http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-108416367-B
Outgoing Links
| Predicate | Object |
|---|---|
| classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-253 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24147 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24155 |
| classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 |
| filingDate | 2018-02-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| grantDate | 2021-12-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationDate | 2021-12-10-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| publicationNumber | CN-108416367-B |
| titleOfInvention | Sleep staging method based on decision-level fusion of multi-sensor data |
| abstract | The invention discloses a sleep staging method based on multi-sensor data decision-level fusion. The method first uses radar sensors and audio sensors to collect radar and audio data throughout the night, and extracts radar and audio signal features; Classification, establish the radar residual segment model and the radar + audio segment model according to the data classification; then use the classifier to identify and classify the radar features in the radar residual segment model, and obtain the model prediction result 1, and use the classifier to classify the radar + audio segment model. The radar and audio features are identified and classified, and the model prediction results A and B are obtained; then the naive Bayesian model is used to make decisions on the model prediction results A and B, and the model prediction result 2 is obtained; finally, the model prediction result 1 and the model prediction result 2. Perform time series splicing to obtain the results of sleep staging for the whole night. The method is simple and easy to implement, has high accuracy, and is consistent with the actual situation. |
| priorityDate | 2018-02-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
| type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 15.