Loading…
Reduction of Communication Cost for Edge-Heavy Sensor using Divided CNN
Sensor networks allow us to collect data, such as camera images, over a wide area. Understanding the sensing area by aggregating and processing the data from multiple sensors is promising. Deep Learning (DL) is a powerful method for interpreting data. However, communication cost on the sensor networ...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 245 |
| container_issue | |
| container_start_page | 244 |
| container_title | |
| container_volume | |
| creator | Ikeda, Yoshihiro Yanagisawa, Yutaka Kishino, Yasue Mizutani, Shin Shirai, Yoshinari Suyama, Takayuki Matsumura, Kohei Noma, Haruo |
| description | Sensor networks allow us to collect data, such as camera images, over a wide area. Understanding the sensing area by aggregating and processing the data from multiple sensors is promising. Deep Learning (DL) is a powerful method for interpreting data. However, communication cost on the sensor network and computational cost on the server are two substantial problems of aggregating and processing data from multiple sensors. We therefore propose divided processing of the DL between a server and a powerful Edge-Heavy Sensor (EHS). In our study, we reduced transmission data to twelve times lower than the amount of raw input data while maintaining a 4.5% decrease in the DL's recognition accuracy. |
| doi_str_mv | 10.1109/RTCSA.2018.00042 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_8607260</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8607260</ieee_id><sourcerecordid>8607260</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-9f257334fe2667a3d731ab7d307ecd9e0adf81bcc4fbbab58f309487684d56b93</originalsourceid><addsrcrecordid>eNotjE9LwzAcQKMgOGbvgpd8gdb8afJLjiPOTRgTtnkeSZOMiG2laQf79g719ODxeAg9UlJRSvTz7mD2i4oRqipCSM1uUKFBUcGVBBBa36IZ40yUlBN6j4qcP68ZpwCasRla7YKfmjH1He4jNn3bTl1q7K8wfR5x7Ae89KdQroM9X_A-dPlqppy6E35J5-SDx2a7fUB30X7lUPxzjj5elwezLjfvqzez2JSJghhLHZkAzusYmJRguQdOrQPPCYTG60Csj4q6pqmjc9YJFTnRtQKpai-k03yOnv6-KYRw_B5Sa4fLUUkCTBL-A2JITBo</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Reduction of Communication Cost for Edge-Heavy Sensor using Divided CNN</title><source>IEEE Xplore All Conference Series</source><creator>Ikeda, Yoshihiro ; Yanagisawa, Yutaka ; Kishino, Yasue ; Mizutani, Shin ; Shirai, Yoshinari ; Suyama, Takayuki ; Matsumura, Kohei ; Noma, Haruo</creator><creatorcontrib>Ikeda, Yoshihiro ; Yanagisawa, Yutaka ; Kishino, Yasue ; Mizutani, Shin ; Shirai, Yoshinari ; Suyama, Takayuki ; Matsumura, Kohei ; Noma, Haruo</creatorcontrib><description>Sensor networks allow us to collect data, such as camera images, over a wide area. Understanding the sensing area by aggregating and processing the data from multiple sensors is promising. Deep Learning (DL) is a powerful method for interpreting data. However, communication cost on the sensor network and computational cost on the server are two substantial problems of aggregating and processing data from multiple sensors. We therefore propose divided processing of the DL between a server and a powerful Edge-Heavy Sensor (EHS). In our study, we reduced transmission data to twelve times lower than the amount of raw input data while maintaining a 4.5% decrease in the DL's recognition accuracy.</description><identifier>EISSN: 2325-1301</identifier><identifier>EISBN: 9781538677599</identifier><identifier>EISBN: 1538677598</identifier><identifier>DOI: 10.1109/RTCSA.2018.00042</identifier><identifier>CODEN: IEEPAD</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Computational efficiency ; Deep learning ; Edge Computing ; Image coding ; Information science ; Sensor Network ; Sensors ; Servers</subject><ispartof>2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), 2018, p.244-245</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8607260$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,27925,54555,54932</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8607260$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Ikeda, Yoshihiro</creatorcontrib><creatorcontrib>Yanagisawa, Yutaka</creatorcontrib><creatorcontrib>Kishino, Yasue</creatorcontrib><creatorcontrib>Mizutani, Shin</creatorcontrib><creatorcontrib>Shirai, Yoshinari</creatorcontrib><creatorcontrib>Suyama, Takayuki</creatorcontrib><creatorcontrib>Matsumura, Kohei</creatorcontrib><creatorcontrib>Noma, Haruo</creatorcontrib><title>Reduction of Communication Cost for Edge-Heavy Sensor using Divided CNN</title><title>2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)</title><addtitle>RTCSA</addtitle><description>Sensor networks allow us to collect data, such as camera images, over a wide area. Understanding the sensing area by aggregating and processing the data from multiple sensors is promising. Deep Learning (DL) is a powerful method for interpreting data. However, communication cost on the sensor network and computational cost on the server are two substantial problems of aggregating and processing data from multiple sensors. We therefore propose divided processing of the DL between a server and a powerful Edge-Heavy Sensor (EHS). In our study, we reduced transmission data to twelve times lower than the amount of raw input data while maintaining a 4.5% decrease in the DL's recognition accuracy.