Thesis (M.A.(Information Science))--University of Pretoria, 2001.

Thesis (M.S.)--West Virginia University, 2010. / Title from document title page. Document formatted into pages; contains ix, 128 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 93-102).

Thesis (Ph. D.)--University of Canterbury, 2007. / Typescript (photocopy). Includes bibliographical references (p. 215-227). Also available via the World Wide Web.

Thesis (Ph. D.)--West Virginia University, 2007. / Title from document title page. Document formatted into pages; contains xi, 129 p. : ill. Includes abstract. Includes bibliographical references (p. 125-129).

Thesis (M.S.)--West Virginia University, 2001. / Title from document title page. Document formatted into pages; contains vi, 75 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 53-54).

The research community in software engineering is trying to find a way on how to achieve the goal of having a fault-free software. The industry that will use a near fault-free software will have it easier to lower the costs of maintenance and the versions of delivered software will be more qualitative. In this case, fault prediction can be used in order to achieve the above objectives. Fully applied fault prediction is not yet achieved on an industrial scale. There is some progress attained in the field during recent years. But knowing and understanding what available tools and algorithms regarding fault prediction can give is yet a goal to be achieved by the industry. In this thesis, two fault prediction algorithms and several metrics combinations are tested in an industrial and open source project. The main goal is to understand how much fault prediction is integrated and effective in a continuous delivery environment using real case scenarios. The manually collected data, from several versions and in different time periods were applied using two already present algorithms: Naive Bayes and Clustering. As a result, while the usage of this prediction depends on the company needs, further research in the field can be extended.

No description available.

No description available.

No description available.

Context: With the rising popularity of machine learning, looking at its shortcomings is valuable in seeing how well machine learning is applicable. Is it possible to apply the clustering with a small dataset? Objectives: This thesis consists of a literature study, a survey and an experiment. It investigates how two different unsupervised machine learning algorithms DBSCAN(Density-Based Spatial Clustering of Applications with Noise) and K-means run on a dataset gathered from a survey. Methods: Making a survey where we can see statistically what most people chose and apply clustering with the data from the survey to confirm if the clustering has the same patterns as what people have picked statistically. Results: It was possible to identify patterns with clustering algorithms using a small dataset. The literature studies show examples that both algorithms have been used successfully. Conclusions: It's possible to see patterns using DBSCAN and K-means on a small dataset. The size of the dataset is not necessarily the only aspect to take into consideration, feature and parameter selection are both important as well since the algorithms need to be tuned and customized to the data.