FreeTrack: Device-Free Human Tracking With Deep Neural Networks and Particle Filtering

Zhou, Rui; Tang, Mingjie; Gong, Ziyuan

doi:10.1109/jsyst.2019.2921554

Cited by 23 publications

(12 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, the denoising ability is significant in preprocess. Although some algorithms [16], [18] have been proposed to alleviate the effects of noise for CSIbased indoor localization, new method is missing for adaptive denoising.…”

Section: A Design Challengesmentioning

confidence: 99%

“…The over-fitting problem caused by reducing the residual exceedingly is avoided. w = (X T X + I ) −1 X T C (18) For fast calculation, the optimization function can be described as the multiplication of matrix. As shown in Eq.…”

Section: P(x W)mentioning

confidence: 99%

“…For comparison, two methods for pre-processing are implemented: 1) the combination of mean and MDS [16], and 2) the combination of DBSCAN and PCA [18], these two methods will be abbreviated as MDS and DBSCAN. For a fair comparison, all these three schemes use the same dataset.…”

Section: ) Benchmarksmentioning

confidence: 99%

“…Wang et al [17] proposed to utilized Bi-Modal information in 5GHz to improve the feature, then implemented deep learning on indoor localization. In 2019, Zhou et al [18] used the density-based spatial clustering method (DBSCAN) to reduce the noise in the raw CSI data, and applied principal component analysis (PCA) to extract the most contributing information. They apply this combined approach to device-free human tracking.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

C-Map: Hyper-Resolution Adaptive Preprocessing System for CSI Amplitude-Based Fingerprint Localization

et al. 2019

View full text Add to dashboard Cite

With the increasing popularity of location-based services, channel state information (CSI) has received widespread attention in positioning due to the fine-grained information it provides. However, the raw amplitudes of CSI are especially sensitive to noise and easily effected by the frequency-selective fading. As the expanding of test area, positioning is disturbed by random noise and insufficient resolution of features severely. In this paper, we propose Cluster-Mapping (C-Map), an adaptive pre-processing system for CSI amplitude-based fingerprint localization. This system models positioning as a classification problem, an adaptive processing mechanism is constructed according to the characteristics of CSI amplitude. C-Map mainly contains two parts: dynamic denoising and feature enhancement. In the dynamic denoising, effective features are screened out by clustering iteratively, without specifying parameters according to the experimental environment. In the feature enhancement, polynomial fitting with regularization is used to reduce jagged fluctuations, then the trend of variation over 30 sub-carriers are described by combining derivation with nonlinear kernel function. Extensive experiments are conducted in typical environments to verify the superior performance of C-Map for the preprocessing of CSI amplitude. Compared with the combination of mean and multidimensional scaling (MDS), the average positioning error of C-Map is reduced 28.1% in comprehensive indoor environment, and 19% in garage. Furthermore, compared with the combination of DBSCAN and principal component analysis (PCA), the average positioning error of C-Map is reduced 33.1% in comprehensive indoor environment, and 28% in garage.INDEX TERMS Channel state information (CSI), feature enhancement, data pre-processing, wireless communication, indoor localization.

show abstract

Section: A Design Challengesmentioning

confidence: 99%

Section: P(x W)mentioning

confidence: 99%

Section: ) Benchmarksmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

C-Map: Hyper-Resolution Adaptive Preprocessing System for CSI Amplitude-Based Fingerprint Localization

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Recently, the trend has been going towards utilizing more powerful neural network (NN)-based classifiers to further improve the classification accuracy when having multiple possible events. These classifiers in general require a huge training data set [6]- [8]. A few examples of recent studies on activity sensing are classification of different human activities [3], human identity identification [7], human tracking [8], gesture recognition [9], and line-of-sight (LOS)/non line-of-sight (NLOS) identification in vehicle-tovehicle (V2V) networks using multiple-input multiple-output (MIMO)-based systems [10].…”

Section: Introductionmentioning

confidence: 99%

Sensing and Classification Using Massive MIMO: A Tensor Decomposition-Based Approach

Manoj

Tian²,

Gunnarsson³

et al. 2021

IEEE Wireless Commun. Lett.

View full text Add to dashboard Cite

Wireless-based activity sensing has gained significant attention due to its wide range of applications. We investigate radio-based multi-class classification of human activities using massive multiple-input multiple-output (MIMO) channel measurements in line-of-sight and non line-of-sight scenarios. We propose a tensor decomposition-based algorithm to extract features by exploiting the complex correlation characteristics across time, frequency, and space from channel tensors formed from the measurements, followed by a neural network that learns the relationship between the input features and output target labels. Through evaluations of real measurement data, it is demonstrated that the classification accuracy using a massive MIMO array achieves significantly better results compared to the state-of-the-art even for a smaller experimental data set.

show abstract

A Real-Time Human Tracking System Using Convolutional Neural Network and Particle Filter

Nguyen

Bui

2021

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

FreeTrack: Device-Free Human Tracking With Deep Neural Networks and Particle Filtering

Cited by 23 publications

References 21 publications

C-Map: Hyper-Resolution Adaptive Preprocessing System for CSI Amplitude-Based Fingerprint Localization

C-Map: Hyper-Resolution Adaptive Preprocessing System for CSI Amplitude-Based Fingerprint Localization

Sensing and Classification Using Massive MIMO: A Tensor Decomposition-Based Approach

A Real-Time Human Tracking System Using Convolutional Neural Network and Particle Filter

Contact Info

Product

Resources

About