Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651
Browse
11 results
Search Results
Article Detection of Hand Osteoarthritis from Hand Radiographs Using Convolutional Neural Networks with Transfer Learning(Turkiye Klinikleri, 2020) Üreten, Kemal; Erbay, Hasan; Maraş, Hadi HakanArticle Petrol Flow Pattern Identification Via Data Mining Techniques(2012) Olcer, N.; Elbasi, E.Nowadays, petrol is an important resource for whole world, researchers are working on several mathematical models for flow pattern identification. One previous study is to find characterization of reservoir modeling in petrol flow data. Spatial data-mining can be used in reservoir geological research and ranking reservoir modeling. To find petrol flow patterns there is a study which aims to investigate and analyze the hole cleaning performance of gasified drilling fluids in horizontal, directional and vertical wells experimentally. Also, to identify the drilling parameters those have the major influence on cuttings transport, to define the flow pattern types and boundaries as well as to observe the behavior of cuttings in detail by using digital image processing techniques, and to develop a mechanistic model based on the fundamental principles of physics and mathematics with the help of the experimental observations. In this study we worked on petrol flow data with following features: mud flow rate, mud superficial velocity, pipe rotation per minute, rate of penetration, pressure transmitter and drill pipe. These features have been used in different classification and clustering algorithms to classify in nine class; Dispersed, Moving Bed, Stationary Bed, Dispersed Annular, Bubble, Elongated Bubble, Slug, Wavy Stratified, and Wavy Annular.We have received very promising results from 93% to 100% accuracy using different data mining algorithms. © Sila Science.Conference Object Citation - Scopus: 13Predicting Flight Delays With Artificial Neural Networks: Case Study of an Airport(Ieee, 2017) Demir, Engin; Demir, Vahap BurhanAir transportation has an important place among transportation systems and it is indispensable for the flights to perform their voyages in scheduled time in order to ensure the comfort of passengers and controllability of operational costs. There are several reasons for flight delays like weather conditions, excessive intensity in air traffic, accidents or closed airfields, conditions that will lead to an increase in distances between planes and operational delays in ground services. In this study, using the data collected from the sensors located in the airport and the information about the flight, the goal is develop a machine learning model to estimate departure delays of flights using artificial neural networks.Conference Object Citation - Scopus: 1Localization of Semantic Category Classification in Fmri Images(Ieee, 2014) Alkan, Sarper; Yarman-Vural, Fatos T.In this study, we provide a methodology to localize the brain regions that contribute to semantic category classification. For this purpose we first cluster the data using spectral clustering. Then we extract local features within each cluster by using mesh-arc descriptors. Finally, we test the classification accuracy of each cluster against a hypothesis testing measure we provide here. We have found that, for the experimental task at hand, calcerine fissure and angular gyrus were most effective in classification. These results are shown to be match well with the nature of the experiment. Thus the validity of our approach is confirmed.Conference Object Citation - Scopus: 1A New Multi-Agent Decision Making Structure and Application To Model-Based Fault Diagnosis Problem(Institute of Electrical and Electronics Engineers Inc., 2017) Leblebicioglu, M.K.; Zengin, Y.; Schmidt, K.W.A new hierarchical multi-agent decision-making structure has been proposed. There are two phases of the structure. The first phase is the construction phase where the decision making structure consisting of switching and classification agents is built on the training data set generated by the system scenarios. In construction phase, switching and classification agents are trained and made ready for decision-making. In the decision phase, which is the second phase, the class of the new data sample is decided. This process is carried out by the transmission of the data sample to the correct classifier agent by the switching agents and the classification by the classifier agent. The proposed structure is applied to a complex fault identification problem and a successful result is obtained. The structure is also adaptable to other big data decision making problems. © 2017 IEEE.Conference Object Spam Detection With Fasttext Based Features(Institute of Electrical and Electronics Engineers Inc., 2024) Karadeniz, T.; Tokdemir, G.; Maraş, H.H.Fasttext is a powerful word representation method that creates word representations based on vectors of character n-grams. In this work, we propose a method that utilizes fasttext features for a novel feature engineering model for the spam detection problem. In the feature engineering method, the combination of average, mean of second derivative; mean peak and standard deviation of fasttext features are computed. Finally, tf-idf features are also considered for the modeling process. The success of each feature engineering technique is measured and reported. The combination of the five feature extraction methods, tested on two spam detection datasets, yielded promising results with an accuracy of 0.978 on e-mail spam detection and an accuracy of 0.986 on sms spam classification. © 2024 IEEE.Conference Object Citation - Scopus: 1Comparative Analysis of Machine Learning Techniques Using Customer Feedback Reviews of Oil and Gas Companies(Association for Computing Machinery, 2020) Alrawi, L.N.; Ashour, O.I.A.Sentiment analysis is the process of computationally identifying and categorizing opinions from a piece of text to determine whether the writer's attitude towards a practical topic, products or services is positive, negative or neutral. In this study, Machine Learning techniques are used to perform sentiment analysis on Oil and Gas customer feedback data. We present a comparison of different classification algorithms used for opinion mining, including Support Vector Machine (SVM), Naïve Bayes (NB), Instance Based Learning (IB3), Random Forest (RF), Partial Decision trees (PART), and Logit Boost (LB). Many studies have been performed on sentiment analysis in different sectors, but research into Oil and Gas customer feedback has been limited. Therefore, we have targeted a pathless sector, namely the Petroleum sector, where