Yazar "Kuncan, Fatma" seçeneğine göre listele

Listeleniyor 1 - 20 / 26
  • [ X ]
    Öğe
    A hybrid model for classification of medical data set based on factor analysis and extreme learning machine: FA + ELM
    (Elsevier Ltd, 2022) Kaya, Yılmaz; Kuncan, Fatma
    Data mining techniques such as classification, clustering, and prediction are used extensively for medical diagnosis in epidemiological fields. A hybrid model based on Factor Analysis (FA) and Extreme Learning Machine (ELM) was proposed in this study for diagnosing breast cancer, Lymphography, and erythemato-squamous diseases. The proposed hybrid model consists of two stages. Firstly, FA was used for preprocessing the medical dataset, and then, the factors obtained using FA were used as input features for the ELM model. Dermatology, Lymphography, and Wisconsin Breast Cancer real datasets obtained from the UCI machine learning database were used to test the proposed model. An average success rate of 96.39 % and 96.94 % was obtained after classifying the dermatology dataset with ELM and FA + ELM models. While the success rate obtained by classifying the lymphography data set using ELM is 84.50 %, the result obtained with FA + ELM is 85.10 %. The success rates of 97.10 % and 97.25 % are achieved respectively for Wisconsin Breast Cancer (WBC) using ELM and FA + ELM. As a result, it was observed that preprocessing of the data increased the average classification success in three different medical datasets used for the classification problem. It is considered that the proposed hybrid model will be helpful for the decision-making stage in medical diagnosis systems. © 2022 Elsevier Ltd
  • [ X ]
    Öğe
    A New Approach for Congestive Heart Failure and Arrhythmia Classification Using Angle Transformation with LSTM
    (Springer Heidelberg, 2022) Kaya, Yilmaz; Kuncan, Fatma; Tekin, Ramazan
    Electrocardiogram (ECG) is widely used as a diagnostic method to identify various heart diseases such as heart failure, cardiac and sinus rhythms. The ECG signal analyzes the electrical activity of the heart and shows waveforms that help detect heart irregularities. A new approach is suggested for automatic identification of congestive heart failure (CHF) and arrhythmia (ARR). In this study, long short-term memory neural networks (LSTM) were used to classify ECG signals by combining LSTM and angle transform (AT) methods. The AT uses the angular information of the neighbor signals on both sides of the target signal to classify ECG signals. The new signals obtained as a result of AT conversion vary between 0 and 359. Histogram of new signals determines the inputs to the LSTM method. LSTM uses histograms to distinguish between three different conditions: ARR, CHF, and normal sinus rhythm (NSR). The proposed approach is tested on ECG signals received from MIT-BIH and BIDMC databases. The experimental results have shown that the proposed method, AT + LSTM, has achieved high success rate of classifying ECG signals. The success rate in classifying CHF, ARR, and NSR ECG signals for 70-30% training sets was observed as 98.97%. Further experiments were conducted for varying training-testing dataset ratio to demonstrate the robustness of the proposed approach, and success rates are observed between 98.56 and 100%. Another experiment regarding different values of the dR and dL distance parameters of the AT model has shown that the performance of the proposed method increases while increasing the distance value. The success rates from increasing the distance value were obtained between 98.97 and 100%. To show the effect of segment lengths of ARR, NSR, and CHF signals on classification success, these signals were divided into segments of 10,000, 5000, and 1000 lengths. Achieved success rates ranged from 97.75 to 98.97%. Considering the results, high results were observed with the AT + LSTM approach, which is generally recommended in all scenarios.
  • [ X ]
    Öğe
    A new approach for congestive heart failure and arrhythmia classifiication using downsampling local binary patterns with LSTM
    (Tubitak Scientific & Technological Research Council Turkey, 2022) Akda, Sueleyman; Kuncan, Fatma; Kaya, Yilmaz
    Electrocardiogram (ECG) is a vital diagnosis approach for the rapid explication and detection of various heart diseases, especially cardiac arrest, sinus rhythms, and heart failure. For this purpose, in this study, a different perspective based on downsampling one-dimensional-local binary pattern (1D-DS-LBP) and long short-term memory (LSTM) is presented for the categorization of Electrocardiogram (ECG) signals. A transformation method named 1D-DS-LBP has been presented for Electrocardiogram signals. The 1D-DS-LBP method processes the bigness smallness relationship between neighbors. According to the proposed method, by downsampling the signal, the histograms of 1D local binary patterns (1D-LBP) calculated from the obtained signal groups are collected and included as a reference to the long short-term memory structure. The long short-term memory structure has been applied to 1D-DS-LBP conversion applied ECG signals with both unidirectional and bidirectional. To test the proposed approach, ECG signals of three (3) different states of congestive heart failure (CHF), arrhythmia (ARR), and normal sinus rhythm (NSR) consisting of 972 signals were used. Signals were taken from the MIT-BIH and BIDMC databases. Experiments were carried out in various scenarios. We observed that the success rate of the proposed approach obtained very high classification accuracies compared to other studies in the literature. The obtained ECG diagnostic performance values varied between 96.80% and 99.79%. Based on this, this approach has a high potential to have a wide field of study in medical applications.
