An Indoor Localization System Using Residual Learning with Channel State Information
With the increasing demand of location-based services, neural network (NN)-based intelligent indoor localization has attracted great interest due to its high localization accuracy. However, deep NNs are usually affected by degradation and gradient vanishing. To fill this gap, we propose a novel indo...
Gespeichert in:
Veröffentlicht in: | Entropy (Basel, Switzerland) Switzerland), 2021-05, Vol.23 (5), p.574, Article 574 |
---|---|
Hauptverfasser: | , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 5 |
container_start_page | 574 |
container_title | Entropy (Basel, Switzerland) |
container_volume | 23 |
creator | Xu, Chendong Wang, Weigang Zhang, Yunwei Qin, Jie Yu, Shujuan Zhang, Yun |
description | With the increasing demand of location-based services, neural network (NN)-based intelligent indoor localization has attracted great interest due to its high localization accuracy. However, deep NNs are usually affected by degradation and gradient vanishing. To fill this gap, we propose a novel indoor localization system, including denoising NN and residual network (ResNet), to predict the location of moving object by the channel state information (CSI). In the ResNet, to prevent overfitting, we replace all the residual blocks by the stochastic residual blocks. Specially, we explore the long-range stochastic shortcut connection (LRSSC) to solve the degradation problem and gradient vanishing. To obtain a large receptive field without losing information, we leverage the dilated convolution at the rear of the ResNet. Experimental results are presented to confirm that our system outperforms state-of-the-art methods in a representative indoor environment. |
doi_str_mv | 10.3390/e23050574 |
format | Article |
fullrecord | <record><control><sourceid>proquest_webof</sourceid><recordid>TN_cdi_webofscience_primary_000653916200001</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_96e84726ac5d4bffbd2237125ba999de</doaj_id><sourcerecordid>2532344958</sourcerecordid><originalsourceid>FETCH-LOGICAL-c446t-cd44f62b33e5430555a32ad5f2a1a9c10740d8993723e95c6e0357124163bd5c3</originalsourceid><addsrcrecordid>eNqNkV1rFDEUhgdRbK1e-A8GvFFkNd8zuRHKUHVhodCP65BJzuxmmUlqkrG0v97sblmsV17lcM6Th8N5q-o9Rl8olegrEIo44g17UZ1iJOWCUYRe_lWfVG9S2iJEKMHidXVCGRIN4uK0ujn39dLbEGK9CkaP7lFnF3x9_ZAyTPVtcn5dX0FydtZjvQId_a5z7_Km7jbaexjr66wzFMsQ4rT__bZ6Negxwbun96y6_X5x0_1crC5_LLvz1cIwJvLCWMYGQXpKgZctOeeaEm35QDTW0mDUMGRbKWlDKEhuBCDKG0wYFrS33NCzannw2qC36i66SccHFbRT-0aIa6VjdmYEJQW0rCFCG25ZPwy9JYQWF--1lNJCcX07uO7mfgJrwOeox2fS5xPvNmodfqsWcyw5KYKPT4IYfs2QsppcMjCO2kOYkyKcClaOznboh3_QbZijL6faUYQyJnlbqE8HysSQUoThuAxGape7OuZe2M8H9h76MCTjwBs48gghwanEgpQK4UK3_093Lu9D7cLsM_0D7PK9Ug</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2532344958</pqid></control><display><type>article</type><title>An Indoor Localization System Using Residual Learning with Channel State Information</title><source>DOAJ Directory of Open Access Journals</source><source>Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals</source><source>PubMed Central Open Access</source><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Web of Science - Science Citation Index Expanded - 2021<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" /></source><source>PubMed Central</source><creator>Xu, Chendong ; Wang, Weigang ; Zhang, Yunwei ; Qin, Jie ; Yu, Shujuan ; Zhang, Yun</creator><creatorcontrib>Xu, Chendong ; Wang, Weigang ; Zhang, Yunwei ; Qin, Jie ; Yu, Shujuan ; Zhang, Yun</creatorcontrib><description>With the increasing demand of location-based services, neural network (NN)-based intelligent indoor localization has attracted great interest due to its high localization accuracy. However, deep NNs are usually affected by