Browsing by Author "Unluturk, Sevcan"

Now showing 1 - 4 of 4

Citation - WoS: 1
Citation - Scopus: 2
Discrimination of Bio-Crystallogram Images Using Neural Networks
(Springer, 2014) Unluturk, Sevcan; Unluturk, Mehmet S.; Pazir, Fikret; Kuscu, Alper
This study utilized a unique neural network model for texture image analysis to differentiate the crystallograms from pairs of fresh red pepper fruits from conventional and organic farms. The differences in visually analyzed samples are defined as the distribution of crystals on the circular glass underlay, the thin or thick structure of crystal needles, the angles between branches and side needles, etc. However, the visual description and definition of bio-crystallogram images has major disadvantages. A novel methodology called an image neural network (INN) has been developed to overcome these shortcomings. The 1,488 x 2,240 pixel bio-crystallogram images were acquired in a lab and cropped to 425 x 1,025 pixel images. These depicted either a conventional sweet red pepper or an organic sweet red pepper. A set of 19 images was utilized to train the image neural network. A new set of 4 images was then prepared to test the INN performance. Overall, the INN achieved an average recognition performance of 100 %. This high level of recognition suggests that the INN is a promising method for the discrimination of bio-crystallogram images. In addition, Hinton diagrams were utilized to display the optimality of the INN weights.
Citation - WoS: 12
Citation - Scopus: 13
The Discrimination of Raw and Uht Milk Samples Contaminated With Penicillin G and Ampicillin Using Image Processing Neural Network and Biocrystallization Methods
(Academic Press Inc Elsevier Science, 2013) Unluturk, Sevcan; Pelvan, Merve; Unluturk, Mehmet S.
This paper utilized a neural network for texture image analysis to differentiate between milk, either raw or ultra high temperature (UHT) with antibiotic residues (e.g., penicillin G and ampicillin) and milk without antibiotic residues. The biocrystallization method was applied to obtain biocrystallogram images for milk samples spiked with penicillin G and ampicillin at different concentration levels. The biocrystallogram images were used as an input for a designed neural network called the image processing neural network (ImgProcNN). The visual differences in these images that were based on textural properties, including the distribution of crystals on the circular grass underlay, the thin or thick structure of the crystal needles, and the angles between the branches and the side needles, were used to discriminate the antibiotic-free milk samples from samples with antibiotic residues. The visual description and definition of these images have major disadvantages. In this study, the ImgProcNN was developed to overcome the shortcomings of these visual descriptions and definitions. Overall, the neural network achieved an average recognition performance between 86% and 100%. This high level of recognition suggests that the neural network used in this paper has potential as a method for discriminating raw and UHT milk samples contaminated with different antibiotics. (C) 2013 Elsevier Inc. All rights reserved.
Citation - WoS: 87
Citation - Scopus: 99
Modeling Inactivation Kinetics of Liquid Egg White Exposed To Uv-C Irradiation
(Elsevier, 2010) Unluturk, Sevcan; Atilgan, Mehmet R.; Baysal, A. Handan; Unluturk, Mehmet S.
The efficiency of UV-C irradiation as a non-thermal pasteurization process for liquid egg white (LEW) was investigated. LEW inoculated with Escherichia coli K-12 (ATCC 25253), pathogenic strain of Escherichia coli O157:H7 (NCTC12900) and Listeria innocua (NRRL B33314) were treated with UV light using a bench top collimated beam apparatus. Inoculated LEW samples were exposed to UV-C irradiation of known UV intensity of 1.314 mW/cm(2) and sample depth of 0.153 cm for 0, 3 5, 7, 10, 13, 17 and 20 min. The populations of E. coli K-12, E. coli 0157:H7 and L. innocua were reduced after 20 min of exposure by 0.896, 1.403 and 0.960 log CFU respectively. Additionally, the inactivation data obtained for each strain suspended in LEW was correlated by using Weibull (2 parameter), Log-Linear (1 parameter), Horn (2 parameter) and modified Chick Watson (2 parameter) models. The inactivation kinetics of E. coli K-12, E. coli 0157:H7 and L. innocua were best described by modified Chick Watson model with the smallest root mean squared error (RMSE) (R-2 >= 0.92). (C) 2010 Elsevier B.V. All rights reserved.
Citation - WoS: 1
Citation - Scopus: 2
Process Neural Network Method: Case Study I: Discrimination of Sweet Red Peppers Prepared by Different Methods
(Hindawi Publishing Corporation, 2011) Unluturk, Sevcan; Unluturk, Mehmet S.; Pazir, Fikret; Kuscu, Alper
This study utilized a feed-forward neural network model along with computer vision techniques to discriminate sweet red pepper products prepared by different methods such as freezing and pureeing. The differences among the fresh, frozen and pureed samples are investigated by studying their bio-crystallogram images. The dissimilarity in visually analyzed bio-crystallogram images are defined as the distribution of crystals on the circular glass underlay and the thin or the thick structure of crystal needles. However, the visual description and definition of bio-crystallogram images has major disadvantages. A methodology called process neural network (ProcNN) has been studied to overcome these shortcomings.