Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4565369 | LWT - Food Science and Technology | 2006 | 11 Pages |
A commercially available Cyranose-320™ conducting polymer-based electronic nose system was used to analyse the headspace from fresh beef strip loins (M. Longissimus lumborum) stored at 4° and 10 °C. The raw signals obtained from the electronic nose system were pre-processed by various signal-processing techniques to extract area-based features. Principal component analysis was subsequently performed on the processed signals to further reduce the dimensionalities. Classification models using radial basis function neural networks were developed using the extracted features. The performance of the developed models was validated using leave-1-out cross-validation method. The developed models classified meat samples stored at two storage temperatures into two groups, i.e., “unspoiled” (microbial counts<6.0 log10 cfu/g) and “spoiled” (microbial counts ⩾6.0 log10 cfu/g). Maximum total classification accuracies of 100% were obtained for both the samples stored at 10 and 4 °C. Classification models based on “Area scaled” feature showed higher accuracies than that obtained using “Area unscaled feature.”