XJXiayan Ji

Xiayan Ji

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiayan Ji has a total of 19 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    SMILE: Sensor Data-driven Detection and Counterfactual Pattern Analysis for Loneliness in Older Adults

    by Xiayan Ji, Ahhyun Yuh, Viktor Erdélyi, Teruhiro Mizumoto, Hyonyoung Choi, Sean Harrison, Emma Cho, Takashi Suehiro, Takeshi Nakagawa, Yutian Cheng, et al.

    Prolonged loneliness in older adults increases the risk of dementia, cardiovascular diseases, and premature death. However, timely detection and behavioral pattern analysis are challenging due to the slow progression of loneliness and diverse individual lifestyles. To address these barriers, we propose SMILE, an end-to-end framework for sensor-driven detection and counterfactual pattern analysis of loneliness. Our approach uses non-intrusive sensors to passively observe behavior and build a personalized profile over time. When SMILE detects meaningful changes in activity patterns, it employs generative models to produce counterfactual sensor profiles—synthetic representations of behavior predicted to result in lower loneliness scores. Suggested pattern changes are identified as the difference between observed and counterfactual profiles, highlighting the behaviors most associated with loneliness. We conducted a 6-month feasibility study with 18 participants from the United States and 15 from Japan to develop and evaluate SMILE. Our framework integrates a Time-series Transformer (TST) model for loneliness detection, which achieved 96.25% accuracy, and a diffusion model for generating behavioral explanations, which outperformed a baseline by up to 76.69%. These findings highlight the potential of SMILE to support sensor-driven, personalized loneliness detection and behavioral explanation in aging populations.


  • Open Access

    Exploring Effective Sensing Indicators of Loneliness For Elderly Community in US and Japan

    by Xiayan Ji, Ahhyun Yuh, Viktor Erdélyi, Teruhiro Mizumoto, Hyonyoung Choi, Sean Lee Harrison, Emma Cho, James Weimer, Hajime Nagahara, Teruo Higashino, et al.

    Loneliness has long affected the elderly community. This issue is significantly worsened by the social isolation resulting from the COVID-19 pandemic. To address this pressing issue, we employed a sensor-based methodology to predict loneliness and potentially inform interventions. We deployed sensors in the residences of 22 elderly participants from US and Japan, gathering daily activities data through 22 sensor features. Given the extensive feature set, we identify the most effective sensors to ensure unobtrusiveness while upholding privacy. Regression analysis of these features revealed that our best-performing Random Forest model achieved an R2 value of 0.86, on par with existing literature. In addition, we found that the sleep mattress sensor and temperature-humidity sensor were particularly indicative of loneliness. In summary, our research contributes to the HCI literature with effective non-invasive sensing modalities in assessing elderly loneliness, together with insights from our real-world sensor deployments in US and Japan-based elderly communities.


  • Open Access

    Short: Integrated Sensing Platform for Detecting Social Isolation and Loneliness In the Elderly Community

    by Xiayan Ji, Xian Li, Ahhyun Yuh, Claire Kendell, Amanda Watson, James Weimer, Hajime Nagahara, Teruo Higashino, Teruhiro Mizumoto, Viktor Erdelyi, et al.

    Social isolation is an objective absence or paucity of contacts and interactions between a person and a social network. Loneliness is a subjective feeling of being alone, separated, or apart from others. These two highly correlated mental health concerns significantly increase the elderly's risk of premature death from all causes, a risk that may rival those of smoking, obesity, and physical inactivity. In this work, we propose an integrated design for technology usage to tackle the aforementioned mental healthcare concerns involving the elderly community. The technology infrastructure is an Internet-of-Things (IoT) monitoring system aiming to detect social isolation and promptly predict the risk of loneliness. With our system, interventions can be developed to maintain the mental well-being of the elderly, a salient need due to the social disruptions incurred by COVID-19.


  • Open Access

    iCareLoop: Closed-Loop Sensing and Intervention for Gerontological Social Isolation and Loneliness

    by Xiayan Ji, Ahhyun Yuh, Hyonyoung Choi, Amanda Watson, Claire Kendell, Xian Li, James Weimer, Hajime Nagahara, Teruo Higashino, Teruhiro Mizumoto, et al.

    Social isolation refers to a lack of social contact and interaction, while loneliness is the subjective feeling of being alone. These two mental health concerns are highly correlated and can significantly increase the risk of premature death in the elderly. In fact, this risk may even rival that of smoking, obesity, and physical inactivity. To address this issue, we propose iCareLoop, a closed-loop decision support system with clinician-in-the-loop actuation to mitigate gerontological social isolation and loneliness. By implementing targeted interventions, this system can help maintain the mental well-being of elderly individuals, which is particularly crucial given the social disruptions caused by the COVID-19 pandemic.


  • Open Access

    Incremental Anomaly Detection with Guarantee in the Internet of Medical Things

    by Xiayan Ji, Hyonyoung Choi, Oleg Sokolsky, Insup Lee

    The Internet of Medical Things (IoMT), aided by learning-enabled components, is becoming increasingly important in health monitoring. However, the IoMT-based system must be highly reliable since it directly interacts with the patients. One critical function for facilitating reliable IoMT is anomaly detection, which involves sending alerts when a medical device’s usage pattern deviates from normal behavior. Due to the safety-critical nature of IoMT, the anomaly detectors are expected to have consistently high accuracy and low error, ideally being bounded with a guarantee. Besides, since the IoMT-based system is non-stationary, the anomaly detector and the performance guarantee should adapt to the evolving data distributions. To tackle these challenges, we propose a framework for incremental anomaly detection in IoMT with a Probably Approximately Correct (PAC)-based two-sided guarantee, guided by a human-in-the-loop design to accommodate shifts in anomaly distributions. As a result, our framework can improve detection performance and provide a tight guarantee on False Alarm Rate (FAR) and Miss Alarm Rate (MAR). We demonstrate the effectiveness of our design using synthetic data and the real-world IoMT monitoring platform VitalCore.