http://rdf.ncbi.nlm.nih.gov/pubchem/patent/CN-115227266-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_2fca358171fed028f7c7821b53a663da |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-7267 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/A61B5-389 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06K9-62 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/A61B5-389 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-08 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-04 |
filingDate | 2022-06-29-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_15694d21421ad23b94f53fae92637fe2 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f3a102174c073cbebf9d31d53c5c0257 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_cebc833f27c7c20a47a42897fc7ef3f6 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_c4f91670a3efa157dde36063b5dc4b18 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_cd72f46345e91cd98eac28018b9fd783 |
publicationDate | 2022-10-25-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | CN-115227266-A |
titleOfInvention | A kind of myoelectric signal classification method, computer equipment and readable storage medium |
abstract | The invention belongs to the technical field of medical signal analysis, and specifically discloses an electromyographic signal classification method, computer equipment and a readable storage medium. Among them, the EMG signal classification method first obtains multiple eigenmode functions through empirical mode decomposition of EMG signals, which not only retains the information of the original data to the greatest extent, but also approximates the clinical manual quantitative analysis method to a certain extent; Then a dual-branch fusion network is constructed. By using two convolutional layers with different size convolution kernels and different sizes of pooling layers as a dual-branch structure, the output dimension of each branch is the same, and the dual-branch output is fused in the channel dimension. , the network combines dense blocks, transformation blocks and other structures, which can not only increase the diversity of feature information, but also reduce parameters and reduce the risk of overfitting, and can retain important information of the global context. The invention can accurately classify the electromyographic signals of ALS patients and healthy people, and is convenient to provide reference for auxiliary diagnosis of ALS. |
priorityDate | 2022-06-29-04:00^^<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/CID22978774 http://rdf.ncbi.nlm.nih.gov/pubchem/substance/SID419701332 |
Total number of triples: 22.