Browsing by Author "Karci, Ali"

Now showing 1 - 11 of 11

Applications and Comparisons of Optimization Algorithms Used in Convolutional Neural Networks
(Ieee, 2019) Seyyarer, Ebubekir; Uckan, Taner; Hark, Cengiz; Ayata, Faruk; Inan, Mevlut; Karci, Ali
Nowadays, it is clear that the old mathematical models are incomplete because of the large size of image data set. For this reason, the Deep Learning models introduced in the field of image processing meet this need in the software field In this study, Convolutional Neural Network (CNN) model from the Deep Learning Algorithms and the Optimization Algorithms used in Deep Learning have been applied to international image data sets. Optimization algorithms were applied to both datasets respectively, the results were analyzed and compared The success rate was approximately 96.21% in the Caltech 101 data set, while it was observed to be approximately 10% in the Cifar-100 data set.
Cricket Behaviour-Based Evolutionary Computation Technique in Solving Engineering Optimization Problems
(Springer, 2016) Canayaz, Murat; Karci, Ali
Meta-heuristicalgorithms are widely used in various areas such as engineering, statistics, industrial, image processing, artificial intelligence etc. In this study, the Cricket algorithm which is a novel nature-inspired meta-heuristic algorithm approach which can be used for the solution of some global engineering optimization problems was introduced. This novel approach is a meta-heuristic method that arose from the inspiration of the behaviour of crickets in the nature. It has a structure for the use in the solution of various problems. In the development stage of the algorithm, the good aspects of the Bat, Particle Swarm Optimization and Firefly were experimented for being applied to this algorithm. In addition to this, because of the fact that these insects intercommunicate through sound, the physical principles of sound propagation in the nature were practiced in the algorithm. Thanks to this, the compliance of the algorithm to real life tried to be provided. This new developed approach was applied on the familiar global engineering problems and the obtained results were compared with the results of the algorithm applied to these problems.
Effects of the Stochastic and Deterministic Movements in the Optimization Processes
(Gazi Univ, Fac Engineering Architecture, 2022) Seyyarer, Ebubekir; Karci, Ali; Ates, Abdullah
In this study, a linear function representing the iris data set is obtained by making use of the MLR model. SGD, Momentum, Adagrad, RMSProp, Adadelta and Adam optimization algorithms are used to find the optimum values of coefficients of this function. An initialization method with initial population is recommended for these coefficients, which are generally initialized with a fixed or random value in MLRs. IAE, ITAE, MSE and ISE error functions are used as objective functions in the MLR model used. Initial populations of the methods are developed by using a proposed deterministic and classical stochastic initialization methods between upper and lower bounds. The method that are initialized stochasticaly is run several times as seen in literature and the mean values are calculated. On the other hand, the application that is initialized deterministic is only run once. According to the results of deterministic and stochastic initialization methods, it is observed that the coefficients and iteration numbers obtained in both applications are close to each other. Despite very high temporal gain is achieved from the application that is initialized deterministic. As a result of the comparisons, the linear model obtained with Adadelta and MSE reaches the result in the shortest time.
Extractive Multi-Document Text Summarization Based on Graph Independent Sets
(Cairo Univ, Fac Computers & information, 2020) Uckan, Taner; Karci, Ali
We propose a novel methodology for extractive, generic summarization of text documents. The Maximum Independent Set, which has not been used previously in any summarization study, has been utilized within the context of this study. In addition, a text processing tool, which we named KUSH, is suggested in order to preserve the semantic cohesion between sentences in the representation stage of introductory texts. Our anticipation was that the set of sentences corresponding to the nodes in the independent set should be excluded from the summary. Based on this anticipation, the nodes forming the Independent Set on the graphs are identified and removed from the graph. Thus, prior to quantification of the effect of the nodes on the global graph, a limitation is applied on the documents to be summarized. This limitation prevents repetition of word groups to be included in the summary. Performance of the proposed approach on the Document Understanding Conference (DUC-2002 and DUC-2004) datasets was calculated using ROUGE evaluation metrics. The developed model achieved a 0.38072 ROUGE performance value for 100-word summaries, 0.51954 for 200-word summaries, and 0.59208 for 400-word summaries. The values reported throughout the experimental processes of the study reveal the contribution of this innovative method. (C) 2019 Production and hosting by Elsevier B.V. on behalf of Faculty of Computers and Artificial Intelligence, Cairo University.
