Open AccessUsing Derived kernel as a new Method for Recognition a Similarity Learning.
Author(s) -
Ramadhan Abdo Musleh Alsaidi,
Ayed R. A. Alanzi,
Saleh Rehiel Alenazi,
Madallah Alruwaili
Publication year - 2020
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.c5705.029320
Subject(s) - pattern recognition (psychology) , pearson product moment correlation coefficient , artificial intelligence , entropy (arrow of time) , correlation coefficient , computer science , similarity measure , machine learning , kernel (algebra) , correlation , measure (data warehouse) , artificial neural network , similarity (geometry) , mathematics , data mining , statistics , physics , quantum mechanics , combinatorics , image (mathematics) , geometry
A new technique for feature withdrawal by neural response is going to be familiarized in this research work by merging an entropy measure with Squared Pearson correlation Coefficient (SPCC) method. The process of choosing effective models on the basis of entropy measures was proposed further to enhance the ability to select templates. For more accurate similarity measure we used the statistical significant relationship between functions. The research illustrate that the proposed method is proficiently compared with the state-of-the-art methods.