Multi-Feature Fusion Based Recognition and Relevance Analysis of Propagation Scenes for High-Speed Railway Channels

Zhou, Tao; Wang, Yingjie; Wang, Cheng-Xiang; Salous, Sana; Liu, Liu; Cheng, Tao

doi:10.1109/tvt.2020.2999313

Cited by 24 publications

(5 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The change of the AOA and AOD can be quantified by RMS angle spread (RMS‐AS). It is given by (Czink & Xuefeng, 2005; Zhou, Wang, et al, 2020)

σ_{θ} = \sqrt{\overset{θ^{2}}{true} - {(\overset{θ}{true})}^{2}}

where

\overset{θ^{2}}{true}

and

\overset{θ}{true}

can be written as

\overset{θ^{2}}{true} = \frac{\sum_{k} P ((), θ_{k}) θ_{k}^{2}}{\sum_{k} P ((), θ_{k})}

\overset{θ}{true} = \frac{\sum_{k} P ((), θ_{k}) θ_{k}}{\sum_{k} P ((), θ_{k})}

where P ( θ k ) and θ k are the power and angle of the k th multipath component. Figure 8 shows that at 1.4725 GHz, when the Tx and Rx are both located in the rectangular tunnel, the RMS‐AS of AOA and AOD is ~13° to 16°; when the Tx and Rx are located in differently shaped sections of the tunnel (and link distance is larger), the RMS‐AS of AOA is 6° to 15° and the RMS‐AS of AOD is 4° to 15°.…”

Section: Virtual Mimo Measurementmentioning

confidence: 99%

Investigation of MIMO Channel Characteristics in Tunnel at 1.4725 and 6 GHz

et al. 2020

View full text Add to dashboard Cite

In recent years, high-speed railway and subway are being built rapidly in China. Tunnel scenario is a major scenario in some of the high-speed railways and most of the subways. Channel characteristic is the decisive condition of wireless communication system design in tunnel. The availability of multiple-input multiple-output (MIMO) in tunnel is an important issue in the next generation communication network. This paper presents results from a wideband measurement campaign at center frequency of 1.4725 and 6 GHz in a tunnel laboratory. The path loss, root-mean-square delay spread (RMS-DS) characteristics by single-input single-output (SISO) measurement and the angle spread, channel matrix singular values, and MIMO capacity at various link distances by MIMO measurement are illustrated. and these provide insights for MIMO system deployment. And also, the threshold of singular value for channel matrix rank reduction is given.

show abstract

“…The change of the AOA and AOD can be quantified by RMS angle spread (RMS‐AS). It is given by (Czink & Xuefeng, 2005; Zhou, Wang, et al, 2020)

σ_{θ} = \sqrt{\overset{θ^{2}}{true} - {(\overset{θ}{true})}^{2}}

where

\overset{θ^{2}}{true}

and

\overset{θ}{true}

can be written as

\overset{θ^{2}}{true} = \frac{\sum_{k} P ((), θ_{k}) θ_{k}^{2}}{\sum_{k} P ((), θ_{k})}

\overset{θ}{true} = \frac{\sum_{k} P ((), θ_{k}) θ_{k}}{\sum_{k} P ((), θ_{k})}

Section: Virtual Mimo Measurementmentioning

confidence: 99%

Investigation of MIMO Channel Characteristics in Tunnel at 1.4725 and 6 GHz

et al. 2020

View full text Add to dashboard Cite

show abstract

“…• Zhou et al [25] propose a deep neural network (DNN) and a score fusion scheme for classification purposes. Four scenarios related to high-speed railway channels (Rural, Station, Suburban and Multi-link) are classified by using four channel features (K Factor, RMS delay spread, RMS Doppler power spectrum and RMS angular spread).…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence and Dimensionality Reduction: Tools for Approaching Future Communications

Ramírez-Arroyo

García

Alex‐Amor

et al. 2022

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

This article presents a novel application of the t-distributed Stochastic Neighbor Embedding (t-SNE) clustering algorithm to the telecommunication field. t-SNE is a dimensionality reduction algorithm that allows the visualization of large dataset into a 2D plot. We present the applicability of this algorithm in a communication channel dataset formed by several scenarios (anechoic, reverberation, indoor and outdoor), and by using six channel features. Applying this artificial intelligence (AI) technique, we are able to separate different environments into several clusters allowing a clear visualization of the scenarios. Throughout the article, it is proved that t-SNE has the ability to cluster into several subclasses, obtaining internal classifications within the scenarios themselves. t-SNE comparison with different dimensionality reduction techniques (PCA, Isomap) is also provided throughout the paper. Furthermore, post-processing techniques are used to modify communication scenarios, recreating a real communication scenario from measurements acquired in an anechoic chamber. The dimensionality reduction and classification by using t-SNE and Variational AutoEncoders show good performance distinguishing between the recreation and the real communication scenario. The combination of these two techniques opens up the possibility for new scenario recreations for future mobile communications. This work shows the potential of AI as a powerful tool for clustering, classification and generation of new 5G propagation scenarios.

show abstract

“…• Zhou et al [24] propose a deep neural network (DNN) and a score fusion scheme for classification purposes. Four scenarios related to high-speed railway channels (Rural, Station, Suburban and Multi-link) are classified by using four channel features (K Factor, RMS delay spread, RMS Doppler power spectrum and RMS angular spread).…”

Section: Introductionmentioning

confidence: 99%

Artificial Intelligence and Dimensionality Reduction: Tools for approaching future communications

Ramírez-Arroyo,

García,

Alex-Amor

et al. 2021

Preprint

View full text Add to dashboard Cite

This article presents a novel application of the tdistributed Stochastic Neighbor Embedding (t-SNE) clustering algorithm to the telecommunication field. t-SNE is a dimensionality reduction (DR) algorithm that allows the visualization of large dataset into a 2D plot. We present the applicability of this algorithm in a communication channel dataset formed by several scenarios (anechoic, reverberation, indoor and outdoor), and by using six channel features. Applying this artificial intelligence (AI) technique, we are able to separate different environments into several clusters allowing a clear visualization of the scenarios. Throughout the article, it is proved that t-SNE has the ability to cluster into several subclasses, obtaining internal classifications within the scenarios themselves. t-SNE comparison with different dimensionality reduction techniques (PCA, Isomap) is also provided throughout the paper. Furthermore, post-processing techniques are used to modify communication scenarios, recreating a real communication scenario from measurements acquired in an anechoic chamber. The dimensionality reduction and classification by using t-SNE and Variational AutoEncoders (VAE) show good performance distinguishing between the recreation and the real communication scenario. The combination of these two techniques opens up the possibility for new scenario recreations for future mobile communications. This work shows the potential of AI as a powerful tool for clustering, classification and generation of new 5G propagation scenarios.

show abstract

Multi-Feature Fusion Based Recognition and Relevance Analysis of Propagation Scenes for High-Speed Railway Channels

Cited by 24 publications

References 45 publications

Investigation of MIMO Channel Characteristics in Tunnel at 1.4725 and 6 GHz

Investigation of MIMO Channel Characteristics in Tunnel at 1.4725 and 6 GHz

Artificial Intelligence and Dimensionality Reduction: Tools for Approaching Future Communications

Artificial Intelligence and Dimensionality Reduction: Tools for approaching future communications

Contact Info

Product

Resources

About