Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/8651
Browse
11 results
Search Results
Article Citation - WoS: 18Citation - Scopus: 27Application of Bilstm-Crf Model With Different Embeddings for Product Name Extraction in Unstructured Turkish Text(Springer London Ltd, 2024) Arslan, SerdarNamed entity recognition (NER) plays a pivotal role in Natural Language Processing by identifying and classifying entities within textual data. While NER methodologies have seen significant advancements, driven by pretrained word embeddings and deep neural networks, the majority of these studies have focused on text with well-defined grammar and structure. A significant research gap exists concerning NER in informal or unstructured text, where traditional grammar rules and sentence structure are absent. This research addresses this crucial gap by focusing on the detection of product names within unstructured Turkish text. To accomplish this, we propose a deep learning-based NER model which combines a Bidirectional Long Short-Term Memory (BiLSTM) architecture with a Conditional Random Field (CRF) layer, further enhanced by FastText embeddings. To comprehensively evaluate and compare our model's performance, we explore different embedding approaches, including Word2Vec and Glove, in conjunction with the Bidirectional Long Short-Term Memory and Conditional Random Field (BiLSTM-CRF) model. Furthermore, we conduct comparisons against BERT to assess the efficacy of our approach. Our experimentation utilizes a Turkish e-commerce dataset gathered from the internet, where traditional grammatical and structural rules may not apply. The BiLSTM-CRF model with FastText embeddings achieved an F1 score value of 57.40%, a precision value of 55.78%, and a recall value of 59.12%. These results indicate promising performance in outperforming other baseline techniques. This research contributes to the field of NER by addressing the unique challenges posed by unstructured Turkish text and opens avenues for improved entity recognition in informal language settings, with potential applications across various domains.Article Citation - WoS: 6Citation - Scopus: 7An Island Parallel Harris Hawks Optimization Algorithm(Springer London Ltd, 2022) Dokeroglu, Tansel; Sevinc, EnderThe Harris hawk optimization (HHO) is an impressive optimization algorithm that makes use of unique mathematical approaches. This study proposes an island parallel HHO (IP-HHO) version of the algorithm for optimizing continuous multi-dimensional problems for the first time in the literature. To evaluate the performance of the IP-HHO, thirteen unimodal and multimodal benchmark problems with different dimensions (30, 100, 500, and 1000) are evaluated. The implementation of this novel algorithm took into account the investigation, exploitation, and avoidance of local optima issues effectively. Parallel computation provides a multi-swarm environment for thousands of hawks simultaneously. On all issue cases, we were able to enhance the performance of the sequential version of the HHO algorithm. As the number of processors increases, the suggested IP-HHO method enhances its performance while retaining scalability and improving its computation speed. The IP-HHO method outperforms the other state-of-the-art metaheuristic algorithms on average as the size of the dimensions grows.Article Citation - WoS: 4Citation - Scopus: 6A New Robust Harris Hawk Optimization Algorithm for Large Quadratic Assignment Problems(Springer London Ltd, 2023) Dokeroglu, Tansel; Ozdemir, Yavuz SelimHarris Hawk optimization (HHO) is a new robust metaheuristic algorithm proposed for the solution of large intractable combinatorial optimization problems. The hawks are cooperative birds and use many intelligent hunting techniques. This study proposes new HHO algorithms for solving the well-known quadratic assignment problem (QAP). Large instances of the QAP have not been solved exactly yet. We implement HHO algorithms with robust tabu search (HHO-RTS) and introduce new operators that simulate the actions of hawks. We also developed an island parallel version of the HHO-RTS algorithm using the message passing interface. We verify the performance of our proposed algorithms on the QAPLIB benchmark library. One hundred and twenty-five of 135 problems are solved optimally, and the average deviation of all the problems is observed to be 0.020%. The HHO-RTS algorithm is a robust algorithm compared to recent studies in the literature.Article Citation - WoS: 12Citation - Scopus: 15A Novel Fractional Operator Application for Neural Networks Using Proportional Caputo Derivative(Springer London Ltd, 2023) Alkan, Sertan; Baleanu, Dumitru; Altan, GokhanIn machine learning models, one of the most popular models