Browsing by Author "Akyokuş, Selim"
Now showing items 1-20 of 28
-
Analysis of preprocessing methods on classification of Turkish texts
Torunoğlu, Dilara; Çakırman, Erhan; Ganiz, Murat Can; Akyokuş, Selim; Gürbüz, Mustafa Z. (IEEE, 2011-06)Preprocessing is an important task and critical step in information retrieval and text mining. The objective of this study is to analyze the effect of preprocessing methods in text classification on Turkish texts. We ... -
The Analysis of text categorization represented with word embeddings using homogeneous classifiers
Kilimci, Zeynep Hilal; Akyokuş, Selim (IEEE, 2019)Text data mining is the process of extracting and analyzing valuable information from text. A text data mining process generally consists of lexical and syntax analysis of input text data, the removal of non-informative ... -
An application of community discovery in academical social networks
Arslan, Enis; Akyokuş, Selim; Ganiz, Murat Can (IEEE, 2013)The objective of this study is to discover social communities in a social network using different social network community discovery methods that utilize metrics and structures like degree, clustering coefficient, k-cores, ... -
An application of community discovery in academical social networks
Arslan, Enis (Doğuş Üniversitesi Fen Bilimleri Enstitüsü, 2013-01)The objective of this thesis is to discover social communities in a social network using different social network community discovery methods that utilizes metrics and structures like degree, clustering coefficient, k-cores, ... -
Application of neural networks in talent management
Waheed, Sajjad; Zaim, Abdül Halim; Zaim, Halil; Sertbaş, Ahmet; Akyokuş, Selim (IEEE, 2013)Study of talent management is getting more attentions in the recent years. It was found that there are no easy classification methods for verifying talents. This paper discusses the application of neural networks for a ... -
Automatic hyperlink generation
Şerifoğlu, Deniz (Doğuş Üniversitesi Fen Bilimleri Enstitüsü, 2010-09)One of the most important inventions of today is the Internet. Hundreds of millions of people anytime, from anywhere, can enter the Internet. On the Internet web pages are represented in HTML format and pages are linked ... -
Büyük verilerde finansal piyasa tahmini: derin öğrenme
Hasan, Afan; Kalıpsız, Oya; Akyokuş, Selim (IEEE, 2017)Derin Öğrenme, büyük miktarda etiketsiz / denetlenmemiş veriden öğrenmeyi başarılı bir şekilde gerçekleştirebildiğinden, büyük verilerden anlamlı gösterimler ve desenler çıkartmayı cazip hale getiriyor. En nasit tanımıyla ... -
A comparison of feature and semantic-based summarization algorithms for Turkish
Güran, Aysun; Bekar, Eren; Akyokuş, Selim (Erciyes University, 2010-06)In this paper we analyze the performances of a feature-based and two semantic-based text summarization algorithms on a new Turkish corpus. The feature-based algorithm uses the statistical analysis of paragraphs, sentences, ... -
Deep learning and word embedding-based heterogeneous classifier ensembles for text classification
Kilimci, Zeynep Hilal; Akyokuş, Selim (Hindawi, 2018)The use of ensemble learning, deep learning, and effective document representation methods is currently some of the most common trends to improve the overall accuracy of a tex classification/categorization system. Ensemble ... -
Document clustering using GIS visualizing and EM clustering method
Doğdaş, Tayfun; Akyokuş, Selim (IEEE, 2013)This paper uses expectation-maximization clustering algorithm and a simple multidimensional projection method for visualization and data reduction. The multidimensional data is projected into a 2D Cartesian coordinate ... -
The effectiveness of homogenous ensemble classifiers for Turkish and English texts
Kilimci, Zeynep Hilal; Akyokuş, Selim; Omurca, Sevinç İlhan (IEEE, 2016-08)Text categorization has become more and more popular and important problem day by day because of the large proliferation of documents in many fields. To come up with this problem, several machine learning techniques are ... -
An efficient algorithm for 3D rectangular box packing
Gürbüz, M. Zahid; Akyokuş, Selim; Emiroğlu, İbrahim; Güran, Aysun (Society for ETAI of Republic of Macedonia, 2009-09)Getting highest occupancy rate of capacity of a container is very important for the companies, which deals in shipping or has shipping as a part of their main activities. They have to fit 3D boxes in container with optimum ... -
Enhanced password authentication through keystroke typing characteristics
Güven, Özlem; Akyokuş, Selim; Uysal, Mitat; Güven, Aykut (ACTA Press, 2007-02-12)Biometric security systems enable more secure authentication methods to access a computer system's resources. This paper presents a biometric security system based on keystroke dynamics that enable hardening or strengthening ... -
The evaluation of heterogeneous classifier ensembles for Turkish texts
Kilimci, Zenep Hilal; Akyokuş, Selim; Omurca, Sevinç İlhan (IEEE, 2017)The basic idea behind the classifier ensembles is to use more than one classifier by expecting to improve the overall accuracy. It is known that the classifier ensembles boost the overall classification performance by ... -
The evaluation of word embedding models and deep learning algorithms for Turkish text classification
Kilimci, Zeynep Hilal; Akyokuş, Selim (IEEE, 2019)The use of word embedding models and deep learning algorithms are currently the most common and popular trends to enhance the overall performance of a text classification/categorization system. Word embedding models are ... -
Exploiting Turkish Wikipedia as a semantic resource for text classification
Poyraz, Mitat; Ganiz, Murat Can; Akyokuş, Selim; Görener, Burak; Kilimci, Zeynep Hilal (IEEE, 2012)Majority of the existing text classification algorithms are based on the "bag of words" (BOW) approach, in which the documents are represented as weighted occurrence frequencies of individual terms. However, semantic ... -
Helmholtz principle based supervised and unsupervised feature selection methods for text mining
Tutkan, Melike; Ganiz, Murat Can; Akyokuş, Selim (Elsevier, 2016-09)One of the important problems in text classification is the high dimensionality of the feature space. Feature selection methods are used to reduce the dimensionality of the feature space by selecting the most valuable ... -
An improved 2D glass cutting solution with genetic algorithms
Gürbüz, Mustafa Z.; Emiroğlu, İbrahim; Akyokuş, Selim (IEEE, 2011-06)2D glass cutting is an important problem for glass manufacturers. The objective of 2D glass cutting is to minimize the amount of waste when cutting a whole glass sheet into several pieces according to given cutting orders. ... -
An improved demand forecasting model using deep learning approach and proposed decision integration strategy for supply chain
Kilimci, Zeynep Hilal; Akyüz, A. Okay; Uysal, Mitat; Akyokuş, Selim; Uysal, M. Ozan; Atak Bülbül, Berna; Ekmiş, Mehmet Ali (Wiley ; Hindawi, 2019)Demand forecasting is one of the main issues of supply chains. It aimed to optimize stocks, reduce costs, and increase sales, profit, and customer loyalty. For this purpose, historical data can be analyzed to improve demand ... -
Intelligent focused crawler: Learning which links to crawl
Taylan, Duygu; Poyraz, Mitat; Akyokuş, Selim; Ganiz, Murat Can (IEEE, 2011-06)A web crawler is defined as an automated program that methodically scans through Internet pages and downloads any page that can be reached via links. With the exponential growth of the Web, fetching information about a ...
