Multi-task Deep Learning for Human Activity, Speed, and Body Weight Estimation using Commercial Smart Insoles

Healthcare professionals and individual users use wearable devices equipped with various sensors for healthcare management. Recently, the joint usage of artificial intelligence and these wearable sensors has played an essential role in healthcare management by providing a wide range of applications...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE internet of things journal 2023-04, p.1-1
Hauptverfasser: Kim, Jaeho, Kang, Hyewon, Yang, Jaewan, Jung, Haneul, Lee, Seulki, Lee, Junghye
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 1
container_issue
container_start_page 1
container_title IEEE internet of things journal
container_volume
creator Kim, Jaeho
Kang, Hyewon
Yang, Jaewan
Jung, Haneul
Lee, Seulki
Lee, Junghye
description Healthcare professionals and individual users use wearable devices equipped with various sensors for healthcare management. Recently, the joint usage of artificial intelligence and these wearable sensors has played an essential role in healthcare management by providing a wide range of applications such as fitness tracking, gym activity monitoring, patient rehabilitation monitoring, and disease detection. These tasks eventually aim to enhance personal well-being and better manage the user's physical health by monitoring different activity types and body weight changes. Here, we present an efficient multi-task learning framework based on commercial smart insoles that can solve three tasks related to physical health management: activity classification, speed estimation, and body weight estimation. Our multi-task framework converts the sensor data from the smart insole to a recurrence plot, which shows significant performance improvement compared to processing the raw time series data. In addition, we utilized a modified MobileNetV2 as our backbone network, which has a total parameter of less than 100K and a computational budget of 0.34G of multiply-accumulate operations. Furthermore, we collected a vast dataset from 72 users carrying out 16 experiments, which contains the largest number of people for multi-task learning purposes using smart insoles. Extensive experiments show that the proposed multi-task learning framework is extremely efficient while outperforming or leading to comparable performance against single-task models.
doi_str_mv 10.1109/JIOT.2023.3267335
format Article
fullrecord <record><control><sourceid>ieee</sourceid><recordid>TN_cdi_ieee_primary_10102648</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>10102648</ieee_id><sourcerecordid>10102648</sourcerecordid><originalsourceid>FETCH-ieee_primary_101026483</originalsourceid><addsrcrecordid>eNqFjM1qAjEURoNQUFofQHBxH8AZ86OxLlurqCguFFxKcK726iQZkkxh3r4Wunf1Lc45H2M9wXMh-HS4Xu0OueRS5UrqiVLjFutIJSfZSGvZZt0Yb5zzhzoWU91hdluXibJk4h2-ECvYoAmO3BUuPsCytsbBxznRD6VmAPsKsRiAcQV8-qKBI9L1O8E8JrImkXdQx7925q3FcCZTwt6akGDloi8xvrGXiykjdv_3lfUX88NsmREinqrweAnNSXDBpR69qyf4FxC8SIk</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Multi-task Deep Learning for Human Activity, Speed, and Body Weight Estimation using Commercial Smart Insoles</title><source>IEEE Electronic Library (IEL)</source><creator>Kim, Jaeho ; Kang, Hyewon ; Yang, Jaewan ; Jung, Haneul ; Lee, Seulki ; Lee, Junghye</creator><creatorcontrib>Kim, Jaeho ; Kang, Hyewon ; Yang, Jaewan ; Jung, Haneul ; Lee, Seulki ; Lee, Junghye</creatorcontrib><description>Healthcare professionals and individual users use wearable devices equipped with various sensors for healthcare management. Recently, the joint usage of artificial intelligence and these wearable sensors has played an essential role in healthcare management by providing a wide range of applications such as fitness tracking, gym activity monitoring, patient rehabilitation monitoring, and disease detection. These tasks eventually aim to enhance personal well-being and better manage the user's physical health by monitoring different activity types and body weight changes. Here, we present an efficient multi-task learning framework based on commercial smart insoles that can solve three tasks related to physical health management: activity classification, speed estimation, and body weight estimation. Our multi-task framework converts the sensor data from the smart insole to a recurrence plot, which shows significant performance improvement compared to processing the raw time series data. In addition, we utilized a modified MobileNetV2 as our backbone network, which has a total parameter of less than 100K and a computational budget of 0.34G of multiply-accumulate operations. Furthermore, we collected a vast dataset from 72 users carrying out 16 experiments, which contains the largest number of people for multi-task learning purposes using smart insoles. Extensive experiments show that the proposed multi-task learning framework is extremely efficient while outperforming or leading to comparable performance against single-task models.