http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-112487991-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCAdditional | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2218-12 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F2218-08 |
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N20-10 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-214 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-23213 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-2411 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N20-10 |
| filingDate | 2020-12-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2022-12-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2022-12-16-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-112487991-B |
| titleOfInvention | A high-precision load identification method and system based on feature self-learning |
| abstract | The invention discloses a high-precision load identification method and system based on feature self-learning. The invention includes acquiring high-density and multi-dimensional electrical data, performing special waveform slicing operations according to a waveform extraction method, and pre-screening waveforms. The selected waveforms are placed into a waveform pool; the most appropriate features are selected for each waveform slice using a minimum redundancy and maximum correlation approach. The waveform slices are dynamically analyzed according to the optimal features, and the existing model is updated using a partial structure hiding support vector machine algorithm. Accurately identify the current waveform slice based on the classification model in the model library, and output the identification result. The invention can process high-density multi-dimensional sampling data, select the optimal feature set by using the minimum redundancy and maximum correlation through waveform extraction, and use the partial structure hidden support vector machine to automatically learn the dynamic load feature model, and Use the trained model for load identification. |
| priorityDate | 2020-12-02-04:00^^<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/SID456171974 |
Total number of triples: 18.