ABNORMALITY MODEL LEARNING DEVICE, METHOD, AND PROGRAM
Accuracy of unsupervised anomalous sound detection is improved using a small number of pieces of anomalous sound data. A threshold deciding part (13) calculates an anomaly score for each of a plurality of pieces of anomalous sound data, using a normal model learned with normal sound data and an anom...
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng ; fre ; ger |
| 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 | KOIZUMI, Yuma HARADA, Noboru KAWACHI, Yuta SAITO, Shoichiro NAKAGAWA, Akira MURATA, Shin |
| description | Accuracy of unsupervised anomalous sound detection is improved using a small number of pieces of anomalous sound data. A threshold deciding part (13) calculates an anomaly score for each of a plurality of pieces of anomalous sound data, using a normal model learned with normal sound data and an anomaly model expressing the pieces of anomalous sound data, and decides a minimum value among the anomaly scores as a threshold. A weight updating part (14) updates, using a plurality of pieces of normal sound data, the pieces of anomalous sound data and the threshold, weights of the anomaly model so that all the pieces of anomalous sound data are judged as anomalous, and probability of the pieces of normal sound data being judged as anomalous is minimized. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_EP3680639B1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>EP3680639B1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_EP3680639B13</originalsourceid><addsrcrecordid>eNrjZDBzdPLzD_J19PEMiVTw9Xdx9VHwcXUM8vP0c1dwcQ3zdHbVUfB1DfHwd9FRcPRzUQgI8ncPcvTlYWBNS8wpTuWF0twMCm6uIc4euqkF-fGpxQWJyal5qSXxrgHGZhYGZsaWTobGRCgBAKoLJ0Q</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ABNORMALITY MODEL LEARNING DEVICE, METHOD, AND PROGRAM</title><source>esp@cenet</source><creator>KOIZUMI, Yuma ; HARADA, Noboru ; KAWACHI, Yuta ; SAITO, Shoichiro ; NAKAGAWA, Akira ; MURATA, Shin</creator><creatorcontrib>KOIZUMI, Yuma ; HARADA, Noboru ; KAWACHI, Yuta ; SAITO, Shoichiro ; NAKAGAWA, Akira ; MURATA, Shin</creatorcontrib><description>Accuracy of unsupervised anomalous sound detection is improved using a small number of pieces of anomalous sound data. A threshold deciding part (13) calculates an anomaly score for each of a plurality of pieces of anomalous sound data, using a normal model learned with normal sound data and an anomaly model expressing the pieces of anomalous sound data, and decides a minimum value among the anomaly scores as a threshold. A weight updating part (14) updates, using a plurality of pieces of normal sound data, the pieces of anomalous sound data and the threshold, weights of the anomaly model so that all the pieces of anomalous sound data are judged as anomalous, and probability of the pieces of normal sound data being judged as anomalous is minimized.</description><language>eng ; fre ; ger</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; COMPUTING ; CONTROL OR REGULATING SYSTEMS IN GENERAL ; CONTROLLING ; COUNTING ; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS ; MEASURING ; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS ; PHYSICS ; REGULATING ; TESTING ; TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES ; TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR</subject><creationdate>2023</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=20231115&DB=EPODOC&CC=EP&NR=3680639B1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,780,885,25564,76547</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20231115&DB=EPODOC&CC=EP&NR=3680639B1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>KOIZUMI, Yuma</creatorcontrib><creatorcontrib>HARADA, Noboru</creatorcontrib><creatorcontrib>KAWACHI, Yuta</creatorcontrib><creatorcontrib>SAITO, Shoichiro</creatorcontrib><creatorcontrib>NAKAGAWA, Akira</creatorcontrib><creatorcontrib>MURATA, Shin</creatorcontrib><title>ABNORMALITY MODEL LEARNING DEVICE, METHOD, AND PROGRAM</title><description>Accuracy of unsupervised anomalous sound detection is improved using a small number of pieces of anomalous sound data. A threshold deciding part (13) calculates an anomaly score for each of a plurality of pieces of anomalous sound data, using a normal model learned with normal sound data and an anomaly model expressing the pieces of anomalous sound data, and decides a minimum value among the anomaly scores as a threshold. A weight updating part (14) updates, using a plurality of pieces of normal sound data, the pieces of anomalous sound data and the threshold, weights of the anomaly model so that all the pieces of anomalous sound data are judged as anomalous, and probability of the pieces of normal sound data being judged as anomalous is minimized.