Browsing by Author "Panagou, Efstathios Z."

Now showing 1 - 7 of 7
  • Thumbnail Image
    ItemOpen Access
    Application of spectroscopic and multispectral imaging technologies on the assessment of ready-to-eat pineapple quality: A performance evaluation study of machine learning models generated from two commercial data analytics tools
    (Elsevier, 2020-06-03) Manthou, Evanthia; Lago, Sergio-Llaneza; Dagres, Evaggelos; Lianou, Alexandra; Tsakanikas, Panagiοtis; Panagou, Efstathios Z.; Anastasiadi, Maria; Mohareb, Fady; Nychas, George-John E.
    Recently, rapid, non-invasive analytical methods relying on vibrational spectroscopy and hyper/multispectral imaging, are increasingly gaining popularity in food science. Although such instruments offer a promising alternative to the conventional methods, the analysis of generated data demands complex multidisciplinary approaches based on data analytics tools utilization. Therefore, the objective of this work was to (i) assess the predictive power of different analytical platforms (sensors) coupled with machine learning algorithms in evaluating quality of ready-to-eat (RTE) pineapple (Ananas comosus) and (ii) explore the potentials of The Unscrambler software and the online machine-learning ranking platform, SorfML, in developing the predictive models required by such instruments to assess quality indices. Pineapple samples were stored at 4, 8, 12 °C and dynamic temperatures and were subjected to microbiological (total mesophilic microbial populations, TVC) and sensory analysis (colour, odour, texture) with parallel acquisition of spectral data. Fourier-transform infrared, fluorescence (FLUO) and visible sensors, as well as Videometer instrument were used. For TVC, almost all the combinations of sensors and Partial-least squares regression (PLSR) algorithm from both analytics tools reached values of root mean square error of prediction (RMSE) up to 0.63 log CFU/g, as well as the highest coefficient of determination values (R2). Moreover, Linear Support Vector Machine (SVM Linear) combined with each one of the sensors reached similar performance. For odour, FLUO sensor achieved the highest overall performance, when combined with Partial-least squares discriminant analysis (PLSDA) in both platforms with accuracy close to 85%, but also with values of sensitivity and specificity above 85%. The SVM Linear and MSI combination also achieved similar performance. On the other hand, all models developed for colour and texture showed poor prediction performance. Overall, the use of both analytics tools, resulted in similar trends concerning the feasibility of the different analytical platforms and algorithms on quality evaluation of RTE pineapple.
  • Thumbnail Image
    ItemOpen Access
    A comparison of artificial neural networks and partial least squares modelling for the rapid detection of the microbial spoilage of beef fillets based on Fourier transform infrared spectral fingerprints
    (Elsevier Science B.V., Amsterdam, 2011-06-30T00:00:00Z) Panagou, Efstathios Z.; Mohareb, Fady R.; Argyri, Anthoula A.; Bessant, Conrad M.; Nychas, George-John E.
    A series of partial least squares (PLS) models were employed to correlate spectral data from FTIR analysis with beef fillet spoilage during aerobic storage at different temperatures (0, 5, 10, 15, and 20°C) using the dataset presented by Argyri etal. (2010). The performance of the PLS models was compared with a three-layer feed-forward artificial neural network (ANN) developed using the same dataset. FTIR spectra were collected from the surface of meat samples in parallel with microbiological analyses to enumerate total viable counts. Sensory evaluation was based on a three-point hedonic scale classifying meat samples as fresh, semi-fresh, and spoiled. The purpose of the modelling approach employed in this work was to classify beef samples in the respective quality class as well as to predict their total viable counts directly from FTIR spectra. The results obtained demonstrated that both approaches showed good performance in discriminating meat samples in one of the three predefined sensory classes. The PLS classification models showed performances ranging from 72.0 to 98.2% using the training dataset, and from 63.1 to 94.7% using independent testing dataset. The ANN classification model performed equally well in discriminating meat samples, with correct classification rates from 98.2 to 100% and 63.1 to 73.7% in the train and test sessions, respectively. PLS and ANN approaches were also applied to create models for the prediction of microbial counts. The performance of these was based on graphical plots and statistical indices (bias factor, accuracy factor, root mean square error). Furthermore, results demonstrated reasonably good correlation of total viable counts on meat surface with FTIR spectral data with PLS models presenting better performance indices compared to ANN.