  • [ X ]
    Öğe
    A new approach for physical human activity recognition based on co-occurrence matrices
    (Springer, 2022) Kuncan, Fatma; Kaya, Yilmaz; Tekin, Ramazan; Kuncan, Melih
    In recent years, it has been observed that many researchers have been working on different areas of detection, recognition and monitoring of human activities. The automatic determination of human physical activities is often referred to as human activity recognition (HAR). One of the most important technology that detects and tracks the activity of the human body is sensor-based HAR technology. In recent days, sensor-based HAR attracts attention in the field of computers due to its wide use in daily life and is a rapidly growing field of research. Activity recognition (AR) application is carried out by evaluating the signals obtained from various sensors placed in the human body. In this study, a new approach is proposed to extract features from sensor signals using HAR. The proposed approach is inspired by the Gray Level Co-Occurrence Matrix (GLCM) method, which is widely used in image processing, but it is applied to one-dimensional signals, unlike GLCM. Two datasets were used to test the proposed approach. The datasets were created from the signals obtained from the accelerometer, gyro and magnetometer sensors. Heralick features were obtained from co-occurrence matrix created after 1D-GLCM (One (1) Dimensional-Gray Level Co-Occurrence Matrix) was applied to the signals. HAR operation has been carried out for different scenarios using these features. Success rates of 96.66 and 93.88% were obtained for two datasets, respectively. It has been observed that the new approach proposed within the scope of the study provides high success rates for HAR applications. It is thought that the proposed approach can be used in the classification of different signals.
  • [ X ]
    Öğe
    A new approach for physical human activity recognition from sensor signals based on motif patterns and long-short term memory
    (Elsevier Sci Ltd, 2022) Kuncan, Fatma; Kaya, Yilmaz; Yiner, Zueleyha; Kaya, Mahmut
    Numerous studies have been carried out in recent years on the recognition, tracking, and discrimination of human activities. Automatic recognition of physical activities is often referred to as human activity recognition (HAR). There are generally vision-based and sensor-based approaches for activity recognition. The computer vision-based approach generally works well in laboratory conditions, but it can fail in real-world problems due to clutter, variable light intensity, and contrast. Sensor-based HAR systems are realized by continuously monitoring and analyzing physiological signals measured from heterogeneous sensors connected to the person's body. In this study, the Motif Patterns (MP) approach, which extracts features from sensor signals, is proposed for HAR. The success of the HAR systems depends on the effectiveness of the features extracted from the signals. The LSTM network is a special kind of recurrent neural network that has been used to make very successful predictions on time series data where long-term dependencies are. The LSTM network type offers a successful solution approach to solving long-term dependencies problems such as human activity recognition. The classification process was carried out with Long-Short Term Memory (LSTM) using MP features extracted from accelerometer, gyroscope, and magnetometer sensor signals. A large dataset of 9120 signals was used to test the proposed approach. A high success rate of 98.42 % was achieved with the proposed MP + LSTM method. As a result, it has been seen that the proposed approach has been obtained with a high success rate for HAR using sensor signals.
  • [ X ]
    Öğe
    A new approach to COVID-19 detection from x-ray images using angle transformation with GoogleNet and LSTM
    (Iop Publishing Ltd, 2022) Kaya, Yilmaz; Yiner, Zuleyha; Kaya, Mahmut; Kuncan, Fatma
    Declared a pandemic disease, COVID-19 has affected the lives of millions of people and had significant effects on public health. Despite the development of effective vaccines against COVID-19, cases continue to increase worldwide. According to studies in the literature, artificial intelligence methods are used effectively for the detection of COVID-19. In particular, deep-learning-based approaches have achieved very good results in clinical diagnostic studies and other fields. In this study, a new approach using x-ray images is proposed to detect COVID-19. In the proposed method, the angle transform (AT) method is first applied to the x-ray images. The AT method proposed in this study is an important novelty in the literature, as there is no such approach in previous studies. This transformation uses the angle information created by each pixel on the image with the surrounding pixels. Using the AT approach, eight different images are obtained for each image in the dataset. These images are trained with a hybrid deep learning model, which combines GoogleNet and long short-term memory (LSTM) models, and COVID-19 disease detection is carried out. A dataset from the Mendeley database is used to test the proposed approach. A high classification accuracy of 98.97% is achieved with the AT + GoogleNet + LSTM approach. The results obtained were also compared with other studies in the literature. The presented results reveal that the proposed method is successful for COVID-19 detection using chest x-ray images. Direct transfer methods were also applied to the data set used in the study. However, worse results were observed according to the proposed approach. The proposed approach has the flexibility to be applied effectively to different medical images.
