Deep Cross-Project Software Reliability Growth Model Using Project Similarity-Based Clustering

Software reliability is an essential characteristic for ensuring the qualities of software products. Predicting the potential number of bugs from the beginning of a development project allows practitioners to make the appropriate decisions regarding testing activities. In the initial development phases, applying traditional software reliability growth models (SRGMs) with limited past data does not always provide reliable prediction result for decision making. To overcome this, herein, we propose a new software reliability modeling method called a deep cross-project software reliability growth model (DC-SRGM). DC-SRGM is a cross-project prediction method that uses features of previous projects’ data through project similarity. Specifically, the proposed method applies cluster-based project selection for the training data source and modeling by a deep learning method. Experiments involving 15 real datasets from a company and 11 open source software datasets show that DC-SRGM can more precisely describe the reliability of ongoing development projects than existing traditional SRGMs and the LSTM model.

Deep Cross-Project Software Reliability Growth Model using Project Similarity Based Clustering

Software reliability is an important characteristic for ensuring the qualities of software products. Predicting the potential number of bugs from the beginning of a development project allows practitioners to make the appropriate decisions regarding testing activities. In the initial development phases, applying traditional software reliability growth models (SRGMs) with limited past data does not always provide reliable prediction result for decision making. To overcome this, herein we propose a new software reliability modeling method called deep cross-project software reliability growth model (DC-SRGM). DC-SRGM is a cross-project prediction method that uses features of previous projects’ data through project similarity. Specifically, the proposed method applies cluster-based project selection for training data source and modeling by a deep learning method. Experiments involving 15 real datasets from a company and 11 open source software datasets show that DC-SRGM can more precisely describe the reliability of ongoing development projects than existing traditional SRGMs and the LSTM model.

Developing a hybrid software reliability growth model

PurposeThe purpose of this paper is to develop a new software reliability growth model considering different fault distribution function before and after the change point.Design/methodology/approachIn this paper, the authors have developed a framework to incorporate change-point in developing a hybrid software reliability growth model by considering different distribution functions before and after the change point.FindingsNumerical illustration suggests that the proposed model gives better results in comparison to the existing models.Originality/valueThe existing literature on change point-based software reliability growth model assumes that the fault correction trend before and after the change is governed by the same distribution. This seems impractical as after the change in the testing environment, the trend of fault detection or correction may not follow the same trend; hence, the assumption of same distribution function may fail to predict the potential number of faults. The modelling framework assumes different distributions before and after change point in developing a software reliability growth model.

A STUDY OF VARIOUS SOFTWARE RELIABILITY SYSTEMS BY USING ANN

One of the quantifiable credits of software quality is reliability.Programmable/ Software Reliability Growth Model (SRGM) can be used for continuous quality during difficult times. In all conditions where test work fluctuates over time, the customary time-sensitive SRGM may not be clear enough. In order to close this gap, testing work was used instead of time in SRGM. It may be unwise to put forward a restricted test pressure limit in advance because the test work will be endless within the incomprehensible test time. Later in this article, we propose a permanent test stress service related to the old inhomogeneous Poisson process model (NHPP). We use an artificial neural network (ANN) to configure the proposed model, which contains frustration data from the software. Here, it is reasonable to obtain a huge load of game plans for the comparison model, which represents past disappointment data in a comparable way. We use artificial intelligence methods to select game plans with reasonable load for the model to describe the past and future data well. We use a reasonable software disappointment data set to decompose the presentation of the proposed model from the current model. Use the artificial neural network method to design the general Direct Software Reliability Growth Model (SRGM) through test work.: The true quality software is shown by current research mainly focuses on the best method of general guessing modeling.