Bio


Yiwen Dong is a postdoc fellow at the Stanford Institute of Human-Centered Artificial Intelligence (HAI). Her research interest is human behavior characterization and health monitoring through their interactions with the physical environment. Her current work focuses on human and animal health monitoring through gait-induced floor vibrations.

While buildings are traditionally considered as passive and indifferent, her works allow the buildings to be both self-aware and user-aware. Yiwen developed systems that utilize ambient structural vibrations to infer human behaviors and health status, which enables many smart building applications such as in-home patient monitoring and elder care, intruder prevention and occupant management, animal health monitoring, and welfare. She strives for the next-generation intelligent infrastructures by exploring the potential of structural monitoring for human-centered purposes.

Yiwen has an interdisciplinary background in civil engineering, electrical engineering, and AI. Yiwen received her Master’s degree in Structural Engineering at Stanford University and her Bachelor’s degree in civil engineering at Nanyang Technological University. She won various awards (Best Paper Award, runner-ups in competitions) in ubiquitous computing and cyber-physical system conferences. She is passionate about combining the physical knowledge from the living environments, sensing approaches from cyber-physical systems, and data-driven models from machine learning to infer people’s behavior patterns and health status.

Honors & Awards


  • HAI Fellowship, Stanford HAI (2024)
  • Best Paper Award, IMAC 2024 (2024)
  • CEE Rising Star, MIT CEE Rising Star Committee (2023)
  • Centennial Teaching Assistant, Stanford University (2023)
  • 2nd Place, Dynamics Paper Competition, Engineering Mechanics Institute (06/09/2023)
  • Best Poster Award (runner-up), ACM BuildSys 2022 (11/10/2022)
  • Best Paper Award (runner-up), IMAC 2023 (02/16/2022)
  • Best Paper Award, Second Nurse Care Activity Recognition Challenge, HASCA Workshop, UbiComp 2020 (09/17/2020)
  • Gold Medal, Professional Engineers Board, Singapore (2018)
  • Dean’s List Excellent Academic Award, Nanyang Technological University, Singapore (2014-2018)
  • SM2 Scholarship, Ministry of Education, Singapore (2013)

Professional Education


  • Doctor of Philosophy, Stanford University, EE-PMN (2024)
  • Doctor of Philosophy, Stanford University, CEE-PHD (2024)
  • Master of Science, Stanford University, CEE-MS (2020)
  • B.Eng., Nanyang Technological University, Singapore, Civil Engineering (2018)
  • M.S., Stanford University, Structural Engineering (2020)

Stanford Advisors


All Publications


  • Ambient floor vibration sensing advances theaccessibility of functional gait assessments for children with muscular dystrophies. Scientific reports Dong, Y., Iammarino, M., Liu, J., Codling, J., Fagert, J., Mirshekari, M., Lowes, L., Zhang, P., Noh, H. Y. 2024; 14 (1): 10774

    Abstract

    Muscular dystrophies (MD) are a group of genetic neuromuscular disorders that cause progressive weakness and loss of muscles over time, influencing 1 in 3500-5000 children worldwide. New and exciting treatment options have led to a critical need for a clinical post-marketing surveillance tool to confirm the efficacy and safety of these treatments after individuals receive them in a commercial setting. For MDs, functional gait assessment is a common approach to evaluate the efficacy of the treatments because muscle weakness is reflected in individuals' walking patterns. However, there is little incentive for the family to continue to travel for such assessments due to the lack of access to specialty centers. While various existing sensing devices, such as cameras, force plates, and wearables can assess gait at home, they are limited by privacy concerns, area of coverage, and discomfort in carrying devices, which is not practical for long-term, continuous monitoring in daily settings. In this study, we introduce a novel functional gait assessment system using ambient floor vibrations, which is non-invasive and scalable, requiring only low-cost and sparsely deployed geophone sensors attached to the floor surface, suitable for in-home usage. Our system captures floor vibrations generated by footsteps from patients while they walk around and analyzes such vibrations to extract essential gait health information. To enhance interpretability and reliability under various sensing scenarios, we translate the signal patterns of floor vibration to pathological gait patterns related to MD, and develop a hierarchical learning algorithm that aggregates insights from individual footsteps to estimate a person's overall gait performance. When evaluated through real-world experiments with 36 subjects (including 15 patients with MD), our floor vibration sensing system achieves a 94.8% accuracy in predicting functional gait stages for patients with MD. Our approach enables accurate, accessible, and scalable functional gait assessment, bringing MD progressive tracking into real life.