  • [ X ]
    Öğe
    A new automatic bearing fault size diagnosis using time-frequency images of CWT and deep transfer learning methods
    (Tubitak Scientific & Technological Research Council Turkey, 2022) Kaya, Yilmaz; Kuncan, Fatma; Ertunc, H. Metin
    Bearings are generally used as bearings or turning elements. Bearings are subjected to high loads and rapid speeds. Furthermore, metal-to-metal contact within the bearing makes it sensitive. In today's machines, bearing failures disrupt the operation of the system or completely stop the system. Bearing failures that can occur can cause enormous damage to the entire system. Therefore, it is necessary to anticipate bearing failures and to carry out a regular diagnostic examination. Various systems have been developed for fault diagnosis. In recent years, deep transfer learning (DTL) methods are often preferred in current bearing diagnosis models, as they provide time savings and high success rates. Deep transfer learning models also improve diagnosis accuracy under certain conditions by greatly reducing human intervention. Diagnosis at the right time is very important for the sustainability and efficiency of industrial production. A technique based on continuous wavelet transform (CWT) and two dimensional (2D) convolutional neural networks (CNN) is presented in this paper to detect fault size from vibration data of various bearing failure types. Time-frequency (TF) color scalogram images for bearing vibration signals were obtained using the CWT method. Using AlexNet, GoogleNet, Resnet, VGG16, and VGG19 deep transfer learning methods with scalogram images, fault size prediction from vibration signals was performed. Five different transfer deep learning models were used for three different data sets. It was observed that the success rates obtained varied between 96.67% and 100%.
  • [ X ]
    Öğe
    A new content-free approach to identification of document language: Angle patterns
    (Gazi Univ, Fac Engineering Architecture, 2022) Noyan, Tuba; Kuncan, Fatma; Tekin, Ramazan; Kaya, Yilmaz
    Graphical/Tabular Abstract Language identification (LI) in text mining is the process of detecting the natural language in which a document or part of it is written. LI aims to mimic a human's ability to recognize certain languages from text by computer algorithms. LI can be defined as a classification problem subject based on the information used in word or character size for any document. When the literature is examined for LI application, it is seen that various linguistic or statistical-based approaches are used. Linguistic methods are methods that perform LI according to a special word or character of a language. These methods are applied based on the special rules of the languages. When we look at the statistical methods, it shows that the words or characters that make up the language depend on their frequency and distribution. The statistical approaches used are content -independent methods. The semantic context of the text is not concerned with its content. According to linguistic methods, it does not provide sufficient information about the content of the text. The proposed model in this study is a statistical approach. Figure A. Proposed block diagram for LI Purpose: In this study, a new LI approach using the angle information between the UTF-8 values of the characters in the text is proposed. The proposed angle pattern method is used for feature extraction from texts. Angle patterns method is a statistical approach. In the angle method, there are two distance parameters, R and L, which express which neighborhood to look at from the reference point to the left and right. Theory and Methods: To test the proposed approach, four datasets, two created by the authors and two publicly available on the Internet, were used. By using the features obtained by the angle pattern method, classification process was carried out with different machine learning methods such as Random Forest, Support Vector Machine, Linear Discriminant Analysis, Naive Bayes and K-nearest neighbor. Language identification performance results determined from four different data sets were observed as 96.81%, 99.39%, 93.31% and 98.60%, respectively. Results: According to the performance results achieved as a result of the study, it has been determined that the proposed angle pattern method provides important distinguishing information in language identification application. It is thought that the proposed approach in this study can be used in many different text mining applications such as spam recognition, text categorization, as well as LI application.
