Dr Lu Bai

Knowledge Transfer Partnership (KTP) Associate

About

Dr Lu Bai is Knowledge Transfer Partnership (KTP) Associate in the School of Engineering and Digital Arts.

Publications

Article

  • Bai, L. et al. (2014). Quantitative Assessment of Limb Motion by Inertial Sensors Before and After Botulinum Toxin for Spasticity. Archives of Physical Medicine and Rehabilitation [Online] 95. Available at: http://dx.doi.org/10.1016/j.apmr.2014.07.205.
    To develop an assessment tool utilising inertial sensors to investigate an objective measure of the efficacy of upper limb rehabilitation before and after Botulinum toxin (BTX) in clinical setting.

Conference or workshop item

  • Lee, J., Efstratiou, C. and Bai, L. (2016). OSN Mood Tracking: Exploring the Use of Online Social Network Activity as an Indicator of Mood Changes. in: Workshop on Mental Health Sensing and Intervention in conjunction with UBICOMP'16. pp. 1171-1179.
    Online social networks (OSNs) have become an integral part of our everyday lives, where we share our thoughts and feelings. This study analyses the extent to which the changes of an individual’s real-world psychological mood can be inferred by tracking their online activity on Face- book and Twitter. By capturing activities from the OSNs and ground truth data via experience sampling, it was found that mood changes can be detected within a window of 7 days for 61% of the participants by using specific, combined on- line activity signals. The participants fall into three distinct groups: those whose mood correlates positively with their online activity, those who correlate negatively and those who display a weak correlation. We trained two classifiers to identify these groups using features from their online activity, which achieved precision of 95.2% and 84.4% respectively. Our results suggest that real-world mood changes can be passively tracked through online activity on OSNs.
  • Bai, L., Efstratiou, C. and Ang, C. (2016). weSport: Utilising Wrist-Band Sensing to Detect Player Activities in Basketball Games. in: WristSense 2016: Workshop on Sensing Systems and Applications Using Wrist Worn Smart Devices (co-located with IEEE PerCom 2016).. Available at: https://sites.google.com/site/wristsenseworkshop2016/.
    Wristbands have been traditionally designed to track the activities of a single person. However there is an opportunity to utilize the sensing capabilities of wristbands to offer activity tracking services within the domain of team-based sports games. In this paper we demonstrate the design of an activity tracking system capable of detecting the players’ activities within a one-to-one basketball game. Relying on the inertial sensors of wristbands and smartphones, the system can capture the shooting attempts of each player and provide statistics about their performance. The system is based on a two- level classification architecture, combining data from both players in the game. We employ a technique for semi-automatic labelling of the ground truth that requires minimum manual input during a training game. Using a single game as a training dataset, and applying the classifier on future games we demonstrate that the system can achieve a good level of accuracy detecting the shooting attempts of both players in the game (precision 91.34%, recall 94.31%).
Last updated