S
Shiming He
Researcher at Changsha University of Science and Technology
Publications - 24
Citations - 540
Shiming He is an academic researcher from Changsha University of Science and Technology. The author has contributed to research in topics: Wireless network & Smart grid. The author has an hindex of 9, co-authored 24 publications receiving 348 citations. Previous affiliations of Shiming He include Nanjing University of Posts and Telecommunications & Hunan Police Academy.
Papers
More filters
Journal ArticleDOI
Parameters Compressing in Deep Learning
TL;DR: This work uses reshaping and unfolding to let vector be the input and output of Tensor-Factorized Neural Networks, and gets a lower bound of the number of parameters.
Journal ArticleDOI
An efficient privacy-preserving compressive data gathering scheme in WSNs
Kun Xie,Kun Xie,Xueping Ning,Xin Wang,Shiming He,Zuoting Ning,Xiaoxiao Liu,Jigang Wen,Zheng Qin +8 more
TL;DR: A novel Efficient Privacy-Preserving Compressive Data Gathering Scheme is proposed, which exploits homomorphic encryption functions in compressive data gathering to thwart the traffic analysis/flow tracing and realize the privacy preservation.
Journal ArticleDOI
Multiple Strategies Differential Privacy on Sparse Tensor Factorization for Network Traffic Analysis in 5G
TL;DR: A multiple-strategies differential privacy framework on STF, MDPSTF, can provide general data protection for HOHDST network traffic data with high-security promise and the theoretical proof of privacy bound is presented.
Journal ArticleDOI
Energy-Aware Routing for SWIPT in Multi-Hop Energy-Constrained Wireless Network
TL;DR: This paper concurrently considers SWIPT and routing selection in MECWN and proposes an iterative allocation algorithm to reduce the energy consumption and demonstrates that the proposed algorithms can effectively exploit those node resources whose energy are not enough and significantly decrease the energy consume.
Journal ArticleDOI
LogEvent2vec: LogEvent-to-Vector Based Anomaly Detection for Large-Scale Logs in Internet of Things.
Jin Wang,Jin Wang,Yangning Tang,Shiming He,Shiming He,Changqing Zhao,Pradip Kumar Sharma,Osama Alfarraj,Amr Tolba,Amr Tolba +9 more
TL;DR: An offline feature extraction model, named LogEvent2vec, which takes the log event as input of word2vec to extract the relevance between log events and vectorize log events directly, and can significantly reduce computational time by 30 times and improve accuracy, comparing with word2 vec.