http://rdf.ncbi.nlm.nih.gov/pubchem/patent/KR-20120085164-A
Outgoing Links
Predicate | Object |
---|---|
assignee | http://rdf.ncbi.nlm.nih.gov/pubchem/patentassignee/MD5_80043ffec136c9502d017a28fe37b576 |
classificationCPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentcpc/G06N3-12 |
classificationIPCInventive | http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06F19-00 http://rdf.ncbi.nlm.nih.gov/pubchem/patentipc/G06N3-12 |
filingDate | 2011-10-06-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
inventor | http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_2c6fddb2e1c091ea9ac1c932ae4ca3f7 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_616d2633971f0bf6946da8c40068134a http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f7628b31b476d597e3f66a1268a71618 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_53a6b07844419552944dc5817b99338b http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_eedee71130caa0e53d03676ffb9d1049 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_f529341657694a59a5bd227c15aa713a http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_0c6da4e7714e778fa48b37380bc8b347 http://rdf.ncbi.nlm.nih.gov/pubchem/patentinventor/MD5_728de50191ff9a36d22eb403c35ffe26 |
publicationDate | 2012-07-31-04:00^^<http://www.w3.org/2001/XMLSchema#date> |
publicationNumber | KR-20120085164-A |
titleOfInvention | Multiple Linear Regression-Artificial Neural Network Hybrid Model Predicting Polarization Degree of Pure Organic Compound |
abstract | The present invention consists of up to five elements such as hydrogen (H), carbon (C), nitrogen (N), oxygen (O), and sulfur (S), and is composed of pure molecules consisting of up to 25 atoms except hydrogen. A mathematical model for predicting the polarizability of organic compounds with high accuracy is provided. The above model is based on the many multi-linearity of several organic descriptors as independent variables and polarity as dependent variables for a large number of organic compounds satisfying the above-mentioned conditions. An artificial neural network that obtains the best of the multiple linear regression models by using a genetic algorithm and then outputs the polarization degree by inputting the values of molecular descriptors included in the model. It is an example of a quantitative structure-property relationship (QSPR) model, which is a hybrid model of multiple linear regression-artificial neural network that further improves predictive performance by constructing. Predict the polarization degree of a compound purely made of this molecule. As such, the present invention provides a method for predicting a reliable polarization value even for a large number of organic compounds in which the experimental values are not known, thereby saving the cost and time required for the experiment, and thus promoting R & D activities in related industries. It produces effects such as facilitating. |
priorityDate | 2011-10-06-04:00^^<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/substance/SID458394811 |
Total number of triples: 20.