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

A neural-network contention controller for packet switching networks.

le N Binh1, H C Chong

  • 1Dept. of Electr. and Comput. Syst. Eng., Monash Univ., Clayton, Vic.

IEEE Transactions on Neural Networks
|January 1, 1995
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

A retrospective record review of tuberculous infections in rheumatoid arthritis patients on biologics in Malaysia.

The Medical journal of Malaysia·2023
Same author

Manipulation under Anaesthesia for Patient Reported Stiffness after Total Knee Arthroplasty in an Asian Population.

Malaysian orthopaedic journal·2020
Same author

Pre-operative pressure pain thresholds do not meaningfully explain satisfaction or improvement in pain after knee replacement: a cohort study.

Osteoarthritis and cartilage·2018
Same author

Self-reported symptoms of depression, anxiety and stress among patients with Rheumatoid Arthritis in a Malaysian rheumatology centre - prevalence and correlates.

The Medical journal of Malaysia·2018
Same author

Revision total knee arthroplasty for failed high tibial osteotomy and unicompartmental knee arthroplasty have similar patient-reported outcome measures in a two-year follow-up study.

The bone & joint journal·2017
Same author

Targeting nuclear receptors in cancer-associated fibroblasts as concurrent therapy to inhibit development of chemoresistant tumors.

Oncogene·2017
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

This study introduces a novel K-winner-take-all neural network for high-speed packet switching networks. The new design effectively manages output contention, preventing packet loss in synchronous switching systems.

Area of Science:

  • Computer Science
  • Neural Networks
  • Network Engineering

Background:

  • Packet switching networks face output contention challenges in synchronous switching modes.
  • Existing solutions may struggle with high-speed, high-capacity demands without packet loss.

Purpose of the Study:

  • To present a novel approach for resolving output contention in packet switching networks.
  • To design a contention controller using K-winner-take-all neural network techniques.

Main Methods:

  • A K-winner-take-all neural network was designed with a speedup factor for real-time computation.
  • Simulations were conducted to evaluate the controller's performance with 10 neurons.
  • Analysis included constraints related to "frozen state" and same initial state.

Related Experiment Videos

Main Results:

  • The K-winner network controller demonstrated effective management of output contention.
  • The approach enables nonblocking switching in high-speed, high-capacity packet switches.
  • The system achieved operation without packet loss.

Conclusions:

  • The K-winner-take-all neural network offers a viable solution for packet switching output contention.
  • An optoelectronic contention controller based on this neural network is proposed.
  • This method supports high-performance, reliable packet switching.