NETWORK EVALUATION METHOD, NETWORK EVALUATION DEVICE AND PROGRAM
To provide a network evaluation method, a network evaluation device and a program capable of extracting long-term feature quantity of a network without consuming memory, and learning the long-term feature quantity of the network while minimizing switching between kernel space and user space in OS as...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; jpn |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | TANIGUCHI ATSUSHI YAMADA HIROSHI MINAMI YUKI SAKAIDA NORIO KAWABATA TAICHI KURIMOTO TAKASHI URUSHIYA SHIGEO |
| description | To provide a network evaluation method, a network evaluation device and a program capable of extracting long-term feature quantity of a network without consuming memory, and learning the long-term feature quantity of the network while minimizing switching between kernel space and user space in OS as much as possible.SOLUTION: A network evaluation method and device according to the present invention are configured to: compress feature quantity of measured data of resource amount for a long-term in kernel space in OS hence to perform clustering learning; compress the learning result further for the long-term to perform the clustering learning; and thereafter repeatedly perform the same process a predetermined number of times.SELECTED DRAWING: Figure 1
【課題】ネットワークの長期的な特徴量をメモリを消費せずに抽出でき、ＯＳのカーネル空間とユーザ空間との切替を極力少なくしつつネットワークの長期的な特徴量を学習できるネットワーク評価方法、ネットワーク評価装置及びプログラムを提供することを目的とする。【解決手段】本発明に係るネットワーク評価方法及び装置は、資源量の計測データの特徴量に対してＯＳのカーネル空間で長周期に圧縮しクラスタリング学習を行い、その学習結果に対してさらに長周期に圧縮しクラスタリング学習を行い、以降、同様の処理を所定回数、繰り返し実行することとした。【選択図】図１ |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_JP2019057028A</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>JP2019057028A</sourcerecordid><originalsourceid>FETCH-epo_espacenet_JP2019057028A3</originalsourceid><addsrcrecordid>eNrjZHDwcw0J9w_yVnANc_QJdQzx9PdT8HUN8fB30VHAIuXiGubp7Krg6OeiEBDk7x7k6MvDwJqWmFOcyguluRmU3FxDnD10Uwvy41OLCxKTU_NSS-K9AowMDC0NTM0NjCwcjYlSBAAdrStL</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>NETWORK EVALUATION METHOD, NETWORK EVALUATION DEVICE AND PROGRAM</title><source>esp@cenet</source><creator>TANIGUCHI ATSUSHI ; YAMADA HIROSHI ; MINAMI YUKI ; SAKAIDA NORIO ; KAWABATA TAICHI ; KURIMOTO TAKASHI ; URUSHIYA SHIGEO</creator><creatorcontrib>TANIGUCHI ATSUSHI ; YAMADA HIROSHI ; MINAMI YUKI ; SAKAIDA NORIO ; KAWABATA TAICHI ; KURIMOTO TAKASHI ; URUSHIYA SHIGEO</creatorcontrib><description>To provide a network evaluation method, a network evaluation device and a program capable of extracting long-term feature quantity of a network without consuming memory, and learning the long-term feature quantity of the network while minimizing switching between kernel space and user space in OS as much as possible.SOLUTION: A network evaluation method and device according to the present invention are configured to: compress feature quantity of measured data of resource amount for a long-term in kernel space in OS hence to perform clustering learning; compress the learning result further for the long-term to perform the clustering learning; and thereafter repeatedly perform the same process a predetermined number of times.SELECTED DRAWING: Figure 1
【課題】ネットワークの長期的な特徴量をメモリを消費せずに抽出でき、ＯＳのカーネル空間とユーザ空間との切替を極力少なくしつつネットワークの長期的な特徴量を学習できるネットワーク評価方法、ネットワーク評価装置及びプログラムを提供することを目的とする。【解決手段】本発明に係るネットワーク評価方法及び装置は、資源量の計測データの特徴量に対してＯＳのカーネル空間で長周期に圧縮しクラスタリング学習を行い、その学習結果に対してさらに長周期に圧縮しクラスタリング学習を行い、以降、同様の処理を所定回数、繰り返し実行することとした。【選択図】図１</description><language>eng ; jpn</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2019</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190411&DB=EPODOC&CC=JP&NR=2019057028A$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20190411&DB=EPODOC&CC=JP&NR=2019057028A$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>TANIGUCHI ATSUSHI</creatorcontrib><creatorcontrib>YAMADA HIROSHI</creatorcontrib><creatorcontrib>MINAMI YUKI</creatorcontrib><creatorcontrib>SAKAIDA NORIO</creatorcontrib><creatorcontrib>KAWABATA TAICHI</creatorcontrib><creatorcontrib>KURIMOTO TAKASHI</creatorcontrib><creatorcontrib>URUSHIYA SHIGEO</creatorcontrib><title>NETWORK EVALUATION METHOD, NETWORK EVALUATION DEVICE AND PROGRAM</title><description>To provide a network evaluation method, a network evaluation