  • [ X ]
    Öğe
    A Novel Approach for Activity Recognition with Down-Sampling 1D Local Binary Pattern Features
    (Univ Suceava, Fac Electrical Eng, 2019) Kuncan, Fatma; Kaya, Yilmaz; Kuncan, Melih
    The sensors on the mobile devices directly reflect the physical and demographic characteristics of the user. Sensor signals may contain information about the gender and movement of the person. Automatic recognition of physical activities often referred to as human activity recognition (HAR). In this study, a novel feature extraction approach for the HAR system using the mobile sensor signals, the Down Sampling One Dimensional Local Binary Pattern (DS-1D-LBP) method is proposed. Feature extraction from signals is one of the most critical stages of HAR because the success of the HAR system depends on the features extraction. The proposed HAR system consists of two stages. In the first stage, DS-ID-LBP conversion was applied to the sensor signals in order to extract statistical features from the newly formed signals. In the last stage, classification with Extreme Learning Machine (ELM) was performed using these features. The highest success rate was 96.87 percent in the experimental results according to the different parameters of DS-ID-LBP and ELM. As a result of this study, the novel approach demonstrated that the proposed model performed with a high success rate using mobile sensor signals for the HAR system.
  • [ X ]
    Öğe
    Analysis of Different Machine Learning Techniques with PCA in the Diagnosis of Breast Cancer
    (2022) Yılmaz, Hüseyin; Kuncan, Fatma
    In recent years, different types of cancer cases are common. Increasing cancer cases, A rapidly increasing health for countries and humanity becomes a problem. In addition to being the most common cancer among women today, breast cancer has surpassed lung cancer as the most common cancer type in the world since 2021. Early diagnosis greatly reduces the risk of death in breast cancer, and benign tumors are correctly diagnosed, allows the classification of this field to be a new research topic. New developments in the field of Medicine and Technology Machine learning, classification algorithms and computerized diagnosis are used in the correct classification of tumors. increased its use. These systems are extremely important in terms of being an assistant to the expert opinion. In this study, in the Wisconsin Breast Cancer dataset, it is aimed to accelerate the diagnosis of the disease and to reduce the tumors, different machine learning to minimize treatment processes by providing accurate classification techniques were used. In this study, we reduced our dataset to 171 data using Principal Component Analysis (PCA) to accelerate disease diagnosis on the Wisconsin Breast Cancer dataset and 2 different classification processes were performed using 5 different machine learning. The success rate of each algorithm was compared, and it was revealed that Logistic Regression was the most successful method with an accuracy rate of 98.8% after PCA.
  • Küçük Resim
    Öğe
    Elektronik kart imalatında dizgi makinelerinde görüntü işleme sisteminin tasarlanması
    (IETS'18 International Engineering and Technology Symposium, 03-05 May, 2018, 3-5 Mayıs 2018) Sarac, Güneş; Kandilli, İsmet; Kuncan, Melih; Kuncan, Fatma
    Dizgi Makineleri, elektronik kartlarda malzemelerin lehimleme öncesi PCB karta montajını makineler vasıtasıyla hızlıca yapabilen ve bu malzemeleri verilen koordinatlara yerleştirilmesi, yönlerinin doğru olduğunun kontrolünü otomatik yapan sistemlerdir. İki farklı kısımdan oluşurlar; Mekanik ve Görüntü işleme sistemleridir. Dizgi makinaları yapı olarak CNC tezgâhlarına benzemekte ve ülkemizde imalatı yapılabilen sistemlerdir. Dizgi makinaları ile CNC tezgâhlarını ayıran tek özellik ise görüntü işleme özelliğidir. CNC tezgâhlarında sadece malzeme koordinatları verildiği sürece çalışmaktadır. Dizgi makinalarında ise koordinat bilgisine ek olarak, aldığı malzemenin yönünün doğru olup olmadığı kontrol edilmesi gerekmektedir. Dizgi makinaları ülkemizde üretimi yapılmamaktadır. Satışları ise yurt dışından temini edilerek yapılmakta ve ülkemizdeki CNC tezgâhlarının sadece görüntü işleme özelliği eklenmiş ve birkaç değişiklik yapılarak yüksek maliyetlerle, bu sektörde kullanılması sağlanmaktadır [1,2] (Şekil 1). Bu çalışmayla, görüntü işleme özelliği tasarlayarak ülkemiz genelinde CNC tezgâh üreticilerine yeni bir sektör kazandırarak, dizgi makinaları üretimine geçişlerini sağlamak ve ülkemizde üretilmesini hedeflenmektedir. Çalışmanın bir diğer amacı, düşük görüntü işleme kapasitedeki dizgi makinalarını revize ederek, görüntü işleme kalitesini arttırmak ve makine özelliğini geliştirmektir (Şekil 2).
