Earticle

초록

영어

Initialization parameters of Self-organizing map networks (SOM) have a great influence in their final result. This is the only known problem of SOM networks. The uncertainty of solution is resolved with the fusion methods in many machine learning algorithms. Motivated by this application, we aim to reduce the uncertainty in SOM final result and provide a more robust solution. This is done by aggregating the results obtained from several run of SOM network. The objective in uniting several SOM run is to reduce the effect of two above factors and reach a more appropriate solution. To achieve this, a number of methods for integration of SOM solutions have been proposed and their characteristics are discussed in detail. Finally, these approaches are experimentally compared with some recently proposed SOM networks and their effectiveness are investigated.

목차

Abstract
 1. Introduction
 2. Preliminary
  2.1. Self-Organizing Map Algorithm
  2.2. Limitation of SOM Algorithm
 3. Related Work
 4. Proposed Method
  4.1. Chaos Generation Step
  4.2. Matching Step
  4.2. Fusion Step
 5. Experimental Result
  5.1. Setup
  5.2. Cluster Validity Measurement
  5.3. Quality Comparison by Given Labels
  5.4. Quality Comparison by Measurement
 6. Conclusion
 References

키워드

저자

• Amin Allahyar [ Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran ]
• Hadi Sadoghi Yazdi [ Department of Computer Engineering, Ferdowsi University of Mashhad, Mashhad, Iran, Center of Excellence on Soft Computing and Intelligent Information Processing, Ferdowsi University of Mashhad ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Control and Automation

• 간기

  월간

• pISSN

  2005-4297

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605