mlsanityData to 14 Oct 2026

WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch

arXiv 2502.05783 ↗First posted 9 Feb 2025cs.HC cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

While just-in-time interventions (JITIs) have effectively targeted common health behaviors, individuals often have unique needs to intervene in personal undesirable actions that can negatively affect physical, mental, and social well-being. We present WatchGuardian, a smartwatch-based JITI system that empowers users to define custom interventions for these personal actions with a small number of samples. For the model to detect new actions based on limited new data samples, we developed a few-shot learning pipeline that finetuned a pre-trained inertial measurement unit (IMU) model on public hand-gesture datasets. We then designed a data augmentation and synthesis process to train additional classification layers for customization. Our offline evaluation with 26 participants showed that with three, five, and ten examples, our approach achieved an average accuracy of 76.8%, 84.7%, and 87.7%, and an F1 score of 74.8%, 84.2%, and 87.2% We then conducted a four-hour intervention study to compare WatchGuardian against a rule-based intervention. Our results demonstrated that our system led to a significant reduction by 64.0 +- 22.6% in undesirable actions, substantially outperforming the baseline by 29.0%. Our findings underscore the effectiveness of a customizable, AI-driven JITI system for individuals in need of behavioral intervention in personal undesirable actions. We envision that our work can inspire broader applications of user-defined personalized intervention with advanced AI solutions.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 26 of its 162 references that are in the map. First posted on arXiv 9 Feb 2025.

Builds on

26 of 162 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  3. 2019Self-supervised Visual Feature Learning with Deep Neural Networks: A Surveycited by 657
  4. 2017Data Augmentation of Wearable Sensor Data for Parkinson's Disease Monitoring using Convolutional Neural Networkscited by 131
  5. 2019Multi-task Self-Supervised Learning for Human Activity Detectioncited by 102
  6. 2022Self-supervised Learning for Human Activity Recognition Using 700,000 Person-days of Wearable Datacited by 75
  7. 2019Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activitycited by 70
  8. 2016Recognizing Detailed Human Context In-the-Wild from Smartphones and Smartwatchescited by 42
  9. 2022Data Augmentation techniques in time series domain: A survey and taxonomycited by 41
  10. 2021Designing AI for Trust and Collaboration in Time-Constrained Medical Decisions: A Sociotechnical Lenscited by 35
  11. 2024IMUGPT 2.0: Language-Based Cross Modality Transfer for Sensor-Based Human Activity Recognitioncited by 22
  12. 2020Near-Tight Margin-Based Generalization Bounds for Support Vector Machinescited by 19
14 more
  1. 2020Online Few-shot Gesture Learning on a Neuromorphic Processorcited by 18
  2. 2020FS-HGR: Few-shot Learning for Hand Gesture Recognition via ElectroMyographycited by 17
  3. 2023Accuracy-Time Tradeoffs in AI-Assisted Decision Making under Time Pressurecited by 17
  4. 2023MindShift: Leveraging Large Language Models for Mental-States-Based Problematic Smartphone Use Interventioncited by 16
  5. 2022Enabling hand gesture customization on wrist-worn devicescited by 15
  6. 2018On PAC-Bayesian Bounds for Random Forestscited by 10
  7. 2020Detecting Receptivity for mHealth Interventions in the Natural Environmentcited by 8
  8. 2024EchoWrist: Continuous Hand Pose Tracking and Hand-Object Interaction Recognition Using Low-Power Active Acoustic Sensing On a Wristbandcited by 8
  9. 2024Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Interventioncited by 5
  10. 2024InteractOut: Leveraging Interaction Proxies as Input Manipulation Strategies for Reducing Smartphone Overusecited by 4
  11. 2024GesturePrint: Enabling User Identification for mmWave-based Gesture Recognition Systemscited by 4
  12. 2023Enabling Voice-Accompanying Hand-to-Face Gesture Recognition with Cross-Device Sensingcited by 3
  13. 2021Anticipatory Detection of Compulsive Body-focused Repetitive Behaviors with Wearablescited by 2
  14. 2024Wearable Sensor-Based Few-Shot Continual Learning on Hand Gestures for Motor-Impaired Individuals via Latent Embedding Exploitationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wildcited by 10
  2. 2026Proactive Service Agents: A Unified Decision Framework, Methods, and Evaluationcited by 2
  3. 2026Attack by Unlearning: Unlearning-Induced Adversarial Attacks on Graph Neural Networkscited by 1
  4. 2025FM-FoG: A Real-Time Foundation Model-based Wearable System for Freezing-of-Gait Mitigationcited by 0