  • [ X ]
    Öğe
    EVALUATION OF PERFORMANCE OF CLASSIFICATION ALGORITHMS IN PREDICTION OF HEART FAILURE DISEASE
    (2022) Coşkun, Cevdet; Kuncan, Fatma
    Success rates and performances of Gaussian Naive Bayes, Support Vector Machines, Linear Discriminant Analysis, Decision Tree and Random Forest classifier algorithms from machine learning methods were evaluated using the Heart Failure Prediction dataset. Label encoder method was used primarily in data preprocessing techniques on the data set. Catalog data (5 pieces) in the data set have been converted into numerical data. In addition, it was observed that there were negative values in the data in a field and this situation was converted to values in the range of 0 - 1 with min-max conversion methods. After the pre-processing, analyzes were made with classification algorithms. As a result of these analyzes, a success rate of 90.76% was achieved with the random forest algorithm, which is an ensemble classifier. In the study, 80% of the data was used for training and 20% for testing. Of the 184 data used for the test, 102 of them were patients with heart failure and 72 of them were from those without the disease. The success of the random forest algorithm in estimating those with heart failure disease was 93.1% (95 observations), and the success in predicting those without the disease was 87.8% (72 observations).
  • [ X ]
    Öğe
    Giyilebilir sensör işaretlerinden hareket tanıma için yeni yaklaşımlar
    (Siirt Üniversitesi, 2019) Kuncan, Fatma; Kaya, Yılmaz
    Son yıllarda insan hareketlerinin tanınması, izlenmesi ve ayırt edilmesi alanında birçok faklı çalışma yapılmaktadır. Hareket tanıma (HT) için genellikle iki ana yaklaşım kullanılmaktadır. Bunlar vizyon tabanlı (bilgisayarlı görü) yaklaşım ve sensör (algılayıcı) tabanlı yaklaşımdır. Sensör tabanlı yaklaşım, insan hareketlerinin durumunu yansıtan fizyolojik sinyallerin sürekli izlenmesini sağlayarak vücut hareketlerini algılamayı sağlamaktadır. HT sisteminde hareketleri birbirinden en iyi şekilde ayırt eden özniteliklerin belirlenmesi gerekmektedir. Öznitelik seçimi yapıldıktan sonra makine öğrenmesi yöntemleri ile sınıflandırma işlemleri gerçekleştirilmektedir. Özniteliklerin iyi seçilmemesi durumunda sınıflandırma performansı düşeceğinden, öznitelik çıkarımı örüntü tanıma sürecinde önemli bir rol oynamaktadır. Bu çalışmada HT için sensör işaretlerinden öznitelik çıkarımını gerçekleştiren yeni yaklaşımlar önerilmektedir. Çalışma kapsamında öznitelik çıkarımı için dokuz farklı yeni yaklaşım önerilmiştir. Bu yaklaşımlar: Bir Boyutlu Yerel İkili Örüntüler (1B-YİÖ), Ortalama Tabanlı Bir Boyutlu Yerel İkili Örüntüler (OT-1B-YİÖ), Medyan Tabanlı Bir Boyutlu Yerel İkili Örüntüler (MT-1B-YİÖ), Çok Ölçekli Bir Boyutlu Yerel İkili Örüntüler (ÇÖ-1B-YİÖ), Ağırlıklandırılmış Bir Boyutlu Sağlam Yerel İkili Örüntüler (A-1B-YİÖ), Komşuluk Tabanlı Bir Boyutlu Yerel İkili Örüntüler (KT-1B-YİÖ), Kaydırmalı Bir Boyutlu Yerel İkili Örüntüler (K-1B-YİÖ), Üçlü Desenli Bir Boyutlu Yerel İkili Örüntüler (ÜD-1B-YİÖ) ve İndirgenmiş Bir Boyutlu Yerel İkili Örüntüler (İ-1B-YİÖ) yöntemleridir. Önerilen yaklaşımlar görüntü işleme uygulamalarında sıkça kullanılan Yerel İkili Örüntüler metoduna dayalı olarak geliştirilen Bir Boyutlu Yerel İkili Örüntüler metodu baz alınarak geliştirilmiştir. Önerilen HT sistemi altı aşamadan oluşmaktadır. Birinci aşamada, insanların çeşitli fiziksel hareketlerine ait sensör işaretlerinin temini yapılmıştır. İkinci aşamada, bu sensör işaretlerine geliştirilen öznitelik çıkarım yöntemleri uygulanarak daha anlamlı işaretler elde edilmiştir. Üçüncü aşamada, elde edilen anlamlı işaretlerin histogramları oluşturulmuştur. Dördüncü aşamada, oluşturulan histogramlardan öznitelikler elde edilmiştir. Beşinci aşamada, elde edilen öznitelikler Rastgele Orman Algoritması (RO) makine öğrenmesi yöntemi ile sınıflandırılmıştır. Altıncı aşamada, çeşitli kriterlere göre geliştirilen öznitelik çıkarım yöntemlerinin karşılaştırılmaları yapılmıştır. Geliştirilen yöntemler ile elde edilen özniteliklerin Rastgele Orman algoritmasına göre sınıflandırılmaları yapılarak en yüksek başarı oranının %95,83 oranı ile İ-1B-YİÖ metodunda gerçekleştiği gözlenmiştir.
