Hai Wang

TL;DR: This work uses accelerometer embedded in the smartphones to classify five activities, such as staying still, walking, running, and going upstairs and downstairs, and constructs an activity recognition model based on location-independent smartphone.

TL;DR: In this paper, the authors developed a quantitative approach to characterize model compression techniques on a representative embedded deep learning architecture, the NVIDIA Jetson Tx2, and performed extensive experiments by considering 11 influential neural network architectures from the image classification and the natural language processing domains.

TL;DR: This paper investigates energy consumption jointly together with interference coordination for ultra-dense HetNets, and formulates max-min energy-efficient enhanced inter-cell interference coordination configuration problem and proposes a novel iterative and distributed algorithm to solve the problem by using fractional programming and Lagrangian dual theory.

TL;DR: This work converts the programming problem into resource allocation sub-problem and computing offloading sub- problem, and proposes an efficient joint downlink and uplink offloading algorithm for ultra-dense HetNets.