Publications

A Collaborative Compression Scheme for Fast Activity Recognition on Mobile Devices Via Global Compression Ratio Decision

We provide an alternative called Channel Equalization in this paper to reactivate these inhibited channels by performing whitening or decorrelation operation, which compels all channels to contribute more or less to feature representation.

Junjie Liang, Lei Zhang*, Chaolei Han, Can Bu, Hao Wu and Aiguo Song

TMC 2023-5 (Journal Paper)

IEEE Transactions on Mobile Computing (CCF Rank A, IF=6.075)

DOI: 10.1109/TMC.2023.3271306

[PDF] [Code (GitHub)]

 

Theses

Research on Multiple-Channel Convolutional Neural Network based Human Activity Recognition

Learning the influence of multiple channels on CNN based HAR tasks. Because of some people’s obstruction, this work process is very bumpy.

Wenbo Huang

Master Thesis, School of Electrical and Automation Engineering, Nanjing Normal University; June, 2022

[PDF] [Slide]