Loading…

A Phone-Based Distributed Ambient Temperature Measurement System With an Efficient Label-Free Automated Training Strategy

Enhancing the energy efficiency of buildings significantly relies on monitoring indoor ambient temperature. The potential limitations of conventional temperature measurement techniques, together with the omnipresence of smartphones, have redirected researchers' attention towards the exploration...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on mobile computing 2024-12, Vol.23 (12), p.11781-11793
Main Authors: Chen, Dayin, Shi, Xiaodan, Zhang, Haoran, Song, Xuan, Zhang, Dongxiao, Chen, Yuntian, Yan, Jinyue
Format: Magazinearticle
Language:English
Subjects:
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites cdi_FETCH-LOGICAL-c296t-b961d58806c10e0cef22941a60a2b1127d34046f2f606926ad030f8fbaa3f0303
container_end_page 11793
container_issue 12
container_start_page 11781
container_title IEEE transactions on mobile computing
container_volume 23
creator Chen, Dayin
Shi, Xiaodan
Zhang, Haoran
Song, Xuan
Zhang, Dongxiao
Chen, Yuntian
Yan, Jinyue
description Enhancing the energy efficiency of buildings significantly relies on monitoring indoor ambient temperature. The potential limitations of conventional temperature measurement techniques, together with the omnipresence of smartphones, have redirected researchers' attention towards the exploration of phone-based ambient temperature estimation methods. However, existing phone-based methods face challenges such as insufficient privacy protection, difficulty in adapting models to various phones, and hurdles in obtaining enough labeled training data. In this study, we propose a distributed phone-based ambient temperature estimation system which enables collaboration among multiple phones to accurately measure the ambient temperature in different areas of an indoor space. This system also provides an efficient, cost-effective approach with a few-shot meta-learning module and an automated label generation module. It shows that with just 5 new training data points, the temperature estimation model can adapt to a new phone and reach a good performance. Moreover, the system uses crowdsourcing to generate accurate labels for all newly collected training data, significantly reducing costs. Additionally, we highlight the potential of incorporating federated learning into our system to enhance privacy protection. We believe this study can advance the practical application of phone-based ambient temperature measurement, facilitating energy-saving efforts in buildings.
doi_str_mv 10.1109/TMC.2024.3399843
format magazinearticle
fullrecord <record><control><sourceid>swepub_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TMC_2024_3399843</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10529590</ieee_id><sourcerecordid>oai_DiVA_org_mdh_69507</sourcerecordid><originalsourceid>FETCH-LOGICAL-c296t-b961d58806c10e0cef22941a60a2b1127d34046f2f606926ad030f8fbaa3f0303</originalsourceid><addsrcrecordid>eNpNkMFOwzAQRCMEEqVw58DBH0DK2k7c-BhKC0itQGqBo-Uk69aoSSrbFerfk1CEOO1oNW8OL4quKYwoBXm3WkxGDFgy4lzKLOEn0YCmaRaDEHDaZy5iyjg_jy68_wSgmZTjQXTIyeumbTC-1x4r8mB9cLbYhy7ndWGxCWSF9Q6dDnuHZIHad7fu_8uDD1iTDxs2RDdkaowtf4C5LnAbzxwiyfehrXW_tnLaNrZZk2XotnB9uIzOjN56vPq9w-htNl1NnuL5y-PzJJ_HJZMixIUUtEqzDERJAaFEw5hMqBagWUEpG1c8gUQYZgQIyYSugIPJTKE1N13kw-j2uOu_cLcv1M7ZWruDarVVD_Y9V61bq7raKCFTGHd1ONZL13rv0PwBFFRvWnWmVW9a_ZrukJsjYhHxXz1lMpXAvwHiQ3tb</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>magazinearticle</recordtype></control><display><type>magazinearticle</type><title>A Phone-Based Distributed Ambient Temperature Measurement System With an Efficient Label-Free Automated Training Strategy</title><source>IEEE Xplore (Online service)</source><creator>Chen, Dayin ; Shi, Xiaodan ; Zhang, Haoran ; Song, Xuan ; Zhang, Dongxiao ; Chen, Yuntian ; Yan, Jinyue</creator><creatorcontrib>Chen, Dayin ; Shi, Xiaodan ; Zhang, Haoran ; Song, Xuan ; Zhang, Dongxiao ; Chen, Yuntian ; Yan, Jinyue</creatorcontrib><description>Enhancing the energy efficiency of buildings