Fen Bilimleri Enstitüsü: Recent submissions

  • Radio map estimation with neural networks and active learning for indoor localization 
    Güler, Sıla. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2019.)
    In this thesis, a practical indoor localization technique is proposed. In contrast to the state of art approaches, this practical approach does not deal with the multi path problems and shadowing effects of electromagnetic ...
  • Part - based person re - identification in a cafe setting 
    Özdemir Pehlivan, Hilal. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    Person re-identification (re-id) is a challenging task particularly when people have various poses and some parts of the person’s body are occluded or missing in the view. In this thesis, we propose a part-based person re-id ...
  • Speaker adapted speech synthesis with deep neural networks 
    Öztürk, Miraç Göksu. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    Text-to-speech (TTS) systems have been an assisting technology since the 1970s. Although commercial use has begun decades ago, synthetic speech quality is still not as good as recorded speech. One particular subject of ...
  • Parallel point classification into geographical regions 
    Tarmur, Sanver. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    The amount of data generated by social media, social networks and distributed platforms such as blockchain, have reached quite high levels. There are various use cases to process this huge amount of data. One is to classify ...
  • S-Loc and my environment: a new localization system for autonomous robots 
    Çelik, Buluç. (Thesis (M.S.)-Bogazici University. Institute for Graduate Studies in Science and Engineering, 2005., 2005.)
    The localization problem is the detection of the pose of a robot relative to theenvironment using the information about the environment sensed by the robot whenthe starting position is unknown. In short, it is answering ...
  • Named entity recognition in Turkish using deep learning models and joint learning 
    Akdemir, Arda. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    Named Entity Recognition (NER) is the task of detecting and categorizing the entities in a given text. It is an important task in Natural Language Processing (NLP) and forms the basis of many NLP systems. Previous work on ...
  • Tracing the colors of clothing in painting with image analysis 
    Sarı, Cihan. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    In this thesis, we propose an automated methodology to study the trend of color preferences for male and female subjects of paintings over several hundred years. This study is part of a larger project on understanding how ...
  • Data stream analysis 
    Çalışkan, Mine Melodi. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    In this thesis we give a survey of online machine learning algorithms for data stream analysis. After giving an overview of standard batch algorithms, we explain batch-to-online conversion, and we give a in-depth description ...
  • Tensor decomposition models for knowledge graphs 
    Akbayrak, Semih. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    Extracting new unknown facts from given facts in the format of triples(entity relation-entity) is a popular statistical relational learning task and defined with the name of knowledge graph link prediction problem. Due to ...
  • Collaborative filtering and content based hybrid models for recommending scientific articles 
    Öğretir, Mine. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    Recommendation systems (RS) are programs that assist users in accessing infor mation in vast amount of data collections. In this thesis, we investigate hybrid models that use both implicit ratings such as tags, bookmarks ...
  • Parallel resampling for real - time sequential Monte Carlo 
    Bozkurt, Alper Kamil. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    Sequential Monte Carlo (SMC) methods are well known and widely used for state estimation in nonlinear/non-Gaussian dynamical systems. However due to the heavy computational requirements, they may not satisfy the real-time ...
  • Isolated sign language classification using hand descriptors and trajectory based methods 
    Özdemir, Oğulcan. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    In this thesis, we propose a sign language recognition system in which we have adapted and simplified the Improved Dense Trajectory (IDT) approach which was originally proposed for large-scale human action recognition ...
  • Daily life oriented indoor localization by fusion of smartphone sensors and Wi-Fi 
    Nurdağ, Ayşe Vildan. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    Smartphones are leading among the fastest-growing technologies. With their nu merous features, smartphones are the best assistants to users in their lives on several counts. However, a smartphone still requires an extensive ...
  • Realistic performance evaluation of edge computing scenarios over a hybrid testbed using sofware - defined networking 
    Eşrefoğlu, Raşit Mete. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    As mobile computing becomes more and more widespread along with more com plex and distributed applications, the importance of providing these applications to users at high speed and with high efficiency is increasing. One ...
  • Design and implementation of an iot-based home automation system utilizing fog and cloud computing paradigms 
    Özmen, Hüseyin Anıl. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    There are considerable amount of architectures and implementations for home automation systems in both industry and academia. Many of them target to inform home residents who can be anywhere in the world using Cloud ...
  • Build.net: a graphical application generator for object-oriented software and sample applications 
    Gönen, Mehmet. (Thesis (M.S)-Bogazici University.Institute for Graduate Studies in Science and Engineering, 2005., 2005.)
    Existing application and code generators are designed for domain-specific tasks. They are used in the intermediate steps of software development process and are notintended to develop full scale applications. BUILD.NET ...
  • Indoor visual understanding with RGB-D images using deep neural network 
    Doyran, Metehan. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    We created a visual understanding pipeline for house robots with Red-Green-Blue Depth (RGB-D) sensors. Our pipeline consists of three components; (i) an RGB-D object detection network,(ii)asimpletrackingalgorithm,and(iii)a3D ...
  • Trust enhanced secure routing in SDN 
    Sertbaş, Nurefşan. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    The presence of programmable entities, namely controllers and switches, in Soft ware Defined Networks (SDNs) provides a hierarchical architecture to achieve dynamic and manageable networks for easily utilizing high bandwidth ...
  • Affordance - based altruistic robotic architecture for human - robot collaboration 
    İmre, Mert. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    This thesis proposes a computational model for altruistic behavior, shows its im plementation on a physical robot, and presents the results of human-robot interaction experiments conducted with the implemented system. ...
  • The effect of game complexity on deep reinforcement learning 
    Emekligil, Erdem. (Thesis (M.S.) - Bogazici University. Institute for Graduate Studies in Science and Engineering, 2018., 2018.)
    Deep Reinforcement Learning (DRL) combines deep neural networks with re inforcement learning. These methods, unlike their predecessors, learn end-to-end by extracting high-dimensional representations from raw sensory data ...

Search Digital Archive


Browse

My Account