DHCLoc: A Device-Heterogeneity-Tolerant and Channel-Adaptive Passive WiFi Localization Method Based on DNN

Hao, Lifei; Huang, Baoqi; Jia, Bing; Mao, Guoqiang

doi:10.1109/jiot.2021.3106902

Cited by 19 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, to obtain the location of each sniffed device, WiFi-based localization approaches [36] such as KNN and WKNN can be employed to localize this device by using the RSS measurements from different sniffers during a time window. Advanced treatments, such as data cleaning, data filtering, and location fingerprint optimization, can also be utilized to improve the localization accuracy.…”

Section: Preliminaries On Passive Wifi Sensingmentioning

confidence: 99%

See 1 more Smart Citation

On the Fine-Grained Crowd Analysis via Passive WiFi Sensing

Hao,

Huang,

Jia

et al. 2024

IEEE Trans. on Mobile Comput.

Self Cite

View full text Add to dashboard Cite

Regarding the passive WiFi sensing based crowd analysis, this paper first theoretically investigates its limitations, and then proposes a deep learning based scheme targeted for returning fine-grained crowd states in large surveillance areas. To this end, three key challenges are coped with: to relieve the influences of the randomness and sparsity induced by passive WiFi sensing, an attention-based deep convolutional autoencoder model is designed to recover accurate crowd density maps in a way similar to image reconstruction; to combat the anonymity caused by MAC randomization, following the identification of local high-density crowds (LHDCs) with the density clustering algorithm, i.e. DM-DBSCAN, a bidirectional convolutional LSTM based model is employed to infer LHDC speeds; to overcome the absence of passive WiFi sensing datasets for model training, three semi-synthetic datasets are produced by emulating passive WiFi sensing with practical pedestrian tracking datasets. Extensive experiments confirm that, the proposed scheme significantly outperforms existing WiFi-based methods in terms of crowd density estimation and provides superior crowd speed estimation. More importantly, the scheme can also produce consistent crowd states on a real-world dataset, revealing that it has the ability to support accurate, visualized and real-time crowd monitoring in large surveillance areas.

show abstract

Section: Preliminaries On Passive Wifi Sensingmentioning

confidence: 99%

“…To establish the relationship between error distributions and corresponding scenario configurations, localization errors are investigated by using five public datasets [36], [49], i.e. LAB, OFFICE, CETC, HCXY and SYL, and one self-collected dataset WiCAM (see Section 6.1).…”

Section: Empirical Distributions Of Localization Errorsmentioning

confidence: 99%

On the Fine-Grained Crowd Analysis via Passive WiFi Sensing

Hao,

Huang,

Jia

et al. 2024

IEEE Trans. on Mobile Comput.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Table 1 lists the existing studies on the wave source location estimation. The source location estimation method is classified into three approaches: RSS [19], [20], [21], [22], TDOA [23], [24], and DOA [18], [25], [26], [27], [28], [29], [30], [31]. A comprehensive performance comparison of these approaches in millimeter-wave band wireless systems was presented in [32].…”

Section: Related Workmentioning

confidence: 99%

“…The RSS-based approach [19], [20], [21], [22] exploits the fact that the signal strength attenuates depending on the propagation distance, and can be easily implemented without any additional special measurement functions. In [19], the user location was estimated from the uplink RSS information without prior knowledge of the transmit power and pathloss exponent in distributed massive MIMO environments.…”

Section: Related Workmentioning

confidence: 99%

“…However, the location information may not be available or disclosed for temporary or license-exempt system, because it is not recorded in the database [18]. Thus, several approaches for wave source location estimation, such as received signal strength (RSS) [19], [20], [21], [22], time difference of arrival (TDOA) [23], [24], and direction of arrival (DOA) [18], [25], [26], [27], [28], [29], [30], [31], have been studied. From a practical point of view, the DOA-based approach is considered as a promising technique that realizes the high estimation accuracy [32].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Experimental Demonstration of Wave Source Location Estimation Method for Spectrum Sharing in 28-GHz-Band 5G System

2023

View full text Add to dashboard Cite

This paper experimentally investigates a direction of arrival (DOA)-based wave source location estimation method for spectrum sharing in millimeter-wave band local and private fifth-generation (5G) mobile communication systems. In the DOA-based wave source location estimation, it is important to extract a line-of-sight (LOS) component from the received signals. Considering that in 5G systems, synchronization signal / physical broadcast channel (SS/PBCH) blocks are transmitted with beam-sweeping for initial access, our measurement system performs the DOA estimation based on the maximum-power block where the LOS component seems to be dominant. In the DOA estimation, taking advantage of the sparsity of the propagation channels in both angular space and delay time domains, our measurement system adopts the compressed sensing (CS)-based approach. As for the measurement antenna, a directional pattern is employed, which enables the estimation with only four antenna elements. We experimentally demonstrate the performance of the wave source location estimation in an outdoor environment using a commercial 28 GHz-band 5G base station (BS). Experimental results show that our measurement system achieves a location estimation error of 5.8 m based on 20 measurements.

show abstract

Attention-Based Cross-Domain Gesture Recognition Using WiFi Channel State Information

Hong

Huang

et al. 2022

Algorithms and Architectures for Parallel Processing

View full text Add to dashboard Cite

DHCLoc: A Device-Heterogeneity-Tolerant and Channel-Adaptive Passive WiFi Localization Method Based on DNN

Cited by 19 publications

References 36 publications

On the Fine-Grained Crowd Analysis via Passive WiFi Sensing

On the Fine-Grained Crowd Analysis via Passive WiFi Sensing

Experimental Demonstration of Wave Source Location Estimation Method for Spectrum Sharing in 28-GHz-Band 5G System

Attention-Based Cross-Domain Gesture Recognition Using WiFi Channel State Information

Contact Info

Product

Resources

About