Application of an Electronic Nose Coupled with Fuzzy-Wavelet Network for the Detection of Meat Spoilage
Food product safety is one of the most promising areas for the application of electronic noses. Their application in this domain is mainly focused on quality control, freshness evaluation, shelf-life analysis and authenticity assessment. In this paper, the performance of a portable electronic nose has been evaluated in monitoring the spoilage of beef fillets stored either aerobically or under modified atmosphere packaging, at different storage temperatures. A novel multi-output fuzzy wavelet neural network architecture has been developed, which incorporates a clustering pre-processing stage for the definition of fuzzy rules. The dual purpose of the proposed modelling approach is not only to classify beef samples in the relevant quality class (i.e. fresh, semi-fresh and spoiled), but also to predict their associated microbiological population, based on total viable counts. For the case of aerobic packaging, model was able to classify correctly 67 out of 70 aerobic samples (95.71%), while successful identification of microbial counts resulted in a 4.57% standard error of prediction. However, under modified atmosphere packaging scenario, results were rather inferior, as proposed model achieved a 92.95% classification rate (66 out of 71 samples), while the standard error of prediction of microbial counts was increased to 5.74%. In comparison to these results, prediction performances of models used extensively in the area of Food Microbiology, such as MLP and PLS, revealed their deficiencies, while ANFIS and SVM models revealed their robustness in providing acceptable prediction performances for either aerobic or MAP packaging conditions. Results evaluation indicated that the proposed modelling scheme could be considered as a valuable detection methodology in food microbiology.
KeywordsFuzzy wavelet neural networks System identification Principal components analysis Meat spoilage Neural networks Clustering Classification
The author would like to thank Dr. E.Z. Panagou from Agricultural University of Athens, Greece for providing the enose dataset, as well as the related microbiological analysis that correspond to the beef samples.
- Abiyev, R.H., Kaynak, O. (2008a). Identification and control of dynamic plants using fuzzy wavelet neural networks, Proc. of the IEEE International Symposium on Intelligent Control, 1295–1301.Google Scholar
- Al-Anazi, A., Gates, I.D. (2010). Support-vector regression for permeability prediction in a heterogeneous reservoirs: SPE 126339, SPE Reservoir Evaluation & Engineering 485–495.Google Scholar
- Alshejari, A., Kodogiannis, V.S. (2016). An Intelligent Decision Support System for the Detection of Meat Spoilage using Multispectral Images, Neural Computing and Applications, (In Press).Google Scholar
- Argyri, A. A., Panagou, E. Z., Tarantilis, P. A., Polysiou, M., & Nychas, G.-J. E. (2010). Rapid qualitative and quantitative detection of beef fillets spoilage based on Fourier transform infrared spectroscopy data and artificial neural networks. Sensors and Actuators B, 145, 146–154.CrossRefGoogle Scholar
- Balasubramanian, S., Amamcharla, J., Shin, J.-E. (2016). Possible Application of Electronic Nose Systems for Meat Safety: An Overview, Electronic Noses and Tongues in Food Science, 59–71.Google Scholar
- Berna, A.Z., Anderson, A.R., Trowell, S.C. (2009). Bio-benchmarking of electronic nose sensors, PLoS ONE, 4(7).Google Scholar
- Christiansen, A.N., Carstensen, J.M., Papadopoulou, O., Chorianopoulos, N., Panagou, E.Z., & Nychas, G-J.E (2011). Multi spectral imaging analysis for meat spoilage discrimination, 7th International Conference on Predictive Modelling of Food Quality and Safety, Dublin, Ireland.Google Scholar
- Fend, R., Kolk, A. H. J., Bessant, C., Buijtels, P., Klatser, P. R., & Woodman, A. C. (2006). Prospects for clinical application of electronic-nose technology to early detection of mycobacterium tuberculosis in culture and sputum. Journal of Clinical Microbiology, 44(6), 2039–2045.CrossRefGoogle Scholar
- Jang, J.S.R. Sun, C.T., Mizutani, E. (1997). Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence, Prentice-Hall.Google Scholar
- Khot, L. R., Panigrahi, S., Doetkott, C., & Chang, Y. (2012). Evaluation of technique to overcome small dataset problems during neural-network based contamination classification of packaged beef using integrated olfactory sensor system. LWT - Food Science and Technology, 45(2), 233–240.CrossRefGoogle Scholar
- Kodogiannis, V.S., & Petrounias, I. (2012). Modelling of survival curves in food microbiology using adaptive fuzzy inference neural networks, 2012 IEEE Int. Conf. on Computational Intelligence for Measurement Systems and Applications IEEE (CIMSA 2012), IEEE. pp. 35–40. doi: 10.1109/CIMSA.2012.6269596.
- Kodogiannis, V.S., Amina, M., Petrounias, I. (2013). A clustering-based fuzzy-wavelet neural network model for short-term load forecasting, International Journal of Neural Systems, 23(5).Google Scholar
- Li, S.,Wang, P., Goel, L. (2016). A Novel Wavelet-Based Ensemble Method for Short-Term Load Forecasting with Hybrid Neural Networks and Feature Selection, IEEE Transactions on power systems, 31(3) .Google Scholar
- O’Sullivan, M.G., Kerry, J.P. (2009). Sensory evaluation of fresh meat, in Improving the sensory and nutritional quality of fresh meat, Woodhead Publishing Limited.Google Scholar
- Panagou, E. Z., Kodogiannis, V., Nychas, G.J-E. (2007). Modelling fungal growth using radial basis function neural networks: The case of the ascomycetous fungus Monascus ruber van Tieghem. International Journal of Food Microbiology, 117, 276--286.Google Scholar
- Rutkowska, D. (2002). Neuro-Fuzzy Architectures and Hybrid Learning, Springer.Google Scholar
- Vapnik, V. (1998). Statistical learning theory. New York: Wiley.Google Scholar