Extractive Text Summarization Via Graph Entropy
(Ieee, 2019) Hark, Cengiz; Uckan, Taner; Seyyarer, Ebubekir; Karci, Ali
There is growing interest in automatic summarizing systems. This study focuses on a subtractive, general and unsupervised summarization system. It is provided to represent the texts to be summarized with graphs and then graph entropy is used to interpret the structural stability and structural information content on the graphs representing the text files. The performance of the proposed text summarizing approach for the purpose of summarizing the text on the data set of Document Understanding Conference (DUC-2002) including open access texts and summaries of these texts was calculated using the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) evaluation metrics. Experimental processes were repeated for 200 and 400 word abstracts. Experimental results reveale that the proposed text summarizing system performs competitively with competitive methods for different ROUGE metrics.
Investigation of Cricket Behaviours as Evolutionary Computation for System Design Optimization Problems
(Elsevier Sci Ltd, 2015) Canayaz, Murat; Karci, Ali
In this study, the behaviours of an insect species called cricket were investigated and tried to develop a new meta-heuristic algorithm approach that may be used in solving optimization problems by modelling these behaviours. These insect species make a sound by flapping their wings and attract the other crickets around them. While creating this algorithm, the physics laws related to propagation of sound as well as the crickets ability to predict the temperature with the number of flaps were also considered. The approach performance was tried to be shown by applying the developed approach at the end of the study to both numeric problems and cantilever stepped and welded beam that are of system design optimization problems. (C) 2015 Elsevier Ltd. All rights reserved.
A New Multi-Document Summarisation Approach Using Saplings Growing-Up Optimisation Algorithms: Simultaneously Optimised Coverage and Diversity
(Sage Publications Ltd, 2024) Hark, Cengiz; Uckan, Taner; Karci, Ali
Automatic text summarisation is obtaining a subset that accurately represents the main text. A quality summary should contain the maximum amount of information while avoiding redundant information. Redundancy is a severe deficiency that causes unnecessary repetition of information within sentences and should not occur in summarisation studies. Although many optimisation-based text summarisation methods have been proposed in recent years, there exists a lack of research on the simultaneous optimisation of scope and redundancy. In this context, this study presents an approach in which maximum coverage and minimum redundancy, which form the two key features of a rich summary, are modelled as optimisation targets. In optimisation-based text summarisation studies, different conflicting objectives are generally weighted or formulated and transformed into single-objective problems. However, this transformation can directly affect the quality of the solution. In this study, the optimisation goals are met simultaneously without transformation or formulation. In addition, the multi-objective saplings growing-up algorithm (MO-SGuA) is implemented and modified for text summarisation. The presented approach, called Pareto optimal, achieves an optimal solution with simultaneous optimisation. Experimentation with the MO-SGuA method was tested using open-access (document understanding conference; DUC) data sets. Performance success of the MO-SGuA approach was calculated using the recall-oriented understudy for gisting evaluation (ROUGE) metrics and then compared with the competitive practices used in the literature. Testing achieved a 26.6% summarisation result for the ROUGE-2 metric and 65.96% for ROUGE-L, which represents an improvement of 11.17% and 20.54%, respectively. The experimental results showed that good-quality summaries were achieved using the proposed approach.
