Dissertation > Excellent graduate degree dissertation topics show

Research on Auto-Determination of the Parameter Values of Pulse-Coupled Neural Network

Author: QiChunLiang
Tutor: MaYiDe
School: Lanzhou University
Course: Circuits and Systems
Keywords: Pulse-coupled neural network Genetic algorithm Gradient descent algorithm LMS principle Self-adaptive
CLC: TP183
Type: Master's thesis
Year: 2006
Downloads: 148
Quote: 3
Read: Download Dissertation

Abstract


Artificial neural networks plays the key role in the fields of artificial intelligence and image processing because of it’s imitation of the wisdom and power of biological nervous system. As a new kind of neural network, Pulse-Coupled Neural Network (PCNN) has been put more emphasis on the research in many fields since it was proposed by Johnson in 1994. PCNN model was created by the research and understanding in the visual cortex of small mammal such as cat and produces synchronous bursts of pulses from neurons with similar activity, effectively grouping them by phase and pulse frequency, which makes it significantly different from the conventional artificial neurons. Just because the model derives directly from the studies of the mammal’s visual properties, PCNN has been used successfully in image processing fields.PCNN model is a algorithm with multiple parameters, and finding the proper value of these parameters is an onerous task. The drawback of the PCNN hinders its further development and application. So many simplified PCNN model is adopted in many papers. The remaining parameters are, nevertheless, manually adjusted according to the concrete application. The high accuracy is unachievable with the simplified model and the quality of latter study is affected.Up to now, no papers which investigate the auto-determination of the parameter values of PCNN model in full-range and systematically exist. Based on the mentioned above, two algorithms which can performs the auto-determination are presented in this research. As one part of this paper, genetic algorithm which is a general purpose stochastic optimization for search problem is utilized to determine these parameter values automatically, and an automatic PCNN system is established. Through the segmentation, the performance of the automatic PCNN system is verified. As another part of this paper, gradient descent algorithm is adopted to search parameters which can reduce the error between the desired output and the actual output gradually according to the LMS principle, then a self-adaptive PCNN system is established. Given only an input and the desired output, the adaptive PCNN system can find all parameter values necessary to approximate the desired output.The correctness and dependability of two algorithms are verified by experiment results, the good foundation for the latter study of PCNN model in image processing is established.

Related Dissertations

  1. Development of the Platform for Compressor Optimization Design and Aerodynamic Optimization Design in the Transonic Compressor,TH45
  2. Design and Research on Stabilization Loop of Gyro Stabilized Pod Control System,V241.5
  3. The Application of Fuzzy Comprehensive Evaluation Based on Genetic Algorithm in Vocational Evaluation of Classroom Teaching,G712
  4. Study on Taste Characteristic of Taste Peptide Enzymatic Production from Oyster Base on A Neural Network Method,TS254.4
  5. Design and Realization of the Magnetic Antenna in MW and SW Bands Based on Genetic Algorithm,TN820
  6. Citrus Image Segmentation Based on Genetic Algorithm,TP391.41
  7. Research of Scheduling Algorithm Based on Hybrid Adaptive Genetic Algorithm in Computing Grid,TP393.09
  8. Public Transport Optimal Dispatching Based on the Genetic-Newton Algorithm,TP18
  9. BP network optimization based on genetic algorithm optimization of the biodiesel process,TE667
  10. An Adaptive Processing Node Selection Based Spatio-Temporal Query Alogrithm,TN929.5
  11. The Research on Texture Synthesis Technology from Cloud Theory & Been Evolution Genetic Algorithm,TP391.41
  12. Research on Clustering Algorithm Based on Genetic Algorithm and Rough Set Theory,TP18
  13. The Design and Implementation of Email Analysis and Forensies System,D918.2
  14. Sdesign and Implementation of Course Scheduling Management System,TP311.52
  15. Sentence Similarity Computing Research and Application of Intelligent Question Answering System,TP391.1
  16. The Study and Development of Production Planning and Management System for Small and Medium Discrete Enterprises,TP311.52
  17. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  18. Research on Oranically-Structured of Expanding Large Scale Systems Based on Parameter Optimization,TP273
  19. Optimization of EDM Parameters,TG661
  20. Research on Network Anomaly Detection Based on Projection Pursuit Regression,TP393.08
  21. The Modified Harmony Search Algorithm with Control Parameters Co-evolution and Its Application,TP391.3

CLC: > Industrial Technology > Automation technology,computer technology > Automated basic theory > Artificial intelligence theory > Artificial Neural Networks and Computing
© 2012 www.DissertationTopic.Net  Mobile