Multipoint Channel Charting With Multiple-Input Multiple-Output Convolutional Autoencoder

Huang, Howard; Langerman, Jack

doi:10.1109/plans46316.2020.9109875

Cited by 15 publications

(11 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to these methods, we generate probability maps for each individual transmit antenna, which can then be fused to improve localization accuracy while reducing the complexity of the neural network and storage requirements. Multi-point localization strategies, where CSI from multiple APs or cellular BSs is combined, have been proposed in [30], [31] for channel charting. While such approaches only enable relative localization, they also require the exchange of CSI features to a centralized processor that performs channel charting.…”

Section: B Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion

Gönültaş

Lei

Langerman

et al. 2022

IEEE Trans. Wireless Commun.

Self Cite

View full text Add to dashboard Cite

Channel state information (CSI)-based fingerprinting via neural networks (NNs) is a promising approach to enable accurate indoor and outdoor positioning of user equipments (UEs), even under challenging propagation conditions. In this paper, we propose a positioning pipeline for wireless LAN MIMO-OFDM systems which uses uplink CSI measurements obtained from one or more unsynchronized access points (APs). For each AP receiver, novel features are first extracted from the CSI that are robust to system impairments arising in real-world transceivers. These features are the inputs to a NN that extracts a probability map indicating the likelihood of a UE being at a given grid point. The NN output is then fused across multiple APs to provide a final position estimate. We provide experimental results with realworld indoor measurements under line-of-sight (LoS) and non-LoS propagation conditions for an 80 MHz bandwidth IEEE 802.11ac system using a two-antenna transmit UE and two AP receivers each with four antennas. Our approach is shown to achieve centimeter-level median distance error, an order of magnitude improvement over a conventional baseline.

show abstract

Section: B Contributionsmentioning

confidence: 99%

“…If relative location information is sufficient, self-supervised methods known as channel charting [27]- [29] avoid expensive measurement campaigns. If CSI measurements from multiple APs are available, then the accuracy of channel charting can be improved significantly [30], [31].…”

Section: Introductionmentioning

confidence: 99%

CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion

Gönültaş

Lei

Langerman

et al. 2022

IEEE Trans. Wireless Commun.

Self Cite

View full text Add to dashboard Cite

show abstract

“…If relative location information is sufficient, self-supervised methods known as channel charting [25]- [27] avoid expensive measurement campaigns. Furthermore, if CSI measurements from multiple APs are available, it was shown in [28], [29] that the accuracy of channel charting methods can be improved significantly.…”

Section: A the Challenges Of Indoor Positioning Using Rf Signalsmentioning

confidence: 99%

CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion

Gönültaş¹,

Lei²,

Langerman³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Channel state information (CSI)-based fingerprinting via neural networks (NNs) is a promising approach to enable accurate indoor and outdoor positioning of user equipments (UEs), even under challenging propagation conditions. In this paper, we propose a CSI-based positioning pipeline for wireless LAN MIMO-OFDM systems operating indoors, which relies on NNs that extract a probability map indicating the likelihood of a UE being at a given grid point. We propose methods to fuse these probability maps at a centralized processor, which enables improved positioning accuracy if CSI is acquired at different access points (APs) and extracted from different transmit antennas. To improve positioning accuracy, we propose the design of CSI features that are robust to hardware and system impairments arising in real-world MIMO-OFDM transceivers. We provide experimental results with real-world indoor measurements under line-of-sight (LoS) and non-LoS propagation conditions, and for multi-antenna and multi-AP measurements. Our results demonstrate that probability fusion significantly improves positioning accuracy without requiring exact synchronization between APs and that centimeter-level median distance error is achievable.

show abstract

“…A triplet neural network learns the mapping from CSI samples to CCcoordinates, using time stamp side information to classify pairs of samples to come from nearby or remote spatial locations. Unfortunately, in a semi-supervised setting with challenging non-Line-of-Sight (NLOS) channels and largescale network coverage areas, the methods of [15], [16] are not capable of exploiting unlabeled data samples to improve Multipoint channel charting (MPCC) [18], [19] is an unsupervised method that produces trustworthy channel charts by combining all CSI available at multiple BSs and by exploiting redundancy in multi-point CSI to combat the distortion occurring in single-point channel charting results. In this paper, we propose a semi-supervised multi-point channel charting (SS-MPCC) framework for large-scale network-side cellular localization.…”

Section: Introductionmentioning

confidence: 99%

“…Graph-based semi-supervised multi-point channel charting framework. location estimates.Multipoint channel charting (MPCC)[18],[19] is an unsupervised method that produces trustworthy channel charts by combining all CSI available at multiple BSs and by exploiting redundancy in multi-point CSI to combat the distortion occurring in single-point channel charting results. In this paper, we propose a semi-supervised multi-point channel charting (SS-MPCC) framework for large-scale network-side cellular localization.…”

mentioning

confidence: 99%

Network-side Localization via Semi-Supervised Multi-point Channel Charting

Deng

Tirkkonen

Zhang

et al. 2021

2021 International Wireless Communications and Mobile Computing (IWCMC)

View full text Add to dashboard Cite

We consider the network-side mobile localization problem in future 5G and beyond wireless networks with distributed multi-antenna base stations (BSs). For this application, we propose a semi-supervised multi-point channel charting (SS-MPCC) framework, which consists of (i) collaborative collection of channel state information (CSI) and other sideinformation by distributed BSs; (ii) local CSI feature extraction and self-learning of a dissimilarity metric, and (iii) global graph construction and constrained manifold learning. We show that side-information from routine network operations, including timestamps, channel qualities, and a small set of labeled samples, can be exploited to construct a consistent global graph. The graph is then mapped to a 2D channel chart using constrained manifold learning for localization purposes. We evaluate the performance of SS-MPCC in a simulated urban outdoor scenario with realistic user motion. Our results show that SS-MPCC achieves a mean localization error of 5.6 m with only 10% of labeled CSI samples. SS-MPCC does not require accurate synchronization among multiple BSs and is promising for future cellular localization.

show abstract

Multipoint Channel Charting With Multiple-Input Multiple-Output Convolutional Autoencoder

Cited by 15 publications

References 20 publications

CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion

CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion

CSI-Based Multi-Antenna and Multi-Point Indoor Positioning Using Probability Fusion

Network-side Localization via Semi-Supervised Multi-point Channel Charting

Contact Info

Product

Resources

About