Semi-supervised Learning with Network Embedding on Ambient RF Signals for Geofencing Services

doi:10.1109/ICDE55515.2023.00208

科研成果详情

题名	Semi-supervised Learning with Network Embedding on Ambient RF Signals for Geofencing Services
作者	Zhuo，Weipeng 1; Chiu，Ka Ho 1; Chen，Jierun 1; Tan，Jiajie 1; Sumpena，Edmund 2; Chan，S. H.Gary 1; Ha，Sangtae 3; Lee，Chul Ho 4
发表日期	2023
会议名称	39th IEEE International Conference on Data Engineering, ICDE 2023
会议录名称	Proceedings - International Conference on Data Engineering
ISSN	1084-4627
卷号	2023-April
页码	2713-2726
会议日期	2023-04-03——2023-04-07
会议地点	Anaheim
摘要	In applications such as elderly care, dementia anti-wandering and pandemic control, it is important to ensure that people are within a predefined area for their safety and well-being. We propose GEM, a practical, semi-supervised Geofencing system with network EMbedding, which is based only on ambient radio frequency (RF) signals. GEM models measured RF signal records as a weighted bipartite graph. With access points on one side and signal records on the other, it is able to precisely capture the relationships between signal records. GEM then learns node embeddings from the graph via a novel bipartite network embedding algorithm called BiSAGE, based on a Bipartite graph neural network with a novel bi-level SAmple and aggreGatE mechanism and non-uniform neighborhood sampling. Using the learned embeddings, GEM finally builds a one-class classification model via an enhanced histogram-based algorithm for in-out detection, i.e., to detect whether the user is inside the area or not. This model also keeps on improving with newly collected signal records. We demonstrate through extensive experiments in diverse environments that GEM shows state-of-the-art performance with up to 34% improvement in F-score. BiSAGE in GEM leads to a 54% improvement in F-score, as compared to the one without BiSAGE.
DOI	10.1109/ICDE55515.2023.00208
URL	查看来源
语种	英语English
Scopus入藏号	2-s2.0-85167686956
引用统计
文献类型	会议论文
条目标识符	https://repository.uic.edu.cn/handle/39GCC9TT/13683
专题	个人在本单位外知识产出
作者单位	1.The Hong Kong University of Science and Technology,Hong Kong 2.Johns Hopkins University,United States 3.University of Colorado Boulder,United States 4.Texas State University,United States
推荐引用方式 GB/T 7714	Zhuo，Weipeng,Chiu，Ka Ho,Chen，Jierunet al. Semi-supervised Learning with Network Embedding on Ambient RF Signals for Geofencing Services[C], 2023: 2713-2726.