  • Küçük Resim
    Öğe
    Güneş enerjisiyle arabalarda soğutma ve ısıtma sisteminin tasarımı
    (International Conference on Multidisciplinary, Science, Engineering and Technology (IMESET’17), 2017) Kandilli, İsmet; Minaz, M.Recep; Kuncan, Melih; Kuncan, Fatma
    Güneş enerjisinden pek çok alanda etkin kullanılmasına rağmen soğutma ve ısıtma sistemlerinde gelişmeler artarak devam etmektedir. Güneş enerjisinin soğutmada ve ısıtmada kullanılması, ekonomik olarak çok önemlidir. Güneş enerjisinden elde edilen enerjiyle, arabalarda soğutma ve ısıtma işlemi kullanılması geliştirilmektedir. Küresel ısınmanın artmasıyla beraber, güneş enerjisiyle soğutma çok önemli bir yerdedir. Güneş enerjiyei soğutma sistemi, güneşin sebep olduğu soğutma ihtiyacı, güneşin enerjisiyle karşılanır. Arabanın üzerine yerleştirilen güneş panelleriyle, elde edilen enerji akülerde depolanır. Arabada ek akü sistemi kullanılmıştır. Akülerden alınan enerjiyle, arabanın sıcaklığını istediğimiz derecede kontrol ederek ayarlanmaktadır. Güneş enerjisiyle arabalarda, soğutma ve ısıtma sistemlerinin tasarımıyla, soğutmada motora binen yük azaltılmaktadır. Böylelikle, arabada yakıt tüketimi azaltılmaktadır. Despite the use of many areas from solar energy, improvements in cooling and heating systems continue. The use of solar energy in cooling and heating is economically important. With the energy obtained from solar energy, the use of cooling and heating processes in cars is being developed. With global warming, cooling with solar energy is very important. The solar energy cooling system, the cooling requirement caused by the sun, is covered by the solar energy. With the solar panel placed on the car, the energy obtained is stored in the battery. An additional battery system was used on the car. With the energy from the chimney, the temperature of the car is adjusted by controlling it at the desired level. In solar-powered cars, cooling and heating systems are designed to reduce the load on the engine during cooling. Thus, fuel consumption is reduced in the car.
  • [ X ]
    Öğe
    Human Face Recognition Using Deep Neural Networks
    (2022) Kaplan, Kaplan; Kuncan, Fatma
    In recent years, many researchers have been using computer-based systems containing artificial intelligence applications for different applications. Human recognition application is one of the studies carried out in this field. Face and object recognition applications, which were originally designed for security measures, are also used in the entertainment and shopping sectors recently. These applications are gaining even more popularity with the mobile application development of various companies. In face recognition applications, deep learning methods can be preferred if the data is large and complex. In this study, a 3-layer Convolutional Neural Network (CNN) has been developed for a face recognition application. The developed model was applied to the Libor Spacek's Facial Images Databases dataset. As a result of the application of the proposed method on the data set, it was determined that the accuracy rate was 99.29%. This means that the application can be adapted for real recognition systems.