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</subject><subject>COMPUTING</subject><subject>CONTROL OR REGULATING SYSTEMS IN GENERAL</subject><subject>CONTROLLING</subject><subject>COUNTING</subject><subject>FUNCTIONAL ELEMENTS OF SUCH SYSTEMS</subject><subject>MEASURING</subject><subject>MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS</subject><subject>PHYSICS</subject><subject>REGULATING</subject><subject>TESTING</subject><subject>TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES</subject><subject>TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2023</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNrjZDBzdPLzD_J19PEMiVTw9Xdx9VHwcXUM8vP0c1dwcQ3zdHbVUfB1DfHwd9FRcPRzUQgI8ncPcvTlYWBNS8wpTuWF0twMCm6uIc4euqkF-fGpxQWJyal5qSXxrgHGZhYGZsaWTobGRCgBAKoLJ0Q</recordid><startdate>20231115</startdate><enddate>20231115</enddate><creator>KOIZUMI, Yuma</creator><creator>HARADA, Noboru</creator><creator>KAWACHI, Yuta</creator><creator>SAITO, Shoichiro</creator><creator>NAKAGAWA, Akira</creator><creator>MURATA, Shin</creator><scope>EVB</scope></search><sort><creationdate>20231115</creationdate><title>ABNORMALITY MODEL LEARNING DEVICE, METHOD, AND PROGRAM</title><author>KOIZUMI, Yuma ; HARADA, Noboru ; KAWACHI, Yuta ; SAITO, Shoichiro ; NAKAGAWA, Akira ; MURATA, Shin</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_EP3680639B13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng ; fre ; ger</language><creationdate>2023</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>CONTROL OR REGULATING SYSTEMS IN GENERAL</topic><topic>CONTROLLING</topic><topic>COUNTING</topic><topic>FUNCTIONAL ELEMENTS OF SUCH SYSTEMS</topic><topic>MEASURING</topic><topic>MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS</topic><topic>PHYSICS</topic><topic>REGULATING</topic><topic>TESTING</topic><topic>TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES</topic><topic>TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR</topic><toplevel>online_resources</toplevel><creatorcontrib>KOIZUMI, Yuma</creatorcontrib><creatorcontrib>HARADA, Noboru</creatorcontrib><creatorcontrib>KAWACHI, Yuta</creatorcontrib><creatorcontrib>SAITO, Shoichiro</creatorcontrib><creatorcontrib>NAKAGAWA, Akira</creatorcontrib><creatorcontrib>MURATA, Shin</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>KOIZUMI, Yuma</au><au>HARADA, Noboru</au><au>KAWACHI, Yuta</au><au>SAITO, Shoichiro</au><au>NAKAGAWA, Akira</au><au>MURATA, Shin</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ABNORMALITY MODEL LEARNING DEVICE, METHOD, AND PROGRAM</title><date>2023-11-15</date><risdate>2023</risdate><abstract>Accuracy of unsupervised anomalous sound detection is improved using a small number of pieces of anomalous sound data. A threshold deciding part (13) calculates an anomaly score for each of a plurality of pieces of anomalous sound data, using a normal model learned with normal sound data and an anomaly model expressing the pieces of anomalous sound data, and decides a minimum value among the anomaly scores as a threshold. A weight updating part (14) updates, using a plurality of pieces of normal sound data, the pieces of anomalous sound data and the threshold, weights of the anomaly model so that all the pieces of anomalous sound data are judged as anomalous, and probability of the pieces of normal sound data being judged as anomalous is minimized.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng ; fre ; ger |
| recordid | cdi_epo_espacenet_EP3680639B1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING CONTROL OR REGULATING SYSTEMS IN GENERAL CONTROLLING COUNTING FUNCTIONAL ELEMENTS OF SUCH SYSTEMS MEASURING MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS PHYSICS REGULATING TESTING TESTING STATIC OR DYNAMIC BALANCE OF MACHINES ORSTRUCTURES TESTING STRUCTURES OR APPARATUS NOT OTHERWISE PROVIDED FOR |
| title | ABNORMALITY MODEL LEARNING DEVICE, METHOD, AND PROGRAM |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-01T09%3A49%3A15IST&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=KOIZUMI,%20Yuma&rft.date=2023-11-15&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EEP3680639B1%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 |