Redirigiendo al acceso original de articulo en 17 segundos...
Inicio  /  Applied Sciences  /  Vol: 12 Par: 21 (2022)  /  Artículo
ARTÍCULO
TITULO

Research on Generalized Hybrid Probability Convolutional Neural Network

Wenyi Zhou    
Hongguang Fan    
Jihong Zhu    
Hui Wen and Ying Xie    

Resumen

This paper first studies the generalization ability of the convolutional layer as a feature mapper (CFM) for extracting image features and the classification ability of the multilayer perception (MLP) in a CNN. Then, a novel generalized hybrid probability convolutional neural network (GHP-CNN) is proposed to solve abstract feature classification with an unknown distribution form. To measure the generalization ability of the CFM, a new index is defined and the positive correlation between it and the CFM is researched. Generally, a fully trained CFM can extract features that are beneficial to classification, regardless of whether the data participate in training the CFM. In the CNN, the fully connected layer in the MLP is not always optimal, and the extracted abstract feature has an unknown distribution. Thus, an improved classifier called the structure-optimized probabilistic neural network (SOPNN) is used for abstract feature classification in the GHP-CNN. In the SOPNN, the separability information is not lost in the normalization process, and the final classification surface is close to the optimal classification surface under the Bayesian criterion. The proposed GHP-CNN utilizes the generalization ability of the CFM and the classification ability of the SOPNN. Experiments show that the proposed network has better classification ability than the existing hybrid neural networks.

 Artículos similares

       
 
Aníbal Coronel, Fernando Huancas and Stefan Berres    
In the present article, we research the existence of the positive periodic solutions for a mathematical model that describes the propagation dynamics of a pathogen living within a vector population over a plant population. We propose a generalized compar... ver más
Revista: Applied Sciences

 
Yijiao Guo, Luchen Zhang, Lei Yu, Shaoze Luo, Chuang Liu and Yuan Liu    
To account for changes in the performance of spillway aerator structures of high-altitude dams, depressurization generalized model experiments and theoretical analyses were conducted in this study. Measurements were taken for ventilation hole air velocit... ver más
Revista: Water

 
Valerii Kozlovskyi, Ivan Shvets, Yurii Lysetskyi, Mikolaj Karpinski, Aigul Shaikhanova and Gulmira Shangytbayeva    
The classification of the natural and anthropogenic destabilizing factors of a telecommunications network as a complex system is presented herein. This research shows that to evaluate the parameters of a telecommunications network in the presence of dest... ver más
Revista: Information

 
Cornel Ilinca, Stefan Ciprian Stanca and Cristian Gabriel Anghel    
This study examines all of the equations necessary to derive the parameters for seven probability distributions of three parameters typically used in flood frequency research, namely the Pearson III (PE3), the generalized extreme value (GEV), the Weibull... ver más
Revista: Water

 
Md Whaiduzzaman, Adnan Sakib, Nisha Jaman Khan, Sudipto Chaki, Labiba Shahrier, Sudipto Ghosh, Md. Saifur Rahman, Md. Julkar Nayeen Mahi, Alistair Barros, Colin Fidge, Scott Thompson-Whiteside and Tony Jan    
This paper delves into the complex task of evaluating a website user interface (UI) and user experience (UX), a process complicated by gaps in research. To bridge this, we introduced an innovative human?computer interaction (HCI) framework that synergize... ver más
Revista: Applied Sciences