Predict Software Failures Research Articles

Prevent: An Unsupervised Approach to Predict Software Failures in Production

Prevent: An Unsupervised Approach to Predict Software Failures in Production

Prevent: An Unsupervised Approach to Predict Software Failures in Production

Prevent: An Unsupervised Approach to Predict Software Failures in Production

Prevent: An Unsupervised Approach to Predict Software Failures in Production

Prevent: An Unsupervised Approach to Predict Software Failures in Production

Data sampling approach using heuristic Learning Vector Quantization (LVQ) classifier for software defect prediction

On the basis of quality estimate, early prediction and identification of software flaws is crucial in the software area. Prediction of Software Defects SDP is defined as the process of exposing software to flaws through the use of prediction models and defect datasets. This study recommended a method for dealing with the class imbalance problem based on Improved Random Synthetic Minority Oversampling Technique (SMOTE), followed by Linear Pearson Correlation Technique to perform feature selection to predict software failure. On the basis of the SMOTE data sampling approach, a strategy for software defect prediction is given in this paper. To address the class imbalance, the defect datasets were initially processed using the Improved Random-SMOTE Oversampling technique. Then, using the Linear Pearson Correlation approach, the features were chosen, and using the k-fold cross validation process, the samples were split into training and testing datasets. Finally, Heuristic Learning Vector Quantization is used to classify data in order to predict software problems. Based on measures like sensitivity, specificity, FPR, and accuracy rate for two separate datasets, the performance of the proposed strategy is contrasted with the approaches to classification that presently exist.

PREVENT: A Semi-Supervised Approach to Predict Software Failures in Production new

PREVENT: A Semi-Supervised Approach to Predict Software Failures in Production new

PREVENT: A Semi-Supervised Approach to Predict Software Failures in Production

PREVENT: A Semi-Supervised Approach to Predict Software Failures in Production

PREVENT: A Semi-Supervised Approach to Predict Software Failures in Production

PREVENT: A Semi-Supervised Approach to Predict Software Failures in Production

Predicting failures in agile software development through data analytics

Artificial intelligence-driven software development paradigms have been attracting much attention in academia, industry and the government. More specifically, within the last 5 years, a wave of data analytics is affecting businesses from all domains, influencing engineering management practices in many industries and making a difference in academic research. Several major software vendors have been adopting a form of "intelligent" development in one or more phases of their software development processes. Agile for example, is a well-known example of a lifecycle used to build intelligent and analytical systems. The agile process consists of multiple sprints; in each sprint a specific software feature is developed, tested, refined and documented. However, because agile development depends on the context of the project, testing is performed differently in every sprint. This paper introduces a method to predict software failures in the subsequent agile sprints. That is achieved by utilizing analytical and statistical methods (such as using Mean Time between Failures and modelling regression). The novel method is called: analytics-driven testing (ADT). ADT predicts errors and their locations (with a certain statistical confidence level). That is done by continuously measuring MTBF for software components, and using a forecasting regression model for estimating where and what types of software system failures are likely to occur. ADT is presented and evaluated.

A generalized JM model with applications to imperfect debugging in software reliability

For their nice mathematical properties, state space models have been widely used, especially for forecasting. Over the last decades, the study of tracking software reliability by statistical models has attracted scientists’ attention. However, most of models focus on perfect debugging although practically imperfect debugging arises everywhere. In this paper, a non-Gaussian state space model is modified to predict software failure time with imperfect debugging. In fact, this model is very flexible so that we can modify the system equation in this model to satisfy the various situations. Besides, this model is suitable for tracking software reliability, and applied to two well known datasets on software failures.

Prediction of software failures through logistic regression

The quality of software has been a main concern since the inception of computer software. To be able to produce high quality software, software developers and software testers alike need continuous improvements in their developing and testing methodologies. These improvements should result in better coverage of the input domain, efficient test cases, and in spending fewer testing resources. In this paper we focus on an approach for generating efficient test cases based on the special properties of Design of Experiments and developing a logistic regression model of predicting test case outcomes. Design of Experiments will be utilized to efficiently minimize the number of test cases and the logistic regression model will be used to predict software failures. This approach, in turn, would provide the software tester with a model that reduces the number of test cases, predicts test case outcomes, reduces cost, and allows better forecast of release readiness. We demonstrate our approach using two case studies (TI Interactive software and Microsoft's Pocket PC operating system).

Predicting operational software availability and its applications to telecommunication systems

It is essential to predict customer-perceived software availability during software development and determine when to release the software to maintain a balance among time-to-market, development cost and software quality. This paper presents methods and procedures to predict software failure rates from a user perspective in system test phases and to reverse-engineer in order to estimate software release time for given availability targets. Software reliability analysis is conducted based on non-homogenous Poisson process models. Software system test data of current release are used to estimate the number of residual faults by the end of system tests and data of previous releases or similar products (including system test data, post-system test data and field failure data) provide a means to predict a user-perceived average failure rate of a fault. Software system availability can be predicted from these estimates. Both execution and calendar times are considered. A software resource utilization model is developed to transfer one testing time to another. A telecommunications application illustrates how to calculate the failure rate and testing time to meet the software availability requirements.

A study of the exponential smoothing technique in software reliability growth prediction

Software reliability models can provide quantitative measures of the reliability of software systems which are of growing importance today. Most of the models are parametric ones which rely on the modelling of the software failure process as a Markov or non-homogeneous Poisson process. It has been noticed that many of them do not give a very accurate prediction of future software failures as the focus is on the fitting of past data. In this paper we study the use of the double exponential smoothing technique to predict software failures. The proposed approach is a non-parametric one and has the ability of providing more accurate prediction compared with traditional parametric models because it gives a higher weight to the most recent failure data for a better prediction of future behaviour. The method is very easy to use and requires a very limited amount of data storage and computational effort. It can be updated instantly without much calculation. Hence it is a tool that should be more commonly used in practice. Numerical examples are shown to highlight the applicability. Comparisons with other commonly used software reliability growth models are also presented. © 1997 John Wiley & Sons, Ltd.