publications

2025

1. ACM HEALTH

   

   Addressing Cohort Variability with Adaptive Fusion of Wearable and Clinical Data: A Case Study in Predicting Pancreatic Surgery Outcomes

   Jingwen Zhang, Ruiqi Wang, Ziqi Xu, Hanyang Liu, Jorge Rodriguez, Heidy Cos, Rohit Srivastava, Lacey Raper, Dominic Sanford, Chet Hammill, and 1 more author

   ACM Transactions on Computing for Healthcare, 2025
2. UbiComp 2026

   

   CHEF-VL: Detecting Cognitive Sequencing Errors in Cooking with Vision-language Models

   Ruiqi Wang, Peiqi Gao, Patrick John Lynch, Tingjun Liu, Yejin Lee, Carolyn Baum, Lisa Tabor Connor, and Chenyang Lu

   Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, Dec 2025

   To be presented at UbiComp / ISWC 2026.

   Abs DOI Bib

   Minimally obtrusive support for individuals with subjective cognitive decline (SCD) is important for fostering independence in completing daily tasks. In overseeing these tasks, occupational therapists may choose to help as errors arise and provide corrective courses of action. To accomplish this, therapists must be able to recognize task-specific actions, as well as the appropriate sequence for them to occur. However, manual monitoring by therapists is not always feasible in real-world environments, motivating the need for automated systems capable of recognizing actions and detecting sequencing errors. To address this, we present CHEF-VL, an online Cognitive Human Error Detection Framework with Vision-Language Models in smart kitchen environments. CHEF-VL combines two novel vision-language models, with one fine-tuned for online human action recognition and the other specially engineered to track key environmental states. An Action-State Merger integrates these two streams of information to reduce prediction noise and correct misrecognized actions. A two-year occupational therapy project of over 100 participants with and without SCD was organized to collect video data for task evaluation. Empirical results demonstrate that CHEF-VL improves both action recognition and sequencing error detection performance, offering a promising solution for real-world assistive technologies in smart home settings.

   @article{wang2025chefvl,
     author = {Wang, Ruiqi and Gao, Peiqi and Lynch, Patrick John and Liu, Tingjun and Lee, Yejin and Baum, Carolyn and Connor, Lisa Tabor and Lu, Chenyang},
     title = {CHEF-VL: Detecting Cognitive Sequencing Errors in Cooking with Vision-language Models},
     journal = {Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies},
     year = {2025},
     volume = {9},
     number = {4},
     articleno = {220},
     month = dec,
     doi = {10.1145/3770714},
     url = {https://doi.org/10.1145/3770714},
     publisher = {ACM New York, NY, USA},
     address = {New York, NY, USA},
     note = {<a href="https://dl.acm.org/journal/imwut" style="color: #0047AB; font-weight: bold;">To be presented at UbiComp / ISWC 2026.</a>},
   }

3. EMSOFT 2025

   

   Real-Time Video-Based Human Action Recognition on Embedded Platforms

   Ruiqi Wang, Zichen Wang, Peiqi Gao, Mingzhen Li, Jaehwan Jeong, Yihang Xu, Yejin Lee, Carolyn Baum, Lisa Connor, and Chenyang Lu

   ACM Transactions on Embedded Computing Systems (SPECIAL ISSUE ESWEEK 2025), Sep 2025

   2025 ACM SIGBED International Conference on Embedded Software (EMSOFT).

   Abs DOI Bib HTML Code

   Advances in computer vision and deep learning have made video-based Human Action Recognition (HAR) increasingly feasible. However, running HAR on live video streams encounters significant delays on embedded platforms due to computational demands. This work addresses real-time HAR performance challenges through four key contributions: (1) an experimental study identifying standard Optical Flow (OF) extraction as the primary latency bottleneck in a state-of-the-art HAR pipeline, (2) an analysis of the latency-accuracy trade-off between traditional and deep learning-based OF methods, underscoring the need for an efficient motion feature extractor with minimal impact on accuracy, (3) the design of Integrated Motion Feature Extractor (IMFE), a novel unified neural network architecture that substantially reduces motion feature extraction latency, and (4) the development of RT-HARE, a real-time HAR system optimized for embedded platforms. Experiments on three benchmark datasets of various characteristics using the Nvidia Jetson Xavier NX platform demonstrate that RT-HARE achieves real-time HAR with lower and more stable latency, reduced power consumption, and a smaller memory footprint while maintaining recognition accuracy comparable to more complex server-based HAR models.

