http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111207739-A
Outgoing Links
| Predicate | Object |
|---|---|
| assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_4ce984e4ec645c861ce04414132ccb58 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01C21-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-045 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-048 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01C21-16 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01C21-20 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01C21-16 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
| filingDate | 2018-11-22-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_20c084a2b9e522fc14afc9febcbbdb36 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_9be407321c51fb92197c6ac4613f6ece http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_7f2b4d9a13755bdc98e59fba0fc6fbe9 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_db3675044431b713a7fe2fa29416e81a http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_fe563ad2fa86aeb5bee06cff31513241 |
| publicationDate | 2020-05-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-111207739-A |
| titleOfInvention | Pedestrian zero-speed detection method and device based on GRU neural network |
| abstract | The present invention provides a pedestrian zero-speed detection method based on a GRU neural network. The GRU includes an update gate and a reset gate, and includes the following steps: receiving and recording data x t sent by the IMU in real time; The data h t-1 output by the hidden layer at a moment outputs a value between 0 and 1 through the update gate, and the update gate vector u t is obtained by calculation; the data x t and the data h t-1 enter the sigmoid layer of the reset gate and output a A value between 0 and 1, the reset gate vector r t is calculated, and the tanh layer creates a new candidate memory value vector Take the update gate vector u t as the weight vector, the candidate memory value vector The output vector h t of the GRU unit is obtained by weighted averaging with the data h t-1 output by the hidden layer at the previous moment; select different data x t as the input vector to repeat the above steps, carry out GRU training and verification, and obtain the optimal GRU model , to detect and judge the pedestrian zero speed on the collected data. |
| isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114019182-A |
| priorityDate | 2018-11-22-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 28.