A Novel Target Recognition Based Radio Channel Clustering Algorithm

Chen Huang; Ruisi He; Zhangdui Zhong; Bo Ai; Gongpu Wang; Zhimeng Zhong; Claude Oestges; Katsuyuki Haneda

doi:10.1109/WCSP.2018.8555662

A Novel Target Recognition Based Radio Channel Clustering Algorithm

Chen Huang, Ruisi He^*, Zhangdui Zhong, Bo Ai, Gongpu Wang, Zhimeng Zhong, Claude Oestges, Katsuyuki Haneda

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

3 Citations (Scopus)

Abstract

In this paper, a novel target recognition based clustering algorithm is proposed for time-varying channels. Power angle spectrum (PAS) is extracted from measurement data by using Bartlett beamformer. Then the clusters in the PAS are separated from the background by using the proposed algorithm, where the amplitude distribution of the elements in the PAS is considered. Moreover, morphology operations are applied to further divide the clusters which are connected to each other. It is found that, the dominating clusters in both line-of-sight (LoS) and non-line-of-sight (NLoS) environments can be well recognized by the proposed algorithm with low computation cost. By using the proposed algorithm, the dynamic changes of the clusters in real-Time channel measurement can be clearly observed, without using any high-resolution parameter estimation.

Original language	English
Title of host publication	2018 10th International Conference on Wireless Communications and Signal Processing, WCSP 2018
Publisher	IEEE
ISBN (Electronic)	978-1-5386-6119-2
ISBN (Print)	978-1-5386-6120-8
DOIs	https://doi.org/10.1109/WCSP.2018.8555662
Publication status	Published - 30 Nov 2018
MoE publication type	A4 Article in a conference publication
Event	International Conference on Wireless Communications and Signal Processing - Hangzhou, China Duration: 18 Oct 2018 → 20 Oct 2018 Conference number: 10

Publication series

Name	International Conference on Wireless Communications and Signal Processing
Publisher	IEEE
ISSN (Print)	2325-3746
ISSN (Electronic)	2472-7628

Conference

Conference	International Conference on Wireless Communications and Signal Processing
Abbreviated title	WCSP
Country	China
City	Hangzhou
Period	18/10/2018 → 20/10/2018

Keywords

Channel modeling
clustering
machine learning
target recognition
wireless communications

Access to Document

10.1109/WCSP.2018.8555662

Link to publication in Scopus

Fingerprint Dive into the research topics of 'A Novel Target Recognition Based Radio Channel Clustering Algorithm'. Together they form a unique fingerprint.

Cite this

Huang, C., He, R., Zhong, Z., Ai, B., Wang, G., Zhong, Z., Oestges, C., & Haneda, K. (2018). A Novel Target Recognition Based Radio Channel Clustering Algorithm. In 2018 10th International Conference on Wireless Communications and Signal Processing, WCSP 2018 [8555662] (International Conference on Wireless Communications and Signal Processing). IEEE. https://doi.org/10.1109/WCSP.2018.8555662

Huang, Chen ; He, Ruisi ; Zhong, Zhangdui ; Ai, Bo ; Wang, Gongpu ; Zhong, Zhimeng ; Oestges, Claude ; Haneda, Katsuyuki. / A Novel Target Recognition Based Radio Channel Clustering Algorithm. 2018 10th International Conference on Wireless Communications and Signal Processing, WCSP 2018. IEEE, 2018. (International Conference on Wireless Communications and Signal Processing).

@inproceedings{177c877684c140ecb654a009e4dc066a,

title = "A Novel Target Recognition Based Radio Channel Clustering Algorithm",

abstract = "In this paper, a novel target recognition based clustering algorithm is proposed for time-varying channels. Power angle spectrum (PAS) is extracted from measurement data by using Bartlett beamformer. Then the clusters in the PAS are separated from the background by using the proposed algorithm, where the amplitude distribution of the elements in the PAS is considered. Moreover, morphology operations are applied to further divide the clusters which are connected to each other. It is found that, the dominating clusters in both line-of-sight (LoS) and non-line-of-sight (NLoS) environments can be well recognized by the proposed algorithm with low computation cost. By using the proposed algorithm, the dynamic changes of the clusters in real-Time channel measurement can be clearly observed, without using any high-resolution parameter estimation.",

