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

Communication channel equalization using complex-valued minimal radial basis function neural networks.

Jianping Deng1, Narasimhan Sundararajan, P Saratchandran

  • 1Sch. of Electr. and Electron. Eng., Nanyang Technol. Univ., Singapore.

IEEE Transactions on Neural Networks
|February 5, 2008
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

Microfluidic Confinement for Constructing Chiral Helical Polyacetylene-Based Monodispersed Circularly Polarized Luminescent Microspheres with Controlled Morphology.

ACS macro letters·2026
Same author

Synergistic Chirality Transmission and Energy Transfer in Clusteroluminescent Cholesteric Cellulose Derivatives for Amplified Circularly Polarized Luminescence.

Angewandte Chemie (International ed. in English)·2026
Same author

A Computer Numerical Control Wire Electrical Discharge Machining Strategy for Fabricating Cobalt-Copper Bimetallic Oxide Maze-like Micro-Supercapacitors.

Micromachines·2026
Same author

Immunoglobulin A lambda multiple myeloma- related light-chain cardiac amyloidosis presenting with progressive heart failure with preserved ejection fraction: a multimodality imaging case report.

European heart journal. Case reports·2026
Same author

Dock2 Protects Colitis by Facilitating Akkermansia Colonization via Suppressing IL-22-Reg3 Activity.

Inflammation·2026
Same author

Multicolor Circularly Polarized Long Afterglow in Perovskite-Based Materials: Co-Driven by Chiral Selective Absorption and Circularly Polarized Phosphorescence Energy Transfer.

ACS applied materials & interfaces·2026
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

A new complex neural network equalizer, the complex minimal resource allocation network (CMRAN), significantly improves Quadrature Amplitude Modulation (QAM) signal equalization. It achieves superior performance with lower network complexity compared to existing methods.

Area of Science:

  • Signal Processing
  • Artificial Intelligence
  • Telecommunications

Background:

  • Quadrature Amplitude Modulation (QAM) signals are widely used in digital communication systems.
  • Channel impairments, particularly nonlinearity, degrade QAM signal quality and increase symbol error rates.
  • Existing equalization techniques often struggle with complexity and performance trade-offs.

Purpose of the Study:

  • To introduce a novel complex radial basis function neural network for QAM signal equalization.
  • To develop a sequential learning algorithm, complex minimal resource allocation network (CMRAN), capable of dynamic network structure adaptation.
  • To evaluate the effectiveness of CMRAN against established equalization methods.

Main Methods:

  • Implementation of a complex radial basis function neural network architecture.

Related Experiment Videos

  • Utilization of the complex minimal resource allocation network (CMRAN) algorithm for sequential learning and neuron adaptation (growth/pruning).
  • Comparative performance analysis against Functional Link Artificial Neural Network (FLANN) and Gaussian Stochastic Gradient (SG) RBF equalizers.

    • Main Results:

    • The CMRAN equalizer demonstrated superior performance in reducing symbol error rates for nonlinear channel equalization.
    • CMRAN achieved a more parsimonious network structure, indicating lower computational complexity.
    • The proposed method outperformed both FLANN and SG RBF equalizers in the evaluations.

    Conclusions:

    • The CMRAN algorithm offers a highly effective and efficient solution for QAM signal equalization in challenging communication channels.
    • Dynamic network adaptation in CMRAN leads to improved performance and reduced complexity.
    • This approach represents a significant advancement in neural network-based channel equalization techniques.