L
Liang Xu
Researcher at University of Science and Technology Beijing
Publications - 9
Citations - 57
Liang Xu is an academic researcher from University of Science and Technology Beijing. The author has contributed to research in topics: Deep learning & Feature (computer vision). The author has an hindex of 2, co-authored 9 publications receiving 24 citations.
Papers
More filters
Journal ArticleDOI
Modeling IoT Equipment With Graph Neural Networks
TL;DR: This paper proposes a graph neural network-based modeling approach for IoT equipment (called GNNM-IoT), which considers both temporal and inner logic relations of data, in which vertices denote sensor data and edges denote relationships between vertices.
Journal ArticleDOI
A Streaming Cloud Platform for Real-Time Video Processing on Embedded Devices
Weishan Zhang,Haoyun Sun,Dehai Zhao,Liang Xu,Xin Liu,Huansheng Ning,Jiehan Zhou,Yi Guo,Su Yang +8 more
TL;DR: The results show the proposed platform can run deep learning algorithms on embedded devices while meeting the high scalability and fault tolerance required for real-time video processing.
Book ChapterDOI
FLSTM: Feature Pattern-Based LSTM for Imbalanced Big Data Analysis
Liang Xu,Xingjie Zeng,Weishan Zhang,Jiangru Yuan,Pengcheng Ren,Zhang Ruicong,Wuwu Guo,Jiehan Zhou +7 more
TL;DR: The experimental results show that the FLSTM can improve failure prediction with imbalanced big data and the failure prediction system performs well.
Proceedings ArticleDOI
Deep Learning Based Container Text Recognition
TL;DR: The CTDRNet consists of three components: text detection enables to improve detection accuracy for single words; text recognition has faster convergence speed and detection accuracy; and post-processing improves detection and recognition accuracy.
Book ChapterDOI
A Deep Learning-Based Hybrid Data Fusion Method for Object Recognition
TL;DR: The experiment shows that the FD-DFM model has higher accuracy than other existing methods with fruit recognition and integrates feature fusion and decision fusion into neural networks with the D-S evidence theory.