Scent classification by K nearest neighbors using ion-mobility spectrometry measurements. (January 2019)

• Record Type: Journal Article
• Authors: Müller, Philipp; Salminen, Katri; Nieminen, Ville; Kontunen, Anton; Karjalainen, Markus; Isokoski, Poika; Rantala, Jussi; Savia, Mariaana; Väliaho, Jari; Kallio, Pasi; Lekkala, Jukka; Surakka, Veikko
• Is Part Of: Expert systems with applications. Volume 115(2019)
• Page Start: 593
• Page End: 606
• Publication Date: 2019-01
• Subjects: Machine learning -- K nearest neighbours -- Ion-mobility spectrometry -- Scent classification; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2018.08.042
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: K Nearest Neighbor classifies scents and their chemical components. Scents/ chemicals are classified using only ion-mobility spectrometry measurements. Classification using k-dimensional tree search is approximately 8-times faster. By principal component analysis 71–86% of features are ignored for classification. Abstract: Various classifiers for scent classification based on measurements using an electronic nose (eNose) have been studied recently. In general, classifiers rely on a static database containing reference eNose measurements for known scents. However, most of these approaches require retraining of the classifier every time a new scent needs to be added to the training database. In this paper, the potential of a K nearest neighbors ( K NN) classifier is investigated to avoid the time-consuming retraining when updating the database. To speed up classification, a k -dimensional tree search in the K NN classifier and principal component analysis (PCA) are studied. The tests with scents presented to an eNose based on ion-mobility spectrometry (IMS) show that the K NN method classifies scents with high accuracy. Using a k -dimensional tree search instead of an exhaustive search has no significant influence on the misclassification rate but reduces the classification time considerably. The use of PCA-transformed data results in a higher misclassification rate than the use of IMS data when only the first principal components explaining 95% of the total variance are used but in a similar misclassification rate when the first principal components explaining 99% of the total variance are used. In conclusion, the proposed method can be recommended for classifying scents measured with IMS-based eNoses.