   @article{wang2025real,
     author = {Wang, Ruiqi and Wang, Zichen and Gao, Peiqi and Li, Mingzhen and Jeong, Jaehwan and Xu, Yihang and Lee, Yejin and Baum, Carolyn and Connor, Lisa and Lu, Chenyang},
     title = {Real-Time Video-Based Human Action Recognition on Embedded Platforms},
     year = {2025},
     issue_date = {November 2025},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     volume = {24},
     number = {5s},
     issn = {1539-9087},
     url = {https://doi.org/10.1145/3761795},
     doi = {10.1145/3761795},
     journal = {ACM Transactions on Embedded Computing Systems (SPECIAL ISSUE ESWEEK 2025)},
     month = sep,
     articleno = {135},
     numpages = {24},
     keywords = {Human action recognition, embedded and real-time systems, machine learning systems, computer vision, latency optimization},
     note = {<a href="https://esweek.org/schedule/" style="color: #0047AB; font-weight: bold;">2025 ACM SIGBED International Conference on Embedded Software (EMSOFT).</a>},
   }

2024

1. SEC 2024

   

   Optimizing Edge Offloading Decisions for Object Detection

   Jiaming Qiu, Ruiqi Wang, Brooks Hu, Roch Guérin, and Chenyang Lu

   In 2024 IEEE/ACM Symposium on Edge Computing (SEC), Sep 2024

   Abs DOI arXiv Bib HTML Code

   Recent advances in machine learning and hardware have produced embedded devices capable of performing real-time object detection with commendable accuracy. We consider a scenario in which embedded devices rely on an onboard object detector, but have the option to offload detection to a more powerful edge server when local accuracy is deemed too low. Resource constraints, however, limit the number of images that can be offloaded to the edge. Our goal is to identify which images to offload to maximize overall detection accuracy under those constraints. To that end, the paper introduces a reward metric designed to quantify potential accuracy improvements from offloading individual images, and proposes an efficient approach to make offloading decisions by estimating this reward based only on local detection results. The approach is computationally frugal enough to run on embedded devices, and empirical findings indicate that it outperforms existing alternatives in improving detection accuracy even when the fraction of offloaded images is small. Code for the paper’s solution is available at https://github.com/qiujiaming315/edgeml-object-detection.

   @inproceedings{qiu2024optimizing,
     author = {Qiu, Jiaming and Wang, Ruiqi and Hu, Brooks and Guérin, Roch and Lu, Chenyang},
     booktitle = {2024 IEEE/ACM Symposium on Edge Computing (SEC)},
     title = {Optimizing Edge Offloading Decisions for Object Detection},
     year = {2024},
     volume = {},
     number = {},
     pages = {164-177},
     organization = {IEEE},
     keywords = {Accuracy;Correlation;Image edge detection;System performance;Estimation;Detectors;Object detection;Real-time systems;Servers;Edge computing;edge AI;object detection;embedded machine learning;distributed computing},
     doi = {10.1109/SEC62691.2024.00021},
   }

2. Infection Control
   & Hospital
   Epidemiology

   

   Leveraging Bluetooth low-energy technology to improve contact tracing among healthcare personnel in hospital setting during the coronavirus disease 2019 (COVID-19) pandemic

   M. Cristina Vazquez Guillamet, Ashraf Rjob, Jingwen Zhang, Ruixuan Dai, Ruiqi Wang, Christopher Damulira, Reshad Hamauon, Jeff Candell, Jennie H. Kwon, Hilary Babcock, and 1 more author

   Infection Control & Hospital Epidemiology, Sep 2024

   Abs DOI HTML

   To improve contact tracing for healthcare workers, we built and configured a Bluetooth low-energy system. We predicted close contacts with great accuracy and provided an additional contact yield of 14.8%. This system would decrease the effective reproduction number by 56% and would unnecessarily quarantine 0.74% of employees weekly.

2023

1. RTSS 2023
   Best Student
   Paper Award

   

   Progressive Neural Compression for Adaptive Image Offloading Under Timing Constraints

   Ruiqi Wang, Hanyang Liu, Jiaming Qiu, Moran Xu, Roch Guérin, and Chenyang Lu

   In 2023 IEEE Real-Time Systems Symposium (RTSS), Sep 2023

   Best Student Paper Award

   Awarded Abs DOI arXiv Bib HTML Code

   Best Student Paper Award

   IoT devices are increasingly the source of data for machine learning (ML) applications running on edge servers. Data transmissions from devices to servers are often over local wireless networks whose bandwidth is not just limited but, more importantly, variable. Furthermore, in cyber-physical systems interacting with the physical environment, image offloading is also commonly subject to timing constraints. It is, therefore, important to develop an adaptive approach that maximizes the inference performance of ML applications under timing constraints and the resource constraints of IoT devices. In this paper, we use image classification as our target application and propose progressive neural compression (PNC) as an efficient solution to this problem. Although neural compression has been used to compress images for different ML applications, existing solutions often produce fixed-size outputs that are unsuitable for timing-constrained offloading over variable bandwidth. To address this limitation, we train a multi-objective rateless autoencoder that optimizes for multiple compression rates via stochastic taildrop to create a compression solution that produces features ordered according to their importance to inference performance. Features are then transmitted in that order based on available bandwidth, with classification ultimately performed using the (sub)set of features received by the deadline. We demonstrate the benefits of PNC over state-of-the-art neural compression approaches and traditional compression methods on a testbed comprising an IoT device and an edge server connected over a wireless network with varying bandwidth.

