Modeling individual differences: A case study of the application of system identification for personalizing a physical activity intervention

Phatak, Sayali S.; Freigoun, Mohammad T.; Martín, César A.; Rivera, Daniel E.; Korinek, Elizabeth V.; Adams, Marc A.; Buman, Matthew P.; Klasnja, Predrag; Hekler, Eric B.

doi:10.1016/j.jbi.2018.01.010

Cited by 45 publications

(62 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Another line of work has applied data-driven approach to understand and predict the effect of interventions on people's health (Sloan et al 2018;Robinson et al 2019;Zeevi et al 2015;Phatak et al 2018). The most traditional method estimates the population-level intervention effect from randomized controlled trial (RCT) data (Sloan et al 2018;Robinson et al 2019).…”

Section: Prediction Of Health Conditionsmentioning

confidence: 99%

“…Interventions should be tailored to the individual needs, account for personal levels of fitness, allow for personal control of the activity and its outcomes, and provide for social support by family, peers, and communities (Seefeldt et al 2002). Tailoring variables include time-invariant predictors (e.g., sex), time-variant predictors (e.g., stress) and contextual factors (e.g., weather, day of the week) (Phatak et al 2018).…”

Section: Introductionmentioning

confidence: 99%

“…Existing work focuses only on a subset of these challenges. For example, Phatak et al (2018) developed a system that generates recommendations based on the median value of steps/day from the baseline period. Their system does not take into account the distribution of the physical activity throughout the day as a predictor of the behavior change.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Recommender System for Responsive Engagement of Senior Adults in Daily Activities

et al. 2020

View full text Add to dashboard Cite

Understanding and predicting how people change their behavior after an intervention from time series data is an important task for health recommender systems. This task is especially challenging when the time series data is frequently sampled. In this paper, we develop and propose a novel recommender system that aims to promote physical activeness in elderly people. The main novelty of our recommender system is that it learns how senior adults with different lifestyle change their activeness after a digital health intervention from minute-by-minute fitness data in an automated way. We trained the system and validated the recommendations using data from senior adults. We demonstrated that the low-level information contained in time series data is an important predictor of behavior change. The insights generated by our recommender system could help senior adults to engage more in daily activities.

show abstract

Section: Prediction Of Health Conditionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recommender System for Responsive Engagement of Senior Adults in Daily Activities

et al. 2020

View full text Add to dashboard Cite

show abstract

“…has been used in many applications, but for accurate estimation in the presence of noise and uncertainties, these techniques have various problems. To improve the performance of linear estimation techniques, nonlinear techniques for system estimation have been introduced in the literature [5]. Nonlinear estimation techniques can be divided into three main categories.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Finite-Time Convergence Fuzzy ARXLaguerre System Estimation

Piltan¹,

TayebiHaghighi²,

Sahamijoo³

et al. 2019

IJISA

View full text Add to dashboard Cite

Convergence speed for system identification and estimation is a popular topic for determining the kinematics and dynamic identification/estimation of the parameters of robot manipulators. In this paper, adaptive fuzzy inverse dynamic system estimation is used to improve robust modeling, especially for a serial links robot manipulator. The Lyapunov technique is used to analyze the convergence rate of the tracking error and increase the accuracy response of the parameter estimation. Performance of robot estimation is conducted, and the results show fast convergence of the proposed finite time technique for a 6-DOF robot manipulator.Index Terms-Finite-time, robot manipulator, fuzzy logic inverse dynamic modeling, parameter estimation, unknown dynamic parameters.

show abstract

“…While using the application, participants increased their daily steps by over 2600 per day, as compared to the baseline period in which physical activity goals were not specified (Korinek et al, 2018). Additionally, individual differences in predictors of success on a given day support that an individual-level of tailoring in interventions is justified and may further improve outcomes (Phatak et al, 2018). Of note, control systems interventions do not have the capacity to adjust for specific participants who might not be responding well to a particular type of intervention (e.g.…”

Section: Introductionmentioning

confidence: 99%

Can the artificial intelligence technique of reinforcement learning use continuously-monitored digital data to optimize treatment for weight loss?

et al. 2018

View full text Add to dashboard Cite

Behavioral weight loss (WL) trials show that, on average, participants regain lost weight unless provided long-term, intensive-and thus costly-intervention. Optimization solutions have shown mixed success. The artificial intelligence principle of "reinforcement learning" (RL) offers a new and more sophisticated form of optimization in which the intensity of each individual's intervention is continuously adjusted depending on patterns of response. In this pilot, we evaluated the feasibility and acceptability of a RL-based WL intervention, and whether optimization would achieve equivalent benefit at a reduced cost compared to a non-optimized intensive intervention. Participants (n = 52) completed a 1-month, group-based in-person behavioral WL intervention and then (in Phase II) were randomly assigned to receive 3 months of twice-weekly remote interventions that were non-optimized (NO; 10-min phone calls) or optimized (a combination of phone calls, text exchanges, and automated messages selected by an algorithm). The Individually-Optimized (IO) and Group-Optimized (GO) algorithms selected interventions based on past performance of each intervention for each participant, and for each group member that fit into a fixed amount of time (e.g., 1 h), respectively. Results indicated that the system was feasible to deploy and acceptable to participants and coaches. As hypothesized, we were able to achieve equivalent Phase II weight losses (NO = 4.42%, IO = 4.56%, GO = 4.39%) at roughly one-third the cost (1.73 and 1.77 coaching hours/participant for IO and GO, versus 4.38 for NO), indicating strong promise for a RL system approach to weight loss and maintenance.

show abstract

Modeling individual differences: A case study of the application of system identification for personalizing a physical activity intervention

Cited by 45 publications

References 53 publications

Recommender System for Responsive Engagement of Senior Adults in Daily Activities

Recommender System for Responsive Engagement of Senior Adults in Daily Activities

Adaptive Finite-Time Convergence Fuzzy ARXLaguerre System Estimation

Can the artificial intelligence technique of reinforcement learning use continuously-monitored digital data to optimize treatment for weight loss?

Contact Info

Product

Resources

About