Study of Fish Species Discrimination Via Electronic Nose
Abstract
Fish freshness is a critical issue in determining fish quality. Since fish freshness changes according to the fish species, fish species has to be identified before examining the freshness. So far, fish species have been distinguished through different methods such as image processing. In this paper, an electronic nose has been used to distinguish between different species of fish. Thus, both freshness and species of fish will be determined just using a single, low cost device. The aim of this study is to distinguish between three different species of fish - horse mackerel, anchovy and whiting - by using an electronic nose composed of 8 different metal oxide gas sensors. In order to distinguish between the species of fish, a whole new method, which is not applied to this kind of data previously, is used and proposed for use in the pattern recognition unit of the electronic nose. It is examined in three parts such as signal pre-processing, feature extraction and classification. In the pre-processing stage, to reduce the negative effect of sensor drift, a new method is applied to the raw signal in addition to the well-known baseline manipulation method. In the feature extraction part, the sub-sampling method which is not frequently used is applied to the pre-processed signal. The extracted features are used in the classification part. The structure of the proposed classification algorithm is based on binary decision tree structure. The binary decision tree structure is composed of nodes. In every node of the decision tree structure, the feature spaces or classification algorithm can be changed according to the problem. Classification results demonstrate the effectiveness of the presented models. The overall accuracy of the identification of fish species achieved with the proposed methods is 96.18%. The performance of the proposed method is also compared to conventional methods such as Naive Bayes, k-Nearest Neighbor and Linear Discriminant Analysis. The successes of these classifiers are 84.73, 80 and 82.4, respectively. (C) 2015 Elsevier B.V. All rights reserved.