significantly relies on monitoring indoor ambient temperature. The potential limitations of conventional temperature measurement techniques, together with the omnipresence of smartphones, have redirected researchers' attention towards the exploration of phone-based ambient temperature estimation methods. However, existing phone-based methods face challenges such as insufficient privacy protection, difficulty in adapting models to various phones, and hurdles in obtaining enough labeled training data. In this study, we propose a distributed phone-based ambient temperature estimation system which enables collaboration among multiple phones to accurately measure the ambient temperature in different areas of an indoor space. This system also provides an efficient, cost-effective approach with a few-shot meta-learning module and an automated label generation module. It shows that with just 5 new training data points, the temperature estimation model can adapt to a new phone and reach a good performance. Moreover, the system uses crowdsourcing to generate accurate labels for all newly collected training data, significantly reducing costs. Additionally, we highlight the potential of incorporating federated learning into our system to enhance privacy protection. We believe this study can advance the practical application of phone-based ambient temperature measurement, facilitating energy-saving efforts in buildings.</description><identifier>ISSN: 1536-1233</identifier><identifier>ISSN: 1558-0660</identifier><identifier>EISSN: 1558-0660</identifier><identifier>DOI: 10.1109/TMC.2024.3399843</identifier><identifier>CODEN: ITMCCJ</identifier><language>eng</language><publisher>IEEE</publisher><subject>Crowdsourcing ; Data models ; Estimation ; label-free ; MAML ; phone ; Task analysis ; Temperature distribution ; Temperature measurement ; temperature measuring ; Uncertainty</subject><ispartof>IEEE transactions on mobile computing, 2024-12, Vol.23 (12), p.11781-11793</ispartof><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><cites>FETCH-LOGICAL-c296t-b961d58806c10e0cef22941a60a2b1127d34046f2f606926ad030f8fbaa3f0303</cites><orcidid>0000-0001-9575-4988 ; 0000-0002-4641-0641 ; 0000-0003-4566-8197 ; 0000-0003-4042-7888 ; 0000-0003-0300-0762 ; 0000-0001-5125-1860 ; 0000-0001-6930-5994</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10529590$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>230,776,780,881,27904,54774</link.rule.ids><backlink>$$Uhttps://urn.kb.se/resolve?urn=urn:nbn:se:mdh:diva-69507$$DView record from Swedish Publication Index$$Hfree_for_read</backlink></links><search><creatorcontrib>Chen, Dayin</creatorcontrib><creatorcontrib>Shi, Xiaodan</creatorcontrib><creatorcontrib>Zhang, Haoran</creatorcontrib><creatorcontrib>Song, Xuan</creatorcontrib><creatorcontrib>Zhang, Dongxiao</creatorcontrib><creatorcontrib>Chen, Yuntian</creatorcontrib><creatorcontrib>Yan, Jinyue</creatorcontrib><title>A Phone-Based Distributed Ambient Temperature Measurement System With an Efficient Label-Free Automated Training Strategy</title><title>IEEE transactions on mobile computing</title><addtitle>TMC</addtitle><description>Enhancing the energy efficiency of buildings significantly relies on monitoring indoor ambient temperature. The potential limitations of conventional temperature measurement techniques, together with the omnipresence of smartphones, have redirected researchers' attention towards the exploration of phone-based ambient temperature estimation methods. However, existing phone-based methods face challenges such as insufficient privacy protection, difficulty in adapting models to various phones, and hurdles in obtaining enough labeled training data. In this study, we propose a distributed phone-based ambient temperature estimation system which enables collaboration among multiple phones to accurately measure the ambient temperature in different areas of an indoor space. This system also provides an efficient, cost-effective approach with a few-shot meta-learning module and an automated label generation module. It shows that with just 5 new training data points, the temperature estimation model can adapt to a new phone and reach a good performance. Moreover, the system uses crowdsourcing to generate accurate labels for all newly collected training data, significantly reducing costs. Additionally, we highlight the potential of incorporating federated learning into our system to enhance privacy protection. We believe this study can advance the practical application of phone-based ambient temperature measurement, facilitating energy-saving efforts in buildings.