skip to main content


Search for: All records

Creators/Authors contains: "Peng, Zhencan"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Knowing the object grabbed by a hand can offer essential contextual information for interaction between the human and the physical world. This paper presents a novel system, ViObject, for passive object recognition that uses accelerometer and gyroscope sensor data from commodity smartwatches to identify untagged everyday objects. The system relies on the vibrations caused by grabbing objects and does not require additional hardware or human effort. ViObject's ability to recognize objects passively can have important implications for a wide range of applications, from smart home automation to healthcare and assistive technologies. In this paper, we present the design and implementation of ViObject, to address challenges such as motion interference, different object-touching positions, different grasp speeds/pressure, and model customization to new users and new objects. We evaluate the system's performance using a dataset of 20 objects from 20 participants and show that ViObject achieves an average accuracy of 86.4%. We also customize models for new users and new objects, achieving an average accuracy of 90.1%. Overall, ViObject demonstrates a novel technology concept of passive object recognition using commodity smartwatches and opens up new avenues for research and innovation in this area.

     
    more » « less
    Free, publicly-accessible full text available March 6, 2025
  2. Wearable devices like smartwatches and smart wristbands have gained substantial popularity in recent years. However, their small interfaces create inconvenience and limit computing functionality. To fill this gap, we propose ViWatch, which enables robust finger interactions under deployment variations, and relies on a single IMU sensor that is ubiquitous in COTS smartwatches. To this end, we design an unsupervised Siamese adversarial learning method. We built a real-time system on commodity smartwatches and tested it with over one hundred volunteers. Results show that the system accuracy is about 97% over a week. In addition, it is resistant to deployment variations such as different hand shapes, finger activity strengths, and smartwatch positions on the wrist. We also developed a number of mobile applications using our interactive system and conducted a user study where all participants preferred our unsupervised approach to supervised calibration. The demonstration of ViWatch is shown at https://youtu.be/N5-ggvy2qfI. 
    more » « less
  3. Recent studies show that large language models (LLM) unintendedly memorize part of the training data, which brings serious privacy risks. For example, it has been shown that over 1% of tokens generated unprompted by an LLM are part of sequences in the training data. However, current studies mainly focus on the exact memorization behaviors. In this paper, we propose to evaluate how many generated texts have near-duplicates (e.g., only differ by a couple of tokens out of 100) in the training corpus. A major challenge of conducting this evaluation is the huge computation cost incurred by near-duplicate sequence searches. This is because modern LLMs are trained on larger and larger corpora with up to 1 trillion tokens. What's worse is that the number of sequences in a text is quadratic to the text length. To address this issue, we develop an efficient and scalable near-duplicate sequence search algorithm in this paper. It can find (almost) all the near-duplicate sequences of the query sequence in a large corpus with guarantees. Specifically, the algorithm generates and groups the min-hash values of all the sequences with at least t tokens (as very short near-duplicates are often irrelevant noise) in the corpus in linear time to the corpus size. We formally prove that only 2 n+1/t+1 -1 min-hash values are generated for a text with n tokens in expectation. Thus the index time and size are reasonable. When a query arrives, we find all the sequences sharing enough min-hash values with the query using inverted indexes and prefix filtering. Extensive experiments on a few large real-world LLM training corpora show that our near-duplicate sequence search algorithm is efficient and scalable.

     
    more » « less