• From past to present: spam detection and identifying opinion leaders in social networks 

  Altınel Girgin, Ayşe Berna; Gümüşçekiçci, Gizem (Yildiz Teknik Univ., 2022-06-22)

  On microblogging sites, which are gaining more and more users every day, a wide range of ideas are quickly emerging, spreading, and creating interactive environments. In some cases, in Turkey as well as in the rest of the ...

• ComStreamClust: a communicative multi-agent approach to text clustering in streaming data 

  Najafi, Ali; Gholipour-Shilabin, Araz; Dehkharghani, Rahim; Mohammadpur-Fard, Ali; Asgari-Chenaghlu, Meysam (Springer Science and Business Media Deutschland GmbH, 2022-07-08)

  Topic detection is the task of determining and tracking hot topics in social media. Twitter is arguably the most popular platform for people to share their ideas with others about different issues. One such prevalent issue ...

• Closeness and uncertainty aware adversarial examples detection in adversarial machine learning 

  Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa Taner (Elsevier Ltd, 2022-07)

  While deep learning models are thought to be resistant to random perturbations, it has been demonstrated that these architectures are vulnerable to deliberately crafted perturbations, albeit being quasi-imperceptible. These ...

• Battle Royale Optimizer for solving binary optimization problems 

  Akan, Taymaz; Agahian, Saeid; Dehkharghani, Rahim (Elsevier B.V., 2022-05)

  Battle Royale Optimizer (BRO) is a recently proposed metaheuristic optimization algorithm used only in continuous problem spaces. The BinBRO is a binary version of BRO. The BinBRO algorithm employs a differential expression, ...

• Uncertainty as a Swiss army knife: new adversarial attack and defense ideas based on epistemic uncertainty 

  Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa Taner (Springer, 2022-04-02)

  Although state-of-the-art deep neural network models are known to be robust to random perturbations, it was verified that these architectures are indeed quite vulnerable to deliberately crafted perturbations, albeit being ...

• k-Means clustering by using the calculated Z-scores from QEEG data of children with dyslexia 

  Eroğlu, Günet; Arman, Fehim (Taylor & Francis, 2022-05-15)

  Learning the subtype of dyslexia may help shorten the rehabilitation process and focus more on the relevant special education or diet for children with dyslexia. For this purpose, the resting-state eyes-open 2-min QEEG ...

• Exploiting epistemic uncertainty of the deep learning models to generate adversarial samples 

  Tuna, Ömer Faruk; Çatak, Ferhat Özgür; Eskil, Mustafa Taner (Springer, 2022-02-18)

  Deep neural network (DNN) architectures are considered to be robust to random perturbations. Nevertheless, it was shown that they could be severely vulnerable to slight but carefully crafted perturbations of the input, ...

• BinBRO: Binary Battle Royale Optimizer algorithm 

  (Rahkar Farshi), Taymaz Akan; Agahian, Saeid; Dehkharghani, Rahim (Elsevier Ltd, 2022-02-04)

  Stochastic methods attempt to solve problems that cannot be solved by deterministic methods with reasonable time complexity. Optimization algorithms benefit from stochastic methods; however, they do not guarantee to obtain ...

• Evaluating the English-Turkish parallel treebank for machine translation 

  Görgün, Onur; Yıldız, Olcay Taner (Tubitak Scientific & Technical Research Council Turkey, 2022)

  This study extends our initial efforts in building an English-Turkish parallel treebank corpus for statistical machine translation tasks. We manually generated parallel trees for about 17K sentences selected from the Penn ...

• On the online coalition structure generation problem 

  Flammini, Michele; Monaco, Gianpiero; Moscardelli, Luca; Shalom, Mordechai; Zaks, Shmuel (AI Access Foundationusc Information Sciences Inst, 2021)

  We consider the online version of the coalition structure generation problem, in which agents, corresponding to the vertices of a graph, appear in an online fashion and have to be partitioned into coalitions by an authority ...

