Accurate WiFi-Based Indoor Positioning with Continuous Location Sampling

Engelen, Jesper E. van; Lier, Jan Jaap van; Takes, Frank W.; Trautmann, H.

doi:10.1007/978-3-030-10997-4_32

Cited by 4 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many studies have explored indoor localization methods using RSSI as location fingerprint [10,13,17]. Because graph can represent the complex topology relationships between different entities, deep learning methods based on graph has become a focus of research.…”

Section: Related Workmentioning

confidence: 99%

Domain Adversarial Graph Convolutional Network Based on RSSI and Crowdsensing for Indoor Localization

Zhang¹,

Fan²,

Shibasaki³

et al. 2022

Preprint

View full text Add to dashboard Cite

In recent years, due to the wider WiFi coverage and the popularization of mobile communication devices, the technology of indoor positioning using WiFi fingerprints has been rapidly developed. Currently, most supervised methods need to collect a large amount of data to construct fingerprint datasets, which is labor-intensive and time-consuming. To solve the problem, we proposed a novel WiDAGCN model that can be trained with a few labeled site survey data and unlabeled crowdsensing WiFi fingerprints. To comprehensively represent the topology structure of the data, we constructed heterogeneous graphs according to the received signal strength indicators (RSSIs) between the waypoints and WiFi access points (APs). We focus on the graph convolutional network (GCN) method and the representation of graph-level features, which were rarely involved in previous WiFi indoor localization studies. Then, we try to minimize the difference between the source and target domains and make full use of the unlabeled data in the target domain using the domain adversarial training scheme. A public indoor localization dataset containing different buildings was used to evaluate the performance of the model. The experimental results show that our system can achieve a competitive localization accuracy in large buildings such as shopping malls.CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing; • Computing methodologies → Machine learning.

show abstract

Section: Related Workmentioning

confidence: 99%

Domain Adversarial Graph Convolutional Network Based on RSSI and Crowdsensing for Indoor Localization

Zhang¹,

Fan²,

Shibasaki³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…This can cause problems in catching the WiFi signal used as an intermediary for communication between the equipment. The signal that has to pass through the barrier before reaching its destination can become weaker than its original strength (van Engelen, J. E., et al, 2019). Even so, most of the problems that arise from a weak signal to an IoT device are simply that the device does not detect the signal.…”

Section: N P R E S Smentioning

confidence: 99%

“…UmaMaheswarara, M., & Kadaru, B. B., 2017), (3) a model to estimate a person's distance from a WiFi centre (van Engelen, J. E., et al, 2019), (4) a model to predict where the ideal location of a WiFi router is placed in a building so that it can reach the entire area with a maximum potential (Suherman, S., et al, 2018;Mathisen, A., et al, 2016), (5) models to detect dangerous objects in a suitcase without having to open the suitcase itself (Wang, C., et al, 2018). In the future, we can enjoy the improved versions of models in our daily lives.…”

Section: Introductionmentioning

confidence: 99%

WiFi Signal Strength Degradation Over Different Building Materials

2021

View full text Add to dashboard Cite

Wireless Fidelity (WiFi) signals experience propagation through air and material in a building. This propagation causes signal decreasing signal strength. This study aims to determine materials in buildings that cause significant signal strength loss so in the future building design could factor in signal strength by using material that doesn't affect signal strength significantly. The testing of signal strength will be done by observing signal strength through different materials. Signal strength will be recorded by using a mobile app. Materials that majorly decrease signal strength are plastics, with the least affecting materials are hollow plywood wall. The use of plastics in a building affects significantly on signal loss and should be replaced if possible with hollow plywood walls.

show abstract