Investigation of Software Reliability Prediction Using Statistical and Machine Learning Methods

Software reliability is a statistical measure of how well software operates with respect to its requirements. There are two related software engineering research issues about reliability requirements. The first issue is achieving the necessary reliability, i.e., choosing and employing appropriate software engineering techniques in system design and implementation. The second issue is the assessment of reliability as a method of assurance that precedes system deployment. In past few years, various software reliability models have been introduced. These models have been developed in response to the need of software engineers, system engineers and managers to quantify the concept of software reliability. This chapter investigates performance of some classical and intelligent machine learning techniques such as Linear regression (LR), Radial basis function network (RBFN), Generalized regression neural network (GRNN), Support vector machine (SVM), to predict software reliability. The effectiveness of LR and machine learning methods is demonstrated with the help of sixteen datasets taken from Data & Analysis Centre for Software (DACS). Two performance measures, root mean squared error (RMSE) and mean absolute percentage error (MAPE) is compared quantitatively obtained from rigorous experiments.

Machine Learning and Value-Based Software Engineering

Software and Intelligent Sciences ◽

10.4018/978-1-4666-0261-8.ch017 ◽

2012 ◽

pp. 287-301

Author(s):

Du Zhang

Keyword(s):

Machine Learning ◽

Software Engineering ◽

Full Range ◽

Training Data ◽

Learning Methods ◽

Engineering Research ◽

Machine Learning Applications ◽

Value Propositions ◽

Software engineering research and practice thus far are primarily conducted in a value-neutral setting where each artifact in software development such as requirement, use case, test case, and defect, is treated as equally important during a software system development process. There are a number of shortcomings of such value-neutral software engineering. Value-based software engineering is to integrate value considerations into the full range of existing and emerging software engineering principles and practices. Machine learning has been playing an increasingly important role in helping develop and maintain large and complex software systems. However, machine learning applications to software engineering have been largely confined to the value-neutral software engineering setting. In this paper, the general message to be conveyed is to apply machine learning methods and algorithms to value-based software engineering. The training data or the background knowledge or domain theory or heuristics or bias used by machine learning methods in generating target models or functions should be aligned with stakeholders’ value propositions. An initial research agenda is proposed for machine learning in value-based software engineering.

Machine Learning and Value-Based Software Engineering

Software Applications ◽

10.4018/978-1-60566-060-8.ch192 ◽

2009 ◽

pp. 3325-3339

Author(s):

Du Zhang

Keyword(s):

Machine Learning ◽

Software Engineering ◽

Full Range ◽

Training Data ◽

Learning Methods ◽

Engineering Research ◽

Machine Learning Applications ◽

Value Propositions ◽

Software engineering research and practice thus far are primarily conducted in a value-neutral setting where each artifact in software development such as requirement, use case, test case, and defect, is treated as equally important during a software system development process. There are a number of shortcomings of such value-neutral software engineering. Value-based software engineering is to integrate value considerations into the full range of existing and emerging software engineering principles and practices. Machine learning has been playing an increasingly important role in helping develop and maintain large and complex software systems. However, machine learning applications to software engineering have been largely confined to the value-neutral software engineering setting. In this paper, the general message to be conveyed is to apply machine learning methods and algorithms to value-based software engineering. The training data or the background knowledge or domain theory or heuristics or bias used by machine learning methods in generating target models or functions should be aligned with stakeholders’ value propositions. An initial research agenda is proposed for machine learning in value-based software engineering.

Ubiquitous Machine Learning and Its Applications - Advances in Computational Intelligence and Robotics ◽

Application of Machine Learning Techniques for Software Reliability Prediction (SRP)

10.4018/978-1-5225-2545-5.ch006 ◽

2017 ◽

pp. 113-142

Author(s):

Pradeep Kumar

Keyword(s):

Software Engineering ◽

Software Reliability ◽

Machine Learning Techniques ◽

Reliability Prediction ◽

Engineering Research ◽

Reliability Models ◽

Software Products ◽

Software Reliability Prediction ◽

Software Release ◽

Software reliability is a statistical measure of how well software operates with respect to its requirements. There are two related software engineering research issues about reliability requirements. The first issue is achieving the necessary reliability, i.e., choosing and employing appropriate software engineering techniques in system design and implementation. The second issue is the assessment of reliability as a method of assurance that precedes system deployment. In past few years, various software reliability models have been introduced. These models have been developed in response to the need of software engineers, system engineers and managers to quantify the concept of software reliability. This chapter on software reliability prediction using ANNs addresses three main issues: (1) analyze, manage, and improve the reliability of software products; (2) satisfy the customer needs for competitive price, on time delivery, and reliable software product; (3) determine the software release instance that is, when the software is good enough to release to the customer.

