AI-powered quality assurance: Enhancing software infrastructure through intelligent fault detection
Individual Researcher Engineering Technology Leader USA.
Review Article
World Journal of Advanced Research and Reviews, 2024, 23(03), 3199-3213
Article DOI: 10.30574/wjarr.2024.23.3.1392
Publication history:
Received on 07 March 2024; revised on 24 September 2024; accepted on 27 September 2024
Abstract:
Recently artificial intelligence (AI) came into software quality assurance (QA), helping us overcome the shortfalls of the traditional fault detection techniques. Manual and semi-automated QA approaches become rapidly hard to scale, in terms of accuracy and efficiency, as software systems are becoming increasingly complex and interdependent. AI driven QA takes advantage of advanced machine learning (ML) models and smart algorithms to optimize fault detection, predictive analysis, and automated decision making. The key innovations are automated test case generation, anomaly detection, and regression test optimization, which eliminate human error and shortens time to market.
As part of this research, this thesis studies integration of AI into QA processes with a framework designed to encompass data collection, preprocessing, model training and deployment. The system we have proposed exploits a feedback loop for its continuous improvement and thus it is adaptable to changing software environment. The system was able to detect faults with relatively high precision and recall by using supervised learning, deep learning, and reinforcement learning techniques.
The case studies show the system works effectively in discovering critical faults of large scale and mobile application projects, thereby validating its scalability and real-world application. AI driven QA is found to increase fault detection accuracy and along with it increase system reliability and development efficiency. This study concludes that testing using AI driven QA is a paradigm shift in software testing and AI driven and intelligent fault management will be the norms of the future.
Keywords:
Artificial Intelligence; Software Quality Assurance; Fault Detection; Machine Learning Models; Automation in Testing; Intelligent Algorithms
Full text article in PDF:
Copyright information:
Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0