Our Work

This is our Project Page. It mainly showcases the past research achievements of our research group.

This study presents a wireless IoT motion sensor (2g) for mice, allowing continuous motion data collection for several days without causing stress to the animals. With a combined segmentation method and imbalanced learning process, the sensor achieves a 94.55% macro-recall in recognizing common mouse behaviors (resting, walking, rearing, digging, eating, grooming, drinking water, and scratching) in cages. This technology offers an improved and less intrusive method for tracking motion behaviors in scientific research compared to existing techniques.

Liu, Y., Chen, M., Chan, C., Chan, H. Y., Wang, J., Yu, X., ... & Li, W. J. (2023). AI‐Enabled Micro Motion Sensors for Revealing the Random Daily Activities of Caged Mice. Advanced Intelligent Systems, 5(4), 2200220.

Chen, M., Szu, H. F., Lin, H. Y., Liu, Y., Chan, H. Y., Wang, Y., ... & Li, W. J. (2023). Phase-based Quantification of Sports Performance Metrics Using a Smart IoT Sensor. IEEE Internet of Things Journal.

DOI: 10.1109/JIOT.2023.3266351

This study introduces a smart Internet-of-Things wristband motion sensor for data-based sports performance evaluation, utilizing a phase-based feature selection method to assess athletes' sequential motions. By analyzing 183 samples of volleyball serve data from players of varying skill levels, machine learning algorithms achieved accuracies of up to 95% in identifying skill levels. Biomechanical principles were used to extract 11 motion-related metrics, with 8 key metrics highly correlated to players' skill levels, providing valuable feedback for coaches and improving athletes' training effectiveness.

Zhang, Y., Wang, J., Yu, H., Zheng, J., Zhao, X., Guo, H., ... & Li, W. J. (2023). A chemotactic microrobot with integrated iridescent surface for optical-tracking. Chemical Engineering Journal, 144222.

Structural colors with the ability to change color with external stimuli can convey rich information. We report here the development of an integrated two-photon polymerization process to create three-dimensional soft micro-robots with integrated iridescent structural color surface that can reflect position and status information of micro-robot. These developments provide a new sensing strategy for micro-robots.

Zhao, Y., Liu, J., Lian, C., Liu, Y., Ren, X., Lou, J., ... & Li, W. J. (2022). A Single Smart Ring for Monitoring 20 Kinds of Multi‐Intensity Daily Activities––From Kitchen Work to Fierce Exercises. Advanced Intelligent Systems, 4(12), 2200204.

This research proposes a wearable human activity recognition (HAR) smart ring capable of accurately identifying 20 multi-intensity activities based on a microinertial measurement unit and a hierarchical decision algorithm. The smart ring offers high accuracy and portability, providing real-time quantitative data for personal lifestyle supervision, time planning, and healthcare management. This advancement enables improved time planning, health management, and disease prediction through statistical analysis of human daily activities combined with big data technology.

J. Suo, Y. Liu, C. Wu, M. Chen, Q. Huang, H. Chan,* G. Zhang, & W. J. Li*. 2022, 'Wide-Bandwidth Nanocomposite-Sensor Integrated Smart Mask for Tracking Multiphase Respiratory Activities', Advanced Science. https://doi.org/10.1002/advs.202203565

Y. Wang, M. Chen, X. Wang, R. H. M. Chan, and W. J. Li, "IoT for Next-Generation Racket Sports Training", IEEE Internet of Things J., 2018 (DOI: 10.1109/JIOT.2018.2837347).

Chen, M, Liu, Y, Tam, J C, Chan, H, Li, X, Chan, C, Li, W J.2021, 'Wireless AI-Powered IoT Sensors for Laboratory Mice Behavior Recognition', IEEE Internet of Things Journal, https://ieeexplore.ieee.org/document/9460111.