Yazar "Sehirli, Eftal" seçeneğine göre listele
Listeleniyor 1 - 12 / 12
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe An application for the classification of egg quality and haugh unit based on characteristic egg features using machine learning models(Pergamon-Elsevier Science Ltd, 2022) Sehirli, Eftal; Arslan, KubraWith the increase in the world population, the nutritional needs of people have been increased. The demand for eggs which is one of the most important food sources has been increased over years. Therefore, it is very important to inform people about egg quality in order to be prepared for adverse situations such as substitution, mislabeling, and fraud. In this study, it is aimed to specify egg quality without using haugh unit (HU). Besides, another aim is to find how much information HU carries about the specification of egg quality. A dataset including 20 features related to eggs taken from 438 chickens created by Poultry Research Institute (PRI) has been analyzed. An application that can classify egg qualities as very good and excellent using machine learning (ML) models like decision tree (DT), linear discriminant analysis (LDA), logistic regression (LR), naive bayes (NB), support vector machines (SVM), K-nearest neighboring (KNN), random forest (RF) and artificial neural networks (ANN) has been developed in this study. In addition to that, HU at the 24th week and the 32nd week which are the most important classifier to determine egg qualities have been classified as low informative, medium informative, and high informative by the developed application. Egg quality has the best been classified by LR model based on accuracy and Matthews correlation coefficient (MCC) values as 98.6% and 0.96, respectively. HU at the 24th week has the best been classified by RF based on accuracy and MCC as 96.8% and 0.93, respectively. HU at the 32nd week has the best been classified by RF based on accuracy and MCC as 95.1% and 0.92, respectively. This paper mainly focuses on the classification of egg quality based on not only HU but also egg characteristic features and the importance of the informative feature of HU to classify egg quality.Öğe Classification of DNA damages on segmented comet assay images using convolutional neural network(Elsevier Ireland Ltd, 2020) Atila, Umit; Baydilli, Yusuf Yargi; Sehirli, Eftal; Turan, Muhammed KamilBackground and Objective: Identification and quantification of DNA damage is a very significant subject in biomedical research area which still needs more robust and effective methods. One of the cheapest, easy to use and most successful method for DNA damage analyses is comet assay. In this study, performance of Convolutional Neural Network was examined on quantification of DNA damage using comet assay images and was compared to other methods in the literature. Methods: 796 single comet grayscale images with 170 x 170 resolution labeled by an expert and classified into 4 classes each having approximately 200 samples as G0 (healthy), G1 (poorly defective), G2 (defective) and G3 (very defective) were utilized. 120 samples were used as test dataset and the rest were used in data augmentation process to achieve better performance with training of Convolutional Neural Network. The augmented data having a total of 9995 images belonging to four classes were used as network training data set. Results: The proposed model, which was not dependent to pre-processing parameters of image processing for DNA damage classification, was able to classify comet images into 4 classes with an overall accuracy rate of 96.1%. Conclusions: This paper primarily focuses on features and usage of Convolutional Neural Network as a novel method to classify comet objects on segmented comet assay images. (C) 2019 Elsevier B.V. All rights reserved.Öğe Determination of margarine adulteration in butter by machine learning on melting video(Springer, 2023) Sehirli, Eftal; Dogan, Cemhan; Dogan, NurcanButter is a product that is often vulnerable to adulteration with cheaper ingredients such as margarine. In this study, butter was artificially adulterated with margarine at different rates to create different levels of adulteration. Then, the melting was captured using video footage, and image processing and machine learning (ML) were used to automatically detect the level of adulteration in the butter. To create the final numerical dataset for ML models, a total of 30,000 images were collected from the video, with equal numbers of images for each class. The images were divided into five classes using an algorithm that detected region of interest (ROI) in the adulterated butter images. Two types of numerical datasets were created: single frame-based and first-middle-last (FML) frame-based. Seven different ML models (decision tree (DT), linear discriminant analysis (LDA), Naive Bayes (NB), support vector machines (SVM), k-nearest neighbor (KNN), random forest (RF) and artificial neural networks (ANN) were trained and tested on the datasets. To improve accuracy and efficiency, 10-fold cross-validation was applied to the ML models. The ML models achieved high accuracy in classifying the loaded butter videos. KNN, RF, and ANN had the highest accuracy (99.9%), followed by SVM (99.7%) and DT (99.4%) on the single frame-based dataset. NB had the lowest accuracy (87.1%). On the FML frame-based dataset, DT had the highest accuracy (99.9%) while SVM had the lowest accuracy (73.3%). Overall, the method used in this study was successful in classifying butter adulteration with high accuracy using image processing and ML techniques.