Convolutional neural networks based indoor Wi-Fi localization with a novel kind of CSI images

Indoor Wi-Fi localization of mobile devices plays a more and more important role along with the rapid growth of location-based services and Wi-Fi mobile devices. In this paper, a new method of constructing the channel state information (CSI) image is proposed to improve the localization accuracy. Co...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:China communications 2019-09, Vol.16 (9), p.250-260
Hauptverfasser: Li, Haihan, Zeng, Xiangsheng, Li, Yunzhou, Zhou, Shidong, Wang, Jing
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 260
container_issue 9
container_start_page 250
container_title China communications
container_volume 16
creator Li, Haihan
Zeng, Xiangsheng
Li, Yunzhou
Zhou, Shidong
Wang, Jing
description Indoor Wi-Fi localization of mobile devices plays a more and more important role along with the rapid growth of location-based services and Wi-Fi mobile devices. In this paper, a new method of constructing the channel state information (CSI) image is proposed to improve the localization accuracy. Compared with previous methods of constructing the CSI image, the new kind of CSI image proposed is able to contain more channel information such as the angle of arrival (AoA), the time of arrival (TOA) and the amplitude. We construct three gray images by using phase differences of different antennas and amplitudes of different subcarriers of one antenna, and then merge them to form one RGB image. The localization method has off-line stage and on-line stage. In the off-line stage, the composed three-channel RGB images at training locations are used to train a convolutional neural network (CNN) which has been proved to be efficient in image recognition. In the on-line stage, images at test locations are fed to the well-trained CNN model and the localization result is the weighted mean value with highest output values. The performance of the proposed method is verified with extensive experiments in the representative indoor environment.
doi_str_mv 10.23919/JCC.2019.09.019
format Article
fullrecord <record><control><sourceid>wanfang_jour_RIE</sourceid><recordid>TN_cdi_ieee_primary_8851471</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8851471</ieee_id><wanfj_id>zgtx201909019</wanfj_id><sourcerecordid>zgtx201909019</sourcerecordid><originalsourceid>FETCH-LOGICAL-c293t-4e6eb514ba0f6deb04c9402bff1f006fd7be1b2c240f457736df0cf900e3a09a3</originalsourceid><addsrcrecordid>eNo9UE1PAjEU7EETCXI38dKLx8XXD7r0aDaiGBIPajyZpt1tsbBuTbuI8ustYHyZvLnMvMwbhC4IjCmTRF4_VNWYApFjyCDyBA2IKFkx4bw8Q6OUVpBnKgQTdIDeqtB9hXbT-9DpFnd2Ew_Ub0NcJ2x0sg32XRNCxK--mHnchlq3fqf3Drz1_TvWuAtftsXrrMPB4eppjv2HXtp0jk6dbpMd_fEQvcxun6v7YvF4N69uFkVNJesLboU1E8KNBicaa4DXkgM1zhEHIFxTGksMrSkHxydlyUTjoHYSwDINUrMhujre3erO6W6pVmET8z9J7Zb9974MkHllHRx1dQwpRevUZ8xJ448ioA7tqdye2hsUZBwsl0eLt9b-y6fTHLck7BcWfm3G</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Convolutional neural networks based indoor Wi-Fi localization with a novel kind of CSI images</title><source>IEEE Electronic Library (IEL)</source><creator>Li, Haihan ; Zeng, Xiangsheng ; Li, Yunzhou ; Zhou, Shidong ; Wang, Jing</creator><creatorcontrib>Li, Haihan ; Zeng, Xiangsheng ; Li, Yunzhou ; Zhou, Shidong ; Wang, Jing</creatorcontrib><description>Indoor Wi-Fi localization of mobile devices plays a more and more important role along with the rapid growth of location-based services and Wi-Fi mobile devices. In this paper, a new method of constructing the channel state information (CSI) image is proposed to improve the localization accuracy. Compared with previous methods of constructing the CSI image, the new kind of CSI image proposed is able to contain more channel information such as the angle of arrival (AoA), the time of arrival (TOA) and the amplitude. We construct three gray images by using phase differences of different antennas and amplitudes of different subcarriers of one antenna, and then merge them to form one RGB image. The localization method has off-line stage and on-line stage. In the off-line stage, the composed three-channel RGB images at training locations are used to train a convolutional neural network (CNN) which has been proved to be efficient in image recognition. In the on-line stage, images at test locations are fed to the well-trained CNN model and the localization result is the weighted mean value with highest output values. The performance of the proposed method is verified with extensive experiments in the representative indoor environment.