Electronic Nose Odor Classification with Advanced Decision Tree Structures

Guney S., Atasoy A., Burget R.

RADIOENGINEERING, cilt.22, sa.3, ss.874-882, 2013 (SCI-Expanded) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 22 Sayı: 3
  • Basım Tarihi: 2013
  • Dergi Adı: RADIOENGINEERING
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED)
  • Sayfa Sayıları: ss.874-882
  • Anahtar Kelimeler: Electronic nose, odor classification, machine learning, data-mining, NEAREST-NEIGHBOR ALGORITHM, FEATURE-EXTRACTION, MULTICLASS, PREDICTION, ARRAY
  • Karadeniz Teknik Üniversitesi Adresli: Evet

Özet

Electronic nose (e-nose) is an electronic device which can measure chemical compounds in air and consequently classify different odors. In this paper, an e-nose device consisting of 8 different gas sensors was designed and constructed. Using this device, 104 different experiments involving 11 different odor classes (moth, angelica root, rose, mint, polis, lemon, rotten egg, egg, garlic, grass, and acetone) were performed. The main contribution of this paper is the finding that using the chemical domain knowledge it is possible to train an accurate odor classification system. The domain knowledge about chemical compounds is represented by a decision tree whose nodes are composed of classifiers such as Support Vector Machines and k-Nearest Neighbor. The overall accuracy achieved with the proposed algorithm and the constructed e-nose device was 97.18 %. Training and testing data sets used in this paper are published online.