degradation and gradient vanishing. To fill this gap, we propose a novel indoor localization system, including denoising NN and residual network (ResNet), to predict the location of moving object by the channel state information (CSI). In the ResNet, to prevent overfitting, we replace all the residual blocks by the stochastic residual blocks. Specially, we explore the long-range stochastic shortcut connection (LRSSC) to solve the degradation problem and gradient vanishing. To obtain a large receptive field without losing information, we leverage the dilated convolution at the rear of the ResNet. Experimental results are presented to confirm that our system outperforms state-of-the-art methods in a representative indoor environment.</description><identifier>ISSN: 1099-4300</identifier><identifier>EISSN: 1099-4300</identifier><identifier>DOI: 10.3390/e23050574</identifier><identifier>PMID: 34067056</identifier><language>eng</language><publisher>BASEL: Mdpi</publisher><subject>Accuracy ; Algorithms ; channel state information (CSI) ; Convolution ; Deep learning ; Degradation ; denoising neural network (NN) ; Indoor environments ; indoor localization ; Localization ; Location based services ; Methods ; Network interface cards ; Neural networks ; Noise ; Noise reduction ; Physical Sciences ; Physics ; Physics, Multidisciplinary ; Propagation ; residual network (ResNet) ; Science & Technology ; Wireless networks</subject><ispartof>Entropy (Basel, Switzerland), 2021-05, Vol.23 (5), p.574, Article 574</ispartof><rights>2021 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2021 by the authors. 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>true</woscitedreferencessubscribed><woscitedreferencescount>4</woscitedreferencescount><woscitedreferencesoriginalsourcerecordid>wos000653916200001</woscitedreferencesoriginalsourcerecordid><citedby>FETCH-LOGICAL-c446t-cd44f62b33e5430555a32ad5f2a1a9c10740d8993723e95c6e0357124163bd5c3</citedby><cites>FETCH-LOGICAL-c446t-cd44f62b33e5430555a32ad5f2a1a9c10740d8993723e95c6e0357124163bd5c3</cites><orcidid>0000-0003-1412-3282</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8151952/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8151952/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,315,729,782,786,866,887,2104,2116,27931,27932,39265,53798,53800</link.rule.ids></links><search><creatorcontrib>Xu, Chendong</creatorcontrib><creatorcontrib>Wang, Weigang</creatorcontrib><creatorcontrib>Zhang, Yunwei</creatorcontrib><creatorcontrib>Qin, Jie</creatorcontrib><creatorcontrib>Yu, Shujuan</creatorcontrib><creatorcontrib>Zhang, Yun</creatorcontrib><title>An Indoor Localization System Using Residual Learning with Channel State Information</title><title>Entropy (Basel, Switzerland)</title><addtitle>ENTROPY-SWITZ</addtitle><description>With the increasing demand of location-based services, neural network (NN)-based intelligent indoor localization has attracted great interest due to its high localization accuracy. However, deep NNs are usually affected by degradation and gradient vanishing. To fill this gap, we propose a novel indoor localization system, including denoising NN and residual network (ResNet), to predict the location of moving object by the channel state information (CSI). In the ResNet, to prevent overfitting, we replace all the residual blocks by the stochastic residual blocks. Specially, we explore the long-range stochastic shortcut connection (LRSSC) to solve the degradation problem and gradient vanishing. To obtain a large receptive field without losing information, we leverage the dilated convolution at the rear of the ResNet. Experimental results are presented to confirm that our system outperforms state-of-the-art methods in a representative indoor environment.