    View details for DOI 10.1038/s41598-024-60034-5

    View details for PubMedID 38729999

  • Ubiquitous Gait Analysis through Footstep-Induced Floor Vibrations. Sensors (Basel, Switzerland) Dong, Y., Noh, H. Y. 2024; 24 (8)

    Abstract

    Quantitative analysis of human gait is critical for the early discovery, progressive tracking, and rehabilitation of neurological and musculoskeletal disorders, such as Parkinson's disease, stroke, and cerebral palsy. Gait analysis typically involves estimating gait characteristics, such as spatiotemporal gait parameters and gait health indicators (e.g., step time, length, symmetry, and balance). Traditional methods of gait analysis involve the use of cameras, wearables, and force plates but are limited in operational requirements when applied in daily life, such as direct line-of-sight, carrying devices, and dense deployment. This paper introduces a novel approach for gait analysis by passively sensing floor vibrations generated by human footsteps using vibration sensors mounted on the floor surface. Our approach is low-cost, non-intrusive, and perceived as privacy-friendly, making it suitable for continuous gait health monitoring in daily life. Our algorithm estimates various gait parameters that are used as standard metrics in medical practices, including temporal parameters (step time, stride time, stance time, swing time, double-support time, and single-support time), spatial parameters (step length, width, angle, and stride length), and extracts gait health indicators (cadence/walking speed, left-right symmetry, gait balance, and initial contact types). The main challenge we addressed in this paper is the effect of different floor types on the resultant vibrations. We develop floor-adaptive algorithms to extract features that are generalizable to various practical settings, including homes, hospitals, and eldercare facilities. We evaluate our approach through real-world walking experiments with 20 adults with 12,231 labeled gait cycles across concrete and wooden floors. Our results show 90.5% (RMSE 0.08s), 71.3% (RMSE 0.38m), and 92.3% (RMSPE 7.7%) accuracy in estimating temporal, spatial parameters, and gait health indicators, respectively.

    View details for DOI 10.3390/s24082496

    View details for PubMedID 38676114

    View details for PubMedCentralID PMC11053483

  • PigSense: Structural Vibration-based Activity and Health Monitoring System for Pigs ACM TRANSACTIONS ON SENSOR NETWORKS Dong, Y., Bonde, A., Codling, J. R., Bannis, A., Cao, J., Macon, A., Rohrer, G., Miles, J., Sharma, S., Brown-Brandl, T., Sangpetch, A., Sangpetch, O., Zhang, P., Noh, H. 2024; 20 (1)

    View details for DOI 10.1145/3604806

    View details for Web of Science ID 001153087600001

  • Characterizing the variability of footstep-induced structural vibrations for open-world person identification MECHANICAL SYSTEMS AND SIGNAL PROCESSING Dong, Y., Fagert, J., Noh, H. 2023; 204
  • Poster: Drive-by City Wide Trash Sensing for Neighborhood Sanitation Need Fernandez, T., Chang, Y., Codling, J., Dong, Y., Zhang, J., Joe-Wong, C., Noh, H., Zhang, P., Assoc Computing Machinery ASSOC COMPUTING MACHINERY. 2024: 704-705
  • Robust Person Identification Across Various Shoe Types Using Footstep-Induced Structural Vibrations Dong, Y., Sun, H., Wang, R., Noh, H., Glisic, B., Limongelli, M. P., Ng, C. T. SPIE-INT SOC OPTICAL ENGINEERING. 2024

