window appears best at
determining START while a 5-minute window appears best for END and TIB. Further investigation on
the optimal window length per demographic and condition is required.
In this study, we evaluated the association between sedentary time, light-intensity PA (LPA), and moderate-vigorous PA (MVPA) and CMR biomarkers (high density lipoprotein level, low density lipoprotein level, triglycerides, fasting glucose, total cholesterol, blood pressure, and body mass index). Additionally, we examined if the detrimental association between sedentary time and CMR biomarkers is partially or fully attenuated by MVPA. Baseline objective physical activity and cardiometabolic risk data from a two-arm-cluster randomized trial (Stand&Move@work) were used in this study. Multilevel models clustered by worksite evaluated the fixed effects and interaction between MVPA and sedentary time on CMR. Data from 630 sedentary working adults (from 24 worksites) were included in the analysis. The sample was mainly middle aged (44.6±11.2) females (74%) with race distributions as follows; 70.5% white, 13.8% hispanic, 4.1% black, 5.1% asian, and 2.1% other. Our study showed detrimental trends consistent with previous studies between sedentary behavior and cardiometabolic outcomes including HDL, LDL, and total cholesterol. MVPA demonstrated beneficial associations with lipoproteins including HDL, LDL, total cholesterol, and triglycerides. We observed that high levels of MVPA may be able to partially attenuate the negative effects of highly sedentary behavior on fasting glucose, total cholesterol, and LDL levels. Overall, sedentary behavior indicated deleterious associations with cardiometabolic outcomes. Future directions for this study could examine a more at-risk population or a highly active population for further assessment of CMR biomarkers and the effects of behavior.
The application (app) “BeWell24” mitigates this diabetes risk through targeting sleep, physical activity, sedentary behavior, and diet, and is being delivered through mHealth technology to attenuate the higher-risk of the prediabetic Veteran population. In order for full scale dissemination, this thesis examines a provider perspective of the ‘Post-intervention interview guide’, performed with a Phoenix Veterans Affairs Health Care System (PVAHCS) provider. It then suggests revisions to the interview guide based on the provider’s interview and existing literature. This thesis also emphasizes the rationale behind these proposed changes to be organized in line with the iPARIHS framework (integrated Promoting Action on Research Implementation in Health Services).
Overall, the provider responded positively to BeWell24 and the ‘Post-intervention interview guide’, with constructive suggestions for each question in the interview guide. The main theme of the provider’s answers and comments were to prioritize efficiency and preserve standard clinical flow. A revised interview guide is provided, which prospectively presents as a more brief and focused interview organized by the iPARIHS framework. This revised interview guide could aid in the clarity of provider responses, specifically for the prospective interviews of the ongoing larger BeWell24 study and future studies.