Spoilage Identification of Beef Using an Electronic Nose System

Abstract

A commercially available Cyranose-320. conducting polymer-based electronic nose system was used to analyze the volatile organic compounds emanating from fresh beef strip loins (M. Longisimmus lumborum) stored at 4°C and 10°C. Two statistical techniques, i.e., linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA), were used to develop classification models from the collected sensor signals. The performances of the developed models were validated by two different methods: leave-1-out crossvalidation, and bootstrapping. The developed models classified meat samples based on the microbial population into "unspoiled" (microbial counts <6.0 log10 cfu/g) and "spoiled" (microbial counts > 6.0 log10 cfu/g). Overall, quadratic discriminant-based classification models performed better than linear discriminant analysis based models. For the meat samples stored at 10°C, the highest classification accuracies obtained by the LDA method with leave-1-out and bootstrapping validations were 87.10% and 85.87%, respectively. On the other hand, classification by QDA and subsequent validation by leave-1-out and bootstrapping provided highest accuracies of 87.5% and 97.38%, respectively. For samples stored at 4°C, the LDA method provided highest classification accuracies of 79.17% and 85.64% using leave-1-out and bootstrapping validation, respectively. When the QDA method was used, the highest classification accuracies obtained for the samples stored at 4°C were 87.50% and 98.48%, respectively, with leave-1-out and bootstrapping validations.

Independent component analysis-processed electronic nose data for predicting Salmonella typhimurium populations in contaminated beef

“…Several researchers have reported the use of electronic nose systems for determining the quality of meat, grains, coffee, mushrooms, beer, cheese, fish, beverages, blueberry and sugars (Balasubramanian et al, 2004;Di Natale et al, 1997;Olsson, Borjesson, Lundstedt, & Schnurer, 2002;Schaller, Bosset, & Escher, 1998).…”

Onion sour skin detection using a gas sensor array and support vector machine

“…It is shown that the performance of the 32-sensor and 10-sensor schemes were comparable (67% vs. 69%), however, the six-sensor scheme performed significantly better than its counterparts with 85% classification accuracy. Combined data 31, 5,23,6,28,26,29,9,20,18 It is interesting to note that although the six-sensor scheme trailed the other two schemes in the model cross validation, it outperformed the other two schemes considerably in the model validation. The potential reason for this performance discrepancy between the six-sensor scheme and 32-or 10-sensor schemes may lie in the fact that the four sensors (sensor 5, 6, 23, and 31) that are more sensitive to the water vapor were excluded from these six sensors.…”

“…The E-nose has been utilized in various food quality evaluation applications such as predicting apple, pear, and banana ripeness [15][16][17], identification of microbes responsible for spoiled beef [18], detection of apple defects [19][20][21], and inspection of grains for quality control [22]. The E-nose was also utilized for the Allium research in the past.…”

Wheat Class Identification Using Thermal Imaging

“…For the classification of agricultural and food materials, statistical (parametric and nonparametric) and artificial neural network classifiers have been used widely (Visen et al 2004;Majumdar and Jayas 2000b;Balasubramanian et al 2004;Dubey et al 2006). The selection of the best classifier for a particular application generally involves some degree of experimentation (Jayas et al 2000;Luo et al 1999).…”