is artificial neural networks. The activation function is one of the important parameters of neural networks. In this paper, the sigmoid function is used as an activation function with a fractional derivative approach to minimize the convergence error in backpropagation and to maximize the generalization performance of neural networks. The proportional Caputo definition is considered a fractional derivative. We evaluated three neural network models on the usage of the proportional Caputo derivative. The results show that the proportional Caputo derivative approach has higher classification accuracy than traditional derivative models in backpropagation for neural networks with and without L2 regularization.Article Citation - WoS: 1Citation - Scopus: 2Dynamical System Parameter Identification Using Deep Recurrent Cell Networks Which Gated Recurrent Unit and When(Springer London Ltd, 2021) Akagunduz, Erdem; Cifdaloz, OguzhanIn this paper, we investigate the parameter identification problem in dynamical systems through a deep learning approach. Focusing mainly on second-order, linear time-invariant dynamical systems, the topic of damping factor identification is studied. By utilizing a six-layer deep neural network with different recurrent cells, namely GRUs, LSTMs or BiLSTMs; and by feeding input/output sequence pairs captured from a dynamical system simulator, we search for an effective deep recurrent architecture in order to resolve the damping factor identification problem. Our study's results show that, although previously not utilized for this task in the literature, bidirectional gated recurrent cells (BiLSTMs) provide better parameter identification results when compared to unidirectional gated recurrent memory cells such as GRUs and LSTM. Thus, indicating that an input/output sequence pair of finite length, collected from a dynamical system and when observed anachronistically, may carry information in both time directions to predict a dynamical systems parameter.Article Citation - WoS: 37Citation - Scopus: 36Fmnsics: Fractional Meyer Neuro-Swarm Intelligent Computing Solver for Nonlinear Fractional Lane-Emden Systems(Springer London Ltd, 2022) Raja, Muhammad Asif Zahoor; Umar, Muhammad; Shoaib, Muhammad; Baleanu, Dumitru; Sabir, ZulqurnainThe fractional neuro-evolution-based intelligent computing has substantial potential to solve fractional order systems represented with Lane-Emden equation arising in astrophysics including Newtonian self-gravitating, spherically symmetric and polytropic fluid. The present study aimed to present a neuro-swarm-based intelligent computing solver for the solution of nonlinear fractional Lane-Emden system (NFLES) using by exploitation of fractional Meyer wavelet artificial neural networks (FMW-ANNs) and global optimization mechanism of particle swarm optimization (PSO) combined with rapid local search of sequential quadratic programming (SQP), i.e., FMW-ANN-PSO-SQP. The motivation for the design of FMW-ANN-PSO-SQP intelligent computing comes with an objective of presenting an accurate, reliable, and viable framworks to deal with stiff nonlinear singular models represented with NFLES involving both fractional and integer derivative terms. The designed algorithm is tested for six different variants of NFLESs. The obtained numerical outcomes obtained by the proposed FMW-ANN-PSO-SQP are compared with the exact results to authenticate the correctness, efficacy, and viability, and these aspects are further endorsed statistical observations.Article Citation - WoS: 35Citation - Scopus: 38Emergent Patterns in Diffusive Turing-Like Systems With Fractional-Order Operator(Springer London Ltd, 2021) Baleanu, Dumitru; Owolabi, Kolade M.Patterns obtained in abiotically homogeneous habitats are of specific interest due to the fact that they require an explanation based on the individual behavior of chemical or biological species. They are often referred to as `emergent patterns,' which arise due to nonlinear interactions of species in spatial scales that are much more larger than the individuals characteristic scale. In this work, we examine the spatial pattern formation of diffusive fractional predator-prey models with different functional response. In the first model, we investigate the dynamics of the Riesz fractional predation of Holling type-II functional response with the prey Allee effects, while the second model describes prey-dependent functional response of Ivlev-case and fractional reaction-diffusion. In order to give good guidelines on the correct choice of parameters for numerical simulation experiment of full fractional-order reaction-diffusion systems, we discuss the dynamics of each system in the biologically meaningful region u >= 0 and v >= 0 and give