  • Thumbnail Image
    ItemOpen Access
    Effect of temperature and water activity on growth and ochratoxin A production boundaries of two Aspergillus carbonarius isolates on a simulated grape juice medium
    (Blackwell Publishing Ltd, 2009-07-01T00:00:00Z) Tassou, C. C.; Natskoulis P. I.; Magan, Naresh; Panagou, Efstathios Z.
    Aims: To develop and validate a logistic regression model to predict the growth and ochratoxin A (OTA) production boundaries of two Aspergillus carbonarius isolates on a synthetic grape juice medium as a function of temperature and water activity (aw).
  • Thumbnail Image
    ItemOpen Access
    Novel approaches for food safety management and communication
    (Elsevier, 2016-06-25) Nychas, George-John E.; Panagou, Efstathios Z.; Mohareb, Fady R.
    The current safety and quality controls in the food chain are lacking or inadequately applied and fail to prevent microbial and/or chemical contamination of food products, which leads to reduced confidence among consumers. On the other hand to meet market demands food business operators (producers, retailers, resellers) and regulators need to develop and apply structured quality and safety assurance systems based on thorough risk analysis and prevention, through monitoring, recording and controlling of critical parameters covering the entire product's life cycle. However the production, supply, and processing sectors of the food chain are fragmented and this lack of cohesion results in a failure to adopt new and innovative technologies, products and processes. The potential of using information technologies, for example, data storage, communication, cloud, in tandem with data science, for example, data mining, pattern recognition, uncertainty modelling, artificial intelligence, etc., through the whole food chain including processing within the food industry, retailers and even consumers, will provide stakeholders with novel tools regarding the implementation of a more efficient food safety management system.
  • Thumbnail Image
    ItemOpen Access
    Rapid qualitative and quantitative detection of beef fillets spoilage based on Fourier transform infrared spectroscopy data and artificial neural networks
    (Elsevier, 2009) Argyri, Anthoula A.; Panagou, Efstathios Z.; Tarantilis, P. A.; Polysiou, M.; Nychas, George-John E.
    A machine learning strategy in the form of a multilayer perceptron (MLP) neural network was employed to correlate Fourier transform infrared (FTIR) spectral data with beef spoilage during aerobic storage at chill and abuse temperatures. Fresh beef fillets were packaged under aerobic conditions and left to spoil at 0, 5, 10, 15, and 20 °C for up to 350 hours. FTIR spectra were collected directly from the surface of meat samples, whereas total viable counts of bacteria were obtained with standard plating methods. Sensory evaluation was performed during storage and samples were attributed into three quality classes namely fresh, semi-fresh, and spoiled. A neural network was designed to classify beef samples to one of the three quality classes based on the biochemical profile provided by the FTIR spectra, and in parallel to predict the microbial load (as total viable counts) on meat surface. The results obtained demonstrated that the developed neural network was able to classify with high accuracy the beef samples in the corresponding quality class using their FTIR spectra. The network was able to classify correctly 22 out of 24 fresh samples (91.7%), 32 out of 34 spoiled samples (94.1%), and 13 out of 16 semi-fresh samples (81.2%). No fresh sample was misclassified as spoiled and vice versa. The performance of the network in the prediction of microbial counts was based on graphical plots and statistical indices (bias and accuracy factors, standard error of prediction, mean relative and mean absolute percentage residuals). Results demonstrated good correlation of microbial load on beef surface with spectral data. The results of this work indicated that the biochemical fingerprints during beef spoilage obtained by FTIR spectroscopy in combination with the appropriate machine learning strategy have significant potential for rapid assessment of meat spoilage.
