http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2018150616-A1

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_60e21de07fa18fc54e2150daffc14654
classificationCPCAdditional http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N2291-0258
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L25-51
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/G01N29-46
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G10L25-03
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-088
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-14
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01H17-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-4472
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-4427
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-4445
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N29-52
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01N29-14
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01H17-00
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01N29-52
filingDate 2017-09-14-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_8acd2132451274b15cf5761cd8516180
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_3a0e9d2bb050231406448071e8466694
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9872f360908788bd4f3c1ab922442ee6
publicationDate 2018-08-23-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber WO-2018150616-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, and methods and programs therefor
abstract The present invention provides an abnormal sound detection learning technology that is able to generate a feature-quantity extraction function for detection of abnormal sound, irrespective of the availability of abnormal sound learning data. The abnormal sound detection learning device comprises: a first function updating unit 3 which updates, on the basis of an optimized index of a variational autoencoder, a feature-quantity inverse transformation function and a feature-quantity extraction function which have been inputted; an acoustic feature-quantity extraction unit 4 which extracts an acoustic feature quantity of normal sound on the basis of normal sound learning data; a normal sound model updating unit 5 which updates a normal sound model using the extracted acoustic feature quantity; a threshold updating unit 6 which calculates a threshold value φ ρ corresponding to a false positive rate ρ, which is a specific value, using the normal sound learning data and the inputted feature-quantity extraction function; and a second function updating unit 8 which updates the updated feature-quantity extraction function on the basis of a Neyman-Pearson-type optimization index determined by the calculated threshold φ ρ , wherein the processes performed by the respective units are repeated.
isCitedBy http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113095559-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-2020102671-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-2020125971-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-7254649-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2020202567-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/AU-2019404523-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-7283096-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-11493912-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-2021015405-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-2021144054-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2023120438-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-11489746-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-7196954-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-11609157-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-11604170-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2020129610-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/US-11366627-B2
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/JP-7127525-B2
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/compound/CID160283
http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID415857418

Total number of triples: 47.