MDPI - Publisher of Open Access Journals

22 pages, 1776 KiB

Open AccessArticle

Prediction and Comparative Analysis of Software Reliability Model Based on NHPP and Deep Learning

by Youn Su Kim, Kwang Yoon Song and In Hong Chang

Appl. Sci. 2023, 13(11), 6730; https://doi.org/10.3390/app13116730 - 31 May 2023

Cited by 7 | Viewed by 2173

Over time, software has become increasingly important in various fields. If the current software is more dependent than in the past and is broken owing to large and small issues, such as coding and system errors, it is expected to cause significant damage to the entire industry. To address this problem, the field of software reliability is crucial. In the past, efforts in software reliability were made to develop models by assuming a nonhomogeneous Poisson-process model (NHPP); however, as models became more complex, there were many special cases in which models fit well. Hence, this study proposes a software reliability model using deep learning that relies on data rather than mathematical and statistical assumptions. A software reliability model based on recurrent neural networks (RNN), long short-term memory (LSTM), and gated recurrent units (GRU), which are the most basic deep and recurrent neural networks, was constructed. The dataset was divided into two, Datasets 1 and 2, which both used 80% and 90% of the entire data, respectively. Using 11 criteria, the estimated and learned results based on these datasets proved that the software reliability model using deep learning has excellent capabilities. The software reliability model using GRU showed the most satisfactory results. Full article

(This article belongs to the Special Issue Smart Service Technology for Industrial Applications II)

► Show Figures

Figure 1

32 pages, 4657 KiB

Open AccessArticle

Quantitative Quality Evaluation of Software Products by Considering Summary and Comments Entropy of a Reported Bug

by Madhu Kumari, Ananya Misra, Sanjay Misra, Luis Fernandez Sanz, Robertas Damasevicius and V.B. Singh

Entropy 2019, 21(1), 91; https://doi.org/10.3390/e21010091 - 19 Jan 2019

Cited by 23 | Viewed by 5160

Abstract

A software bug is characterized by its attributes. Various prediction models have been developed using these attributes to enhance the quality of software products. The reporting of bugs leads to high irregular patterns. The repository size is also increasing with enormous rate, resulting in uncertainty and irregularities. These uncertainty and irregularities are termed as veracity in the context of big data. In order to quantify these irregular and uncertain patterns, the authors have appliedentropy-based measures of the terms reported in the summary and the comments submitted by the users. Both uncertainties and irregular patterns have been taken care of byentropy-based measures. In this paper, the authors considered that the bug fixing process does not only depend upon the calendar time, testing effort and testing coverage, but it also depends on the bug summary description and comments. The paper proposed bug dependency-based mathematical models by considering the summary description of bugs and comments submitted by users in terms of the entropy-based measures. The models were validated on different Eclipse project products. The models proposed in the literature have different types of growth curves. The models mainly follow exponential, S-shaped or mixtures of both types of curves. In this paper, the proposed models were compared with the modelsfollowingexponential, S-shaped and mixtures of both types of curves. Full article

► Show Figures

Figure 1

Search Results (2)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI

Saved Queries

Search Filter Reset All

Years

Feature Papers

Subjects

Journals

Article Types

Countries / Regions

Search Results (2)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI