Nature-inspired approaches in Software Fault Prediction

@article{1704594,
      author = {Harshit Saini, Tushar Arora, Sachin Garg},
      title = {Nature-inspired approaches in Software Fault Prediction},
      journal = {Iconic Research And Engineering Journals},
      year = {2023},
      volume = {6},
      number = {12},
      pages = {71-76},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1704594.pdf},
      abstract = {In software engineering, predicting software faults is a crucial task for ensuring high software quality and reducing costs. In recent years, nature inspired approaches have been increasingly used in software fault prediction. In this paper, we explore the effectiveness of six nature inspired algorithms, namely Ant Colony, Particle Swarm Optimization, Firefly, Bat, Harris Hawks, and Genetic Algorithm, for software fault prediction. We evaluate the algorithms using three commonly used datasets, JM1, CM1, and PC1. Our experimental results show that nature inspired approaches can effectively predict software faults, with some algorithms performing better than others depending on the dataset used. Our findings suggest that these approaches have potential to be used as a practical and efficient means for software fault prediction.},
      keywords = {Nature Inspired Algorithms, PSO, Ant Colony Optimization, Harris Hawks, Genetic Algorithm (GA), Python Programming, Jupyter Notebook, Confusion Matrix},
      month = {June},
  }