Revolutionizing Software Debugging: GA-TCN Approach for Advanced Bug Training

EasyChair Preprint 12810

Abstract

Software debugging is a critical process in software development, often requiring significant time and resources to identify and rectify bugs. Traditional debugging methods face challenges in handling complex bugs efficiently. This paper introduces a revolutionary approach to software debugging utilizing Genetic Algorithm (GA) and Temporal Convolutional Networks (TCN). The GA-TCN framework combines the evolutionary search capability of genetic algorithms with the temporal analysis power of TCNs to enhance bug detection and resolution. Through iterative evolution and temporal pattern recognition, GA-TCN dynamically learns from historical debugging data to improve bug identification accuracy and speed up the debugging process. Experimental results demonstrate the effectiveness of the GA-TCN approach in detecting and addressing various types of bugs, outperforming traditional debugging methods significantly. This innovative approach has the potential to revolutionize software debugging practices, enabling developers to streamline the debugging process and deliver more robust and reliable software products.

Keyphrases: Bug Training, Genetic Algorithm, Software Debugging, Temporal Convolutional Networks, evolutionary search, temporal analysis

@booklet{EasyChair:12810,
  author    = {Roni Joni},
  title     = {Revolutionizing Software Debugging: GA-TCN Approach for Advanced Bug Training},
  howpublished = {EasyChair Preprint 12810},
  year      = {EasyChair, 2024}}