Classification of Rice by Combining Electronic Tongue and Nose
- PDF / 1,277,451 Bytes
- 10 Pages / 595.276 x 790.866 pts Page_size
- 99 Downloads / 232 Views
Classification of Rice by Combining Electronic Tongue and Nose Lin Lu & Shaoping Deng & Zhiwei Zhu & Shiyi Tian
Received: 23 May 2014 / Accepted: 15 December 2014 # Springer Science+Business Media New York 2014
Abstract One hundred twenty indica rice samples were determined by electronic tongue and electronic nose. The potential of the combinational approaches of electronic tongue and nose for rice analysis, with the aim of differentiating conventional and hybrid rice, was investigated. Principal component analysis (PCA) and locally linear embedding (LLE) were used to preprocess data from electronic systems. Support vector machine (SVM) model and K-nearest neighbors (KNN) model were established with the values from PCA and LLE algorithms as attributes. For the combination of electronic tongue and nose, the prediction accuracies of PCA-SVM, PCA-KNN, LLE-SVM, and LLE-KNN models were 55, 55, 85, and 80 %. The LLE-based models achieved better prediction accuracies than PCAbased models. These results demonstrated that LLE algorithm coupled with SVM or KNN for the combined electronic signals was effective in extracting and analyzing features for detecting rice. The LLE-SVM model achieved a little higher accuracy than the LLE-KNN model. It can be concluded that the combination of electronic systems coupled with LLE-based model have a great potential in the prediction of rice types.
Keywords Electronic tongue . Electronic nose . LLE . SVM . KNN
L. Lu : S. Deng : S. Tian (*) College of Food Science and Biotechnology, Zhejiang Gongshang University, Hangzhou 310035, China e-mail: [email protected] L. Lu : Z. Zhu Rice Product Quality Supervision and Inspection Center, Ministry of Agriculture, China National Rice Research Institute, Hangzhou 310006, China
Introduction Rice (Oryza sativa L.) consumed by over half of the world’s population is an important cereal crop. In the promotion of market demand and new breeding technology, the improvement of rice quality traits was launched and hybrid rice varieties were cultivated. Compared to conventional rice, hybrid rice has variant contents in chemical compounds and volatiles. In some cases, the quality difference between hybrid and conventional rice needs to be distinguished. The compounds of rice, i.e., starch (Derycke et al. 2005; Martin and Fitzgerald 2002; Cheng et al. 2005), amylose content (Singh et al. 2000), and protein (Xie et al. 2008; Bett-Garber et al. 2001), can be analyzed by the traditional chemical methods. However, it is always difficult to show the quality difference just by the content of several components of rice. It is necessary that a new and easy technology can be used to rapidly discriminate conventional and hybrid rice. Electronic tongue and nose, based on sensors array, are a special type of instruments, which can mimic human taste and smell to evaluate food quality. Electronic nose consists of several types of sensor arrays whose output is integrated by advanced signal processing to identify complex odor mixtures rapidly (Schulbach et al. 2004; Z
Data Loading...