   @inproceedings{10405983,
     author = {Wang, Ruiqi and Liu, Hanyang and Qiu, Jiaming and Xu, Moran and Guérin, Roch and Lu, Chenyang},
     booktitle = {2023 IEEE Real-Time Systems Symposium (RTSS)},
     title = {Progressive Neural Compression for Adaptive Image Offloading Under Timing Constraints},
     year = {2023},
     volume = {},
     number = {},
     pages = {118-130},
     keywords = {Performance evaluation;Image coding;Image edge detection;Bandwidth;Timing;Internet of Things;Servers;neural compression;edge offloading;image classification;real-time transmission},
     doi = {10.1109/RTSS59052.2023.00020},
     note = {<span style="color: #EA6329; font-weight: bold;">Best Student Paper Award</span>},
   }

2. UbiComp 2023

   

   Contact Tracing for Healthcare Workers in an Intensive Care Unit

   Jingwen Zhang, Ruixuan Dai, Ashraf Rjob, Ruiqi Wang, Reshad Hamauon, Jeffrey Candell, Thomas Bailey, Victoria J. Fraser, Maria Cristina Vazquez Guillamet, and Chenyang Lu

   Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., Sep 2023

   Abs DOI Bib HTML

   Contact tracing is a powerful tool for mitigating the spread of COVID-19 during the pandemic. Front-line healthcare workers are particularly at high risk of infection in hospital units. This paper presents ContAct TraCing for Hospitals (CATCH), an automated contact tracing system designed specifically for healthcare workers in hospital environments. CATCH employs distributed embedded devices placed throughout a hospital unit to detect close contacts among healthcare workers wearing Bluetooth Low Energy (BLE) beacons. We first identify a set of distinct contact tracing scenarios based on the diverse environmental characteristics of a real-world intensive care unit (ICU) and the different working patterns of healthcare workers in different spaces within the unit. We then develop a suite of novel contact tracing methods tailored for each scenario. CATCH has been deployed and evaluated in the ICU of a major medical center, demonstrating superior accuracy in contact tracing over existing approaches through a wide range of experiments. Furthermore, the real-world case study highlights the effectiveness and efficiency of CATCH compared to standard contact tracing practices.

   @article{10.1145/3610924,
     author = {Zhang, Jingwen and Dai, Ruixuan and Rjob, Ashraf and Wang, Ruiqi and Hamauon, Reshad and Candell, Jeffrey and Bailey, Thomas and Fraser, Victoria J. and Guillamet, Maria Cristina Vazquez and Lu, Chenyang},
     title = {Contact Tracing for Healthcare Workers in an Intensive Care Unit},
     year = {2023},
     issue_date = {September 2023},
     publisher = {Association for Computing Machinery},
     address = {New York, NY, USA},
     volume = {7},
     number = {3},
     url = {https://doi.org/10.1145/3610924},
     doi = {10.1145/3610924},
     journal = {Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.},
     month = sep,
     articleno = {141},
     numpages = {23},
     keywords = {Internet of things (IoT), Bluetooth Low Energy, Contact Tracing, Covid-19},
   }

2022

1. EMSOFT 2022

   

   Adaptive Edge Offloading for Image Classification Under Rate Limit

   Jiaming Qiu, Ruiqi Wang, Ayan Chakrabarti, Roch Guerin, and Chenyang Lu

   IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, Nov 2022

   Abs DOI arXiv Bib HTML Code

   This article considers a setting where embedded devices are used to acquire and classify images. Because of limited computing capacity, embedded devices rely on a parsimonious classification model with uneven accuracy. When local classification is deemed inaccurate, devices can decide to offload the image to an edge server with a more accurate but resource-intensive model. Resource constraints, e.g., network bandwidth, however, require regulating such transmissions to avoid congestion and high latency. This article investigates this offloading problem when transmissions regulation is through a token bucket, a mechanism commonly used for such purposes. The goal is to devise a lightweight, online offloading policy that optimizes an application-specific metric (e.g., classification accuracy) under the constraints of the token bucket. This article develops a policy based on a deep Q-network (DQN), and demonstrates both its efficacy and the feasibility of its deployment on embedded devices. Of note is the fact that the policy can handle complex input patterns, including correlation in image arrivals and classification accuracy. The evaluation is carried out by performing image classification over a local testbed using synthetic traces generated from the ImageNet image classification benchmark.

   @article{article,
     author = {Qiu, Jiaming and Wang, Ruiqi and Chakrabarti, Ayan and Guerin, Roch and Lu, Chenyang},
     year = {2022},
     month = nov,
     pages = {1-1},
     title = {Adaptive Edge Offloading for Image Classification Under Rate Limit},
     volume = {41},
     journal = {IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems},
     doi = {10.1109/TCAD.2022.3197533},
   }