Hyonyoung Choi

Hyonyoung Choi

Auto-generated profile, based on publicly available information

Hyonyoung Choi

University of Pennsylvania, Philadelphia, Pennsylvania, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 October 2016
Verified
Conference Paper
Open access
HCHyon-Young Choi
Hyon-Young Choi
AKAndrew L. King
Andrew L. King
ILInsup Lee
Insup Lee
An increasing amount of distributed real-time systems and other critical infrastructure now rely on Data Distribution Service (DDS) middleware for timely dissementation of data between system nodes. While DDS has been designed specifically for use in distributed real-time systems and exposes a number of QoS properties to programmers, DDS fails to lift time fully into the programming abstraction. The reason for this is simple: DDS cannot directly control the underlying network to ensure that messages always arrive to their destination on time. In this paper we describe a prototype system that uses the OpenFlow SDN protocol to automatically and transparently learn the QoS requirements of DDS participants. Based on the QoS requirements, our system will manipulate the low-level packet forwarding rules in the network to ensure that the QoS requirements are always satisfied. We use real OpenFlow hardware to evaluate how well our prototype is able to manage network contention and guarantee the requested QoS. Additionally, we evaluate how well the reliability and resilience features of a real DDS implementation is able to compensate for network contention on an unmanaged (i.e., normal) ethernet. To the best of our knowledge, this is the first evaluation of performance DDS under extreme network contention conditions.

9 May 2023
Verified
Conference Paper
Open access
XJXiayan Ji
Xiayan Ji
HCHyonyoung Choi
Hyonyoung Choi
OSOleg Sokolsky
Oleg Sokolsky
ILInsup Lee
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.

11 May 2024
Verified
Conference Paper
Open access
XJXiayan Ji
Xiayan Ji
AYAhhyun Yuh
Ahhyun Yuh
VEViktor Erdélyi
Viktor Erdélyi
TMTeruhiro Mizumoto
Teruhiro Mizumoto
HCHyonyoung Choi
Hyonyoung Choi
ILInsup Lee
Insup Lee
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.

18 May 2021
Verified
Conference Paper
Open access
AWAmanda Watson
Amanda Watson
HCHyonyoung Choi
Hyonyoung Choi
ILInsup Lee
Insup Lee
JWJames Weimer
James Weimer
For researchers, especially in remote health monitoring and ubiquitous computing, it is common to expend a significant amount of time and effort to develop data collection systems that can be used outside of the lab or clinic. These systems tend to be customized and highly specific to the task at hand; thus, they are not general enough to support other tasks. In this paper, we present Raproto, an open-source, easy-to-use rapid prototyping platform that facilitates data collection and visualization from sensors on commercially available, off-the-shelf smartwatches. The Raproto platform consists of three components: the smartwatch, communication protocol, and server. These components support the collection, transmission, storage, analysis, and visualization of data. We evaluate our platform on limiting factors including the smartwatch battery life, data loss during transmission, and data latency. Overall, we find that the smartwatch can last for over 24 hours on a single charge, has little to no data loss, and less than a second of data latency per transmission.

6 April 2026 in ACM Transactions on Computing for Healthcare
Verified
Journal Article
Open access
XJXiayan Ji
Xiayan Ji
AYAhhyun Yuh
Ahhyun Yuh
VEViktor Erdélyi
Viktor Erdélyi
TMTeruhiro Mizumoto
Teruhiro Mizumoto
HCHyonyoung Choi
Hyonyoung Choi
ILInsup Lee
Insup Lee
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.

9 May 2023
Verified
Conference Paper
Open access
XJXiayan Ji
Xiayan Ji
AYAhhyun Yuh
Ahhyun Yuh
HCHyonyoung Choi
Hyonyoung Choi
AWAmanda Watson
Amanda Watson
CKClaire Kendell
Claire Kendell
ILInsup Lee
Insup Lee
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.