  • Küçük Resim
    Öğe
    İçmesuyu isale hattının basınç yönetimi sistemiyle kontrolü ve analizi
    (IETS'18 International Engineering and Technology Symposium, 03-05 May, 2018, 3-5 Mayıs 2018) Sönmez, Murat; Şen, Cem; Kandilli, İsmet; Kuncan, Melih; Kuncan, Fatma
    Pressure Management, part of the intelligent network system, is one of the most effective methods known and practiced in combating water losses in drinking water networks. In particular, thanks to the pressure-management system applied at the specified point on the network, it has been found that the losses in the network are greatly reduced with automatic adjustment of the line pressure, sensitive to water usage. Pipe damage, connection problems and water leaks due to high pressures in city network lines are a big problem in today's conditions where water resources are decreasing day by day. Since the availability of new water resources is very difficult and costly to achieve, it is of utmost importance that hydraulic balances are realized correctly in city networks and that water losses and leaks are reduced [1,2]. For this reason, serious studies are being carried out on the planning, development and application of pressure management systems. In this study, an automatic pressure adjustment on the line of 10 water reservoirs is carried out and a network Scada is constructed on the water line of approximately 25 km (Fig. 1a). In the 10 different reservoir volumes included in the Scada system, the networks of the warehouses are controlled on a consumption basis and the water line is managed according to the minimum pressure criterion. Water intake based pressure management is provided by online measurement of inlet and outlet pressures of the line. In each water reservoir, the input control valves and the output network valves are proportionally controlled automatically (Figure 1b). Tanks are in two cell structure, level sensor and level information are taken. The entrance valves are optimized according to the level and usage consumption of the flat line press and 10 different tanks (Figure 2). The pressure was managed by controlling the minimum line pressure and line valve. Akıllı şebeke sisteminin bir parçası olan “Basınç Yönetimi”, içme suyu şebekelerinde karşılaşılan su kayıplarıyla mücadelede bilinen ve uygulanan en etkin yöntemlerden biridir. Özellikle, şebeke üzerinde belirlenen noktalara uygulanan basınç yönetimi sistemi sayesinde, su kullanımına duyarlı olarak, hat basıncının otomatik ayarlanması ile birlikte şebekedeki kayıplar büyük oranda azalmaktadır. Şehir şebekelerinde boru hasarı, bağlantı problemleri ve bunlarla birlikte yüksek basınca bağlı su kaçakları, su kaynaklarının kısıtlı olduğu günümüz koşullarında büyük problem teşkil etmektedir. Yeni su kaynaklarının bulunmasının çok güç ve yüksek maliyetli olması sebebiyle, şehir şebekelerinde hidrolik dengelerin doğru oluşturulması, su kayıp ve kaçaklarının azaltılarak kazanılması çok büyük önem taşımaktadır. Bu sebeple, basınç yönetim sistemlerinin planlanması, geliştirilmesi ve uygulaması konularında ciddi çalışmalar yapılmaktadır. Bu çalışmada, yaklaşık 25 km lik bir isale hattının üzerinde su temini yapmakta olan, 10 adet su deposunun hattın üzerinde ki otomatik basınç ayarı ile şebeke scadası yapılmaktadır (Şekil 1). Scada sistemi dahilinde bulunan 10 adet farklı reservuar hacimlerinde sahip depoların şebekeleri tüketim bazlı kontrol edilmekte, minumum basınç kriterine bağlı olarak isale hattı yönetilmektedir. Hattın giriş ve çıkış basınçları online ölçümü ile su tüketim bazlı basınç yönetimi sağlanmıştır. Her bir su deposunda giriş kontrol vanaları ve çıkış şebeke vanaları oransal olarak otomatik kontrol edilmektedir (Şekil 2). Depolar iki hücre yapısında olup, seviye sensörü ile seviye bilgisi alınmaktadır. İsale hat basıncı ve 10 ayrı deponun seviye ve kullanım tüketimlerine bağlı olarak giriş vanaları optimize edilmiştir (Şekil 3). Minunum hat basıncı ve hat vanası ile kontrol sağlanarak basınç yönetimi yapılmıştır.
  • [ X ]
    Öğe
    Image processing-based realization of servo motor control on a Cartesian Robot with Rexroth PLC
    (2022) Kuncan, Fatma; Öztürk, Sıtkı; Keles, Fatihhan
    The aim of this study was to separate the objects, whose position was determined using Rexroth PLC on a workbench, and bring them to different locations. Position control of synchronous motors with PLC was done with coordinates obtained by image processing. A real-time Gantry robot was set up for the study. An image taken with the camera connected to Gantry robot is transferred to the Matlab environment. The coordinate data obtained by processing the image are separated for the coordinates used, and the position control of the motors is provided. First, the image was changed to grayscale to apply image processing methods. Then, with the image processing formula, ‘viscircles’ has been applied to mark the detected circles. The obtained coordinates were transferred to IndraWorks PLC to be used in the portal robot. Objects in the determined coordinates were moved to another coordinate with the help of the pneumatic system that integrated to Gantry Robot. The system has been tested for different conditions. As a result of studies, it has been observed that both the image processing method and the system work simultaneously with high accuracy. It is thought that the study can be used in many areas in the literature.
