X
Xiangjian He
Researcher at University of Technology, Sydney
Publications - 421
Citations - 7397
Xiangjian He is an academic researcher from University of Technology, Sydney. The author has contributed to research in topics: Image segmentation & Computer science. The author has an hindex of 35, co-authored 401 publications receiving 5511 citations. Previous affiliations of Xiangjian He include Information Technology University & University of Sydney.
Papers
More filters
Journal ArticleDOI
Detection of Denial-of-Service Attacks Based on Computer Vision Techniques
TL;DR: This work presents a proposed EMD-based detection system, which is developed based on a widely used dissimilarity measure, namely Earth Mover's Distance (EMD), that can detect unknown DoS attacks and achieves 99.95 percent detection accuracy on KDD Cup 99 dataset and 90.12 percent on ISCX 2012 IDS evaluation dataset.
Journal ArticleDOI
A Novel Convolutional Neural Network Based Indoor Localization Framework With WiFi Fingerprinting
Xudong Song,Xiaochen Fan,Chaocan Xiang,Qianwen Ye,Leyu Liu,Zumin Wang,Xiangjian He,Ning Yang,Gengfa Fang +8 more
TL;DR: CNNLoc, a Convolutional Neural Network (CNN) based indoor localization system with WiFi fingerprints for multi-building and multi-floor localization and results show CNNLoc outperforms the existing solutions with 100% and 95% success rates on building- level localization and floor-level localization, respectively.
Journal ArticleDOI
A Sybil attack detection scheme for a forest wildfire monitoring application
TL;DR: This paper proposes a Sybil attack detection scheme for a cluster-based hierarchical network mainly deployed to monitor forest wildfire and proposes a two-tier detection scheme that has better network lifetime due to efficient sleep–awake scheduling, higher detection rate and low false-negative rate.
Proceedings ArticleDOI
Blockchain Based Secured Identity Authentication and Expeditious Revocation Framework for Vehicular Networks
TL;DR: A blockchain based authentication and revocation framework for vehicular networks, which not only reduces the computation and communication overhead by mitigating dependency on a trusted authority for identity verification, but also speedily updates the status of revocated vehicles in the shared blockchain ledger.
Journal ArticleDOI
PASCCC: Priority-based application-specific congestion control clustering protocol
TL;DR: A priority-based application-specific congestion control clustering protocol, which integrates the mobility and heterogeneity of the nodes to detect congestion in a network and achieves better performance in terms of the network lifetime, energy consumption, data transmission, and other QoS metrics compared with existing approaches.