    View details for DOI 10.1117/12.3010554

    View details for Web of Science ID 001239374700036

  • TelecomTM: A Fine-Grained and Ubiquitous Traffic Monitoring System Using Pre-Existing Telecommunication Fiber-Optic Cables as Sensors PROCEEDINGS OF THE ACM ON INTERACTIVE MOBILE WEARABLE AND UBIQUITOUS TECHNOLOGIES-IMWUT Liu, J., Yuan, S., Dong, Y., Biondi, B., Noh, H. 2023; 7 (2)

    View details for DOI 10.1145/3596262

    View details for Web of Science ID 001005382400019

  • Stranger Detection and Occupant Identification Using Structural Vibrations Dong, Y., Fagert, J., Zhang, P., Noh, H., Rizzo, P., Milazzo, A. SPRINGER-VERLAG SINGAPORE PTE LTD. 2023: 905-914
  • <i>FreePulse</i> Heart Rate Monitoring System using Ambient Structural Vibrations Codling, J. R., Shulkin, J., Dong, Y., Zhang, J., Latapie, H., Noh, H., Zhang, P., ACM ASSOC COMPUTING MACHINERY. 2023: 364-365
  • Characterizing Crowd Preferences on Stadium Facilities through Dynamic Inverse Reinforcement Learning Dong, Y., Huang, P., Noh, H., ACM ASSOC COMPUTING MACHINERY. 2023: 305-306
  • Poster Abstract: Integration of Physics-Based Building Model and Sensor Data to Develop an Adaptive Digital Twin Miao, B. H., Dong, Y., Wu, Z. Y., Alemdar, B. N., Zhang, P., Kohler, M. D., Noh, H., ACM ASSOC COMPUTING MACHINERY. 2022: 282-283
  • GaitVibe plus : Enhancing Structural Vibration-based Footstep Localization Using Temporary Cameras for In-home Gait Analysis Dong, Y., Liu, J., Noh, H., ACM ASSOC COMPUTING MACHINERY. 2022: 1168-1174
  • Re-Vibe: Vibration-based Indoor Person Re-Identification through Cross-Structure Optimal Transport Dong, Y., Zhu, J., Noh, H., ACM ASSOC COMPUTING MACHINERY. 2022: 348-352
  • MassHog: Weight-Sensitive Occupant Monitoring for Pig Pens using Actuated Structural Vibrations Codling, J. R., Bonde, A., Dong, Y., Cao, S., Sangpetch, A., Sangpetch, O., Noh, H., Zhang, P., ASSOC COMP MACHINERY ASSOC COMPUTING MACHINERY. 2021: 600-605
  • Social Distancing Compliance Monitoring for COVID-19 Recovery Through Footstep-Induced Floor Vibrations SenSys '21 Dong, Y., et al 2021: 399-400
  • Non-parametric Bayesian Learning for Newcomer Detection using Footstep-Induced Floor Vibration IPSN '21 Dong, Y., et al 2021: 404–405

    View details for DOI 10.1145/3412382.3458785

  • PigNet: Failure-Tolerant Pig Activity Monitoring System Using Structural Vibration IPSN '21: International Conference on Information Processing in Sensor Networks Bonde, A., Codling, J., Naruethep, K., Dong, Y., et al 2021: 328–340

    View details for DOI 10.1145/3412382.3458902

  • A window-based sequence-to-one approach with dynamic voting for nurse care activity recognition using acceleration-based wearable sensor UbiComp-ISWC '20 Dong, Y., et al 2020: 390–395

    View details for DOI 10.1145/3410530.3414336

  • MD-Vibe: physics-informed analysis of patient-induced structural vibration data for monitoring gait health in individuals with muscular dystrophy UbiComp-ISWC '20 Dong, Y., et al 2020: 525–531

    View details for DOI 10.1145/3410530.3414610