I am a PhD student at Daily Activity Lab at the University of Texas at Austin. I am interested in leveraging wearable/mobile sensors and machine learning algorithms to analyze and model human signals. In particular, I study the (stress) signals from mother-infant pairs collected longitudinally through their daily interactions. I am supervised by Prof. Kaya de Barbaro and Prof. Edison Thomaz.
“In-the-wild” dataset and individual differences are two characteristics in my research. “In-the-wild” datasets are much noisier and harder to work with comparing to lab data, but they reflect and better model our real world. I intend to build models that can detail individual differences as in health-related applications, it is not enough to have a satisfactory mean accuracy. The model needs to be good with each data point.
I have worked with motion and audio sensors extensively and developed models for parent holding behaviors, parent affect classification and infant crying/fussing classification.
PhD in Electrical and Computer Engineering, 2023 (Expected)
The University of Texas at Austin
MSc in Computer Science, 2018
Gerogia Institute of Technology
BEng in Information Engineering, 2016
City Univeristy of Hong Kong
Physical contact is critical for children’s physical and emotional growth and well-being. Previous studies of physical contact are limited to relatively short periods of direct observation and self-report methods. These methods limit researchers’ understanding of the natural variation in physical contact across families, and its specific impacts on child development. In this study we develop a mobile sensing platform that can provide objective, unobtrusive, and continuous measurements of physical contact in naturalistic home interactions. Using commercially available motion detectors, our model reaches an accuracy of 0.870 (std: 0.059) for a second-by-second binary classification of holding. In addition, we detail five assessment scenarios applicable to the development of activity recognition models for social science research, where required accuracy may vary as a function of the intended use. Finally, we propose a grand vision for leveraging mobile sensors to access high-density markers of multiple determinants of early parent-child interactions, with implications for basic science and intervention.
This paper proposes an algorithm to perform privacy-preserving (PP) speaker recognition using Gaussian mixture models (GMM). We consider a scenario where the users have to enrol their voice biometric with the third-party service providers to access different services (i.e., banking). Once the enrolment is done, the users can authenticate themselves to the system using their voice instead of passwords. Since the voice is unique for individuals, storing the users’ voice features at the third-party server raises privacy concerns. Hence, in this paper we propose a novel technique using randomization to perform voice authentication, which allows users to enrol and authenticate their voice in the encrypted domain, hence privacy is preserved. To achieve this, we redesign the GMM to work on encrypted domain. The proposed algorithm is validated using the widely used TIMIT speech corpus. Experimental results demonstrate that the proposed PP algorithm does not degrade the performance compared to the non-PP method and achieve 96.16% true positive rate and 1.77% false positive rate. Demonstration on Android smartphone shows that the algorithm can be executed within two seconds with only 30% of CPU power.