Yuntao Wang’s research focuses on the efficient sensing of behavioral and physiological data, alongside the design of intelligent interactive interfaces for mobile and wearable devices. His work primarily targets: 1) the development of robust and efficient sensing techniques that perform reliably on mainstream mobile and wearable devices, 2) the extraction of meaningful spatiotemporal patterns from multimodal sensory data, leveraging inherent correlations in natural human behaviors to accurately infer user interaction intentions, and 3) the design of novel interaction interfaces that achieve high recognition accuracy and inference efficiency, optimized for deployment on resource-constrained edge devices. He has published over 80 academic papers and received 9 international conference awards. Additionally, he holds 31 granted invention patents. His innovative achievements have been recognized with several prestigious honors, including the Wu Wenjun Artificial Intelligence Outstanding Youth Award (2024), the Young Elite Scientists Sponsorship Program of the China Association for Science and Technology (CAST, 2022), Leading Talent of the High-Level Innovation and Entrepreneurship Program of Qinghai Province (2024), and the First Prize of the China Electronics Institute Science and Technology Award (2019).
PhD in Computer Science and Technology (with honor), 2016
Tsinghua University
BSc in Computer Science and Technology (with honor), 2011
Beijing University of Posts and Telecommunications
Cough event detection is the foundation of any measurement associated with cough, one of the primary symptoms of pulmonary illnesses. This paper proposes HearCough, which enables continuous cough event detection on edge computing hearables, by leveraging always-on active noise cancellation (ANC) microphones in commodity hearables. Specifically, we proposed a lightweight end-to-end neural network model — Tiny-COUNET and its transfer learning based traning method. When evaluated on our acted cough event dataset, Tiny-COUNET achieved equivalent detection performance but required significantly less computational resources and storage space than cutting-edge cough event detection methods. Then we implemented HearCough by quantifying and deploying the pre-trained Tiny-COUNET to a popular micro-controller in consumer hearables. Lastly, we evaluated that HearCough is effective and reliable for continuous cough event detection through a field study with 8 patients. HearCough achieved 2 Hz cough event detection with an accuracy of 90.0% and an F1-score of 89.5% by consuming an additional 5.2 mW power. We envision HearCough as a low-cost add-on for future hearables to enable continuous cough detection and pulmonary health monitoring.
Face orientation can often indicate users’ intended interaction target. In this paper, we propose FaceOri, a novel face tracking technique based on acoustic ranging using earphones. FaceOri can leverage the speaker on a commodity device to emit an ultrasonic chirp, which is picked up by the set of microphones on the user’s earphone, and then processed to calculate the distance from each microphone to the device. These measurements are used to derive the user’s face orientation and distance with respect to the device. We conduct a ground truth comparison and user study to evaluate FaceOri’s performance. The results show that the system can determine whether the user orients to the device at a 93.5% accuracy within a 1.5 meters range. Furthermore, FaceOri can continuously track user’s head orientation with a median absolute error of 10.9 mm in the distance, 3.7° in yaw, and 5.8° in pitch. FaceOri can allow for convenient hands-free control of devices and produce more intelligent context-aware interactions.
In this paper, we present a novel mobile sensing system called MobilePhys, the first mobile personalized remote physiological sensing system, that leverages both front and rear cameras on a smartphone to generate high-quality self-supervised labels for training personalized contactless camera-based PPG models. To evaluate the robustness of MobilePhys, we conducted a user study with 39 participants who completed a set of tasks under different mobile devices, lighting conditions/intensities, motion tasks, and skin types. Our results show that MobilePhys significantly outperforms the state-of-the-art on-device supervised training and few-shot adaptation methods.
QWERTY is the primary smartphone text input keyboard configuration. However, insertion and substitution errors caused by hand tremors, often experienced by users with Parkinson’s disease, can severely affect typing efficiency and user experience. In this paper, we investigated Parkinson’s users’ typing behavior on smartphones. In particular, we identified and compared the typing characteristics generated by users with and without Parkinson’s symptoms. We then proposed an elastic probabilistic model for input prediction. By incorporating both spatial and temporal features, this model generalized the classical statistical decoding algorithm to correct insertion, substitution and omission errors, while maintaining direct physical interpretation. User study results confirmed that the proposed algorithm outperformed baseline techniques: users reached 22.8 WPM typing speed with a significantly lower error rate and higher user-perceived performance and preference. We concluded that our method could effectively improve the text entry experience on smartphones for users with Parkinson’s disease.
In this paper, we present FlexTouch, a technique that enables large-scale interaction sensing beyond the spatial constraints of capacitive touchscreens using passive low-cost conductive materials. This is achieved by customizing 2D circuit-like patterns with an array of conductive strips that can be easily attached to the sensing nodes on the edge of the touchscreen. FlexTouch requires no hardware modification, and is compatible with various conductive materials (copper foil tape, silver nanoparticle ink, ITO frames, and carbon paint), as well as fabrication methods (cutting, coating, and ink-jet printing). Through a series of studies and illustrative examples, we demonstrate that FlexTouch can support long-range touch sensing for up to 4 meters and everyday object presence detection for up to 2 meters. Finally, we show the versatility and feasibility of FlexTouch through applications such as body posture recognition, human-object interaction as well as enhanced fitness training experiences.
80+ conference or journal papers
49 patents (38 Chinese patents, 5 U.S patents, and 6 PCT WIPO patents)
38 Chinese patents,24 patents were granted:
6 granted PCT WIPO patents:
5 granted U.S. patents:
Academic Services
Organizer
Administrative Service
Volunteer