http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-WO2018150616-A1
Outgoing Links
Predicate | Object |
---|---|
classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N2291-0258 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L25-03 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-047 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-14 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-4472 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-52 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L25-51 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-088 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01H17-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-4427 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-46 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-4445 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01N29-52 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01N29-14 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01H11-08 |
filingDate | 2017-09-14-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2019-12-12-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | JP-WO2018150616-A1 |
titleOfInvention | Abnormal sound detection device, abnormality degree calculation device, abnormal sound generation device, abnormal sound detection learning device, abnormal signal detection device, abnormal signal detection learning device, methods and programs thereof |
abstract | Provided is an abnormal sound detection learning technique capable of generating a feature amount extraction function for detecting abnormal sound regardless of the presence or absence of abnormal sound learning data. The abnormal sound detection learning device is based on the first function update unit 3 that updates the input feature quantity extraction function and the feature quantity inverse transform function based on the optimization index of the variational auto encoder, and the normal sound learning data. An acoustic feature quantity extraction unit 4 that extracts an acoustic feature quantity of a normal sound, a normal sound model update part 5 that updates a normal sound model using the extracted acoustic feature quantity, and normal sound learning data and input A threshold update unit 6 that obtains a threshold value φ ρ corresponding to a false positive rate ρ that is a predetermined value using a feature amount extraction function, and a Neiman Pearson type in which the updated feature amount extraction function is determined by the obtained threshold value φ ρ And a second function updating unit 8 that updates based on the optimization index, and repeatedly performs the processing of each unit. |
priorityDate | 2017-02-15-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Predicate | Subject |
---|---|
isDiscussedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID415857418 http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID160283 |
Total number of triples: 25.