companies express their opinions towards specific products or services. Waikato Environment for Knowledge Analysis (WEKA) is used for experimental results. The WEKA environment is open source software entailing a collection of machine learning algorithms to solve data mining problems. The main aim of this study is to evaluate the efficiency of the above mentioned classifiers in terms of Precision, Recall, F-Measure and Accuracy. The findings of the comparison analysis indicate that the Naïve-Bayes classifier gives the best Accuracy of all classifiers. A small dataset could be considered as a limitation to our study due to the difficulty of gaining more datasets at the time of the research. However, this research will play a vital role for researchers in making decisions about the algorithm that they are going to use to solve their data mining problems. © 2020 ACM.Conference Object Citation - Scopus: 2Multifractional Gaussian Process Based on Self-Similarity Modelling for Ms Subgroups' Clustering With Fuzzy C-Means(Springer international Publishing Ag, 2020) Baleanu, Dumitru; Karaca, YelizMultifractal analysis is a beneficial way to systematically characterize the heterogeneous nature of both theoretical and experimental patterns of fractal. Multifractal analysis tackles the singularity structure of functions or signals locally and globally. While Holder exponent at each point provides the local information, the global information is attained by characterization of the statistical or geometrical distribution of Holder exponents occurring, referred to as multifractal spectrum. This analysis is time-saving while dealing with irregular signals; hence, such analysis is used extensively. Multiple Sclerosis (MS), is an auto-immune disease that is chronic and characterized by the damage to the Central Nervous System (CNS), is a neurological disorder exhibiting dissimilar and irregular attributes varying among patients. In our study, the MS dataset consists of the Expanded Disability Status Scale (EDSS) scores and Magnetic Resonance Imaging (MRI) (taken in different years) of patients diagnosed with MS subgroups (relapsing remitting MS (RRMS), secondary progressive MS (SPMS) and primary progressive MS (PPMS)) while healthy individuals constitute the control group. This study aims to identify similar attributes in homogeneous MS clusters and dissimilar attributes in different MS subgroup clusters. Thus, it has been aimed to demonstrate the applicability and accuracy of the proposed method based on such cluster formation. Within this framework, the approach we propose follows these steps for the classification of the MS dataset. Firstly, Multifractal denoising with Gaussian process is employed for identifying the critical and significant self-similar attributes through the removal of MS dataset noise, by which, mFd MS dataset is generated. As another step, Fuzzy C-means algorithm is applied to the MS dataset for the classification purposes of both datasets. Based on the experimental results derived within the scheme of the applicable and efficient proposed method, it is shown that mFd MS dataset yielded a higher accuracy rate since the critical and significant self-similar attributes were identified in the process. This study can provide future direction in different fields such as medicine, natural sciences and engineering as a result of the model proposed and the application of alternative mathematical models. As obtained based on the model, the experimental results of the study confirm the efficiency, reliability and applicability of the proposed method. Thus, it is hoped that the derived results based on the thorough analyses and algorithmic applications will be assisting in terms of guidance for the related studies in the future.Conference Object Citation - WoS: 40Citation - Scopus: 77Malware Classification Using Deep Learning Methods(Assoc Computing Machinery, 2018) Dogdu, Erdogan; Cakir, BugraMalware, short for Malicious Software, is growing continuously in numbers and sophistication as our digital world continuous to grow. It is a very serious problem and many efforts are devoted to malware detection in today's cybersecurity world. Many machine learning algorithms are used for the automatic detection of malware in recent years. Most recently, deep learning is being used with better performance. Deep learning models are shown to work much better in the analysis of long sequences of system calls. In this paper a shallow deep learning-based feature extraction method (word2vec) is used for representing any given malware based on its opcodes. Gradient Boosting algorithm is used for the classification task. Then, k-fold cross-validation is used to validate the model performance without sacrificing a validation split. Evaluation results show up to 96% accuracy with limited sample data.Article Citation - WoS: 10Citation - Scopus: 15Detection of Hand Osteoarthritis From Hand Radiographs Using Convolutional Neural Networks With Transfer Learning(Tubitak Scientific & Technological Research Council Turkey, 2020) Erbay, Hasan; Maras, Hadi Hakan; Ureten, KemalOsteoarthritis is the most common type of arthritis. Hand osteoarthritis leads to specific structural changes in the joints, such as asymmetric joint space narrowing and osteophytes (bone spurs). Conventional radiography has traditionally been the primary method of visualizing these structural changes and diagnosing osteoarthritis. We aimed to develop a computerized method that is capable of determining the structural changes seen in radiography of the hand and to assist practitioners in interpreting radiographic changes and diagnosing the disease. In this retrospective study, transfer-learning-based convolutional neural networks were trained on a randomly selected dataset containing 332 radiography images of hands from an original set of 420 and were validated with the remaining 88. Multilayer convolutional neural network models were designed based on a transfer learning method using pretrained AlexNet, GoogLeNet, and VGG-19 networks. The accuracies of the models were 93.2% for AlexNet, 94.3% for GoogLeNet, and 96.6% for VGG-19. The sensitivities of these models were 0.9167 for AlexNet, 0.9184 for GoogLeNet, and 0.9574 for VGG-19, while the specificity values were 0.9500, 0.9744, and 0.9756, respectively. The performance metrics, including accuracy, sensitivity, specificity, and precision, of our newly developed automated diagnosis methods are promising in the diagnosis of hand osteoarthritis. Our computer-aided detection systems may help physicians in interpreting hand radiography images, diagnosing osteoarthritis, and saving time.