B
Biyi Fang
Researcher at Michigan State University
Publications - 26
Citations - 774
Biyi Fang is an academic researcher from Michigan State University. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 10, co-authored 23 publications receiving 429 citations. Previous affiliations of Biyi Fang include Microsoft.
Papers
More filters
Proceedings ArticleDOI
NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision
Biyi Fang,Xiao Zeng,Mi Zhang +2 more
TL;DR: NestDNN as discussed by the authors is a framework that takes the dynamics of runtime resources into account to enable resource-aware multi-tenant on-device deep learning for mobile vision systems.
Proceedings ArticleDOI
NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision
Biyi Fang,Xiao Zeng,Mi Zhang +2 more
TL;DR: NestDNN is a framework that takes the dynamics of runtime resources into account to enable resource-aware multi-tenant on-device deep learning for mobile vision systems and achieves as much as 4.2% increase in inference accuracy, 2.0× increase in video frame processing rate and 1.7× reduction on energy consumption.
Proceedings ArticleDOI
BodyScan: Enabling Radio-based Sensing on Wearable Devices for Contactless Activity and Vital Sign Monitoring
TL;DR: Radio is introduced as a new powerful sensing modality for wearable devices and proposed to transform radio into a mobile sensor of human activities and vital signs and presents BodyScan, a wearable system that enables radio to act as a single modality capable of providing whole-body continuous sensing of the user.
Proceedings ArticleDOI
Distream: scaling live video analytics with workload-adaptive distributed edge intelligence
TL;DR: This work presents Distream, a distributed live video analytics system based on the smart camera-edge cluster architecture that is able to adapt to the workload dynamics to achieve low-latency, high-throughput, and scalable live video Analytics.
Proceedings ArticleDOI
DeepASL: Enabling Ubiquitous and Non-Intrusive Word and Sentence-Level Sign Language Translation
Biyi Fang,Jillian Co,Mi Zhang +2 more
TL;DR: DeepASL is presented, a transformative deep learning-based sign language translation technology that enables ubiquitous and non-intrusive American Sign Language (ASL) translation at both word and sentence levels and represents a significant step towards breaking the communication barrier between deaf people and hearing majority.