Yazar "Yucel, Ozgun" seçeneğine göre listele
Listeleniyor 1 - 7 / 7
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe An intelligent based prediction of microbial behaviour in beef(Elsevier Sci Ltd, 2023) Yucel, Ozgun; Tarlak, FatihThe main purpose of this work was to develop different machine learning-based regression methods referred to as decision tree regression (DTR), generalized additive model regression (GAMR) and random forest regression (RFR) to predict bacterial population on beef. For this purpose, 2654 bacterial data points of Listeria monocytogenes, Escherichia coli and Pseudomonas spp. Which are the most investigated bacterial genera in beef were collected from the ComBase database (www.combase.cc). Temperature, salt concentration, water activity and acidity were used as the main predictor variables to estimate the growth or survival behaviour of the microorganisms in beef. The hyperparameters are optimized for proposed machine learning-based regression methods with nested cross-validation. The fitting capabilities of the proposed machine learning algorithms were compared considering their statistical indices (coefficient of determination R2 and root mean square error RMSE). Each regression method provided satisfactory predictions with being 0.931 < R2 < 0.949 and 0.597 < RMSE < 0.692 considering each of the microorganism populations. However, the RFR yielded the best prediction capability and therefore its prediction capability was further assessed. The RFR in the external validation process provided statistical indices being 1.017 < Bias factor <1.151 and 1.137 < Accuracy factor <1.370, indicating that the random forest regression can be reliably employed as an alternative way of describing simultaneously survival and growth behaviour of microorganisms in beef and has a significant potential to be used as an alternative simulation method by skipping a secondary model step in two-step modelling approach, traditionally utilized in the predictive microbiology field.Öğe Application of a machine learning-based regression method to describe Listeria monocytogenes behaviour in milk(Vup Food Research Inst, Bratislava, 2022) Tarlak, Fatih; Yucel, OzgunThe main aim of the present study was to develop a prediction tool to describe Listeria monocytogenes behaviour in milk by employing traditionally used models (the re-parametrized Gompertz, Baranyi and Huang models) and an alterna-tively proposed machine learning-based regression model. The fitting capability of both groups of models was evaluated and compared considering their statistical indices (coefficient of determination R-2, root mean square error RMSE). The machine learning-based regression model provided better predictions (with R-2 of 0.958 and RMSE of 0.407) than the traditionally used models. The prediction capability of both methodologies was tested considering externally collected data from the literature. The machine learning-based regression model in the validation process gave satisfactory sta-tistical indices (bias factor of 1.016 and accuracy factor of 1.056), which is better prediction power than the traditionally used models. These results indicated that the machine learning-based regression method can be reliably employed as an alternative way of describing the growth behaviour of L. monocytogenes in milk. Therefore, the software developed in this work has a significant potential to be used as an alternative simulation method to traditionally used approach in the field of predictive microbiology.Öğe Development of a New Modelling Approach and Performance Evaluation of Meta-heuristic Optimization Algorithms for the Prediction of Kinetic Growth Parameters for Pseudomonas spp. in Fish(Dr M N Khan, 2022) Tarlak, Fatih; Yucel, Ozgun; Khosravi-Darani, KianoushThe main aim of the current work was to build up a new mathematical modelling approach in predictive food microbiology field for the prediction of growth kinetics of microorganisms. For this purpose, the bacterial growth data of Pseudomonas spp. in whole fish (gilt-head seabream) subjected to isothermal and non-isothermal storage temperatures were collected from previously published growth curves. Maximum specific growth rate (1/h) and lag phase duration (h) were described as a function of storage temperature using the direct two-step, direct one-step and inverse dynamic modelling approaches based on various meta-heuristic optimization algorithms. The fitting capability of the modelling approaches and employed optimization algorithms was separately compared, and the one-step modelling approach for the direct methods and the Bayesian optimization method for the used algorithms provided the best goodness of fit results. These two were then further processed in validation step. The inverse dynamic modelling approach based on the Bayesian optimization algorithm yielded satisfactorily statistical indexes (1.02 > Bias factor > 1.09 and 1.07 > Accuracy factor > 1.13), which indicates it can be reliably used as an alternative way of describing the growth behaviour of Pseudomonas spp. in fish in a fast and efficient manner with minimum labour effort.Öğe Development of a Prediction Software for the Growth Kinetics of Pseudomonas spp. in Culture Media using Various Primary Models(Shahid Beheshti Univ Medical Sciences, Fac Med, 2023) Tarlak, Fatih; Yucel, OzgunBackground and Objective: Pseudomonas spp. are bacteria with the widest effects on food spoilage. These bacteria can be found in several environments such as soil and water. The major purpose of this study was to develop a software; by which, the growth behaviours of Pseudomonas spp. in culture media could be predicted.Material and Methods: A total number of 509 bacterial data points of Pseudomonas spp. in culture media were collected from the ComBase database. Temperature and pH were used as the major prediction variables for the description of Pseudomonas spp. behaviours in culture media. Modified Gompertz, Baranyi and Huang models, the most commonly used models in predictive food microbiology to predict the count of microorganisms, were used as well. Fitting capability of each model was assessed and compared with other capabilities considering their statistical indices of the root mean square error, RMSE; coefficient of determination, R2; corrected Akaike information criterion, AICc; and Bayesian information criterion, BIC.Results and Conclusion: Huang model provided better predictions with 0.951 of R2 and 0.825 of RMSE, compared to those of traditionally used models. Prediction capability of the Huang model was assessed considering externally collected data from the ComBase database. Huang model in the validation process provided satisfactory statistical indices (bias factor = 1.027 and accuracy factor = 1.075). These results have revealed that Huang model can be reliably used as a model of describing the growth behaviours of Pseudomonas spp. Furthermore, developed software in this study includes significant potentials for predicting Pseudomonas counts in culture media.