Person: YILDIZ, KAZIM
Loading...
Email Address
Birth Date
Research Projects
Organizational Units
Job Title
Last Name
YILDIZ
First Name
KAZIM
Name
17 results
Search Results
Now showing 1 - 10 of 17
Publication Open Access Classification of hazelnuts with CNN based deep learning system(2022-12-01) ÜLKÜ, EYÜP EMRE; YILDIZ, KAZIM; GÜNEŞ E., ÜLKÜ E. E., YILDIZ K.The rapid development of technology leads to the emergence of technology-based systems in many different areas. In recent years, agriculture has been one of these areas. We come across technological systems in agricultural applications for many different purposes such as growing healthier products, increasing the yield of products, and predicting product productivity. Today, technology-based systems are used more and more widely in agricultural applications. Classification of products quickly and with high accuracy is a very important process in predicting product yield. In this study, it is suggested to use the CNN-based deep learning model VGG16 in order to classify the hazelnut fruit, which is an important agricultural product. The main purpose is to classify hazelnuts according to their quality with a deep learning approach. For that, a new data set was created. There are 15770 images in the created data set. In the study, the data set was used by dividing it into different parts. The classification of hazelnut images was carried out using the VGG16 deep learning model, which is a powerful model for classifying images. As a result of the experiments on the data set created, the classification process of hazelnuts was realized with 0,9873 F1 score. The detection rate of quality hazelnut is 0.9848, the rate of detection of kernel hazelnut is 0.9891 and the rate of detection of damaged hazelnut is 0.9882. In addition, the classification process was carried out with deep learning using 50%, 25% and 10% of the data set in the study. It was observed that the 98.73 %, 95.46 %, 92.62 %, and 88.42 % accuracy rates were achieved when the whole, 50 %, 25 %, and 10 % data sets were used, respectivelyPublication Open Access A Web Based Clustering Analysis Toolbox (WBCA) design Using MATLAB(ELSEVIER SCIENCE BV, 2010) YILDIZ, KAZIM; Savas, Kenan; Yildiz, Kazim; Uzunboylu, HWith the development technology, datas which are saved in databases are rising, useful methods and kind of algorithms for making employable data and are build up for processing. For the solution of this problem data mining tools come into existence, to which clustering algorithms belong. For the clustering area this paper supposed to aid education, the tool was designed for clustering algorithms used easy and effective, cut down of the time that is making programme by the students so with the using of data sets that belongs to students, results of the clustering that was supported graphical items shown with the help of user interface and clustering must be so effective and easy. Purpose of this paper, MATLAB software that is used common by the academic area, making web based toolbox using clustering algorithms for the user. This toolbox use kmeans, agnes, fuzzy cmeans algorithms that are exist in MATLAB software and available web interface for the evaluate clustering results with cluster validity criteria. By courtesy of the toolbox, web user that do not need to have MATLAB software and programming knowledge but only a web browser and they can load their own data into the web server then see the result by the chose of algorithm and download the results their own local computers. In this design MATLAB Web Server (MWS) was used that belong to MATLAB software. With the help of this tool web users can send the parameters to server via the internet and the computer that has on the MWS software, used this then working MWS that is developed in this paper, results can have seen with the web server (C) 2010 Elsevier Ltd. All rights reserved.Publication Open Access Comparison of the machine learning methods to predict wildfire areas(2022-09-01) YILDIZ, KAZIM; BAYAT G., YILDIZ K.In the last decades, global warming has changed the temperature. It caused an increasing the wildfire in everywhere. Wildfires affect people's social lives, animal lives, and countries' economies. Therefore, new prevention and control mechanisms are required for forest fires. Artificial intelligence and neural networks(NN) have been benefited from in the management of forest fires since the 1990s. Since that time, machine learning (ML) methods have been used in environmental science in various subjects. This study aims to present a performance comparison of ML algorithms applied to predict burned area size. In this paper, different ML algorithms were used to forecast fire size based on various characteristics such as temperature, wind, humidity and precipitation, using records of 512 wildfires that took place in a