http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-111474297-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24147 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N33-0006 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2135 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G01N33-0001 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G01N33-00 |
filingDate | 2020-03-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2022-05-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2022-05-03-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-111474297-B |
titleOfInvention | An online drift compensation method for sensors in a bionic olfactory system |
abstract | The invention relates to an online drift compensation method of a sensor in a bionic olfactory system, belonging to the technical field of sensors. The method includes the following steps: step 1) reconstructing the source domain according to the input sample batch number; step 2) constructing a classification model using the reconstructed source domain and target domain samples and saving the prediction result. The source domain is reconstructed using the output response samples of the sensors in the bionic olfactory system in two successive batches, that is, the previous batch of samples that have been predicted by the classification model and the initial batch of manually annotated samples, and then through the conditional distribution adaptive and Manifold regularization builds a classification model to realize online drift compensation of sensors in a bionic olfactory system. The invention can continuously update the gas identification model with the drift of the sensor, which is more in line with the actual production and usage scenarios of the bionic olfactory system in real scenarios, and can prolong the service life of the equipment. |
priorityDate | 2020-03-09-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 18.