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

Parametric signal restoration using artificial neural networks

A Materka1, S Mizushina

  • 1Department of Electrical and Computer Systems Engineering, Monash University, Melbourne (Caulfield East), Australia. materka@lodz.p.lodz.pl

IEEE Transactions on Bio-Medical Engineering
|April 1, 1996
PubMed
Summary

This study introduces a fast, non-iterative artificial neural network (ANN) for parametric signal restoration. The ANN estimator shows comparable performance to least-squares methods in low noise but is superior when trained on noisy data.

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

Five-band microwave radiometer system for non-invasive measurement of brain temperature in new-born infants: system calibration and its feasibility.

Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference·2007
Same author

Monitoring of deep brain temperature in infants using multi-frequency microwave radiometry and thermal modelling.

Physics in medicine and biology·2001
Same author

Guide for the protection of occupationally-exposed personnel in hyperthermia treatment from the potential hazards to health.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group·1993
Same author

Guide to the use of hyperthermia equipment. 2. Microwave heating. The Japanese Society of Hyperthermic Oncology.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group·1993
Same author

Guide to the use of hyperthermic equipment. 1. Capacitively-coupled heating.

International journal of hyperthermia : the official journal of European Society for Hyperthermic Oncology, North American Hyperthermia Group·1993
Same author

Non-invasive thermometry with multi-frequency microwave radiometry.

Frontiers of medical and biological engineering : the international journal of the Japan Society of Medical Electronics and Biological Engineering·1992

Area of Science:

  • Signal Processing
  • Artificial Intelligence
  • Machine Learning

Background:

  • Parametric signal restoration is challenging due to blurring, nonlinear distortion, and additive noise.
  • Traditional methods often rely on iterative numerical techniques for parameter estimation, which can be computationally intensive.

Purpose of the Study:

  • To propose and analyze a novel feedforward artificial neural network (ANN) based estimator for parametric signal restoration.
  • To evaluate the speed and performance of the ANN estimator compared to conventional least-squares techniques, especially under noisy conditions.

Main Methods:

  • A two-stage neural network architecture is employed, involving projection onto the signal subspace.
  • The projected features serve as input to a feedforward neural network for parameter estimation.

Related Experiment Videos

  • Performance analysis includes comparison with the least-squares estimate (LSE) under varying noise levels.

    • Main Results:

    • The ANN estimator offers a significant speed advantage due to its non-iterative nature.
    • For low to moderate noise, ANN performance is comparable to LSE when the network accurately approximates the inverse mapping.
    • The proposed ANN technique demonstrates superiority over LSE when trained directly on noisy signal observations.

    Conclusions:

    • Feedforward ANNs provide an efficient and effective solution for parametric signal restoration.
    • The ANN-based approach offers a robust alternative to traditional methods, particularly in scenarios with noisy data.
    • Further research is needed to explore advanced architectures and training strategies for improved performance.