Automated Software Engineering: A Deep Learning-Based Approach

This book discusses various open issues in software engineering, such as the efficiency of automated testing techniques, predictions for cost estimation, data processing, and automatic code generation. Many traditional techniques are available for addressing these problems. But, with the rapid changes in software development, they often prove to be outdated or incapable of handling the software’s complexity. Hence, many previously used methods are proving insufficient to solve the problems now arising in software development.

The book highlights a number of unique problems and effective solutions that reflect the state-of-the-art in software engineering. Deep learning is the latest computing technique, and is now gaining popularity in various fields of software engineering. This book explores new trends and experiments that have yielded promising solutions to current challenges in software engineering. As such, it offers a valuable reference guide for a broad audience including systems analysts, software engineers, researchers, graduate students and professors engaged in teaching software engineering.

Chapter 1: Selection of Significant Metrics for Improving the Performance of Change-Proneness Modules.- Chapter 2: Effort Estimation of Web based Applications using ERD, use Case Point Method and Machine Learning.- Chapter 3: Usage of Machine Learning in Software Testing.- Chapter 4: Test Scenarios Generation using Combined Object-Oriented Models.- Chapter 5: A Novel Approach of Software Fault Prediction using Deep Learning Technique.- Chapter 6: Feature-Based Semi-Supervised Learning to Detect Malware from Android.