System Identification of <i>Just Walk</i>: Using Matchable-Observable Linear Parametrizations

Santos, P. Lopes dos; Freigoun, Mohammad T.; Martín, César A.; Rivera, Daniel E.; Hekler, Eric B.; Romano, Rodrigo Alvite; Perdicoúlis, T-P Azevedo

doi:10.1109/tcst.2018.2884833

Cited by 5 publications

(3 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Applying control systems principles [ 28 ], matchable-observable linear identification algorithms will be used to estimate linear time-invariant models from iMove intervention data [ 28 ]. Behavioral changes, including standing and walking time, will be assessed as a function of the onset, and offset of individual intervention components (ie, messages) and time-variant determinants (eg, contextual factors).…”

Section: Methodsmentioning

confidence: 99%

Just-In-Time Adaptive Intervention to Sit Less and Move More in People With Type 2 Diabetes: Protocol for a Microrandomized Trial

Daryabeygi-Khotbehsara¹,

Dunstan²,

Islam³

et al. 2023

JMIR Res Protoc

View full text Add to dashboard Cite

Background Reducing sedentary behavior and increasing physical activity in people with type 2 diabetes (T2D) are associated with various positive health benefits. Just-in-time adaptive interventions offer the potential to target both of these behaviors through more contextually aware, tailored, and personalized support. We have developed a just-in-time adaptive intervention to promote sitting less and moving more in people with T2D. Objective This paper presents the study protocol for a microrandomized trial to investigate whether motivational messages are effective in reducing time spent sitting in people with T2D and to determine what behavior change techniques are effective and in which context (eg, location, etc). Methods We will use a 6-week microrandomized trial design. A total of 22 adults with T2D will be recruited. The intervention aims to reduce sitting time and increase time spent standing and walking and comprises a mobile app (iMove), a bespoke activity sensor called Sedentary Behavior Detector (SORD), a messaging system, and a secured database. Depending on the randomization sequence, participants will potentially receive motivational messages 5 times a day. Results Recruitment was initiated in October 2022. As of now, 6 participants (2 female and 4 male) have consented and enrolled in the study. Their baseline measurements have been completed, and they have started using iMove. The mean age of 6 participants is 56.8 years, and they were diagnosed with T2D for 9.4 years on average. Conclusions This study will inform the optimization of digital behavior change interventions to support people with T2D Sit Less and Move More to increase daily physical activity. This study will generate new evidence about the immediate effectiveness of sedentary behavior interventions, their active ingredients, and associated factors. Trial Registration Australian New Zealand Clinical Trial Registry ACTRN12622000426785; https://anzctr.org.au/Trial/Registration/TrialReview.aspx?id=383664 International Registered Report Identifier (IRRID) DERR1-10.2196/41502

show abstract

Section: Methodsmentioning

confidence: 99%

Just-In-Time Adaptive Intervention to Sit Less and Move More in People With Type 2 Diabetes: Protocol for a Microrandomized Trial

Daryabeygi-Khotbehsara¹,

Dunstan²,

Islam³

et al. 2023

JMIR Res Protoc

View full text Add to dashboard Cite

show abstract

“…Unknown model parameters for human behaviour models have been identified using system identification techniques [15,30,42]. System identification involves testing the response of a system to different inputs over time and using this data to estimate model parameters, or refine models.…”

Section: State Of the Artmentioning

confidence: 99%

“…In using existing models we are effectively trying to use a static model in a dynamic world. There is growing recognition of the need to develop computational models of behaviour that quantify interactions between states and how these relationships vary over time [15,18,41,42].…”

Section: Introductionmentioning

confidence: 99%

Persuasive Health

Wilson

Helal

Bull

et al. 2019

Proceedings of the 13th EAI International Conference on Pervasive Computing Technologies for Healthcare

View full text Add to dashboard Cite

With individual behaviour and lifestyle determining 30-50% of people's health, research and supportive technology for affecting behaviour alteration remain urgently needed. Most existing persuasive systems are designed to persuade a user to change a finite set of behaviours to achieve a specific goal. However, if the user's situation or goal changes, such systems cannot adapt to the changes. A much more robust type of persuasive system is needed today to enable adequate health navigation and to empower people to face and change their own realities in terms of a large variety of health behaviours and lifestyles. In this paper, we provide a perspective on the impressive body of work contributed over the past 15 years, to better look into the future of persuasive health and to the opportunities a broader theoretical framework and practical methodologies may bring about. We present a taxonomy that attempts to explain the contributions in this field including health behaviour theory, cybernetic actionbehaviour models, social cognitive theory, and control theory. We identify potentially promising approaches to advance persuasive health's efficacy in empowering individuals to improve their own health outcomes.

show abstract

A control system model of capability-opportunity-motivation and behaviour (COM-B) framework for sedentary and physical activity behaviours

Daryabeygi-Khotbehsara,

Dunstan,

Shariful Islam

et al. 2024

DIGITAL HEALTH

View full text Add to dashboard Cite

Objective Theoretical frameworks are essential for understanding behaviour change, yet their current use is inadequate to capture the complexity of human behaviour such as physical activity. Real-time and big data analytics can assist in the development of more testable and dynamic models of current theories. To transform current behavioural theories into more dynamic models, it is recommended that researchers adopt principles such as control systems engineering. In this article, we aim to describe a control system model of capability-opportunity-motivation and behaviour (COM-B) framework for reducing sedentary behaviour (SB) and increasing physical activity (PA) in adults. Methods The COM-B model is explained in terms of control systems. Examples of effective behaviour change techniques (BCTs) (e.g. goal setting, problem-solving and social support) for reducing SB and increasing PA were mapped to the COM-B model for illustration. Result A fluid analogy of the COM-B system is presented. Conclusions The proposed integrated model will enable empirical testing of individual behaviour change components (i.e. BCTs) and contribute to the optimisation of digital behaviour change interventions.

show abstract

System Identification of Just Walk: Using Matchable-Observable Linear Parametrizations

Cited by 5 publications

References 27 publications

Just-In-Time Adaptive Intervention to Sit Less and Move More in People With Type 2 Diabetes: Protocol for a Microrandomized Trial

Just-In-Time Adaptive Intervention to Sit Less and Move More in People With Type 2 Diabetes: Protocol for a Microrandomized Trial

Persuasive Health

A control system model of capability-opportunity-motivation and behaviour (COM-B) framework for sedentary and physical activity behaviours

Contact Info

Product

Resources

About