Integrating Genetic Algorithm with Temporal Convolutional Neural Networks for Enhanced Technology Assessment and Software Bug Remediation (GA-TCN)

EasyChair Preprint 12805

Abstract

This paper presents a novel approach for technology assessment and software bug remediation through the integration of Genetic Algorithm (GA) with Temporal Convolutional Neural Networks (TCN), coined as GA-TCN. The combination of GA and TCN offers a robust framework for addressing challenges in software development, particularly in bug detection and resolution. By leveraging GA's evolutionary principles and TCN's temporal processing capabilities, this methodology achieves enhanced bug remediation effectiveness and technology assessment accuracy. The proposed GA-TCN framework operates in two phases. In the first phase, GA optimizes the parameters and architecture of TCN to tailor it specifically for bug detection and technology assessment tasks. Through iterative evolution, GA fine-tunes the TCN architecture to efficiently capture temporal dependencies in software code, thereby improving bug detection sensitivity and accuracy. In the second phase, the trained TCN model is deployed for real-time bug detection and technology assessment. TCN utilizes its temporal convolutional layers to analyze software code sequences, identifying patterns indicative of bugs or assessing the technological efficacy of code segments.

Keyphrases: Genetic Algorithm, Software Bug Remediation, technology assessment, temporal convolutional neural networks

@booklet{EasyChair:12805,
  author    = {Asad Ali},
  title     = {Integrating Genetic Algorithm with Temporal Convolutional Neural Networks for Enhanced Technology Assessment and Software Bug Remediation (GA-TCN)},
  howpublished = {EasyChair Preprint 12805},
  year      = {EasyChair, 2024}}