</description><subject>Crowdsourcing</subject><subject>Data models</subject><subject>Estimation</subject><subject>label-free</subject><subject>MAML</subject><subject>phone</subject><subject>Task analysis</subject><subject>Temperature distribution</subject><subject>Temperature measurement</subject><subject>temperature measuring</subject><subject>Uncertainty</subject><issn>1536-1233</issn><issn>1558-0660</issn><issn>1558-0660</issn><fulltext>true</fulltext><rsrctype>magazinearticle</rsrctype><creationdate>2024</creationdate><recordtype>magazinearticle</recordtype><sourceid>ESBDL</sourceid><recordid>eNpNkMFOwzAQRCMEEqVw58DBH0DK2k7c-BhKC0itQGqBo-Uk69aoSSrbFerfk1CEOO1oNW8OL4quKYwoBXm3WkxGDFgy4lzKLOEn0YCmaRaDEHDaZy5iyjg_jy68_wSgmZTjQXTIyeumbTC-1x4r8mB9cLbYhy7ndWGxCWSF9Q6dDnuHZIHad7fu_8uDD1iTDxs2RDdkaowtf4C5LnAbzxwiyfehrXW_tnLaNrZZk2XotnB9uIzOjN56vPq9w-htNl1NnuL5y-PzJJ_HJZMixIUUtEqzDERJAaFEw5hMqBagWUEpG1c8gUQYZgQIyYSugIPJTKE1N13kw-j2uOu_cLcv1M7ZWruDarVVD_Y9V61bq7raKCFTGHd1ONZL13rv0PwBFFRvWnWmVW9a_ZrukJsjYhHxXz1lMpXAvwHiQ3tb</recordid><startdate>20241201</startdate><enddate>20241201</enddate><creator>Chen, Dayin</creator><creator>Shi, Xiaodan</creator><creator>Zhang, Haoran</creator><creator>Song, Xuan</creator><creator>Zhang, Dongxiao</creator><creator>Chen, Yuntian</creator><creator>Yan, Jinyue</creator><general>IEEE</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>ABGEM</scope><scope>ADTPV</scope><scope>AOWAS</scope><scope>D8T</scope><scope>DF7</scope><scope>ZZAVC</scope><orcidid>https://orcid.org/0000-0001-9575-4988</orcidid><orcidid>https://orcid.org/0000-0002-4641-0641</orcidid><orcidid>https://orcid.org/0000-0003-4566-8197</orcidid><orcidid>https://orcid.org/0000-0003-4042-7888</orcidid><orcidid>https://orcid.org/0000-0003-0300-0762</orcidid><orcidid>https://orcid.org/0000-0001-5125-1860</orcidid><orcidid>https://orcid.org/0000-0001-6930-5994</orcidid></search><sort><creationdate>20241201</creationdate><title>A Phone-Based Distributed Ambient Temperature Measurement System With an Efficient Label-Free Automated Training Strategy</title><author>Chen, Dayin ; Shi, Xiaodan ; Zhang, Haoran ; Song, Xuan ; Zhang, Dongxiao ; Chen, Yuntian ; Yan, Jinyue</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c296t-b961d58806c10e0cef22941a60a2b1127d34046f2f606926ad030f8fbaa3f0303</frbrgroupid><rsrctype>magazinearticle</rsrctype><prefilter>magazinearticle</prefilter><language>eng</language><creationdate>2024</creationdate><topic>Crowdsourcing</topic><topic>Data models</topic><topic>Estimation</topic><topic>label-free</topic><topic>MAML</topic><topic>phone</topic><topic>Task analysis</topic><topic>Temperature distribution</topic><topic>Temperature measurement</topic><topic>temperature measuring</topic><topic>Uncertainty</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Chen, Dayin</creatorcontrib><creatorcontrib>Shi, Xiaodan</creatorcontrib><creatorcontrib>Zhang, Haoran</creatorcontrib><creatorcontrib>Song, Xuan</creatorcontrib><creatorcontrib>Zhang, Dongxiao</creatorcontrib><creatorcontrib>Chen, Yuntian</creatorcontrib><creatorcontrib>Yan, Jinyue</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Xplore Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>SWEPUB Mälardalens högskola full text</collection><collection>SwePub</collection><collection>SwePub Articles</collection><collection>SWEPUB Freely available online</collection><collection>SWEPUB Mälardalens högskola</collection><collection>SwePub Articles full text</collection><jtitle>IEEE transactions on mobile