Öğe E-Commerce According To Hobby(Elsevier Science Bv, 2014) Sehirli, Eftal; Orak, Ilhami M.This paper describes a web application called E-Commerce According to Hobby. In this application, E-Commerce According to Hobby application contains some different technologies such as RSS so as to be able to get the news of products from an e-commerce web site, LINQ to SQL and Ado. Net in order to make a connection with SQL Server Database System and compare these two technologies. Thanks to this study, we hope that people who use this application can reach the desired news more easily. Therefore, they can get a chance to get rid of the unrelated news for them. This study aims to increase the user-friendliness to do shopping from a specific e-commerce web site such as EBAY without spending a lot of time in a fast way. (C) 2014 Elsevier Ltd.Öğe Identification of column edges of DNA fragments by using K-means clustering and mean algorithm on lane histograms of DNA agarose gel electrophoresis images(Spie-Int Soc Optical Engineering, 2015) Turan, Muhammed Kamil; Sehirli, Eftal; Elen, Abdullah; Karas, Ismail RakipGel electrophoresis (GE) is one of the most used method to separate DNA, RNA, protein molecules according to size, weight and quantity parameters in many areas such as genetics, molecular biology, biochemistry, microbiology. The main way to separate each molecule is to find borders of each molecule fragment. This paper presents a software application that show columns edges of DNA fragments in 3 steps. In the first step the application obtains lane histograms of agarose gel electrophoresis images by doing projection based on x-axis. In the second step, it utilizes k-means clustering algorithm to classify point values of lane histogram such as left side values, right side values and undesired values. In the third step, column edges of DNA fragments is shown by using mean algorithm and mathematical processes to separate DNA fragments from the background in a fully automated way. In addition to this, the application presents locations of DNA fragments and how many DNA fragments exist on images captured by a scientific camera.Öğe A new approach for measuring the wetting angles of lead-free solder alloys from digital images(Elsevier - Division Reed Elsevier India Pvt Ltd, 2022) Sehirli, Eftal; Erer, Ahmet Mustafa; Turan, Muhammed KamilThis study aims to detect quaternary lead-free solder alloys and measure their dynamic wetting angles with a new approach. The detection of the prepared alloy drop and measurement of its wetting angle are automatically performed by the developed application. A video obtained after experimental studies is filtered over its frames and enhanced a better form in the preprocessing stage. The peak of the half alloy drop is detected by obtaining lane histogram and its global minimum point is found in the segmentation stage. Left and right corner points in contact with the ground are detected by tracking pixel intensity values with the help of the global minimum point. The median point for both left half alloy drop and right half alloy drop is calculated. Thus, circles passing through three points for the left half and right half of the alloy drop are obtained to measure theta(left), theta(right) and theta(mean) wetting angles. In the postprocessing stage, these angles are measured at 0th, 5th, 10th, 15th, 30th, 60th, 90th, 120th, 150th, and 300th seconds after the alloy drop contacted the ground. Besides, measurement of these wetting angles is performed at each second. The obtained results showed that the graph of theta(mean) versus time is an exponential decay graph. This result proves that the alloy drop spreads over the ground as time passes and the value of theta(mean) decreases and is consistent with the observation made during the experiment. (c) 2022 Karabuk University. Publishing services by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).Öğe Non-targeted approach to detect pistachio authenticity based on digital image processing and hybrid machine learning model(Springer, 2023) Dogan, Cemhan; Sehirli, Eftal; Dogan, Nurcan; Buran, IlkayIn this study, we propose a new method for detecting green pea adulteration in pistachio based on digital image and machine learning (ML). An algorithm was built using digital image processing techniques to detect region of interest (ROI) on adulterated pistachio images and a hybrid ML to classify the level of adulteration as class 1 (%0), class 2 (%10), class 3 (%20), class 4 (%30), class 5 (%40), and class 6 (%50) in a fully automated way. A dataset with size of 1254 x 15 were created. Training set and test set with the rate of 80% and 20% based on fivefold cross validation were created. Decision tree, random forest (RF), k-nearest neighboring, support vector machines, naive bayes and artificial neural network (ANN) are performed and compared to classify the level of adulteration in two steps as direct and binary classification. ANN has achieved the highest results as 93.65% of accuracy and 0.87 of Matthews correlation coefficient (MCC) based on direct classification to separate class1, class 2, class 5, and class 6 from class 3 and class 4. RF has achieved the highest results as 89.56% of accuracy and 0.79 of MCC based on binary classification to separate class3 from class 4. As a result of this, a hybrid ML model including ANN and RF in the form of a tree structure to classify the level of pistachio adulterated images was built in this study.Öğe A novel method to identify and grade DNA damage on comet images(Elsevier Ireland Ltd, 2017) Turan, Muhammed Kamil; Sehirli, EftalBackground and objective: In recent years, development of software programs in medicine field has proceeded in a rapid manner. Comet assay is one of the research methods in medicine field that displays whether DNA has damage. In this study, it is aimed to share experience of dynamic time warping method and decision tree to decide whether DNA has damage and grade DNA damage by means of the software program. Methods: The application analyzes manually extracted RGB single comet images whose centers are manually marked. The application performs pixel profile analysis at the directions of vertical and horizontal based on the center of comet. The bidirectional pixel profile results are used as inputs of dynamic time warping. Four novel and one conventional measurement parameters some of which are calculated by dynamic time warping are given to decision tree. Results: The decision tree identifies whether DNA has damage and grades DNA damage categorizing four damage levels with accuracy of 99.03% using only two of five measurement parameters. Conclusions: This paper mainly focuses on features and usage of dynamic time warping and decision tree as a novel method to identify and grade DNA damage on comet images. (C) 2017 Elsevier B.V. All rights reserved.