A particle swarm optimization-aided fuzzy cloud classifier applied for plant numerical taxonomy based on attribute similarity

  • Authors:

  • Hongfei Lu;Erxu Pi;Qiufa Peng;Lanlan Wang;Changjiang Zhang

  • Affiliations:

  • College of Chemistry and Life Science, Zhejiang Normal University, Jinhua 321004, China;College of Chemistry and Life Science, Zhejiang Normal University, Jinhua 321004, China;College of Chemistry and Life Science, Zhejiang Normal University, Jinhua 321004, China;College of Chemistry and Life Science, Zhejiang Normal University, Jinhua 321004, China;College of Information Science and Engineering, Zhejiang Normal University, Jinhua 321004, China

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2009

Quantified Score

Hi-index 12.05

Visualization

Abstract

Data mining techniques are widely used in many fields. One application of data mining in the field of the botany is numerical taxonomy. In the present work, a particle swarm optimization-aided fuzzy cloud classifier based on attribute similarity (PSOCCAS) is used for plant taxonomy by two datasets. Firstly, the proposed classifier is been tested by employing it for the benchmark classification data sets, Fisher's iris data. The testing accuracy is found very encouraging. The performance of our proposed system is only bettered by some genetic algorithm (GA) or evolutionary algorithm (EA)-based fuzzy systems which showed fantastic results. Then for further validation and broadening application, the PSOCCAS has been presented for quantitative features evaluation, 'expected species' selection and successful classification of three sections in genus Camellia (belongs to the family Theaceae). The selected quantitative features are almost those selected in previous works. The method is able to produce 100% accurate classification results in genus Camellia. It is a very simple and robust method to divergences in plant taxonomy. No extensive preprocessing is required. The classification is performed with comparatively comprehensive features than those used in our previous work. The method utilizes the inherent nature of the data in performing various tasks. Consequently, the method can be used for plant numerical taxonomy.