Toplam kayıt 37, listelenen: 1-20

  • Adaptive visual obstacle detection for mobile robots using monocular camera and ultrasonic sensor 

    Tek, Faik Boray; İyidir, İbrahim Kamil; Kırcalı, Doğan (Springer-Verlag, 2012-10-07)
    This paper presents a novel vision based obstacle detection algorithm that is adapted from a powerful background subtraction algorithm: ViBe (VIsual Background Extractor). We describe an adaptive obstacle detection method ...
  • Anatomy based Features for Facial Expression Recognition 

    Benli, Kristin Surpuhi; Eskil, Mustafa Taner (IEEE, 2014-04-23)
    In this study we propose a set of anatomy based features for facial expression recognition. The muscle forces that constitute an expression are solved by tracking carefully selected facial feature points. These points are ...
  • Budding Trees 

    Yıldız, Olcay Taner; İrsoy, Ozan; Alpaydın, Ethem (IEEE Computer Soc, 2014-08-24)
    We propose a new decision tree model, named the budding tree, where a node can be both a leaf and an internal decision node. Each bud node starts as a leaf node, can then grow children, but then later on, if necessary, its ...
  • Chunking in Turkish with conditional random fields 

    Yıldız, Olcay Taner; Solak, Ercan; Ehsani, Razieh; Görgün, Onur; Gelbukh, A (Springer-Verlag, 2015-04-14)
    In this paper, we report our work on chunking in Turkish. We used the data that we generated by manually translating a subset of the Penn Treebank. We exploited the already available tags in the trees to automatically ...
  • Constructing a turkish constituency parse tree Bank 

    Yıldız, Olcay Taner; Solak, Ercan; Çandır, Şemsinur; Görgün, Onur (Springer Verlag, 2015-09-21)
    In this paper, we describe our initial efforts for creating a Turkish constituency parse treebank by utilizing the English Penn Treebank. We employ a semiautomated approach for annotation. In our previouswork [18], the ...
  • Context sensitive search engine 

    Düzağaç, Remzi; Yıldız, Olcay Taner (SPRINGER-VERLAG BERLIN, 2014)
    In this paper, we use context information extracted from the documents in the collection to improve the performance of the search engine. In first step, we extract context using Lucene, DBPedia-Spotlight, and Wordnet. As ...
  • Crossing minimization in weighted bipartite graphs 

    Çakıroğlu, Olca A.; Erten, Cesim; Karataş, Ömer; Sözdinler, Melih (SPRINGER-VERLAG BERLIN, 2007)
    Given a bipartite graph G = (L-0, L-1, E) and a fixed ordering of the nodes in L-0, the problem of finding an ordering of the nodes in L-1 that minimizes the number of crossings has received much attention in literature. ...
  • Demo abstract: TeleHealth - Intelligent healthcare with M2M communication module 

    Erman, Ayşegül Tüysüz; Erman, Kamil; Özgül, Mehmet Emin; Ayyıldız, Cem; Güngör, Çağrı (ACM, 2012-11-06)
    Chronic diseases, such as diabetes, heart disease (e.g. arrhythmia and hypertension), chronic respiratory diseases (e.g. asthma and COPD), are by far the leading cause of mortality in the world, representing 63% of all ...
  • Design of real-time VBR traffic shaping schemes by considering the impact of both buffer overflows and deadline violations 

    Dağ, Tamer; Stavrakakis, Ioannis (INT INST INFORMATICS & SYSTEMICS, 2005)
    While smoothing the traffic of time sensitive applications at the user premises can reduce the losses due to buffer overflows within the network, it may have an adverse effect on the losses due to the deadline violations ...
  • Doǧrudan pazarlama amaçli hedef kitle analizi 

    Kegeci, Sinan; Özbek, Eyüp Erkan; Türkel, Mustafa Sertaç; Düzag̃aç, Remzi; Yıldız, Olcay Taner (Institute of Electrical and Electronics Engineers Inc., 2018-07-05)
    Direct marketing, which is one of the most popular marketing approaches in the recent years, can be defined as the shortest and most accurate way of matching suitable products with the appropriate people. In this paper, ...
  • Driver Recognition Using Gaussian Mixture Models and Decision Fusion Techniques 

