Z
Zhuoling Xiao
Researcher at University of Electronic Science and Technology of China
Publications - 44
Citations - 1188
Zhuoling Xiao is an academic researcher from University of Electronic Science and Technology of China. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 15, co-authored 38 publications receiving 918 citations. Previous affiliations of Zhuoling Xiao include Shanghai Jiao Tong University & Tsinghua University.
Papers
More filters
Journal ArticleDOI
Non-Line-of-Sight Identification and Mitigation Using Received Signal Strength
TL;DR: This study addresses the NLOS identification and mitigation problems using multiple received signal strength (RSS) measurements from WiFi signals using several statistical features of the RSS time series, which are shown to be particularly effective.
Proceedings ArticleDOI
Lightweight map matching for indoor localisation using conditional random fields
TL;DR: MapCraft is presented, a novel, robust and responsive technique that is extremely computationally efficient, does not require training in different sites, and tracks well even when presented with very noisy sensor data, enabling a new era of location-aware applications to be developed.
Proceedings Article
Does BTLE measure up against WiFi? A comparison of indoor location performance
TL;DR: It is demonstrated in experiments that BTLE propagation model can better relate RSSI to range than WiFi, which indicates that BTle can be more accurate when used in localization scenarios.
Journal ArticleDOI
Neighbor-Aided Localization in Vehicular Networks
TL;DR: This work addresses the problem of localization in vehicular ad hoc networks by employing a two-stage Bayesian filter to track the vehicle’s position and leading to a robust localization system that is able to provide useful position information even in the absence of GPS data.
Proceedings ArticleDOI
Robust pedestrian dead reckoning (R-PDR) for arbitrary mobile device placement
TL;DR: R-PDR is presented, based on exploiting how bipedal motion impacts acquired sensor waveforms, and it is demonstrated that regardless of device placement, the number of steps taken with >99.4% accuracy.