Behavioral Sensing and Intervention Paradigm: A Review of Closed-Loop Approaches for Ingestion Health
🤖 AI Summary
Current dietary health interventions predominantly rely on static guidance or manual logging, lacking dynamic sensing and real-time feedback capabilities. To address this gap, we propose a novel “eating-behavior closed-loop intervention” paradigm. Our work systematically reviews 136 studies to establish a comprehensive framework encompassing goal specification, multimodal sensing (wearable sensing, computer vision, and voice interaction), and dynamic intervention delivery. We introduce the first human–environment dual-dimensional sensing-intervention taxonomy, uncovering modality–behavior pairing design principles and critical research gaps. Furthermore, we formalize a structured behavioral closed-loop taxonomy and critically assess limitations of prevailing evaluation methodologies. The proposed framework integrates heterogeneous sensing modalities with real-time computation to enable adaptive, context-aware, and personalized interventions. Empirically grounded, it provides actionable design guidelines for next-generation real-time eating-health systems.
Application Category
📝 Abstract
Ingestive behavior plays a critical role in health, yet many existing interventions remain limited to static guidance or manual self-tracking. With the increasing integration of sensors and perceptual computing, recent systems have begun to support closed-loop interventions that dynamically sense user behavior and provide feedback during or around ingestion episodes. In this survey, we review 136 studies that leverage sensor-enabled or interaction-mediated approaches to influence eating behavior. We propose a behavioral closed-loop paradigm comprising three core components: target behaviors, sensing modalities, and feedback strategies. A taxonomy of sensing and intervention modalities is presented, organized along human- and environment-based dimensions. Our analysis also examines evaluation methods and design trends across different modality-behavior pairings. This review reveals prevailing patterns and critical gaps, offering design insights for future adaptive and context-aware ingestion health interventions.
Problem
Research questions and friction points this paper is trying to address.
Reviewing closed-loop approaches for dynamic ingestion behavior interventions
Analyzing sensor-based and interaction-mediated methods for eating behavior influence
Identifying gaps and trends in adaptive ingestion health intervention design
Innovation
Methods, ideas, or system contributions that make the work stand out.
Closed-loop interventions for dynamic behavior sensing
Sensor-enabled and interaction-mediated eating behavior influence
Taxonomy of human- and environment-based sensing modalities
🔎 Similar Papers
No similar papers found.
