http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-113919387-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_5ff4fc6caa37975b806f3313cae18215 |
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/G06F18-2135 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06F18-24323 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-165 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-726 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-7264 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-372 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/A61B5-16 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/A61B5-372 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/A61B5-00 |
filingDate | 2021-08-18-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_967f556f22d0ae72747cf337e0049d09 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0ebc5ca0033fdd2d3c6d38df3917bb87 |
publicationDate | 2022-01-11-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-113919387-A |
titleOfInvention | Emotion recognition of EEG signals based on GBDT-LR model |
abstract | The invention relates to an EEG signal emotion recognition method based on GBDT-LR model, wherein the EEG signal emotion recognition method based on GBDT-LR model comprises: firstly acquiring a data set of related EEG signals, preprocessing the data set, Use the filtering method to remove the artifacts, use the principal component analysis to reduce its dimension, and obtain a clean EEG signal, then use the wavelet packet decomposition algorithm to extract the small band features in the signal, and then use the information theory algorithm to extract the permutation entropy, Approximate entropy and sample entropy features, which are combined into a feature matrix. The features are then sent to the gradient boosting decision tree (GBDT) model for automatic re-screening and selection of features, and the results of GBDT are One-hot encoded to form new training data, and finally the new features are trained in the classifier. For testing, the classifier is a logistic regression (LR) classifier. |
priorityDate | 2021-08-18-04:00^^<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/compound/CID8879 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID414864229 |
Total number of triples: 25.