Comparative analysis of software reliability predictions using statistical and machine learning methods

International Journal of Intelligent Systems Technologies and Applications ◽

10.1504/ijista.2013.056529 ◽

2013 ◽

Vol 12 (3/4) ◽

pp. 230 ◽

Cited By ~ 1

Author(s):

Pradeep Kumar ◽

Yogesh Singh

Keyword(s):

Machine Learning ◽

Comparative Analysis ◽

Software Reliability ◽

Learning Methods ◽

Machine Learning Methods

Comparing Supervised Machine Learning Techniques for Genre Analysis in Software Engineering Research Articles

10.26615/978-954-452-072-4_008 ◽

2021 ◽

Author(s):

Felipe A. de Britto ◽

◽

Thiago C. Ferreira ◽

Leonardo P. Nunes ◽

Fernando S. Parreiras ◽

...

Keyword(s):

Machine Learning ◽

Software Engineering ◽

Supervised Machine Learning ◽

Machine Learning Techniques ◽

Research Articles ◽

Genre Analysis ◽

Engineering Research ◽

Learning Techniques ◽

Handbook of Research on Innovations and Applications of AI, IoT, and Cognitive Technologies - Advances in Computational Intelligence and Robotics ◽

A Research on Software Engineering Research in Machine Learning

10.4018/978-1-7998-6870-5.ch024 ◽

2021 ◽

pp. 359-371

Author(s):

Komali Dammalapati ◽

B. Sankara Babu ◽

P. Gopala Krishna ◽

V. Subba Ramaiah

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Software Engineering ◽

Rapid Growth ◽

Simulation Models ◽

Software Simulation ◽

Engineering Research ◽

With rapid growth of various well-known methods implemented by the engineers in the software field in order to create a development in automated tasks for manufacturers and researchers working worldwide, the researchers in the field of software engineering (SE) root for concepts of machine learning (ML), a subfield that utilizes deep learning (DL) for the development of such SE tasks. In essence, these systems would highly cope with the featured automation with inbuilt capabilities in engineering to develop the software simulation models. Nevertheless, it is very tough to condense the present scenario in research of situations that necessitate failures, successes, and openings in DL for software-based technology. The survey works for renowned technology of SE and DL held for the latest journals and conferences leading to the span of 85 issued papers throughout 23 distinctive tasks for SE.

Research on the usability of different machine learning methods in visibility forecasting

10.20937/atm.53053 ◽

2021 ◽

Author(s):

Pak Wai Chan ◽

Wu Wen ◽

Lei Li

Keyword(s):

Machine Learning ◽

Wind Speed ◽

Percentage Error ◽

Support Vector ◽

K Nearest Neighbor ◽

Learning Methods ◽

Haze Pollution ◽

Low Visibility ◽

Visibility Forecasting

Haze pollution, mainly characterized by low visibility, is one of the main environmental problems currently faced by China. Accurate haze forecasts facilitate the implementation of preventive measures to control the emission of air pollutants and, thereby mitigate haze pollution. However, it is not easy to accurately predict the low visibility events induced by haze, which requires not only accurate prediction for weather elements, but also refined and real-time updated source emission inventory. In order to obtain reliable forecasting tools, this paper studies the usability of several popular machine learning methods, such as support vector machine, k-nearest neighbor, random forest, as well as several deep learning methods, on the visibility forecasting. Starting from the main factors related to visibility, the relationships between wind speed, wind direction, temperature, humidity, and visibility are discussed. Training and forecasting were performed using the machine learning methods. The accuracy of these methods in visibility forecasting was confirmed through several parameters (i.e., root-mean-square error, mean absolute error, and mean absolute percentage error). The results show that: (1) Among all meteorological parameters, wind speed was the best at reflecting the visibility change patterns; (2) RNN LSTM, and GRU methods performs almost equally well on short-term visibility forecasts(i.e. 1h, 3h, and 6h); (3) A classical machine learning method (i.e. the SVM) performs well in mid- and long-term visibility forecasts; (4) The machine learning methods also have a certain degree of forecast accuracy even for long time periods (e.g. of 72h).