</description><subject>Accuracy</subject><subject>Algorithms</subject><subject>channel state information (CSI)</subject><subject>Convolution</subject><subject>Deep learning</subject><subject>Degradation</subject><subject>denoising neural network (NN)</subject><subject>Indoor environments</subject><subject>indoor localization</subject><subject>Localization</subject><subject>Location based services</subject><subject>Methods</subject><subject>Network interface cards</subject><subject>Neural networks</subject><subject>Noise</subject><subject>Noise reduction</subject><subject>Physical Sciences</subject><subject>Physics</subject><subject>Physics, Multidisciplinary</subject><subject>Propagation</subject><subject>residual network (ResNet)</subject><subject>Science & Technology</subject><subject>Wireless networks</subject><issn>1099-4300</issn><issn>1099-4300</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>HGBXW</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>DOA</sourceid><recordid>eNqNkV1rFDEUhgdRbK1e-A8GvFFkNd8zuRHKUHVhodCP65BJzuxmmUlqkrG0v97sblmsV17lcM6Th8N5q-o9Rl8olegrEIo44g17UZ1iJOWCUYRe_lWfVG9S2iJEKMHidXVCGRIN4uK0ujn39dLbEGK9CkaP7lFnF3x9_ZAyTPVtcn5dX0FydtZjvQId_a5z7_Km7jbaexjr66wzFMsQ4rT__bZ6Negxwbun96y6_X5x0_1crC5_LLvz1cIwJvLCWMYGQXpKgZctOeeaEm35QDTW0mDUMGRbKWlDKEhuBCDKG0wYFrS33NCzannw2qC36i66SccHFbRT-0aIa6VjdmYEJQW0rCFCG25ZPwy9JYQWF--1lNJCcX07uO7mfgJrwOeox2fS5xPvNmodfqsWcyw5KYKPT4IYfs2QsppcMjCO2kOYkyKcClaOznboh3_QbZijL6faUYQyJnlbqE8HysSQUoThuAxGape7OuZe2M8H9h76MCTjwBs48gghwanEgpQK4UK3_093Lu9D7cLsM_0D7PK9Ug</recordid><startdate>20210507</startdate><enddate>20210507</enddate><creator>Xu, Chendong</creator><creator>Wang, Weigang</creator><creator>Zhang, Yunwei</creator><creator>Qin, Jie</creator><creator>Yu, Shujuan</creator><creator>Zhang, Yun</creator><general>Mdpi</general><general>MDPI AG</general><general>MDPI</general><scope>BLEPL</scope><scope>DTL</scope><scope>HGBXW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7TB</scope><scope>8FD</scope><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FR3</scope><scope>HCIFZ</scope><scope>KR7</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0003-1412-3282</orcidid></search><sort><creationdate>20210507</creationdate><title>An Indoor Localization System Using Residual Learning with Channel State Information</title><author>Xu, Chendong ; Wang, Weigang ; Zhang, Yunwei ; Qin, Jie ; Yu, Shujuan ; Zhang, Yun</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c446t-cd44f62b33e5430555a32ad5f2a1a9c10740d8993723e95c6e0357124163bd5c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Accuracy</topic><topic>Algorithms</topic><topic>channel state information (CSI)</topic><topic>Convolution</topic><topic>Deep learning</topic><topic>Degradation</topic><topic>denoising neural network (NN)</topic><topic>Indoor environments</topic><topic>indoor localization</topic><topic>Localization</topic><topic>Location based services</topic><topic>Methods</topic><topic>Network interface cards</topic><topic>Neural networks</topic><topic>Noise</topic><topic>Noise reduction</topic><topic>Physical Sciences</topic><topic>Physics</topic><topic>Physics, Multidisciplinary</topic><topic>Propagation</topic><topic>residual network (ResNet)</topic><topic>Science & Technology</topic><topic>Wireless networks</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Xu, Chendong</creatorcontrib><creatorcontrib>Wang, Weigang</creatorcontrib><creatorcontrib>Zhang, Yunwei</creatorcontrib><creatorcontrib>Qin, Jie</creatorcontrib><creatorcontrib>Yu, Shujuan</creatorcontrib><creatorcontrib>Zhang, Yun</creatorcontrib><collection>Web of Science Core Collection</collection><collection>Science Citation Index Expanded</collection><collection>Web of Science - Science Citation Index Expanded - 