iUpdater: Low Cost RSS Fingerprints Updating for Device-Free Localization

Chang, Liqiong; Xiong, Jie; Wang, Yu; Liu, Chen; Hu, Jianjiang; Fang, Dingyi

doi:10.1109/icdcs.2017.216

Cited by 20 publications

(12 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [21] propose a fingerprint-based device-free localization system named iUpdater to significantly reduce the labor cost and increase the accuracy. It is able to accurately update the whole database with RSS measurements at a small number of reference locations, thus reducing the human labor cost.…”

Section: Related Workmentioning

confidence: 99%

AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems

Liu

et al. 2021

IEEE Trans. Emerg. Top. Comput. Intell.

100

View full text Add to dashboard Cite

With widely deployed WiFi network and the uniqueness feature (fingerprint) of wireless channel information, fingerprinting based WiFi positioning is currently the mainstream indoor positioning method, in which fingerprint database construction is crucial. However, for accuracy, this approach requires enough data to be sampled at many reference points, which consumes excessive efforts and time. In this paper, we collect Channel State Information (CSI) data at reference points by the method of device-free localization, then we convert collected CSI data into amplitude feature maps and extend the fingerprint database using the proposed Amplitude-Feature Deep Convolutional Generative Adversarial Network (AF-DCGAN) model. The use of AF-DCGAN accelerates convergence during the training phase, and substantially increases the diversity of the CSI amplitude feature map. The extended fingerprint database both reduces the human effort involved in fingerprint database construction and the accuracy of an indoor localization system, as demonstrated in the experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems

Liu

et al. 2021

IEEE Trans. Emerg. Top. Comput. Intell.

100

View full text Add to dashboard Cite

show abstract

“…Subsequently, attentions are turned to CSI which reveals the details of the amplitudes and phases of each subcarrier to derive sub-meter or even centimeter-level localization accuracy [12]. CSI fingerprint-based approaches have been explored [16], [28], however, they are difficult to be widely used due to the excessive reliance on the environment. Hence, the parameters of CSI, such as the amplitude [29]- [31], the phase [32]- [34] or AOA [24], [35], [36], are investigated to locate the target.…”

Section: Related Work 1) Indoor Localization and Trackingmentioning

confidence: 99%

Leveraging TPDV to Direction Estimation With a Single Pair of Commodity Devices

et al. 2020

View full text Add to dashboard Cite

In this paper, we propose an indoor passive human tracking system equipped with only one pair of commodity Wi-Fi devices, namely WiBlinker. The key insight is that the motion of moving target not only introduce Doppler frequency shift, but also changes the value of phase difference between two adjacent antennas of the receiver. First of all, a lightweight interpolation scheme is presented to remove the random phase noise in channel state information for improving the accuracy of the trajectory tracing. Instead of using AoA to obtain the moving direction, WiBlinker employs the trend of phase difference variation in direction estimation which is no need multiple Wi-Fi devices and easier to be achieved. Experimental results show that WiBlinker outperforms the conventional multiple Wi-Fi links methods, especially in the case of a sharp turn. INDEX TERMS Indoor human tracking, commodity devices, Angle-of-Arrival, Doppler frequency shift, channel state information.

show abstract

“…7 dB. These values can be previously estimated for the scenario at hand, see, e.g., [6], [10], [11], [24], [29], [30], or one can extend the proposed empirical Bayes method to estimate them. Given z rts , p X rts , p d rts , the model in (7), and all the assumptions, we need to estimate the RSS, f rts g , at the M grid locations, X g .…”

Section: System Modelmentioning

confidence: 99%

“…In [18], an adaptive kernel-based approach is proposed, but there is no discussion on the variations of RSS in practice. In [24], some results on RSS measurements are reported for a WLAN with time, while in [6] some variations over a few seconds and days are reported to emphasize the need for updating the fingerprint for localization purposes. In both cases, indoor WiFi signals are considered.…”

Section: Introductionmentioning

confidence: 99%

Recursive Estimation of Dynamic RSS Fields Based on Crowdsourcing and Gaussian Processes

Santos

Murillo-Fuentes

Djurić

2019

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

In this paper, we address the estimation of a timevarying spatial field of received signal strength (RSS) by relying on measurements from randomly placed and not very accurate sensors. We employ a radio propagation model where the path loss exponent and the transmitted power are unknown with Gaussian priors whose hyper-parameters are estimated by applying the empirical Bayes method. We consider the locations of the sensors to be imperfectly known, which entails that they represent another source of error in the model. The propagation model includes shadowing which is considered to be a zero-mean Gaussian process where the correlation of attenuation between two spatial points is quantified by an exponential function of the distance between the points. The location of the transmitter is also unknown and is estimated from the data. We propose to estimate time-varying RSS fields by a recursive Bayesian method and crowdsourcing. The method is based on Gaussian processes (GP), and it produces the joint distribution of the spatial field. Further, it summarizes all the acquired information by keeping the size of the needed memory bounded. We also present the Bayesian Cramér-Rao bound (BCRB) of the estimated parameters. Finally, we illustrate the performance of our method with experimental results on synthetic and real data sets.

show abstract

iUpdater: Low Cost RSS Fingerprints Updating for Device-Free Localization

Cited by 20 publications

References 25 publications

AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems

AF-DCGAN: Amplitude Feature Deep Convolutional GAN for Fingerprint Construction in Indoor Localization Systems

Leveraging TPDV to Direction Estimation With a Single Pair of Commodity Devices

Recursive Estimation of Dynamic RSS Fields Based on Crowdsourcing and Gaussian Processes

Contact Info

Product

Resources

About