Identification of different wheat seeds by electronic nose

Abstract

A b s t r a c t. The potential of electronic nose to distinguish of wheat seeds was studied. The reproducibility and practicability of electronic nose data was evaluated by repeating the analysis of samples with a time difference of two months. The principle components analysis and linear discriminant analysis were applied to the generated patterns to distinguish the varieties of wheat seeds. The results showed that they could distinguish the wheat varieties properly. The stepwise discriminant analysis and a three-layer backpropagation neural network were developed for pattern prediction models. The results showed that both models could identify the wheat varieties, the back-propagation neural network presented the higher percent of correct classifications in comparison to stepwise discriminant analysis. Moreover, gas chromatography mass spectrometry analysis of the headspaces of same samples confirmed that electronic nose as a powerful tool is able to identify the wheat seeds.K e y w o r d s: electronic nose, wheat seeds, identification, gas chromatography mass spectrometry INTRODUCTIONThe usual methods for identification of wheat seeds are seed protein electrophoresis, DNA molecular markers techniques, morphological identification and field evaluation (Li et al., 2006). In most cases, these methods are expensive and time-consuming, have low reproducibility, both in their commercial as well as in their technological implications. Several attempts have been made recently to classify wheat varieties using nondestructive methods such as machine vision (Douik and Abdellaoui, 2008;, near infrared spectrometer (Li et al., 2008) and thermal imaging (Manickavasagan et al., 2010). Most of them used kernel morphological features of a single grain for variety identification. It would be highly desirable to have an alternative method for classification of wheat varieties, which may use some characteristics of the kernels other than morphological features. A simple variety identification system with less complexity for bulk sample testing (not single grain analysis) would be most desirable in the grain-handling facilities.Electronic nose (E-nose) is instrument which mimics the sense of smell. These devices are typically array of sensors used to detect and distinguish odours precisely in complex samples and at low cost (Peris and EscuderGilabert, 2009). In contrast to the well known analytical gas chromatography mass spectrometry (GC-MS) and sensory techniques that have been used for the analysis of flavour compounds, the E-nose does not give any information about the compounds causing the investigated aroma; neither about the identity of the compounds nor their sensorial properties. Using E-nose the aroma is judged by the so-called 'aroma pattern', which should be characteristic to the investigated substrate (O'Sullivan et al., 2003). With the use of appropriate mathematical methods, E-nose should be capable of recognizing the aroma pattern or of distinguishing it from aroma patterns of other samples (Peris and EscuderGilab...

Assessment of seed quality using non-destructive measurement techniques: a review

“…An electronic nose is an instrument consisting of an array of electronic and chemical sensors with partial specificity and a pattern recognition system that is capable of recognizing simple or complex odours (Wilson and Baietto, 2009). These devices typically have arrays Anisur Rahman and Byoung-Kwan Cho 288 of sensors used to detect and distinguish odours precisely in complex samples and at low cost (Zhou et al, 2012). Electronic nose devices have been employed in a wide variety of applications, including classification of kernels and microbial pathogen detection.…”

“…In addition, machine vision has been shown to exhibit an overall accuracy of greater than 80% in grading maize (Yi et al ., 2007; Wu et al ., 2013) and soybean (Kılıç et al ., 2007). Recently, an electronic nose was used to distinguish among varieties of wheat seeds with an accuracy of 100% (Zhou et al ., 2012). Thermal imaging was used in a recent study to identify eight western Canadian wheat varieties.…”

Stochastic Modeling Technology for Grain Crops Storage Application : Review

“…Wheat seeds classification using ANN was also estimated whereby the method was found to be effective for recognizing wheat varieties [13]. The study [14] showed that back propagation neural network (BPNN) provided more correct wheat classification at 90% than discriminant analysis which was at 83.33%. Further [15] illustrated how Multi layer perceptron back propagation with image processing algorithm gave higher wheat seeds classification accuracy which was at 95%.…”

Spatial Upscaling-Based Algorithm for Detection and Estimation of Hazardous Gases

“…Depending on the demand of application, viz., detection and/or estimation, analysis has been carried out using various pattern recognition techniques [11], [15]. In published literature, principal component analysis (PCA) and its variants [8]- [14], [15], [16], linear discriminant analysis (LDA) [9]- [11], [14], stepwise discriminant analysis [9], hierarchical cluster analysis [12], [14], average slope multiplication [17], support vector machine (SVM) [18] etc. have been used for the detection of gases delivering different accuracies and success rates.…”