</description><identifier>ISSN: 1673-5447</identifier><identifier>DOI: 10.23919/JCC.2019.09.019</identifier><identifier>CODEN: CCHOBE</identifier><language>eng</language><publisher>China Institute of Communications</publisher><subject>Antenna measurements ; Antennas ; channel state information ; convolutional neural network ; CSI image ; Feature extraction ; Fingerprint recognition ; indoor Wi-Fi localization ; Mobile handsets ; Phase locked loops ; Wireless fidelity</subject><ispartof>China communications, 2019-09, Vol.16 (9), p.250-260</ispartof><rights>Copyright © Wanfang Data Co. Ltd. All Rights Reserved.</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c293t-4e6eb514ba0f6deb04c9402bff1f006fd7be1b2c240f457736df0cf900e3a09a3</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Uhttp://www.wanfangdata.com.cn/images/PeriodicalImages/zgtx/zgtx.jpg</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8851471$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8851471$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Li, Haihan</creatorcontrib><creatorcontrib>Zeng, Xiangsheng</creatorcontrib><creatorcontrib>Li, Yunzhou</creatorcontrib><creatorcontrib>Zhou, Shidong</creatorcontrib><creatorcontrib>Wang, Jing</creatorcontrib><title>Convolutional neural networks based indoor Wi-Fi localization with a novel kind of CSI images</title><title>China communications</title><addtitle>ChinaComm</addtitle><description>Indoor Wi-Fi localization of mobile devices plays a more and more important role along with the rapid growth of location-based services and Wi-Fi mobile devices. In this paper, a new method of constructing the channel state information (CSI) image is proposed to improve the localization accuracy. Compared with previous methods of constructing the CSI image, the new kind of CSI image proposed is able to contain more channel information such as the angle of arrival (AoA), the time of arrival (TOA) and the amplitude. We construct three gray images by using phase differences of different antennas and amplitudes of different subcarriers of one antenna, and then merge them to form one RGB image. The localization method has off-line stage and on-line stage. In the off-line stage, the composed three-channel RGB images at training locations are used to train a convolutional neural network (CNN) which has been proved to be efficient in image recognition. In the on-line stage, images at test locations are fed to the well-trained CNN model and the localization result is the weighted mean value with highest output values. The performance of the proposed method is verified with extensive experiments in the representative indoor environment.</description><subject>Antenna measurements</subject><subject>Antennas</subject><subject>channel state information</subject><subject>convolutional neural network</subject><subject>CSI image</subject><subject>Feature extraction</subject><subject>Fingerprint recognition</subject><subject>indoor Wi-Fi localization</subject><subject>Mobile handsets</subject><subject>Phase locked loops</subject><subject>Wireless fidelity</subject><issn>1673-5447</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9UE1PAjEU7EETCXI38dKLx8XXD7r0aDaiGBIPajyZpt1tsbBuTbuI8ustYHyZvLnMvMwbhC4IjCmTRF4_VNWYApFjyCDyBA2IKFkx4bw8Q6OUVpBnKgQTdIDeqtB9hXbT-9DpFnd2Ew_Ub0NcJ2x0sg32XRNCxK--mHnchlq3fqf3Drz1_TvWuAtftsXrrMPB4eppjv2HXtp0jk6dbpMd_fEQvcxun6v7YvF4N69uFkVNJesLboU1E8KNBicaa4DXkgM1zhEHIFxTGksMrSkHxydlyUTjoHYSwDINUrMhujre3erO6W6pVmET8z9J7Zb9974MkHllHRx1dQwpRevUZ8xJ448ioA7tqdye2hsUZBwsl0eLt9b-y6fTHLck7BcWfm3G</recordid><startdate>20190901</startdate><enddate>20190901</enddate><creator>Li, Haihan</creator><creator>Zeng, Xiangsheng</creator><creator>Li, Yunzhou</creator><creator>Zhou, Shidong</creator><creator>Wang, Jing</creator><general>China Institute of Communications</general><general>Department of Electronic Engineering, Tsinghua University, Beijing 100084, China%Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China%Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China</general><general>Department of Electronic Engineering, Tsinghua University, Beijing 100084, China</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>2B.