http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114023449-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_d94573ab2c57e8b193f3a22accddf9fe |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16H50-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G16H50-20 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16H50-30 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G16H50-20 |
filingDate | 2021-11-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_066cd626f0d9ef5969d7c832c254bb02 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_4111e606f9e4845c2c6528ec96f03476 |
publicationDate | 2022-02-08-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-114023449-A |
titleOfInvention | Diabetes risk early warning method and system based on depth self-encoder |
abstract | The invention discloses a diabetes risk early warning method and system based on a depth self-encoder. The method comprises the following steps: acquiring a physical examination data set and preprocessing the physical examination data set; dividing the label-free data set into a training set, a verification set and a test set, and generating labels of the depth self-encoder; designing an encoder and a decoder part of the depth self-encoder, and respectively training and evaluating the encoder and the decoder part by using the training set, the verification set and the test set; and predicting the diabetes risk of the individual to be tested by using the evaluated depth self-encoder and the trained regression model. The invention also discloses a diabetes risk early warning computer device based on the depth self-encoder and a computer readable storage medium. The invention introduces the depth self-encoder, can utilize a small amount of label data more fully; more accurate diabetes early warning is carried out by training a deep self-encoder in advance and combining a logistic regression model; is suitable for different diabetes types and symptoms, and has stronger practicability, generalization and expansibility. |
isCitedBy | http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115359916-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114860922-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114438036-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114438036-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115148361-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115148361-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114783608-B http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114783608-A http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-114860922-B |
priorityDate | 2021-11-05-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
type | http://data.epo.org/linked-data/def/patent/Publication |
Incoming Links
Total number of triples: 269.