national park in Northern Portugal. These algorithms are Multilayer perceptron(MLP), Linear regression, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree and Stacking methods. All algorithms have been implemented on the WEKA environment. The results showed that the SVM method has the best predictive ability among all models according to the Mean Absolute Error (MAE) metric.Publication Open Access Wavelet transform and principal component analysis in fabric defect detection and classification(PAMUKKALE UNIV, 2017) BULDU, ALİ; Yildiz, Kazim; Buldu, AliFabric defects are determined by quality control.staff in textile industry, This process cannot be performed objectively and it constitutes both time and cost difficulties, In this study the cashmere and denim lubric images which ure used often in textile industry ure tried in both detection and classification process. Quality control machine prototype has been manufactured then defected fabric images were obtained with the help of thermal imaging. The fabric defects were detected and classified by using the thermal images, Averagely 95% classification accuracy has been achieved on experiments for two different fabric types. According to the experimental results, the fabric quality control process can be muck after the drying and fixing, without any further quality control step.Publication Open Access Elliptic curve coding technique application for digital signature(WILEY-HINDAWI, 2016-11-25) BULDU, ALİ; Yildiz, Kazim; Buldu, Ali; Saritas, HasanAn elliptic curve coding technique application is proposed in this study. It is one of the asymmetric coding techniques and so crucial in today's world. The application codes messages between two different console screens by using elliptical curve coding technique. It is created by using C# with the class of Crypto Next Generation (CNG) which brings into consideration the messaging system as four different security levels. The aim is to use the necessary additional security precautions when using asymmetric techniques. Cryptography techniques are not used for connection, and messaging occurs in security level 1. Security level 2 describes the public channel for the connection between two console screens which is used for sending and receiving key pair; then messaging occurs. Public channel for the connection between two console screens is used for sending and receiving signed key pair and encrypted data; then messaging occurs in security level 3. Security level 4 is the safest one. A private channel for the connection between two console screens is used for sending and receiving a signed key pair and encrypted data, and then messaging occurs. In addition, Advanced Encryption Standard (AES) technique is used in applications which is one of the symmetric cryptographic techniques for encrypting data. Copyright (C) 2016 John Wiley & Sons, Ltd.Publication Open Access du-CBA: veriden habersiz ve artırımlı sınıflandırmaya dayalı birliktelik kuralları çıkarma mimarisi(2023-01-01) BÜYÜKTANIR, BÜŞRA; YILDIZ, KAZIM; ÜLKÜ, EYÜP EMRE; Büyüktanır B., Yıldız K., Ülkü E. E., Büyüktanır T.İstemci sunucu sistemlerinde makine öğrenmesi modeli kullanılması bir ihtiyaçtır. Ancak istemcilerden verilerin toplanması, sunucuya aktarılması, makine öğrenmesi modeli eğitilmesi ve bu modelin istemcilerde çalışan cihazlara entegre edilmesi bir çok problemi beraberinde getirmektedir. Verilerin istemcilerden sunucuya transferi ağ trafiğine sebep olmakta, fazla enerji gerektirmekte ve veri mahremiyetini istismar edilebilmektedir. Çalışma kapsamında, bahsedilen problemlere çözüm için federe öğrenme mimarisi kullanılmaktadır. Mimariye göre, her bir istemcide istemcinin kendi verilerinden makine öğrenmesi modeli eğitilmektedir. Her bir istemcide eğitilen modeller sunucuya gönderilmekte ve sunucuda bu modeller birleştirilerek yeni bir model oluşturulmaktadır. Oluşturulan nihai model tekrar istemcilere dağıtılmaktadır. Bu çalışmada Veriden Habersiz İlişkili Kurallara Dayalı Sınıflandırma (Data Unaware Classification Based on Association, du-CBA) olarak adlandırılan ilişkisel sınıflandırma algoritması geliştirilmiştir. Federe öğrenme ile klasik öğrenme mimarilerini karşılaştırıp başarılarını ölçmek için çalışma kapsamında benzetim ortamı oluşturulmuştur. Benzetim ortamında du-CBA ve CBA algoritmaları kullanılarak modeller eğitilmiş ve sonuçlar kıyaslanmıştır. Modellerin eğitiminde University of California Irvine (UCI) veri havuzundan alınan beş veri seti kullanılmıştır. Deneysel sonuçlar, her bir veri seti için federe öğrenme ile eğitilen modellerin, klasik öğrenme ile eğitilen modellerle neredeyse aynı doğruluğu elde ettiğini ama eğitim sürelerinin yaklaşık %70 oranında azaldığını göstermiştir. Sonuçlar geliştirilen algoritmanın başarıya ulaştığını ortaya koymaktadır.Publication Open Access Classification of Textures Using Filter Based