Software failures prediction using RBF neural network
One of the prospective techniques for software reliability prediction are those based on nonparametric models, in particular on artificial neural networks. In this paper the study of influence of number of input neurons of network based on radial basis function on the efficiency of software failures...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Odessa National Polytechnic University
2015-06-01
|
Series: | Trudy Odesskogo Politehničeskogo Universiteta |
Subjects: | |
Online Access: | http://pratsi.opu.ua/articles/show/1493 |
Summary: | One of the prospective techniques for software reliability prediction are those based on nonparametric models, in particular on artificial neural networks. In this paper the study of influence of number of input neurons of network based on radial basis function on the efficiency of software failures prediction presented in the form of time series is carried out. Software faults time series are constructed using Chromium and Chromium-OS open source software systems testing data with proposed further processing as a normalized values of the number of software failures in equal intervals, followed by transfer to man-days. It is demonstrated that the closest prediction can be achieved using Inverse Multiquadric activation function with 10…20 input layer neurons and 30 hidden neurons. |
---|---|
ISSN: | 2076-2429 2223-3814 |