  • Thumbnail Image
    ItemOpen Access
    Spoilage assessment of chicken breast fillets by means of Fourier transform Infrared spectroscopy and Multispectral Image Analysis
    (Elsevier, 2021-02-25) Spyrelli, Evgenia D.; Ozcan, Onur; Mohareb, Fady; Panagou, Efstathios Z.; Nychas, George-John E.
    The objective of this research was the evaluation of Fourier transforms infrared spectroscopy (FT-IR) and multispectral image analysis (MSI) as efficient spectroscopic methods in tandem with multivariate data analysis and machine learning for the assessment of spoilage on the surface of chicken breast fillets. For this purpose, two independent storage experiments of chicken breast fillets (n=215) were conducted at 0, 5, 10, and 15 oC for up to 480 h. During storage, samples were analyzed microbiologically for the enumeration of Total Viable Counts (TVC) and Pseudomonas spp. In addition, FT-IR and MSI spectral data were collected at the same time intervals as for microbiological analyses. Multivariate data analysis was performed using two software platforms (a commercial and a publicly available developed platform) comprising several machine learning algorithms for the estimation of the TVC and Pseudomonas spp. population of the surface of the samples. The performance of the developed models was evaluated by intra batch and independent batch testing. Partial Least Squares- Regression (PLS-R) models from the commercial software predicted TVC with root mean square error (RMSE) values of 1.359 and 1.029 log CFU/cm2 for MSI and FT-IR analysis, respectively. Moreover, RMSE values for Pseudomonas spp. model were 1.574 log CFU/cm2 for MSI data and 1.078 log CFU/cm2 for FT-IR data. From the implementation of the in-house sorfML platform, artificial neural networks (nnet) and least-angle regression (lars) were the most accurate models with the best performance in terms of RMSE values. Nnet models developed on MSI data demonstrated the lowest RMSE values (0.717 log CFU/cm2) for intra-batch testing, while lars outperformed nnet on independent batch testing with RMSE of 1.252 log CFU/cm2. Furthermore, lars models excelled with the FT-IR data with RMSE of 0.904 and 0.851 log CFU/cm2 in intra-batch and independent batch testing, respectively. These findings suggested that FT-IR analysis is more efficient than MSI to predict the microbiological quality on the surface of chicken breast fillets
  • Thumbnail Image
    ItemOpen Access
    Table olives volatile fingerprints: Potential of an electronic nose for quality discrimination.
    (Elsevier, 2008-09-25) Panagou, Efstathios Z.; Sahgal, Natasha; Magan, Naresh; Nychas, George-John E.
    In the present work, the potential of an electronic nose to differentiate the quality of fermented green table olives based on their volatile profile was investigated. An electronic gas sensor array system comprising a hybrid sensor array of 12 metal oxide and 10 metal ion-based sensors was used to generate a chemical fingerprint (pattern) of the volatile compounds present in olives. Multivariate statistical analysis and artificial neural networks were applied to the generated patterns to achieve various classification tasks. Green olives were initially classified into three major classes (acceptable, unacceptable, marginal) based on a sensory panel. Multivariate statistical approach showed good discrimination between the class of unacceptable samples and the classes of acceptable and marginal samples. However, in the latter two classes there was a certain area of overlapping in which no clear differentiation could be made. The potential to discriminate green olives in the three selected classes was also evaluated using a multilayer perceptron (MLP) neural network as a classifier with an 18–15–8–3 structure. Results showed good performance of the developed network as only two samples were misclassified in a 66-sample training dataset population, whereas only one case was misclassified in a 12-sample test dataset population. The results of this study provide promising perspectives for the use of a low-cost and rapid system for quality differentiation of fermented green olives based on their volatile profile.