• On the maximum cardinality cut problem in proper interval graphs and related graph classes 

  Boyacı, Arman; Ekim, Tınaz; Shalom, Mordechai (Elsevier B.V., 2022-01-04)

  Although it has been claimed in two different papers that the maximum cardinality cut problem is polynomial-time solvable for proper interval graphs, both of them turned out to be erroneous. In this work we consider the ...

• Unsupervised textile defect detection using convolutional neural networks 

  Koulali, Imane; Eskil, Mustafa Taner (Elsevier Ltd, 2021-12)

  In this study, we propose a novel motif-based approach for unsupervised textile anomaly detection that combines the benefits of traditional convolutional neural networks with those of an unsupervised learning paradigm. It ...

• A mobile app that uses neurofeedback and multi-sensory learning methods improves reading abilities in dyslexia: A pilot study 

  Eroǧlu, Günet; Teber, Serap Tıraş; Ertürk, Kardelen; Kırmızı, Meltem; Ekici, Barış; Arman, Fehim; Balcısoy, Selim Saffet; Özcan, Yusuf Ziya; Çetin, Müjdat (Routledge, 2022-07-03)

  Reading comprehension is difficult to improve for children with dyslexia because of the continuing demands of orthographic decoding in combination with limited working memory capacity. Children with dyslexia get special ...

• Adaptive convolution kernel for artificial neural networks 

  Tek, Faik Boray; Çam, İlker; Karlı, Deniz (Academic Press Inc., 2021-02)

  Many deep neural networks are built by using stacked convolutional layers of fixed and single size (often 3 × 3) kernels. This paper describes a method for learning the size of convolutional kernels to provide varying size ...

• Improved microphone array design with statistical speaker verification 

  Demir, Kadir Erdem; Eskil, Mustafa Taner (Elsevier Ltd, 2021-04)

  Conventional microphone array implementations aim to lock onto a source with given location and if required, tracking it. It is a challenge to identify the intended source when the location of the source is unknown and ...

• Türkçe WordNet oluşturulması ve makine çevirisinde kullanılması 

  Yıldız, Olcay Taner (Tübitak, 2019-12)

  Princeton kelime ağının üretilmesinden beri, diğer dillerde birçok kelime ağı üretilmiştir. Türkçe için en kapsamlı kelime ağı olan KeNet şu anda 80,000 synset içermektedir. Bu synsetler birbirleriyle anlamsal ve diller ...

• Uyarlanır yerel bağlı nöron modelinin incelemesi 

  Tek, Faik Boray (2019-04-10)

  Bu çalışmada uyarlanır yerel bağlı (odaklanan) nöron modelinin bir incelemesi sunulmuştur. Öncelikle bu modelin varolan diğer nöron modelleri ile ilişkisi incelenmiştir. Daha sonra modelin ileri beslemede çalışması ve ...

• Crossing minimization in weighted bipartite graphs 

  Çakıroğlu, Olca Arda; Erten, Cesim; Karataş, Ömer; Sözdinler, Melih (Elsevier B.V., 2009-12)

  Given a bipartite graph G = (L0, L1, E) and a fixed ordering of the nodes in L0, the problem of finding an ordering of the nodes in L1 that minimizes the number of crossings has received much attention in literature. The ...

• An adaptive locally connected neuron model: Focusing neuron 

  Tek, Faik Boray (Elsevier B.V., 2021-01-02)

  This paper presents a new artificial neuron model capable of learning its receptive field in the topological domain of inputs. The experiments include tests of focusing neuron networks of one or two hidden layers on synthetic ...

• A tree-based approach for English-to-Turkish translation 

  Bakay, Özge; Avar, Begüm; Yıldız, Olcay Taner (Tubitak Scientific & Technical Research Council Turkey, 2019)

  In this paper, we present our English-to-Turkish translation methodology, which adopts a tree-based approach. Our approach relies on tree analysis and the application of structural modification rules to get the target side ...

View more