Enhancing Software Bug Training and Evaluation with GA-TCN: A Genetic Algorithm and Time Convolution Neural Network Approach

EasyChair Preprint 12813

Abstract

In the realm of software development, the identification and resolution of bugs are crucial for ensuring the functionality, security, and overall quality of software systems. Traditional bug detection methods often rely on manual inspection and testing, which can be time-consuming and prone to human error. To address these challenges, this study introduces a novel approach called GA-TCN (Genetic Algorithm and Time Convolution Neural Network) for enhancing software bug training and evaluation. GA-TCN integrates the power of genetic algorithms and time convolutional neural networks to automate bug detection and improve the efficiency and accuracy of the process. The genetic algorithm is employed for feature selection and optimization, while the time convolutional neural network is utilized for learning temporal patterns in software code. Through experimentation and evaluation on various software datasets, GA-TCN demonstrates superior bug detection performance compared to traditional methods, showcasing its potential to revolutionize software quality assurance practices.

Keyphrases: Automation, Genetic Algorithm, Software Bug Detection, Time Convolutional Neural Network, feature selection, quality assurance

@booklet{EasyChair:12813,
  author    = {Haney Zaki},
  title     = {Enhancing Software Bug Training and Evaluation with GA-TCN: A Genetic Algorithm and Time Convolution Neural Network Approach},
  howpublished = {EasyChair Preprint 12813},
  year      = {EasyChair, 2024}}