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

Enhanced FMAM based on empirical kernel map.

Min Wang1, Songcan Chen

  • 1Department of Computer Science, Nanjing University of Aeronautics and Astronautics, Nanjing 210016, China. wm_wangmin@yahoo.com.cn

IEEE Transactions on Neural Networks
|June 9, 2005
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

[The effect of chelerythrine on the hypertrophy of cardiac myocytes of neonatal rats induced by different glucose levels and its mechanism].

Yao xue xue bao = Acta pharmaceutica Sinica·2009
Same author

Overexpression of Midkine promotes the viability of BA/F3 cells.

Biochemical and biophysical research communications·2009
Same author

Improved isolation of anti-rhTNF-alpha scFvs from phage display library by bioinformatics.

Molecular biotechnology·2009
Same author

Neuroprotection of ethanol against cerebral ischemia/reperfusion induced brain injury through GABA receptor activation.

Brain research·2009
Same author

[Open-path online monitoring of ambient atmospheric CO2 based on laser absorption spectrum].

Guang pu xue yu guang pu fen xi = Guang pu·2009
Same author

[Effects of Sarcandra glabra extract on immune activity in restraint stress mice].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2009
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 an enhanced fuzzy morphological auto-associative memory (EFMAM) model. EFMAM significantly improves recognition accuracy under hybrid noise, overcoming limitations of previous models.

Area of Science:

  • Computer Science
  • Artificial Intelligence
  • Pattern Recognition

Background:

  • Morphological auto-associative memory (auto-MAM) models offer advantages like unlimited storage and fast recall.
  • Existing models, including fuzzy morphological auto-associative memories (auto-FMAM), are vulnerable to mixed erosion and dilation noise, degrading performance.
  • A need exists for robust auto-associative memory models that can handle complex noise patterns.

Purpose of the Study:

  • To propose an enhanced fuzzy morphological auto-associative memory (EFMAM) model.
  • To improve recognition accuracy and computational efficiency of auto-FMAM under hybrid noise.
  • To address the vulnerability of existing models to combined erosive and dilative noise.

Main Methods:

  • Developed an enhanced fuzzy morphological auto-associative memory (EFMAM) model.

Related Experiment Videos

  • Incorporated an empirical kernel map into the fuzzy morphological auto-associative memory framework.
  • Evaluated EFMAM performance on facial recognition tasks using the ORL database under varying levels of hybrid noise.

    • Main Results:

    • EFMAM demonstrated significantly higher recognition accuracy compared to auto-FMAM under hybrid noise.
    • Average accuracies for EFMAM reached 92%, 90%, and 88% under 10%, 20%, and 30% hybrid noise, respectively.
    • EFMAM also showed improvements in computational effort compared to auto-FMAM.

    Conclusions:

    • The proposed EFMAM model effectively overcomes the limitations of previous auto-associative memory models concerning hybrid noise.
    • EFMAM offers a robust and efficient solution for pattern recognition tasks susceptible to complex noise.
    • The empirical kernel map integration is key to EFMAM's enhanced performance.