Yan WANG'S WEBSITE

Je pense, donc je suis…


Deep Learning Opitmization for Mobile Devices Using Hardware and Software Co-design

 

Synopsis:

The primary goal of this project is to develop cutting-edge algorithms and computer architectures that enables the broad deployment of heavy-cost deep learning models into resource-constrained, heterogeneous mobile edge devices (e.g., low-cost sensing platforms and IoT devices). This project analyzes distinct deep learning behaviors on mobile edge devices and designs different strategies to improve the efficiency of multiple deep-learning-based inference models. Furthermore, this project develops algorithms that can adjust the complexity of different deep learning models to reduce their energy and memory consumption on mobile edge devices.

 

Personnel:

Graduate Students: Tianming Zhao

Undergraduate Students: Luke Jackielaszek

PI: Yan Wang

 

Collaborators:

Yingying Chen (Rutgers University)

Jerry Cheng (New York Institute of Technology)

Jian Liu (University of Tennessee)

 

Publications:

  • Yilin Yang, Yan Wang, and Yingying Chen "EchoLock: Towards Low-effort Mobile User Identification Leveraging Structure-borne Echos," in Proceedings of the 15th ACM ASIA Conference on Computer and Communications Security (ACM ASIACCS 2020), Taipei, Taiwan, June 2020. DOI: 10.1145/3320269.3384741NEW!
  • Tianming Zhao, Yan Wang, Jian Liu, Yingying Chen, Jerry Cheng, and Jiadi Yu. "TrueHeart: Continuous Authentication on Wrist-worn Wearables Using PPG-based Biometrics," in Proceedings of the IEEE International Conference on Computer Communication (INFOCOM 2020), Beijing, China, 2020. DOI: 10.1109/INFOCOM41043.2020.9155526. NEW!

 

Educational Activities:

The PPG-based and acoustic sensing-based user authentication methods and corresponding machine-learning approaches are integrated into the course materials of the cross-listed course CIS4330 / CIS 4360 (Smart Sensing and Devices) at Temple University.

Graduate and undergraduate students are involved in the research tasks and experiments of these projects during their summer internship.


 
Yan Wang, 2019. All rights reserved.