Öğe A novel study to classify breath inhalation and breath exhalation using audio signals from heart and trachea(Elsevier Sci Ltd, 2023) Kavsaoglu, Ahmet Resit; Sehirli, EftalRespiration is a vital process for all living organisms. In the diagnosis and the detection of many health problems, patient's respiration rate, breath inhalation, and breath exhalation conditions are primarily taken into consid-eration by doctors, clinicians, and healthcare staff. In this study, an interactive application is designed to collect audio signals, present visual information about them, create a novel 21253x20 audio signal dataset for the detection of breath inhalation and breath exhalation that can be performed through nose and mouth, and classify audio signals based on machine learning (ML) models as breath inhalation and breath exhalation. Audio signals are received from both volunteers' hearts (method 1) and trachea (method 2). ML models as decision tree (DT), Naive Bayes (NB), support vector machines (SVM), k-nearest neighbor (KNN), gradient boosted trees (GBT), random forest (RF), and artificial neural network model (ANN) are used on the created dataset to classify the received audio signals from nose and mouth into two different conditions. The highest sensitivity, specificity, accuracy, and Matthews correlation coefficient (MCC) for the classification of breath inhalation and breath exhalation are respectively obtained as 91.82%, 87.20%, 89.51%, and 0.79 by method 2 based on majority voting of KNN, RF, and SVM. This paper mainly focuses on usage of audio signals and ML models as a novel approach to classify respiratory conditions based on breath inhalation and breath exhalation via an interactive application. This paper uncovers that audio signals received from method 2 are more effective and eligible to extract information than audio signals received from method 1.Öğe A Randomized Automated Thresholding Method to Identify Comet Objects on Comet Assay Images(Assoc Computing Machinery, 2017) Sehirli, Eftal; Turan, M. Kamil; Demiral, EmrullahDeoxyribonucleic acid (DNA) is an important molecule which has a tendency to easily have damage. Etiology of many diseases like cancer, cardiovascular disease, and immune deficiency is asserted to be based on DNA damage. Comet assay is a reliable, cheap and easy method to specify whether DNA has damage or not. The fact that the number of developing software applications on demand increases day by day comes into prominence of obtaining quick and accurate results in medicine field. In this study, a software application is developed which single comet objects on comet assay images are identified to perform analysis, calculation of comet parameters and decision regarding whether DNA has damage or not. Comet images are converted to red channel images, the randomized automated thresholding method is applied on red channel images and connected component labeling obtains each single comet object. This paper mainly focuses on specifications and mathematical model of the thresholding method.Öğe Ultra-Wideband Positioning System Using TWR and Lateration Methods(Assoc Computing Machinery, 2018) Duru, Anday; Sehirli, Eftal; Kabalci, IdrisIndoor wireless positioning systems enables location based applications to work properly inside buildings. Since GPS technology could not supply desired precision in indoor environment, there has been many positioning systems developed based on different technologies to solve localization problem. In this paper, indoor navigation system based on Ultra-Wideband technology has been proposed. Then, ranging model of the tracking system is established. Trilateration, Least Square Estimation and Centroid Method positioning algorithms are applied to provide a realistic comparison between them. Results are analyzed to compare the accuracy between different algorithms and the ideas are shared to improve the current study.Öğe Uncovering the differences in linguistic network dynamics of book and social media texts(Springer International Publishing Ag, 2016) Turker, Ilker; Sehirli, Eftal; Demiral, EmrullahComplex network studies span a large variety of applications including linguistic networks. To investigate the differences in book and social media texts in terms of linguistic typology, we constructed both sequential and sentence collocation networks of book, Facebook and Twitter texts with undirected and weighted edges. The comparisons are performed using the basic parameters like average degree, modularity, average clustering coefficient, average path length, diameter, average link weight etc. We also presented the distribution graphs for node degrees, edge weights and maximum degree differences of the pairing nodes. The degree difference occurrences are furtherly detailed with the grayscale percentile plots with respect to the edge weights. We linked the network analysis with linguistic aspects like word and sentence length distributions. We concluded that linguistic typology demonstrates a formal usage in book that slightly deviates to informal in Twitter. Facebook interpolates between these media by the means of network parameters, while the informality of Twitter is mostly influenced by the character limitations.
