Machine learning applied to bi-heterocyclic drugs recognition

M. R. Nowak,K. Nowak, M. Grzelczak,B. Szlachetko,L. Sterczewski,E. F. Plinski,P. Swiatek,M. Strzelecka,S. Plinska,W. Malinka

international conference on infrared, millimeter, and terahertz waves（2017）

Cited 1|Views4

No score

Abstract

The application of various statistical machine learning methods for the identification of bi-heterocyclic drugs that are based on the THz spectra is presented. A comparison of classification efficiency with six algorithms (LDA, QDA, SVM, Naive Bayes, KNN with Euclidean metrics and the cosine similarity) is shown and a complete THz system allowing for the identification of drugs with an efficiency of 98% is realized.

Translated text

Key words

bi-heterocyclic drugs recognition,THz spectra,classification efficiency,Naive Bayes,Euclidean metrics,statistical machine learning,bi-heterocyclic drugs identification,LDA,QDA,SVM,KNN,cosine similarity

AI Read Science

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper

Chat Paper

Summary is being generated by the instructions you defined