    Benli, Kristin Surpuhi; Düzağaç, Remzi; Eskil, Mustafa Taner (SPRINGER-VERLAG BERLIN, 2008)
    In this paper we present our research in driver recognition. The goal of this study is to investigate the performance of different classifier fusion techniques in a driver recognition scenario. We are using solely driving ...
  • English-Turkish parallel treebank with morphological annotations and its use in tree-based SMT 

    Görgün, Onur; Yıldız, Olcay Taner; Solak, Ercan; Ehsani, Razieh (SciTePress, 2016)
    In this paper, we report our tree based statistical translation study from English to Turkish. We describe our data generation process and report the initial results of tree-based translation under a simple model. For ...
  • Error propagation through generalized high dimensional model representation for data partitioning 

    Tunga, Mehmet Alper; Demiralp, Metin (WILEY-V C H VERLAG GMBH, 2004)
    In many circumstances the explicit form of a multivariate function is not known; rather a finite number of data is listed from some physical experiments. In such cases a function can be constructed only by imposing some ...
  • Evcil hayvanlar için eylem tanima ve izleme sistemi 

    Demir, Güneycan; Erman, Ayşegül Tüysüz (Institute of Electrical and Electronics Engineers Inc., 2018-07-05)
    In our country, as in the world, domestic animal ownership rate is increasing day by day. Pet owners use a variety of tools and methods to monitor their animals' health. One of the most commonly used methods to track animal ...
  • Extraction and selection of muscle based features for facial expression recognition 

    Benli, Kristin Surpuhi; Eskil, Mustafa Taner (IEEE Computer Soc, 2014-08-24)
    In this study we propose a new set of muscle activity based features for facial expression recognition. We extract muscular activities by observing the displacements of facial feature points in an expression video. The ...
  • Ground plane detection using an rgb-d sensor 

    Kırcalı, Doğan; Tek, Faik Boray (SPRINGER-VERLAG BERLIN, 2014)
    Ground plane detection is essential for successful navigation of vision based mobile robots. We introduce a very simple but robust ground plane detection method based on depth information obtained using anRGB-Depth sensor. ...
  • Ground Plane Detection using Kinect sensor 

    Kırcalı, Doğan; Tek, Faik Boray; İyidir, İbrahim Kamil (IEEE, 2013)
    Ground plane detection is essential for successful navigation of vision based mobile robots. We introduce a novel and robust ground plane detection algorithm using depth information acquired by a Kinect sensor. Unlike ...
  • Interactive learning based nodule detection in ct lung volumes 

    Çam, İlker; Tek, Faik Boray (Institute of Electrical and Electronics Engineers Inc., 2016-06-20)
    We present a novel method to automatically detect lung nodules in CT lung scans. Our method is generalized in the sense that it does not assume/depend a particular organ or a particular nodule type. hence it does not require ...
  • İlişkisel veri tabanlarında mükerrer kayıtların makine öǧrenmesiyle tespiti 

    Bayrak, Ahmet Tuğrul; Yılmaz, Aykut İnan; Yılmaz, Kemal Burak; Düzağaç, Remzi; Yıldız, Olcay Taner (Institute of Electrical and Electronics Engineers Inc., 2018-07-05)
    Veri miktarının artışına paralel olarak, ilişkisel veri tabanlarında mükerrer kayıtlar da artmaktadır. Artan bu kayıtlar kullanıldıkları rapor veya analizlerde tutarsızlığa sebep olabilmektedir. Bu sorunu en aza indirgemek ...
  • A model to describe hybrid conflict environments 

    Çayırcı, Erdal; Bruzzone, Agostino G.; Longo, Franceso; Gunneriusson, Hakan (Dime University of Genoa, 2016)
    This article focuses on the definition, implementation and testing of a model to describe Hybrid Conflict Environments. Without the need of citing specific cases or countries, it is clear that hybrid strategy and warfare ...