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

File access prediction using neural networks.

Prashanta Kumar Patra1, Muktikanta Sahu, Subasish Mohapatra

  • 1Department of Computer Science and Engineering, College of Engineering and Technology, Bhubaneswar 751003, India. pkpatra@cet.edu.in

IEEE Transactions on Neural Networks
|April 28, 2010
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Prediction Intervals01:03

Prediction Intervals

The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 
The...

You might also read

Related Articles

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

Sort by
Same author

Meta-learned dynamic hierarchical fusion for robust multi-scale object classification.

Scientific reports·2026
Same author

Fine-Tuning Large Language Models Using Entity Hallucination Index for Text Summarization.

Journal of visualized experiments : JoVE·2026
Same author

VDNABDS, A DNA-Based Cryptographic Protocol for Enhancing Cloud Security.

Journal of visualized experiments : JoVE·2025
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Dynamic file access predictors using neural networks significantly reduce prediction errors in high-speed computers. This approach improves accuracy and success rates compared to static methods, optimizing memory and disk access times.

Area of Science:

  • Computer Science
  • Machine Learning
  • Computer Architecture

Background:

  • High-speed computer design faces challenges due to the significant latency gap between memory and disk access.
  • Static file access predictors have been employed to mitigate this issue, but with limitations.

Purpose of the Study:

  • To propose and evaluate dynamic file access predictors utilizing neural networks for improved performance.
  • To enhance accuracy, success-per-reference, and effective-success-rate-per-reference in file access prediction.

Main Methods:

  • Implementation of dynamic file access predictors based on neural networks.
  • Comparison of proposed methods against the recent popularity (RP) method and other predictors.
  • Simulation using distributed file system (DFS) traces.

Related Experiment Videos

  • Evaluation of different neural network models like Radial Basis Function (RBF) and Multilayer Perceptron (MLP) with Levenberg-Marquardt (LM) backpropagation.

    • Main Results:

    • The proposed neural network method reduced incorrect predictions from 53.11% to 43.63% compared to the RP method.
    • Manual tuning further improved misprediction rates and effective-success-rate-per-reference.
    • RBF showed better prediction in high-end systems, while MLP with LM backpropagation excelled in systems with high computational capability.
    • Probabilistic and competitive predictors are suitable for resource-limited workstations, with probabilistic predictors being more efficient for servers.

    Conclusions:

    • Multilayer Perceptron (MLP) with the Levenberg-Marquardt (LM) backpropagation algorithm demonstrates a superior file prediction success rate over simpler predictors.
    • Dynamic neural network-based predictors offer a significant advancement in addressing the memory-disk access time gap in high-speed computing.