http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110046675-A

Outgoing Links

Predicate Object
assignee http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_5f2c23a543ebe192f369de8d3d8d9180
classificationCPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-253
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214
http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045
classificationIPCInventive http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62
http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04
filingDate 2019-04-25-04:00^^<http://www.w3.org/2001/XMLSchema#date>
inventor http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_50944688dee80e1a16d58f8da742660a
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_b3e2bd6ccb6f564fe2dc3b514f315762
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_1883b29c2d5c8092a69c0f2fad593305
http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_5d97a1af65862ec70e83fe02cf5d398a
publicationDate 2019-07-23-04:00^^<http://www.w3.org/2001/XMLSchema#date>
publicationNumber CN-110046675-A
titleOfInvention An evaluation method of lower limb motor ability based on improved convolutional neural network
abstract The invention discloses a lower limb movement ability evaluation method based on an improved convolutional neural network. The depth data is binarized by the bilateral filtering method to obtain the gait contour image; the knee joint angle is calculated by the space vector method; the gait contour feature of the gait contour image is extracted by the improved convolutional neural network; The contour feature and the knee joint angle were serially combined and normalized, and then the feature dimension was reduced by the kernel principal component analysis method. This method automatically extracts video image features by using an improved convolutional neural network with a spatial pyramid pooling layer and COCOB optimization algorithm added to the traditional convolutional neural network, which greatly reduces the complexity and improves the evaluation accuracy.
isCitedBy http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112472531-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-110895818-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111680608-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112401834-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112998694-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113537164-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/WO-2021217542-A1
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113537164-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112842261-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112842261-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112906673-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111369626-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112233084-A
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111680608-B
http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112998694-A
priorityDate 2019-04-25-04:00^^<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/SID419512635
http://rdf.ncbi.nlm.nih.gov/pubchem/compound/CID962

Total number of triples: 34.