A CNN-LSTM Quantifier for Single Access Point CSI Indoor Localization

Hoang, Minh Tu; Yuen, Brosnan; Ren, Kai; Dong, Xiaodai; Lü, Tao; Westendorp, Robert; Reddy, K. Ashoka

doi:10.48550/arxiv.2005.06394

Cited by 5 publications

(8 citation statements)

References 31 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, Song et al designed a positioning system based on dual-channel convolutional neural network, named DuLoc, to estimate location using CSI [20]. In reference [33], a CNN-LSTM hybrid model is proposed to provide stable localization results using both temporal information (sliding window processing) and spatial information (converting sequence to picture) of CSI signals, and the positioning accuracy is about 2.5 meters. Different from most works, the reference [34] concentrates on constructing robust positioning characteristics, where the phase differences and amplitude differences of CSI are used to construct three gray images, after that, the three grayscale images are fused into one RGB image for CNN identification and positioning.…”

Section: Related Work a Traditional Positioning Technologiesmentioning

confidence: 99%

The Adaptive Fingerprint Localization in Dynamic Environment

Long

Zheng²,

Zhang

et al. 2022

IEEE Sensors J.

View full text Add to dashboard Cite

Indoor localization service is an indispensable part of modern intelligent life, among which Wi-Fi based fingerprint localization system is popular in indoor positioning researches due to its advantages of low cost and widely deployment. However, Wi-Fi based localization system is susceptible to dynamic environment, and fingerprint collection and updating are time-consuming and labor-intensive. To address this problem, we propose a novel positioning framework based on multiple transfer learning fusion using Generalized Policy Iteration (GPI). Firstly, a 1-Dimension Convolutional Autoencoder (1-D CAE) is designed to extract features from one-dimensional fingerprint data; similar to Convolutional Neural Network (CNN), it can not only pay more attention to the information of different dimensions of fingerprints, but also compress redundant information and reduce noise. After that, Domain Adversarial Neural Network (DANN) and Passive Aggressive (PA) algorithm are fused to train localization model based on unlabeled fingerprint of target domain using the theory of GPI in offline stage. Finally, the model is fine-tuned with unlabeled fingerprints and few labeled fingerprints in daily online predictions to improve the performance of the localization system. Various evaluations in five typical scenarios validate the effectiveness of proposed algorithm in dynamic environment, with low tendency, easy recalibration, long-term stabilization high accuracy and so on.

show abstract

Section: Related Work a Traditional Positioning Technologiesmentioning

confidence: 99%

The Adaptive Fingerprint Localization in Dynamic Environment

Long

Zheng²,

Zhang

et al. 2022

IEEE Sensors J.

View full text Add to dashboard Cite

show abstract

“…LSTM-based tracking methods have also been proposed for indoor environments recently. For instance, in [20], [21], continuous CSI measurements of trajectories were first represented as deep features via a CNN network and then the features were fed into an LSTM network for tracking purposes. However, these learning-based tracking methods are designed under a specific environment and their generality is poor.…”

Section: B Csi-based Trackingmentioning

confidence: 99%

“…• LSTM-F: we compare with the LSTM-based tracking method proposed in [20], [21]. Following [20], we first train an AAResCNN using all the training samples.…”

Section: B Tracking Across Environmentsmentioning

confidence: 99%

“…• LSTM-F: we compare with the LSTM-based tracking method proposed in [20], [21]. Following [20], we first train an AAResCNN using all the training samples. And then, we • LSTM-P: the method is similar to LSTM-F; the only difference is that we use the predicted locations of the AAResCNN as the inputs of the LSTM network.…”

Section: B Tracking Across Environmentsmentioning

confidence: 99%

“…By using built-in IMU, such as acceleration sensor and gyroscope, step length and orientation can be estimated through the pedestrian dead reckoning (PDR) approach [19], with which a more realistic system model can be built. Some learning-based tracking [12], [20], [21] or IMU-aided tracking methods [22], [23] have recently been proposed for indoor environments. By exploring the correlation of CSI measurements or IMU data along a trajectory, these methods achieve better performance than stationary positioning systems and Bayesian filtering tracking systems.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

CSI-fingerprinting Indoor Localization via Attention-Augmented Residual Convolutional Neural Network

Zhang¹,

Sifaou²,

Li³

2022

Preprint

View full text Add to dashboard Cite

Deep learning has been widely adopted for channel state information (CSI)-fingerprinting indoor localization systems. These systems usually consist of two main parts, i.e., a positioning network that learns the mapping from high-dimensional CSI to physical locations and a tracking system that utilizes historical CSI to reduce the positioning error. This paper presents a new localization system with high accuracy and generality. On the one hand, the receptive field of the existing convolutional neural network (CNN)-based positioning networks is limited, restricting their performance as useful information in CSI is not explored thoroughly. As a solution, we propose a novel attention-augmented Residual CNN to utilize the local information and global context in CSI exhaustively. On the other hand, considering the generality of a tracking system, we decouple the tracking system from the CSI environments so that one tracking system for all environments becomes possible. Specifically, we remodel the tracking problem as a denoising task and solve it with deep trajectory prior. Furthermore, we investigate how the precision difference of inertial measurement units will adversely affect the tracking performance and adopt plug-and-play to solve the precision difference problem. Experiments show the superiority of our methods over existing approaches in performance and generality improvement.

show abstract

Device-Free Indoor Localization Based on Multidimensional CSI Features Classification

Tian

Zhang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

With the rapid development of location-based service applications in recent years, indoor localization based on Wi-Fi channel state information (CSI) has attracted extensive attention. Although spatial variations are explicitly reflected in CSI measurements, representation differences caused by small contextual changes tend to be submerged by overall multipath fluctuations, especially in devicefree localization. Most existing model-based solutions either underutilize the spatial and time-frequency information carried by CSI, or the employed models fail to capture small representational changes in CSI well, which makes them struggle to get satisfactory expectations. To address these problems, this paper proposes a progressive device-free localization scheme using multidimensional CSI features classification, named ProLoc. Different from previous works that directly extract the features of raw measurements, ProLoc constructs a model input containing multi-category information of CSI to perform better location inference. First, a time-frequency correlation matrix with low rank is created based on the CSI amplitude, and a 3-order CSI tensor is planned combined with spatial diversity. Second, using a novel low-rank matrix factorization algorithm and the time-frequency gradients of CSI, a 4-order tensor containing multidimensional information is generated as input data. Finally, employing 3D convolutional neural networks and gated recurrent unit, we build a progressive dual-model system to realize the mapping from CSI to target locations in various spatial contexts. Extensive self-evaluations and comparisons with several state-of-the-art methods highlight the superiority of the proposed ProLoc.

show abstract

A CNN-LSTM Quantifier for Single Access Point CSI Indoor Localization

Cited by 5 publications

References 31 publications

The Adaptive Fingerprint Localization in Dynamic Environment

The Adaptive Fingerprint Localization in Dynamic Environment

CSI-fingerprinting Indoor Localization via Attention-Augmented Residual Convolutional Neural Network

Device-Free Indoor Localization Based on Multidimensional CSI Features Classification

Contact Info

Product

Resources

About