conditions for the existence of Hopf bifurcation, and Turing instability with either homogeneous (zero-flux) boundary conditions which imply no external input or Dirichlet boundary conditions. A novel alternating direction implicit based on backward Euler scheme with either the homogeneous Neumann (zero-flux) or Dirichlet boundary is applied for the numerical solution. The performance of this method is compared with that of the shifted Grunwald formula in terms of accuracy and computational time. Numerical experiments which justify our theoretical findings exhibits some fractional-order controlled patterns of stripes, spots and chaotic spirallike structures that are mostly found in animal coats.Article Citation - WoS: 62Citation - Scopus: 53Design of Stochastic Numerical Solver for the Solution of Singular Three-Point Second-Order Boundary Value Problems(Springer London Ltd, 2021) Baleanu, Dumitru; Shoaib, Muhammad; Raja, Muhammad Asif Zahoor; Sabir, ZulqurnainIn this paper, a novel meta-heuristic computing solver is presented for solving the singular three-point second-order boundary value problems using artificial neural networks (ANNs) optimized by the combined strength of global and local search ability of genetic algorithms (GAs) and interior point algorithm (IPA), i.e., ANN-GA-IPA. The inspiration for presenting this numerical work comes from the intention of introducing a consistent framework that combines the effective features of neural networks optimized with the contexts of soft computing to handle with such challenging systems. Three numerical variants of singular second-order system have been taken to examine the proficiency, robustness, and stability of the designed approach. The comparison of the proposed results of ANN-GA-IPA from available exact solutions shows the good agreement with 5 to 7 decimal places of the accuracy which established worth of the methodology through performance analyses on a single and multiple executions.Article Citation - WoS: 65Citation - Scopus: 74Detection of Rheumatoid Arthritis From Hand Radiographs Using a Convolutional Neural Network(Springer London Ltd, 2020) Ureten, Kemal; Erbay, Hasan; Maras, Hadi HakanIntroduction Plain hand radiographs are the first-line and most commonly used imaging methods for diagnosis or differential diagnosis of rheumatoid arthritis (RA) and for monitoring disease activity. In this study, we used plain hand radiographs and tried to develop an automated diagnostic method using the convolutional neural networks to help physicians while diagnosing rheumatoid arthritis. Methods A convolutional neural network (CNN) is a deep learning method based on a multilayer neural network structure. The network was trained on a dataset containing 135 radiographs of the right hands, of which 61 were normal and 74 RA, and tested it on 45 radiographs, of which 20 were normal and 25 RA. Results The accuracy of the network was 73.33% and the error rate 0.0167. The sensitivity of the network was 0.6818; the specificity was 0.7826 and the precision 0.7500. Conclusion Using only pixel information on hand radiographs, a multi-layer CNN architecture with online data augmentation was designed. The performance metrics such as accuracy, error rate, sensitivity, specificity, and precision state shows that the network is promising in diagnosing rheumatoid arthritis.Article Citation - WoS: 29Citation - Scopus: 33Design of Sign Fractional Optimization Paradigms for Parameter Estimation of Nonlinear Hammerstein Systems(Springer London Ltd, 2020) Aslam, Muhammad Saeed; Baleanu, Dumitru; Raja, Muhammad Asif Zahoor; Chaudhary, Naveed IshtiaqFractional calculus plays a fundamental role in understanding the physics of nonlinear systems due to its heritage of uncertainty, nonlocality and complexity. In this study, novel sign fractional least mean square (F-LMS) algorithms are designed for ease in hardware implementation by applying sign function to input data and estimation error corresponding to first and fractional-order derivative terms in weight update mechanism of the standard F-LMS method. Theoretical expressions are derived for proposed sign F-LMS and its variants; strength of methods for different fractional orders is evaluated numerically through computer simulations for parameter estimation problem based on nonlinear Hammerstein system for low and high signal-noise variations. Comparison of the results from true parameters of the model illustrates the worth of the scheme in terms of accuracy, convergence and robustness. The stability and viability of design methodologies are examined through statistical observations on sufficiently large number of independent runs through mean square deviation and Nash-Sutcliffe efficiency performance indices.