Overcurrent Relay Coordination of 154/34,5 Kv Hasancelebi Substation by League Championship Algorithm
(Ieee, 2017) Seyyarer, Abubekir; Akdag, Ozan; Hark, Cengiz; Karci, Ali; Yeroglu, Celaleddin
In this study, non-directional overcurrent relay coordination was done in 154/34.5 kV Malatya Teias Hasancelebi transformer centre using League Championship Algorithm (LCA). Standard inverse time characteristic based on IEC 255-3 is used for the relay is coordinated. The results obtained by the LCA have been used in virtual model, obtained by DigSilent software for overcurrent relays at the Hasancelebi transformer centre. Then, the overcurrent relay coordination was performed by examining the response of the overcurrent relays to the 3-phase fault currents generated in the model.
Probabilistic Dynamic Distribution of Wireless Sensor Networks With Improved Distribution Method Based on Electromagnetism-Like Algorithm
(Elsevier Sci Ltd, 2016) Ozdag, Recep; Karci, Ali
Performance of the Wireless Sensor Networks (WSNs) depends significantly on coverage area which is determined via the effective dynamic distribution of sensors. Making mobile sensors' dynamic distributions, which determines their positions within the network effectively, improves performances of WSNs by enabling sensors to form the coverage area more efficiently. In this paper, we initially propose the electromagnetism-like (EM) algorithm as the sensor distribution strategy to increase the coverage area of network after random distribution of sensors. Forming more effective coverage area by using mobile and stationary sensors and probabilistic detection model has been aimed by developing the Optimal Sensor Detection Algorithm that is based on the proposed EM algorithm (OSDA-EM). For this purpose, it has been thought that we would attain to more realistic results, with probabilistic detection model by forming the coverage area more effectively. Additionally, performance of the developed OSDA-EM algorithm has been compared with the Particle Swarm Optimization (PSO) and Artificial Bee Colony (ABC) algorithms which was previously used in the dynamic distribution of WSNs. Simulation results have shown that the developed OSDA-EM can be preferred in dynamic distribution of WSNs that performed with probabilistic detection model. (C) 2015 Elsevier Ltd. All rights reserved.
Sensor Node Deployment Based on Electromagnetism-Like Algorithm in Mobile Wireless Sensor Networks
(Sage Publications inc, 2015) Ozdag, Recep; Karci, Ali
Thedynamic deployment of sensors in wireless networks significantly affects the performance of the network. However, the efficient application of dynamic deployments which determines the positions of the sensors within the network increases the coverage area of the network. As a result of this, dynamic deployment increases the efficiency of the wireless sensor networks (WSNs). In this paper, dynamic deployment was applied to WSNs which consist of mobile sensors by aiming at increasing the coverage area of the network with electromagnetism-like (EM) algorithm which is a population-based optimization algorithm. A new approach has been improved in calculating the coverage rate of the sensors by using binary detection model so as to carry out the dynamic deployments of sensors and it has been thought to reach realistic results efficiently. Simulation results have shown that the EM algorithm can be preferred in the dynamic deployment of mobile sensors within the wireless networks.
Ssc: Clustering of Turkish Texts by Spectral Graph Partitioning
(Gazi Univ, 2021) Uckan, Taner; Hark, Cengiz; Karci, Ali
There is growing interest in studies on text classification as a result of the exponential increase in the amount of data available. Many studies have been conducted in the field of text clustering, using different approaches. This study introduces Spectral Sentence Clustering (SSC) for text clustering problems, which is an unsupervised method based on graph-partitioning. The study explains how the proposed model proposed can be used in natural language applications to successfully cluster texts. A spectral graph theory method is used to partition the graph into non-intersecting sub-graphs, and an unsupervised and efficient solution is offered for the text clustering problem by providing a physical representation of the texts. Finally, tests have been conducted demonstrating that SSC can be successfully used for text categorization. A clustering success rate of 97.08% was achieved in tests conducted using the TTC-3600 dataset, which contains open-access unstructured Turkish texts, classified into categories. The SSC model proposed performed better compared to a popular k-means clustering algorithm.