computing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Chen, Dayin</au><au>Shi, Xiaodan</au><au>Zhang, Haoran</au><au>Song, Xuan</au><au>Zhang, Dongxiao</au><au>Chen, Yuntian</au><au>Yan, Jinyue</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Phone-Based Distributed Ambient Temperature Measurement System With an Efficient Label-Free Automated Training Strategy</atitle><jtitle>IEEE transactions on mobile computing</jtitle><stitle>TMC</stitle><date>2024-12-01</date><risdate>2024</risdate><volume>23</volume><issue>12</issue><spage>11781</spage><epage>11793</epage><pages>11781-11793</pages><issn>1536-1233</issn><issn>1558-0660</issn><eissn>1558-0660</eissn><coden>ITMCCJ</coden><abstract>Enhancing the energy efficiency of buildings significantly relies on monitoring indoor ambient temperature. The potential limitations of conventional temperature measurement techniques, together with the omnipresence of smartphones, have redirected researchers' attention towards the exploration of phone-based ambient temperature estimation methods. However, existing phone-based methods face challenges such as insufficient privacy protection, difficulty in adapting models to various phones, and hurdles in obtaining enough labeled training data. In this study, we propose a distributed phone-based ambient temperature estimation system which enables collaboration among multiple phones to accurately measure the ambient temperature in different areas of an indoor space. This system also provides an efficient, cost-effective approach with a few-shot meta-learning module and an automated label generation module. It shows that with just 5 new training data points, the temperature estimation model can adapt to a new phone and reach a good performance. Moreover, the system uses crowdsourcing to generate accurate labels for all newly collected training data, significantly reducing costs. Additionally, we highlight the potential of incorporating federated learning into our system to enhance privacy protection. We believe this study can advance the practical application of phone-based ambient temperature measurement, facilitating energy-saving efforts in buildings.</abstract><pub>IEEE</pub><doi>10.1109/TMC.2024.3399843</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0001-9575-4988</orcidid><orcidid>https://orcid.org/0000-0002-4641-0641</orcidid><orcidid>https://orcid.org/0000-0003-4566-8197</orcidid><orcidid>https://orcid.org/0000-0003-4042-7888</orcidid><orcidid>https://orcid.org/0000-0003-0300-0762</orcidid><orcidid>https://orcid.org/0000-0001-5125-1860</orcidid><orcidid>https://orcid.org/0000-0001-6930-5994</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1536-1233
ispartof IEEE transactions on mobile computing, 2024-12, Vol.23 (12), p.11781-11793
issn 1536-1233
1558-0660
1558-0660
language eng
recordid cdi_crossref_primary_10_1109_TMC_2024_3399843
source IEEE Xplore (Online service)
subjects Crowdsourcing
Data models
Estimation
label-free
MAML
phone
Task analysis
Temperature distribution
Temperature measurement
temperature measuring
Uncertainty
title A Phone-Based Distributed Ambient Temperature Measurement System With an Efficient Label-Free Automated Training Strategy
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-23T17%3A51%3A54IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-swepub_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Phone-Based%20Distributed%20Ambient%20Temperature%20Measurement%20System%20With%20an%20Efficient%20Label-Free%20Automated%20Training%20Strategy&rft.jtitle=IEEE%20transactions%20on%20mobile%20computing&rft.au=Chen,%20Dayin&rft.date=2024-12-01&rft.volume=23&rft.issue=12&rft.spage=11781&rft.epage=11793&rft.pages=11781-11793&rft.issn=1536-1233&rft.eissn=1558-0660&rft.coden=ITMCCJ&rft_id=info:doi/10.1109/TMC.2024.3399843&rft_dat=%3Cswepub_cross%3Eoai_DiVA_org_mdh_69507%3C/swepub_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c296t-b961d58806c10e0cef22941a60a2b1127d34046f2f606926ad030f8fbaa3f0303%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=10529590&rfr_iscdi=true