</description><subject>Cameras</subject><subject>Computational efficiency</subject><subject>Deep learning</subject><subject>Edge Computing</subject><subject>Image coding</subject><subject>Information science</subject><subject>Sensor Network</subject><subject>Sensors</subject><subject>Servers</subject><issn>2325-1301</issn><isbn>9781538677599</isbn><isbn>1538677598</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2018</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotjE9LwzAcQKMgOGbvgpd8gdb8afJLjiPOTRgTtnkeSZOMiG2laQf79g719ODxeAg9UlJRSvTz7mD2i4oRqipCSM1uUKFBUcGVBBBa36IZ40yUlBN6j4qcP68ZpwCasRla7YKfmjH1He4jNn3bTl1q7K8wfR5x7Ae89KdQroM9X_A-dPlqppy6E35J5-SDx2a7fUB30X7lUPxzjj5elwezLjfvqzez2JSJghhLHZkAzusYmJRguQdOrQPPCYTG60Csj4q6pqmjc9YJFTnRtQKpai-k03yOnv6-KYRw_B5Sa4fLUUkCTBL-A2JITBo</recordid><startdate>201808</startdate><enddate>201808</enddate><creator>Ikeda, Yoshihiro</creator><creator>Yanagisawa, Yutaka</creator><creator>Kishino, Yasue</creator><creator>Mizutani, Shin</creator><creator>Shirai, Yoshinari</creator><creator>Suyama, Takayuki</creator><creator>Matsumura, Kohei</creator><creator>Noma, Haruo</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201808</creationdate><title>Reduction of Communication Cost for Edge-Heavy Sensor using Divided CNN</title><author>Ikeda, Yoshihiro ; Yanagisawa, Yutaka ; Kishino, Yasue ; Mizutani, Shin ; Shirai, Yoshinari ; Suyama, Takayuki ; Matsumura, Kohei ; Noma, Haruo</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-9f257334fe2667a3d731ab7d307ecd9e0adf81bcc4fbbab58f309487684d56b93</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2018</creationdate><topic>Cameras</topic><topic>Computational efficiency</topic><topic>Deep learning</topic><topic>Edge Computing</topic><topic>Image coding</topic><topic>Information science</topic><topic>Sensor Network</topic><topic>Sensors</topic><topic>Servers</topic><toplevel>online_resources</toplevel><creatorcontrib>Ikeda, Yoshihiro</creatorcontrib><creatorcontrib>Yanagisawa, Yutaka</creatorcontrib><creatorcontrib>Kishino, Yasue</creatorcontrib><creatorcontrib>Mizutani, Shin</creatorcontrib><creatorcontrib>Shirai, Yoshinari</creatorcontrib><creatorcontrib>Suyama, Takayuki</creatorcontrib><creatorcontrib>Matsumura, Kohei</creatorcontrib><creatorcontrib>Noma, Haruo</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE/IET Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Ikeda, Yoshihiro</au><au>Yanagisawa, Yutaka</au><au>Kishino, Yasue</au><au>Mizutani, Shin</au><au>Shirai, Yoshinari</au><au>Suyama, Takayuki</au><au>Matsumura, Kohei</au><au>Noma, Haruo</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Reduction of Communication Cost for Edge-Heavy Sensor using Divided CNN</atitle><btitle>2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)</btitle><stitle>RTCSA</stitle><date>2018-08</date><risdate>2018</risdate><spage>244</spage><epage>245</epage><pages>244-245</pages><eissn>2325-1301</eissn><eisbn>9781538677599</eisbn><eisbn>1538677598</eisbn><coden>IEEPAD</coden><abstract>Sensor networks allow us to collect data, such as camera images, over a wide area. Understanding the sensing area by aggregating and processing the data from multiple sensors is promising. Deep Learning (DL) is a powerful method for interpreting data. However, communication cost on the sensor network and computational cost on the server are two substantial problems of aggregating and processing data from multiple sensors. We therefore propose divided processing of the DL between a server and a powerful Edge-Heavy Sensor (EHS). In our study, we reduced transmission data to twelve times lower than the amount of raw input data while maintaining a 4.5% decrease in the DL's recognition accuracy.</abstract><pub>IEEE</pub><doi>10.1109/RTCSA.2018.00042</doi><tpages>2</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | EISSN: 2325-1301 |
| ispartof | 2018 IEEE 24th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), 2018, p.244-245 |
| issn | 2325-1301 |
| language | eng |
| recordid | cdi_ieee_primary_8607260 |
| source | IEEE Xplore All Conference Series |
| subjects | Cameras Computational efficiency Deep learning Edge Computing Image coding Information science Sensor Network Sensors Servers |
| title | Reduction of Communication Cost for Edge-Heavy Sensor using Divided CNN |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-07T15%3A39%3A35IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Reduction%20of%20Communication%20Cost%20for%20Edge-Heavy%20Sensor%20using%20Divided%20CNN&rft.btitle=2018%20IEEE%2024th%20International%20Conference%20on%20Embedded%20and%20Real-Time%20Computing%20Systems%20and%20Applications%20(RTCSA)&rft.au=Ikeda,%20Yoshihiro&rft.date=2018-08&rft.spage=244&rft.epage=245&rft.pages=244-245&rft.eissn=2325-1301&rft.coden=IEEPAD&rft_id=info:doi/10.1109/RTCSA.2018.00042&rft.eisbn=9781538677599&rft.eisbn_list=1538677598&rft_dat=%3Cieee_CHZPO%3E8607260%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i175t-9f257334fe2667a3d731ab7d307ecd9e0adf81bcc4fbbab58f309487684d56b93%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=8607260&rfr_iscdi=true |