2021</collection><collection>CrossRef</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Engineering Research Database</collection><collection>SciTech Premium Collection</collection><collection>Civil Engineering Abstracts</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Entropy (Basel, Switzerland)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Xu, Chendong</au><au>Wang, Weigang</au><au>Zhang, Yunwei</au><au>Qin, Jie</au><au>Yu, Shujuan</au><au>Zhang, Yun</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>An Indoor Localization System Using Residual Learning with Channel State Information</atitle><jtitle>Entropy (Basel, Switzerland)</jtitle><stitle>ENTROPY-SWITZ</stitle><date>2021-05-07</date><risdate>2021</risdate><volume>23</volume><issue>5</issue><spage>574</spage><pages>574-</pages><artnum>574</artnum><issn>1099-4300</issn><eissn>1099-4300</eissn><abstract>With the increasing demand of location-based services, neural network (NN)-based intelligent indoor localization has attracted great interest due to its high localization accuracy. However, deep NNs are usually affected by degradation and gradient vanishing. To fill this gap, we propose a novel indoor localization system, including denoising NN and residual network (ResNet), to predict the location of moving object by the channel state information (CSI). In the ResNet, to prevent overfitting, we replace all the residual blocks by the stochastic residual blocks. Specially, we explore the long-range stochastic shortcut connection (LRSSC) to solve the degradation problem and gradient vanishing. To obtain a large receptive field without losing information, we leverage the dilated convolution at the rear of the ResNet. Experimental results are presented to confirm that our system outperforms state-of-the-art methods in a representative indoor environment.</abstract><cop>BASEL</cop><pub>Mdpi</pub><pmid>34067056</pmid><doi>10.3390/e23050574</doi><tpages>15</tpages><orcidid>https://orcid.org/0000-0003-1412-3282</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 1099-4300 |
ispartof | Entropy (Basel, Switzerland), 2021-05, Vol.23 (5), p.574, Article 574 |
issn | 1099-4300 1099-4300 |
language | eng |
recordid | cdi_webofscience_primary_000653916200001 |
source | DOAJ Directory of Open Access Journals; Elektronische Zeitschriftenbibliothek - Frei zugängliche E-Journals; PubMed Central Open Access; MDPI - Multidisciplinary Digital Publishing Institute; Web of Science - Science Citation Index Expanded - 2021<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" />; PubMed Central |
subjects | Accuracy Algorithms channel state information (CSI) Convolution Deep learning Degradation denoising neural network (NN) Indoor environments indoor localization Localization Location based services Methods Network interface cards Neural networks Noise Noise reduction Physical Sciences Physics Physics, Multidisciplinary Propagation residual network (ResNet) Science & Technology Wireless networks |
title | An Indoor Localization System Using Residual Learning with Channel State Information |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-05T16%3A55%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_webof&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=An%20Indoor%20Localization%20System%20Using%20Residual%20Learning%20with%20Channel%20State%20Information&rft.jtitle=Entropy%20(Basel,%20Switzerland)&rft.au=Xu,%20Chendong&rft.date=2021-05-07&rft.volume=23&rft.issue=5&rft.spage=574&rft.pages=574-&rft.artnum=574&rft.issn=1099-4300&rft.eissn=1099-4300&rft_id=info:doi/10.3390/e23050574&rft_dat=%3Cproquest_webof%3E2532344958%3C/proquest_webof%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2532344958&rft_id=info:pmid/34067056&rft_doaj_id=oai_doaj_org_article_96e84726ac5d4bffbd2237125ba999de&rfr_iscdi=true |