Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

RefactoCNN-system: an optimized deep learning framework for predicting software refactoring opportunities using

E Lakshmi Prasanna1, K Srinivas2

  • 1Research Scholar, Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Hyderabad, Telangana, 500075, India. lakshmi.prasanna@klh.edu.in.

Scientific Reports
|June 9, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
Improving Translational Accuracy02:07

Improving Translational Accuracy

Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Development of a novel genome exponential amplification reaction (GEAR) assay for rapid and ultrasensitive detection of Salmonella.

World journal of microbiology & biotechnology·2025
Same author

GC/MS Investigation of the Reaction Products of Nitrogen Mustards and N,N-Dialkylaminoethyl-2-Chlorides With Phenol.

Journal of mass spectrometry : JMS·2025
Same author

Classifying fungi biodiversity using hybrid transformer models.

Journal of microbiological methods·2025
Same author

Detection and phylogenetic analysis of <i>Streptobacillus moniliformis</i>, the causative agent of rat-bite fever and Haverhill fever, in free-living greater bandicoot rats in Northeastern India.

Veterinary world·2025
Same author

Novel competitive annealing-mediated isothermal amplification (CAMP)-based detection of epsilon toxin gene in Clostridium perfringens.

Anaerobe·2025
Same author

Seroepidemological investigation of Toxoplasma gondii and Trichinella spp. in pigs reared by tribal communities and small-holder livestock farmers in Northeastern India.

PloS one·2024
Same journal

MT-MRI for detection of renal interstitial fibrosis in renovascular disease.

Scientific reports·2026
Same journal

Detection of underground objects from GPR data using a lightweight YOLO-based approach.

Scientific reports·2026
Same journal

Early systemic inflammatory-metabolic trajectory phenotypes are associated with survival outcomes in metastatic renal cell carcinoma treated with nivolumab.

Scientific reports·2026
Same journal

Water balance components in a dry-seeded rice-wheat system: Untangling the effects of tillage and mulching practices.

Scientific reports·2026
Same journal

Topological approaches to quantum tensor train compression via ZX-calculus and SVD.

Scientific reports·2026
Same journal

determinants of flood impacts and adaptive capacity among market vendors in Walukuba-Masese, Jinja city, Uganda.

Scientific reports·2026
See all related articles

RefactoCNN-System uses deep learning to automatically identify code refactoring opportunities, improving software quality and maintainability. This framework outperforms traditional methods, offering practical solutions for automated software maintenance.

Area of Science:

  • Software Engineering
  • Artificial Intelligence
  • Machine Learning

Background:

  • Traditional refactoring methods rely on rule-based or heuristic approaches with handcrafted features, limiting their effectiveness and generalizability.
  • Existing deep learning models for code analysis are often not optimized for real-world development pipelines.

Purpose of the Study:

  • To present RefactoCNN-System, an efficient deep learning framework for predicting macroscopic refactoring opportunities from raw Java source code.
  • To improve automated software maintenance and code quality management through data-driven refactoring support.

Main Methods:

  • Utilizes Abstract Syntax Trees (ASTs) and token sequences as structured code representations, mapped to embedding vectors.
  • Employs a custom Convolutional Neural Network (CNN) model, enhanced with Bayesian hyperparameter tuning and learning rate scheduling.
Keywords:
Automated software maintenanceCNN modelCode analysisDeep learningSoftware refactoring

Related Experiment Videos

  • Integrates a mapping engine using heuristics to translate classification outputs into developer-friendly refactoring recommendations.

    • Main Results:

    • RefactoCNN-System achieved 94.6% classification accuracy, 93.1% precision, 92.3% recall, and 92.7% F1-score on benchmark datasets.
    • Outperforms traditional machine learning classifiers and existing deep learning baselines in identifying refactoring opportunities.
    • Demonstrates practical usability through qualitative analysis and real-world examples, supported by a public GitHub repository for implementation and reproducibility.

    Conclusions:

    • RefactoCNN-System offers a promising direction for automated, data-driven refactoring support, enhancing code quality and maintainability.
    • The framework's modular and extensible architecture makes it a valuable resource for automated software maintenance.
    • Deep learning capabilities enable automated feature discovery and handling of heterogeneous datasets, surpassing shallow feature-based methods.