</scope><scope>4A8</scope><scope>92I</scope><scope>93N</scope><scope>PSX</scope><scope>TCJ</scope></search><sort><creationdate>20190901</creationdate><title>Convolutional neural networks based indoor Wi-Fi localization with a novel kind of CSI images</title><author>Li, Haihan ; Zeng, Xiangsheng ; Li, Yunzhou ; Zhou, Shidong ; Wang, Jing</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c293t-4e6eb514ba0f6deb04c9402bff1f006fd7be1b2c240f457736df0cf900e3a09a3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Antenna measurements</topic><topic>Antennas</topic><topic>channel state information</topic><topic>convolutional neural network</topic><topic>CSI image</topic><topic>Feature extraction</topic><topic>Fingerprint recognition</topic><topic>indoor Wi-Fi localization</topic><topic>Mobile handsets</topic><topic>Phase locked loops</topic><topic>Wireless fidelity</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Li, Haihan</creatorcontrib><creatorcontrib>Zeng, Xiangsheng</creatorcontrib><creatorcontrib>Li, Yunzhou</creatorcontrib><creatorcontrib>Zhou, Shidong</creatorcontrib><creatorcontrib>Wang, Jing</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Wanfang Data Journals - Hong Kong</collection><collection>WANFANG Data Centre</collection><collection>Wanfang Data Journals</collection><collection>万方数据期刊 - 香港版</collection><collection>China Online Journals (COJ)</collection><collection>China Online Journals (COJ)</collection><jtitle>China communications</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Li, Haihan</au><au>Zeng, Xiangsheng</au><au>Li, Yunzhou</au><au>Zhou, Shidong</au><au>Wang, Jing</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Convolutional neural networks based indoor Wi-Fi localization with a novel kind of CSI images</atitle><jtitle>China communications</jtitle><stitle>ChinaComm</stitle><date>2019-09-01</date><risdate>2019</risdate><volume>16</volume><issue>9</issue><spage>250</spage><epage>260</epage><pages>250-260</pages><issn>1673-5447</issn><coden>CCHOBE</coden><abstract>Indoor Wi-Fi localization of mobile devices plays a more and more important role along with the rapid growth of location-based services and Wi-Fi mobile devices. In this paper, a new method of constructing the channel state information (CSI) image is proposed to improve the localization accuracy. Compared with previous methods of constructing the CSI image, the new kind of CSI image proposed is able to contain more channel information such as the angle of arrival (AoA), the time of arrival (TOA) and the amplitude. We construct three gray images by using phase differences of different antennas and amplitudes of different subcarriers of one antenna, and then merge them to form one RGB image. The localization method has off-line stage and on-line stage. In the off-line stage, the composed three-channel RGB images at training locations are used to train a convolutional neural network (CNN) which has been proved to be efficient in image recognition. In the on-line stage, images at test locations are fed to the well-trained CNN model and the localization result is the weighted mean value with highest output values. The performance of the proposed method is verified with extensive experiments in the representative indoor environment.</abstract><pub>China Institute of Communications</pub><doi>10.23919/JCC.2019.09.019</doi><tpages>11</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 1673-5447
ispartof China communications, 2019-09, Vol.16 (9), p.250-260
issn 1673-5447
language eng
recordid cdi_ieee_primary_8851471
source IEEE Electronic Library (IEL)
subjects Antenna measurements
Antennas
channel state information
convolutional neural network
CSI image
Feature extraction
Fingerprint recognition
indoor Wi-Fi localization
Mobile handsets
Phase locked loops
Wireless fidelity
title Convolutional neural networks based indoor Wi-Fi localization with a novel kind of CSI images
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T00%3A41%3A45IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-wanfang_jour_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Convolutional%20neural%20networks%20based%20indoor%20Wi-Fi%20localization%20with%20a%20novel%20kind%20of%20CSI%20images&rft.jtitle=China%20communications&rft.au=Li,%20Haihan&rft.date=2019-09-01&rft.volume=16&rft.issue=9&rft.spage=250&rft.epage=260&rft.pages=250-260&rft.issn=1673-5447&rft.coden=CCHOBE&rft_id=info:doi/10.23919/JCC.2019.09.019&rft_dat=%3Cwanfang_jour_RIE%3Ezgtx201909019%3C/wanfang_jour_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=8851471&rft_wanfj_id=zgtx201909019&rfr_iscdi=true