keywords = "Channel modeling, clustering, machine learning, target recognition, wireless communications",

author = "Chen Huang and Ruisi He and Zhangdui Zhong and Bo Ai and Gongpu Wang and Zhimeng Zhong and Claude Oestges and Katsuyuki Haneda",

year = "2018",

month = nov,

day = "30",

doi = "10.1109/WCSP.2018.8555662",

language = "English",

isbn = "978-1-5386-6120-8",

series = "International Conference on Wireless Communications and Signal Processing",

publisher = "IEEE",

booktitle = "2018 10th International Conference on Wireless Communications and Signal Processing, WCSP 2018",

address = "United States",

note = "International Conference on Wireless Communications and Signal Processing, WCSP ; Conference date: 18-10-2018 Through 20-10-2018",

}

Huang, C, He, R, Zhong, Z, Ai, B, Wang, G, Zhong, Z, Oestges, C & Haneda, K 2018, A Novel Target Recognition Based Radio Channel Clustering Algorithm. in 2018 10th International Conference on Wireless Communications and Signal Processing, WCSP 2018., 8555662, International Conference on Wireless Communications and Signal Processing, IEEE, International Conference on Wireless Communications and Signal Processing, Hangzhou, China, 18/10/2018. https://doi.org/10.1109/WCSP.2018.8555662

A Novel Target Recognition Based Radio Channel Clustering Algorithm. / Huang, Chen; He, Ruisi; Zhong, Zhangdui; Ai, Bo; Wang, Gongpu; Zhong, Zhimeng; Oestges, Claude; Haneda, Katsuyuki.

2018 10th International Conference on Wireless Communications and Signal Processing, WCSP 2018. IEEE, 2018. 8555662 (International Conference on Wireless Communications and Signal Processing).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - A Novel Target Recognition Based Radio Channel Clustering Algorithm

AU - Huang, Chen

AU - He, Ruisi

AU - Zhong, Zhangdui

AU - Ai, Bo

AU - Wang, Gongpu

AU - Zhong, Zhimeng

AU - Oestges, Claude

AU - Haneda, Katsuyuki

N1 - Conference code: 10

PY - 2018/11/30

Y1 - 2018/11/30

N2 - In this paper, a novel target recognition based clustering algorithm is proposed for time-varying channels. Power angle spectrum (PAS) is extracted from measurement data by using Bartlett beamformer. Then the clusters in the PAS are separated from the background by using the proposed algorithm, where the amplitude distribution of the elements in the PAS is considered. Moreover, morphology operations are applied to further divide the clusters which are connected to each other. It is found that, the dominating clusters in both line-of-sight (LoS) and non-line-of-sight (NLoS) environments can be well recognized by the proposed algorithm with low computation cost. By using the proposed algorithm, the dynamic changes of the clusters in real-Time channel measurement can be clearly observed, without using any high-resolution parameter estimation.

AB - In this paper, a novel target recognition based clustering algorithm is proposed for time-varying channels. Power angle spectrum (PAS) is extracted from measurement data by using Bartlett beamformer. Then the clusters in the PAS are separated from the background by using the proposed algorithm, where the amplitude distribution of the elements in the PAS is considered. Moreover, morphology operations are applied to further divide the clusters which are connected to each other. It is found that, the dominating clusters in both line-of-sight (LoS) and non-line-of-sight (NLoS) environments can be well recognized by the proposed algorithm with low computation cost. By using the proposed algorithm, the dynamic changes of the clusters in real-Time channel measurement can be clearly observed, without using any high-resolution parameter estimation.

KW - Channel modeling

KW - clustering

KW - machine learning

KW - target recognition

KW - wireless communications

UR - http://www.scopus.com/inward/record.url?scp=85059955598&partnerID=8YFLogxK

U2 - 10.1109/WCSP.2018.8555662

DO - 10.1109/WCSP.2018.8555662

M3 - Conference contribution

AN - SCOPUS:85059955598

SN - 978-1-5386-6120-8

T3 - International Conference on Wireless Communications and Signal Processing

BT - 2018 10th International Conference on Wireless Communications and Signal Processing, WCSP 2018

PB - IEEE

T2 - International Conference on Wireless Communications and Signal Processing

Y2 - 18 October 2018 through 20 October 2018

ER -