Affinity Propagation-Based Probability Neural Network Structure Optimization

2014 ◽  
Author(s):  
Yingjuan Xie ◽  
Xinnan Fan ◽  
Junfeng Chen
Keyword(s):  
Neural Network ◽  
Network Structure ◽  
Structure Optimization ◽  
Affinity Propagation ◽  
Probability Neural Network ◽  
Neural Network Structure ◽  
Network Structure Optimization

scholarly journals Feature Selection Combined with Neural Network Structure Optimization for HIV-1 Protease Cleavage Site Prediction

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Hui Liu ◽  
Xiaomiao Shi ◽  
Dongmei Guo ◽  
Zuowei Zhao ◽  
Yimin
Keyword(s):  
Neural Network ◽  
Feature Selection ◽  
Structure Optimization ◽  
Decision Fusion ◽  
Prediction Performance ◽  
Protease Cleavage ◽  
Neural Network Structure ◽  
Network Structure Optimization ◽  
Cleavage Site Prediction ◽  
Hiv 1

It is crucial to understand the specificity of HIV-1 protease for designing HIV-1 protease inhibitors. In this paper, a new feature selection method combined with neural network structure optimization is proposed to analyze the specificity of HIV-1 protease and find the important positions in an octapeptide that determined its cleavability. Two kinds of newly proposed features based on Amino Acid Index database plus traditional orthogonal encoding features are used in this paper, taking both physiochemical and sequence information into consideration. Results of feature selection prove thatp2,p1,p1′, andp2′are the most important positions. Two feature fusion methods are used in this paper: combination fusion and decision fusion aiming to get comprehensive feature representation and improve prediction performance. Decision fusion of subsets that getting after feature selection obtains excellent prediction performance, which proves feature selection combined with decision fusion is an effective and useful method for the task of HIV-1 protease cleavage site prediction. The results and analysis in this paper can provide useful instruction and help designing HIV-1 protease inhibitor in the future.

The Research on Optimization Neural Network Structure Parallel Genetic Algorithm

2012 ◽  
Vol 220-223 ◽  
pp. 2564-2569
Author(s):  
Ming Yan Yu ◽  
Ying Yan ◽  
Hai Yuan Liu ◽  
He Cai Zhi
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Network Structure ◽  
Approximation Error ◽  
Parallel Genetic Algorithm ◽  
Large Space ◽  
Reliable Performance ◽  
Neural Network Structure ◽  
Network Structure Optimization ◽  
Unequal Length

This paper combines the global optimization ability of the symbiotic parallel genetic algorithm and the local optimization ability of the improved LMBP algorithm to research,proposes an neural network structure optimization symbiotic parallel genetic algorithm and to testify the correctness and validity of this algorithm by the simulation experiments. This algorithm realizes unequal length coding, large probability cross, small probability variation, cross and variation between sub-populations, information exchanging between sub-populations etc, and successful implements the optimization of neural network structure. The experimental results shows that this algorithm having reliable performance, searching a large space, be able to find the feasible solution within the specified generalization and approximation error range.

Sign in / Sign up

Export Citation Format

Share Document