</description><identifier>EISSN: 2327-4662</identifier><identifier>DOI: 10.1109/JIOT.2023.3267335</identifier><identifier>CODEN: IITJAU</identifier><language>eng</language><publisher>IEEE</publisher><subject>Artificial intelligence ; body weight estimation ; Deep learning ; human activity recognition ; Intelligent sensors ; Medical services ; multi-task learning ; Multitasking ; recurrence plot ; Sensors ; smart insole ; speed estimation ; Task analysis</subject><ispartof>IEEE internet of things journal, 2023-04, p.1-1</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><orcidid>0009-0004-7162-0845 ; 0000-0003-3221-1526</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/10102648$$EHTML$$P50$$Gieee$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,796,27924,27925,54758</link.rule.ids></links><search><creatorcontrib>Kim, Jaeho</creatorcontrib><creatorcontrib>Kang, Hyewon</creatorcontrib><creatorcontrib>Yang, Jaewan</creatorcontrib><creatorcontrib>Jung, Haneul</creatorcontrib><creatorcontrib>Lee, Seulki</creatorcontrib><creatorcontrib>Lee, Junghye</creatorcontrib><title>Multi-task Deep Learning for Human Activity, Speed, and Body Weight Estimation using Commercial Smart Insoles</title><title>IEEE internet of things journal</title><addtitle>JIoT</addtitle><description>Healthcare professionals and individual users use wearable devices equipped with various sensors for healthcare management. Recently, the joint usage of artificial intelligence and these wearable sensors has played an essential role in healthcare management by providing a wide range of applications such as fitness tracking, gym activity monitoring, patient rehabilitation monitoring, and disease detection. These tasks eventually aim to enhance personal well-being and better manage the user's physical health by monitoring different activity types and body weight changes. Here, we present an efficient multi-task learning framework based on commercial smart insoles that can solve three tasks related to physical health management: activity classification, speed estimation, and body weight estimation. Our multi-task framework converts the sensor data from the smart insole to a recurrence plot, which shows significant performance improvement compared to processing the raw time series data. In addition, we utilized a modified MobileNetV2 as our backbone network, which has a total parameter of less than 100K and a computational budget of 0.34G of multiply-accumulate operations. Furthermore, we collected a vast dataset from 72 users carrying out 16 experiments, which contains the largest number of people for multi-task learning purposes using smart insoles. Extensive experiments show that the proposed multi-task learning framework is extremely efficient while outperforming or leading to comparable performance against single-task models.</description><subject>Artificial intelligence</subject><subject>body weight estimation</subject><subject>Deep learning</subject><subject>human activity recognition</subject><subject>Intelligent sensors</subject><subject>Medical services</subject><subject>multi-task learning</subject><subject>Multitasking</subject><subject>recurrence plot</subject><subject>Sensors</subject><subject>smart insole</subject><subject>speed estimation</subject><subject>Task analysis</subject><issn>2327-4662</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>ESBDL</sourceid><sourceid>RIE</sourceid><recordid>eNqFjM1qAjEURoNQUFofQHBxH8AZ86OxLlurqCguFFxKcK726iQZkkxh3r4Wunf1Lc45H2M9wXMh-HS4Xu0OueRS5UrqiVLjFutIJSfZSGvZZt0Yb5zzhzoWU91hdluXibJk4h2-ECvYoAmO3BUuPsCytsbBxznRD6VmAPsKsRiAcQV8-qKBI9L1O8E8JrImkXdQx7925q3FcCZTwt6akGDloi8xvrGXiykjdv_3lfUX88NsmREinqrweAnNSXDBpR69qyf4FxC8SIk</recordid><startdate>20230413</startdate><enddate>20230413</enddate><creator>Kim, Jaeho</creator><creator>Kang, Hyewon</creator><creator>Yang, Jaewan</creator><creator>Jung, Haneul</creator><creator>Lee, Seulki</creator><creator>Lee, Junghye</creator><general>IEEE</general><scope>97E</scope><scope>ESBDL</scope><scope>RIA</scope><scope>RIE</scope><orcidid>https://orcid.org/0009-0004-7162-0845</orcidid><orcidid>https://orcid.org/0000-0003-3221-1526</orcidid></search><sort><creationdate>20230413</creationdate><title>Multi-task