Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651
Browse
15 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 Citation - Scopus: 3A New Parallel Multi-Objective Harris Hawk Algorithm for Predicting the Mortality of COVID-19 Patients(PeerJ Inc., 2023) Dokeroglu, TanselHarris' Hawk Optimization (HHO) is a novel metaheuristic inspired by the collective hunting behaviors of hawks. This technique employs the flight patterns of hawks to produce (near)-optimal solutions, enhanced with feature selection, for challenging classification problems. In this study, we propose a new parallel multi-objective HHO algorithm for predicting the mortality risk of COVID-19 patients based on their symptoms. There are two objectives in this optimization problem: to reduce the number of features while increasing the accuracy of the predictions. We conduct comprehensive experiments on a recent real-world COVID-19 dataset from Kaggle. An augmented version of the COVID-19 dataset is also generated and experimentally shown to improve the quality of the solutions. Significant improvements are observed compared to existing state-of-the-art metaheuristic wrapper algorithms. We report better classification results with feature selection than when using the entire set of features. During experiments, a 98.15% prediction accuracy with a 45% reduction is achieved in the number of features. We successfully obtained new best solutions for this COVID-19 dataset.Article 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: 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.Article Citation - WoS: 5Citation - Scopus: 8Predicting the Severity of Covid-19 Patients Using a Multi-Threaded Evolutionary Feature Selection Algorithm(Wiley, 2022) Kiziloz, Hakan Ezgi; Sevinc, Ender; Dokeroglu, Tansel; Deniz, AycaThe COVID-19 pandemic has huge effects on the global community and an extreme burden on health systems. There are more than 185 million confirmed cases and 4 million deaths as of July 2021. Besides, the exponential rise in COVID-19 cases requires a quick prediction of the patients' severity for better treatment. In this study, we propose a Multi-threaded Genetic feature selection algorithm combined with Extreme Learning Machines (MG-ELM) to predict the severity level of the COVID-19 patients. We conduct a set of experiments on a recently published real-world dataset. We reprocess the dataset via feature construction to improve the learning performance of the algorithm. Upon comprehensive experiments, we report the most impactful features and symptoms for predicting the patients' severity level. Moreover, we investigate the effects of multi-threaded implementation with statistical analysis. In order to verify the efficiency of MG-ELM, we compare our results with traditional and state-of-the-art techniques. The proposed algorithm outperforms other algorithms in terms of prediction accuracy.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.Article Citation - WoS: 238Citation - Scopus: 308A Comprehensive Survey on Recent Metaheuristics for Feature Selection(Elsevier, 2022) Dokeroglu, Tansel; Deniz, Ayca; Kiziloz, Hakan EzgiFeature selection has become an indispensable machine learning process for data preprocessing due to the ever-increasing sizes in actual data. There have been many solution methods proposed for feature selection since the 1970s. For the last two decades, we have witnessed the superiority of metaheuristic feature selection algorithms, and tens of new ones are being proposed every year. This survey focuses on the most outstanding recent metaheuristic feature selection algorithms of the last two decades in terms of their performance in exploration/exploitation operators, selection methods, transfer functions, fitness value evaluations, and parameter setting techniques. Current challenges of the metaheuristic feature selection algorithms and possible future research topics are examined and brought to the attention of the researchers as well.Article Citation - WoS: 1Citation - Scopus: 3A New Parallel Multi-Objective Harris Hawk Algorithm for Predicting the Mortality of Covid-19 Patients(Peerj inc, 2023) Dokeroglu, TanselHarris' Hawk Optimization (HHO) is a novel metaheuristic inspired by the collective hunting behaviors of hawks. This technique employs the flight patterns of hawks to produce (near)-optimal solutions, enhanced with feature selection, for challenging classification problems. In this study, we propose a new parallel multi-objective HHO algorithm for predicting the mortality risk of COVID-19 patients based on their symptoms. There are two objectives in this optimization problem: to reduce the number of features while increasing the accuracy of the predictions. We conduct comprehensive experiments on a recent real-world COVID-19 dataset from Kaggle. An augmented version of the COVID-19 dataset is also generated and experimentally shown to improve the quality of the solutions. Significant improvements are observed compared to existing state-of-the-art metaheuristic wrapper algorithms. We report better classification results with feature selection than when using the entire set of features. During experiments, a 98.15% prediction accuracy with a 45% reduction is achieved in the number of features. We successfully obtained new best solutions for this COVID-19 dataset.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.