http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113113140-B
Outgoing Links
Predicate | Object |
---|---|
classificationCPCInventive | 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/G16H10-60 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16H50-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16H50-30 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16H10-60 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16H50-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16H50-70 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate | 2021-04-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
grantDate | 2022-09-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationDate | 2022-09-23-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-113113140-B |
titleOfInvention | Diabetes early warning method, system, device and storage medium based on self-supervised DNN |
abstract | The invention discloses a diabetes early warning method based on self-supervision DNN. Including: firstly perform data preprocessing on the original body index data, including label processing, numerical processing, standardization processing, missing value processing, and feature value selection processing; secondly, three deep neural networks are designed, and the processed data is used as input to model Batch iterative training; then perform the above data processing steps on the original body index data of the user to be predicted, input the trained model, and visualize the risk of diabetes for early warning. The invention also discloses a diabetes early warning system based on the self-supervision DNN, a computer device and a computer-readable storage medium. The self-supervised learning method of the present invention can mine the deep correlation of user health indicators with a small amount of label data, and the designed model can be adapted to other prediction tasks, and has the advantages of reliability and extensiveness. |
priorityDate | 2021-04-02-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 226.