  • [ X ]
    Öğe
    Linear Delta Robot Controlled with PLC Based On Image Processing
    (2022) Öztürk, Sıtkı; Kuncan, Fatma
    Delta Robot is taking an important place in industry 4.0. Its ability to work fast and with precision is the reason why this robot now is used worldwide in the industrial field. Delta robots are mostly used for packaging, 3D printing, pick and place, etc. This robot can be controlled using programmable logic controller (PLC) devices. In recent years, image processing methods have been widely used in many robot applications. In this study, it is aimed to ensure that the robot successfully moves to the determined points by using image processing methods. Images for this study were obtained by attaching a camera to the robot system. In this study, the aim is to set the robot to move based on the visual data that is taken by the camera. The coordinates of each object are defined after several steps in image processing. To be able to move the robot to the desired coordinates, inverse and forward kinematic analysis is proposed. The obtained values are transferred to PLC using OPC. The necessary coding in TIA Portal is done to control the motor drivers so that the three stepper motors can ensure the delta robot moves to the desired coordinate position.
  • Küçük Resim
    Öğe
    Mekatronik sistemin uzaktan scada ile kontrolü, control of mechatronic system with remote scada
    (IETS'18 International Engineering and Technology Symposium, 03-05 May, 2018, 3-5 Mayıs 2018) Kandilli, İsmet; Kuncan, Fatma; Cengiz, Ebuze; Kuncan, Melih
    Günümüzde kullanılan otomasyon sistemleri, genellikle mekatronik sistemlerden oluşmaktadır. Mekatronik sistemlerde; makine, elektrik, elektronik ve bilgisayar ekipmanlarından meydana gelmektedir. Mekatronik sistemlerin kontrolünde denetleyiciler kullanılmaktadır. Bu sistemler otomasyon sistemlerinde vazgeçilmez cihazlardır. Bu çalışmada kullanılan mekatronik sistemin, uzaktan SCADA sistemiyle kontrolü önem arz etmektedir. Mekatronik sistemde; pnömatik ekipmanlar, kompresör, sensörler, kompanent malzemeler, selenoid valfler, kısma valfleri birçok türde silindirler ve vakum sistemi bulunmaktadır. Mekatronik sistem çalışması incelediğimizde; fabrikalarda bakım ve bakım ekiplerinin gözünden baktığımızda, küçük bir örneğidir (Şekil 1). Örnek olarak; pnömatik sistem açısından konunun ele alındığında, sistemin yanlış çalışması veya hiç tahrik olmaması yazılan programla ilgilidir. Selenoid valf tahrik sinyali almıyorsa silindir konum değiştirme işlevi yapamaz. Mekatronik sistemin valf odası arıza bulmada çok önemlidir. Sensörlere bağlı olarak arızalar oluşturulabilir ve işlem devamlılığının sağlanabilmesi için doğru çalışması şarttır. Burada arızayı bulup ne olduğunu tartışıp açıklayıp ona göre sisteme müdahale edilmektedir. Bunu normal malzemelerin arızalanması olarak düşünürsek, silindirlerin hava kaçırması keçelerin eskimesi ve valflerin bozulması gibi takip edilebilir. Sistemi besleyen hava hortumlarında sorunlar yaşanması, zamana bağlı olaraktan aşınmalar bozulmalar meydana tabi ki gelebilir [1]. Oluşabilecek arızaların bu mekatronik sistemde uzaktan SCADA sisteminde gözlemlenebilmesi amaçlanmaktadır. Bu çalışma kapsamında Laboratuvar ortamında gerçekleştirilen Mekatronik Sistemde SCADA aracılığıyla oluşan arızalar ve hatalar uzaktan görülebilmesi hedeflenmektedir.
  • [ X ]
    Öğe
    A Method for Determination of Object-Camera Distance by Using Single Camera
    (International Journal Of Natural and Engineering Sciences, 2016-12-12) Kuncan, Fatma; Yıldırım, Mehmet
    In this study, widely used in many areas of the detection object using image processing methods, depending on the technological development in recent years and has been studied determining the distance from the camera of the specified object. The method can be used in robotic applications more cost-effective to measure the distance of the object to the camera using a single webcam proposed. An algorithm has been developed out of the results obtained are optimized algorithm can be used to determine the object distance. The system has been tested and the results are monitored in real time. Comparison with other method (Euclidean distance and histogram thresholding) has been developed algorithm used. The algorithm developed in MATLAB.