An optimized machine learning approach for fault detection and reliability estimation of software testing

Abstract

The past two decades had witnessed a great deal of revolution in the field of digital technology with many state of the art gadgets and handheld devices running on efficient user interfaces. Consumers will brand a product based on several metrics such as error free performance, compatibility with the existing environment, adaptability to changing environments, etc. The overall satisfaction of the consumer is quantified in a general term known as quality of service. Quality of service is dependent on several functional attributes and performance measures. On a backtracking approach, it could be found that performance and functional ability are made possible by the required hardware which in turn is activated or driven by efficient software running in the background. Consumers were widely and drastically attracted to the innumerable smart features incorporated into the operating systems. The efficiency of such operating systems is essentially a software that is largely attributed to the design methodology followed by the rigorous and precise testing methodology employed to maintain the software running without any bugs or errors which becomes a nuisance for consumers. The issue of software testing has been taken as the prime objective of this thesis which by itself is a broad area of research and it is being actively researched in recent time. Hence, the field of software testing is gaining widespread significance with a wide range of testing methodologies and techniques being employed to improve the quality of service rendered to the consumers. newline