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

Software reliability prediction using recurrent neural network with Bayesian regularization.

Liang Tian1, Afzel Noore

  • 1Lane Department of Computer Science and Electrical Engineering, West Virginia University, Morgantown, WV 26506-6109, USA. tian@csee.wvu.edu

International Journal of Neural Systems
|July 10, 2004
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Phosphate-Terminated Nb<sub>2</sub>C MXene as Efficient Catalyst for the Transformation of Glucose Into 5-Hydroxymethylfurfural With 3077 h<sup>-1</sup> Turnover Frequency.

ChemSusChem·2026
Same author

Acid-Triggered, Enzyme-Enabled EPS-Degrading Nanoplatform With Enhanced In Situ Retention for Intravenous Biofilm Therapy.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Investigating the saltiness enhancement in blanch-pretreated celery juice via odor-taste cross-modal integration: insights from EEG, molecular simulations, and flavoromics.

Food chemistry·2026
Same author

Targeting cancer-associated fibroblast-activated HGF/c-MET pathway inhibits extrahepatic cholangiocarcinoma progression and restores gemcitabine therapeutic sensitivity.

Acta pharmaceutica Sinica. B·2026
Same author

Enhancing performance and hydration of waste cathode ray tube glass-Portland cement systems via C-S-H seedings: A multi-scale investigation.

Journal of environmental management·2026
Same author

Establishment and Validation of a Competency-Based Evaluation Indicator System for On-Site Disinfection Service Providers - Shanghai Municipality, China, 2023.

China CDC weekly·2026
Same journal

Latent Space Projections and Atlases, a Cautionary Tale in Deep Neuroimaging using Autoencoders.

International journal of neural systems·2026
Same journal

Transformer-Based Anomaly Detection for Neurodegenerative Screening in MRI Images.

International journal of neural systems·2026
Same journal

Discrete Wavelet Convolution for Learnable Time-Frequency Representation with Application to Seizure Prediction.

International journal of neural systems·2026
Same journal

Automatic Seizure Detection using Hierarchical Spectral-Temporal Feature Learning with an Imbalance-Aware Transformer.

International journal of neural systems·2026
Same journal

Pyramid Vision Transformer-Enhanced Conformer Network for Epileptic Seizure Recognition Using MultiChannel EEG Signals.

International journal of neural systems·2026
Same journal

A Time-Frequency Decoupled Contrastive Learning Framework for Electroencephalography-Based Parkinson's Disease Diagnosis.

International journal of neural systems·2026
See all related articles

This study introduces a recurrent neural network for software reliability prediction using cumulative failure time. The model demonstrates robust performance and superior accuracy compared to existing methods.

Area of Science:

  • Computer Science
  • Software Engineering
  • Artificial Intelligence

Background:

  • Software reliability is crucial for critical systems.
  • Accurate prediction of software failures is challenging.
  • Existing models may not fully capture temporal dependencies.

Purpose of the Study:

  • To propose a novel recurrent neural network (RNN) approach for software reliability prediction.
  • To leverage the temporal properties of cumulative failure time data.
  • To enhance model generalization and reduce overfitting.

Main Methods:

  • Developed a specialized RNN architecture for analyzing cumulative failure time sequences.
  • Implemented Bayesian regularization by adding a penalty term to network weights.

Related Experiment Videos

  • Trained and validated the model on four real-time control and flight dynamic datasets.

    • Main Results:

    • The proposed RNN approach effectively learns temporal patterns in failure data.
    • Bayesian regularization improved generalization and reduced overfitting.
    • The model demonstrated robustness across diverse software projects.
    • Achieved superior performance in goodness-of-fit and next-step-predictability compared to existing models.

    Conclusions:

    • The developed RNN model offers a powerful tool for software reliability prediction.
    • The approach effectively utilizes cumulative failure time data for improved accuracy.
    • This method provides a more reliable prediction of software failures in critical applications.