Deep Learning for Human Activity, Speed, and Body Weight Estimation using Commercial Smart Insoles</title><author>Kim, Jaeho ; Kang, Hyewon ; Yang, Jaewan ; Jung, Haneul ; Lee, Seulki ; Lee, Junghye</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-ieee_primary_101026483</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Artificial intelligence</topic><topic>body weight estimation</topic><topic>Deep learning</topic><topic>human activity recognition</topic><topic>Intelligent sensors</topic><topic>Medical services</topic><topic>multi-task learning</topic><topic>Multitasking</topic><topic>recurrence plot</topic><topic>Sensors</topic><topic>smart insole</topic><topic>speed estimation</topic><topic>Task analysis</topic><toplevel>online_resources</toplevel><creatorcontrib>Kim, Jaeho</creatorcontrib><creatorcontrib>Kang, Hyewon</creatorcontrib><creatorcontrib>Yang, Jaewan</creatorcontrib><creatorcontrib>Jung, Haneul</creatorcontrib><creatorcontrib>Lee, Seulki</creatorcontrib><creatorcontrib>Lee, Junghye</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE Open Access Journals</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><jtitle>IEEE internet of things journal</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Kim, Jaeho</au><au>Kang, Hyewon</au><au>Yang, Jaewan</au><au>Jung, Haneul</au><au>Lee, Seulki</au><au>Lee, Junghye</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Multi-task Deep Learning for Human Activity, Speed, and Body Weight Estimation using Commercial Smart Insoles</atitle><jtitle>IEEE internet of things journal</jtitle><stitle>JIoT</stitle><date>2023-04-13</date><risdate>2023</risdate><spage>1</spage><epage>1</epage><pages>1-1</pages><eissn>2327-4662</eissn><coden>IITJAU</coden><abstract>Healthcare professionals and individual users use wearable devices equipped with various sensors for healthcare management. Recently, the joint usage of artificial intelligence and these wearable sensors has played an essential role in healthcare management by providing a wide range of applications such as fitness tracking, gym activity monitoring, patient rehabilitation monitoring, and disease detection. These tasks eventually aim to enhance personal well-being and better manage the user's physical health by monitoring different activity types and body weight changes. Here, we present an efficient multi-task learning framework based on commercial smart insoles that can solve three tasks related to physical health management: activity classification, speed estimation, and body weight estimation. Our multi-task framework converts the sensor data from the smart insole to a recurrence plot, which shows significant performance improvement compared to processing the raw time series data. In addition, we utilized a modified MobileNetV2 as our backbone network, which has a total parameter of less than 100K and a computational budget of 0.34G of multiply-accumulate operations. Furthermore, we collected a vast dataset from 72 users carrying out 16 experiments, which contains the largest number of people for multi-task learning purposes using smart insoles. Extensive experiments show that the proposed multi-task learning framework is extremely efficient while outperforming or leading to comparable performance against single-task models.</abstract><pub>IEEE</pub><doi>10.1109/JIOT.2023.3267335</doi><orcidid>https://orcid.org/0009-0004-7162-0845</orcidid><orcidid>https://orcid.org/0000-0003-3221-1526</orcidid><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2327-4662
ispartof IEEE internet of things journal, 2023-04, p.1-1
issn 2327-4662
language eng
recordid cdi_ieee_primary_10102648
source IEEE Electronic Library (IEL)
subjects Artificial intelligence
body weight estimation
Deep learning
human activity recognition
Intelligent sensors
Medical services
multi-task learning
Multitasking
recurrence plot
Sensors
smart insole
speed estimation
Task analysis
title Multi-task Deep Learning for Human Activity, Speed, and Body Weight Estimation using Commercial Smart Insoles
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-25T22%3A33%3A52IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Multi-task%20Deep%20Learning%20for%20Human%20Activity,%20Speed,%20and%20Body%20Weight%20Estimation%20using%20Commercial%20Smart%20Insoles&rft.jtitle=IEEE%20internet%20of%20things%20journal&rft.au=Kim,%20Jaeho&rft.date=2023-04-13&rft.spage=1&rft.epage=1&rft.pages=1-1&rft.eissn=2327-4662&rft.coden=IITJAU&rft_id=info:doi/10.1109/JIOT.2023.3267335&rft_dat=%3Cieee%3E10102648%3C/ieee%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=10102648&rfr_iscdi=true