WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929705966370816 |
|---|---|
| author | Lei, Ying Cao, Yancheng Wang, Will Dong, Yuanzhe Yin, Changchang Cao, Weidan Zhang, Ping Yang, Jingzhen Yao, Bingsheng Peng, Yifan Weng, Chunhua Auerbach, Randy Mamykina, Lena Wang, Dakuo Wang, Yuntao Xu, Xuhai |
| author_facet | Lei, Ying Cao, Yancheng Wang, Will Dong, Yuanzhe Yin, Changchang Cao, Weidan Zhang, Ping Yang, Jingzhen Yao, Bingsheng Peng, Yifan Weng, Chunhua Auerbach, Randy Mamykina, Lena Wang, Dakuo Wang, Yuntao Xu, Xuhai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_05783 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch Lei, Ying Cao, Yancheng Wang, Will Dong, Yuanzhe Yin, Changchang Cao, Weidan Zhang, Ping Yang, Jingzhen Yao, Bingsheng Peng, Yifan Weng, Chunhua Auerbach, Randy Mamykina, Lena Wang, Dakuo Wang, Yuntao Xu, Xuhai Human-Computer Interaction Artificial Intelligence Machine Learning 68U35 H.5.2; I.2.1 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. |
| title | WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch |
| topic | Human-Computer Interaction Artificial Intelligence Machine Learning 68U35 H.5.2; I.2.1 |
| url | https://arxiv.org/abs/2502.05783 |