Recognizing Odor Mixtures Using Optimized Fuzzy Neural Network Through Genetic Algorithms

Benyamin Kusumoputro, Teguh P. Arsyad

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)

Abstract

Recognizing odor mixtures is rather difficult in artificial odor recognition system, especially when the number of sensors is limited. Classification is further hampered if the number of unlearned odor mixtures classes is increased. We developed a fuzzy-neuro multilayer perceptron as a pattern classifier and compared its recognition with that of the Probabilistic Neural Network and Back-propagation Neural Network. To enhance the recognition capability of the system, we then optimized fuzzy-neuro multilayer perceptron topology by deleting its weak weight connections using Genetic Algorithms. Experimental results show that the optimized fuzzy-neuro multilayer perceptron has the highest recognition in 18 classes of two-mixture odors with almost 98.2% when using hardware with 16 sensors, compared to 83.3% when using 8 sensors.

Original languageEnglish
Pages (from-to)290-296
Number of pages7
JournalJournal of Advanced Computational Intelligence and Intelligent Informatics
Volume9
Issue number3
DOIs
Publication statusPublished - May 2005

Keywords

  • fuzzy-neuro system
  • genetic algorithms
  • multilayer perceptron
  • neural structure optimization method
  • odor recognition system

Fingerprint

Dive into the research topics of 'Recognizing Odor Mixtures Using Optimized Fuzzy Neural Network Through Genetic Algorithms'. Together they form a unique fingerprint.

Cite this