device and a program capable of extracting long-term feature quantity of a network without consuming memory, and learning the long-term feature quantity of the network while minimizing switching between kernel space and user space in OS as much as possible.SOLUTION: A network evaluation method and device according to the present invention are configured to: compress feature quantity of measured data of resource amount for a long-term in kernel space in OS hence to perform clustering learning; compress the learning result further for the long-term to perform the clustering learning; and thereafter repeatedly perform the same process a predetermined number of times.SELECTED DRAWING: Figure 1
【課題】ネットワークの長期的な特徴量をメモリを消費せずに抽出でき、ＯＳのカーネル空間とユーザ空間との切替を極力少なくしつつネットワークの長期的な特徴量を学習できるネットワーク評価方法、ネットワーク評価装置及びプログラムを提供することを目的とする。【解決手段】本発明に係るネットワーク評価方法及び装置は、資源量の計測データの特徴量に対してＯＳのカーネル空間で長周期に圧縮しクラスタリング学習を行い、その学習結果に対してさらに長周期に圧縮しクラスタリング学習を行い、以降、同様の処理を所定回数、繰り返し実行することとした。【選択図】図１</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2019</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZHDwcw0J9w_yVnANc_QJdQzx9PdT8HUN8fB30VHAIuXiGubp7Krg6OeiEBDk7x7k6MvDwJqWmFOcyguluRmU3FxDnD10Uwvy41OLCxKTU_NSS-K9AowMDC0NTM0NjCwcjYlSBAAdrStL</recordid><startdate>20190411</startdate><enddate>20190411</enddate><creator>TANIGUCHI ATSUSHI</creator><creator>YAMADA HIROSHI</creator><creator>MINAMI YUKI</creator><creator>SAKAIDA NORIO</creator><creator>KAWABATA TAICHI</creator><creator>KURIMOTO TAKASHI</creator><creator>URUSHIYA SHIGEO</creator><scope>EVB</scope></search><sort><creationdate>20190411</creationdate><title>NETWORK EVALUATION METHOD, NETWORK EVALUATION DEVICE AND PROGRAM</title><author>TANIGUCHI ATSUSHI ; YAMADA HIROSHI ; MINAMI YUKI ; SAKAIDA NORIO ; KAWABATA TAICHI ; KURIMOTO TAKASHI ; URUSHIYA SHIGEO</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_JP2019057028A3</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; jpn</language><creationdate>2019</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>TANIGUCHI ATSUSHI</creatorcontrib><creatorcontrib>YAMADA HIROSHI</creatorcontrib><creatorcontrib>MINAMI YUKI</creatorcontrib><creatorcontrib>SAKAIDA NORIO</creatorcontrib><creatorcontrib>KAWABATA TAICHI</creatorcontrib><creatorcontrib>KURIMOTO TAKASHI</creatorcontrib><creatorcontrib>URUSHIYA SHIGEO</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>TANIGUCHI ATSUSHI</au><au>YAMADA HIROSHI</au><au>MINAMI YUKI</au><au>SAKAIDA NORIO</au><au>KAWABATA TAICHI</au><au>KURIMOTO TAKASHI</au><au>URUSHIYA SHIGEO</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>NETWORK EVALUATION METHOD, NETWORK EVALUATION DEVICE AND PROGRAM</title><date>2019-04-11</date><risdate>2019</risdate><abstract>To provide a network evaluation method, a network evaluation device and a program capable of extracting long-term feature quantity of a network without consuming memory, and learning the long-term feature quantity of the network while minimizing switching between kernel space and user space in OS as much as possible.SOLUTION: A network evaluation method and device according to the present invention are configured to: compress feature quantity of measured data of resource amount for a long-term in kernel space in OS hence to perform clustering learning; compress the learning result further for the long-term to perform the clustering learning; and thereafter repeatedly perform the same process a predetermined number of times.SELECTED DRAWING: Figure 1
【課題】ネットワークの長期的な特徴量をメモリを消費せずに抽出でき、ＯＳのカーネル空間とユーザ空間との切替を極力少なくしつつネットワークの長期的な特徴量を学習できるネットワーク評価方法、ネットワーク評価装置及びプログラムを提供することを目的とする。【解決手段】本発明に係るネットワーク評価方法及び装置は、資源量の計測データの特徴量に対してＯＳのカーネル空間で長周期に圧縮しクラスタリング学習を行い、その学習結果に対してさらに長周期に圧縮しクラスタリング学習を行い、以降、同様の処理を所定回数、繰り返し実行することとした。【選択図】図１</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; jpn |
| recordid | cdi_epo_espacenet_JP2019057028A |
| source | esp@cenet |
| subjects | CALCULATING COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | NETWORK EVALUATION METHOD, NETWORK EVALUATION DEVICE AND PROGRAM |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-22T12%3A04%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=TANIGUCHI%20ATSUSHI&rft.date=2019-04-11&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EJP2019057028A%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |