Software reliability forecasting method based on selective dynamic weight neural network integration

Abstract

The invention belongs to the field of software reliability forecasting, and particularly relates to a software reliability forecasting method based on selective dynamic weight neural network integration. The software reliability forecasting method mainly includes the steps: A, generating neural network individuals: selecting Elman neural networks as network individuals and generating n neural network individuals by a Bagging algorithm; B, optimizing the individuals: firstly, determining the cluster number of the generated neural network individuals by a K value optimization algorithm, secondly, clustering the neural network individuals according to a K-mean clustering algorithm to increase individual difference, and finally, integrating the clustered individuals; C, building a dynamic model: building a dynamic weight model based on a fuzzy neural network by the aid of errors of fitting data of the optimized individuals; and D, performing integrated output: combining forecasting results of the optimized individuals with weights generated by the dynamic weight model to generate final forecasting results. A neural network integration algorithm is applied to software reliability forecasting, and the software reliability forecasting method has the advantages of high precision and fine stability.

Description

technical field [0001] The invention belongs to the field of software reliability prediction and can be used for software reliability prediction, in particular to a software reliability prediction method based on selective dynamic weight neural network integration. Background technique [0002] With the continuous development of information technology, computer software has been greatly developed and widely used. However, due to the uncontrollability of the environment in which the computer system is located, potential errors in the software are often induced due to the user's wrong operation, resulting in system failure, which seriously threatens people's lives and property safety. Therefore, people's demand for high-quality software is more and more urgent, and software reliability, which is an important indicator of software quality, has become the focus of attention. [0003] Since the development of software reliability theory, a large number of models and variants hav...

AI Technical Summary

Problems solved by technology

[0005] The present invention proposes a software reliability prediction method for selective dynamic weight neural network integration to overcome problems such as unrobustness and overfitting that exist in the prediction of a single neural network model

Images