Local Feature Extraction(E D P SCIENCES, 2016) YILDIZ, KAZIM; Bocekci, Veysel Gokhan; Yildiz, Kazim; Sikora, A; Choi, B; Wang, SIn this work local features are used in feature extraction process in image processing for textures. The local binary pattern feature extraction method from textures are introduced. Filtering is also used during the feature extraction process for getting discriminative features. To show the effectiveness of the algorithm before the extraction process, three different noise are added to both train and test images. Wiener filter and median filter are used to remove the noise from images. We evaluate the performance of the method with Naive Bayesian classifier. We conduct the comparative analysis on benchmark dataset with different filtering and size. Our experiments demonstrate that feature extraction process combine with filtering give promising results on noisy images.Publication Open Access Application of image processing for quantization and characterization of fabrics with polymeric coatings(PAMUKKALE UNIV, 2018) YILDIZ, KAZIM; Yildiz, Kazim; Yildiz, ZehraIn this study, the dispersion quality of particles on polymeric coating formulations from cotton fabric surfaces was investigated by using gray level co-occurrence matrix and fractal dimension. Coating formulations with various nano particle inclusions were applied on cotton fabrics. The flame retardant property of coated fabrics were examined by thermal gravimetric analysis (TGA). Images from the coated fabric surfaces were obtained by using optical microscopy and then these images were used in gray level and fractal dimension feature extraction processes. The microscopic images of the coated fabrics in various particle amounts were analyzed by using the image processing technique, and then classification and quantization processes were performed. The results of the image processing were compared to the results of TGA. The sample containing 5% montmorillonite (MMT) was found as having the best coating quality level by using feature extraction method in image processing. The average classification performance among all the samples was found as 92.5%.Publication Open Access Fault detection of fabrics using image processing methods(PAMUKKALE UNIV, 2017) ÜLKÜ, EYÜP EMRE; Yildiz, Kazim; Demir, Onder; Ulku, Eyup EmreThis paper presents a computer aided detection (CAD) system which uses wiener filter based approach for detection of defects in poplin fabric. The defective fabric images are taken with the help of the digital camera. The developed system consists of three phases, including preprocessing, segmentation and detection of fabric defect In preprocessing phase, a RGB to gray level conversion and image enhancement operations were applied to digital camera images. In segmentation phase, background of the gray level image segmented using morphologic operations. Then, segmented image was converted to binary image to facilitate fabric defect detection process. Fabric defect detection was performed using wiener filter in the detection phase of the system. Wiener filter is applied to binary level image to eliminate structures which are not defect The developed detection system applied on defective poplin images for detection. The obtained results on different kinds of fabric defects show that the proposed algorithm gives promising results.Publication Open Access Identification of wool and mohair fibres with texture feature extraction and deep learning(INST ENGINEERING TECHNOLOGY-IET, 2020-02) YILDIZ, KAZIM; Yildiz, KazimWool and mohair fibres are both animal-based fibres and having circular scales on their microscopic images from the longitudinal view. Although they look very similar in their microscopic view, they show different physical/chemical properties which determine their usage area. Thus, in textile industry, they need to be separated carefully from each other. The separation of wool/mohair fibres is an important issue and can be performed with human eye by using the microscopic images, that is not time/cost effective and not objective. The novelty of the presented study is to design an objective, easy, rapid, time and cost-effective method in order to separate wool fibre from mohair fibre by using a texture analysis based identification method. For this purpose, microscopic images of both wool and mohair fibres were preprocessed as the texture images. Local binary pattern-based feature extraction process and deep learning were separately used to get determinative information from the fibres. In order to identify the samples, the classification based method was completed. Experimental results indicated that an accurate texture analysis for this kind of animal fibres is possible to identify wool and mohair fibres by using deep learning and machine learning with 99.8% and 90.25% accuracy rates, respectively.