Öğe Development of prediction software to describe total mesophilic bacteria in spinach using a machine learning-based regression approach(Sage Publications Ltd, 2023) Yildirim-Yalcin, Meral; Yucel, Ozgun; Tarlak, FatihThe purpose of this study was to create a tool for predicting the growth of total mesophilic bacteria in spinach using machine learning-based regression models such as support vector regression, decision tree regression, and Gaussian process regression. The performance of these models was compared to traditionally used models (modified Gompertz, Baranyi, and Huang models) using statistical indices like the coefficient of determination (R-2) and root mean square error (RMSE). The results showed that the machine learning-based regression models provided more accurate predictions with an R-2 of at least 0.960 and an RMSE of at most 0.154, indicating that they can be used as an alternative to traditional approaches for predictive total mesophilic. Therefore, the developed software in this work has a significant potential to be used as an alternative simulation method to traditionally used approach in the predictive food microbiology field.Öğe FOOD RECOGNITION AND NUTRITION FACTS DETERMINATION WITH DEEP CONVOLUTION NEURAL NETWORK MODELS(North Univ Center Baia Mare, 2023) Tarlak, Fatih; Yucel, Ozgun; Yilmaz, OnurFood recognition plays a crucial role in various domains including healthcare, nutrition, and the food industry. In healthcare, food recognition is valuable for individuals to monitor their daily food intake and manage their diet effectively. It also aids dietitians and nutritionists in creating personalized meal plans for patients based on their nutritional requirements and preferences. The objective of this research was to develop software capable of recognizing and predicting the nutritional information of commonly consumed fruits and vegetables in Turkey. Basic nutrition data for each food item was collected and organized. A dataset comprising 9,000 food images was gathered, encompassing 200 images for each food item. To train the images, deep learning (DL) algorithms such as GoogleNet, ResNet-50, and Inception-v3 were utilized on platforms like Matlab and.NET Core. Additionally, 900 food images were reserved for external validation purposes. The DL algorithms achieved excellent accuracy, with all models surpassing 98.3% accuracy in predicting food categories. Notably, the Inception-v3 algorithm outperformed the others, achieving an accuracy of 99.1% during the testing phase. Consequently, the Inception-v3 algorithm was chosen to develop software for food recognition and nutrition analysis, intended for both computers and smartphones. The software can be relied upon for food recognition and nutrition analysis, making it highly valuable in healthcare, particularly in tracking the dietary intake of patients with chronic conditions like diabetes, heart disease, or obesity. The system can effectively track the types and quantities of foods consumed, providing personalized feedback to both patients and healthcare providers.Öğe Prediction of Pseudomonas spp. Population in Food Products and Culture Media Using Machine Learning-Based Regression Methods(Mdpi, 2023) Tarlak, Fatih; Yucel, OzgunMachine learning approaches are alternative modelling techniques to traditional modelling equations used in predictive food microbiology and utilise algorithms to analyse large datasets that contain information about microbial growth or survival in various food matrices. These approaches leverage the power of algorithms to extract insights from the data and make predictions regarding the behaviour of microorganisms in different food environments. The objective of this study was to apply various machine learning-based regression methods, including support vector regression (SVR), Gaussian process regression (GPR), decision tree regression (DTR), and random forest regression (RFR), to estimate bacterial populations. In order to achieve this, a total of 5618 data points for Pseudomonas spp. present in food products (beef, pork, and poultry) and culture media were gathered from the ComBase database. The machine learning algorithms were applied to predict the growth or survival behaviour of Pseudomonas spp. in food products and culture media by considering predictor variables such as temperature, salt concentration, water activity, and acidity. The suitability of the algorithms was assessed using statistical measures such as coefficient of determination (R-2), root mean square error (RMSE), bias factor (Bf), and accuracy (A(f)). Each of the regression algorithms showed appropriate estimation capabilities with R-2 ranging from 0.886 to 0.913, RMSE from 0.724 to 0.899, B-f from 1.012 to 1.020, and A(f) from 1.086 to 1.101 for each food product and culture medium. Since the predictive capability of RFR was the best among the algorithms, externally collected data from the literature were used for RFR. The external validation process showed statistical indices of B-f ranging from 0.951 to 1.040 and A(f) ranging from 1.091 to 1.130, indicating that RFR can be used for predicting the survival and growth of microorganisms in food products. Therefore, machine learning approaches can be considered as an alternative to conventional modelling methods in predictive microbiology. However, it is important to highlight that the prediction power of the machine learning regression method directly depends on the dataset size, and it requires a large dataset to be employed for modelling. Therefore, the modelling work of this study can only be used for the prediction of Pseudomonas spp. in specific food products (beef, pork, and poultry) and culture medium with certain conditions where a large dataset is available.