Completed Projects - 2018 Spring

A Classification and Recognition of Baby Crying

Understanding the need of the infant from his/her cry is a major topic which is studied by psychologists and medical doctors at the beginning.

Students: Akın Arpacıoğlu, Salih Can Egin

Advisors: Fikret Gürgen

A Named Entity Recognition Tool for Turkish

In this project, it is aimed to implement a named entity recognition tool for Turkish based on the thesis that Hakan Demir conducted in 2014.

Students: Çağdaş Tombul

Advisors: Arzucan Özgür

Adapting Full Body Synergies

Adapting Full Body Synergies project is an analysis on humans’ way of controlling motor movements.

Students: Ezgi Tekdemir

Advisors: Emre Uğur

Analyzing Market Trends Based on Social Media Data

Nowadays, people share their everyday life issues, happy moments, ideas, plans via Internet on social media platforms and read others’ posts.

Students: Fatih Güven, Emre Eren

Advisors: Ethem Alpaydın

Applications of Hidden Markov Models

Predictive maintenance is one of many applications of HMMs and it has become an increasingly popular topic with the increase in the use of IIoT devices as they lets us get knowledge about the conditions of the systems.

Students: Hakan Şirin

Advisors: Ali Taylan Cemgil

Assessing Communityness of a Group of Social Media Users

Students: Yusufcan Manav

Advisors: Suzan Üsküdarlı

Automatic Differentiation

As the number of computer programs that need the gradient of functions increase, (such as machine learning programs that use gradient descent algorithms) efficient derivation of gradients problem has risen.

Students: Beyza Gül Gürbüz, Esra Aydemir

Advisors: Ali Taylan Cemgil

Bayesian Nonnegative Matrix Factorization as Allocation Model

In this project, we provide efficient, parallelized inference algorithms for Allocation Model which has a close relationship with Nonnegative Matrix Factorization.

Students: Eşref Özdemir

Advisors: Ali Taylan Cemgil

Cancer Classification with Machine Learning Algorithms

Students: Halil Kalkan, İhsan Öztürk

Advisors: Fikret Gürgen, Nuriye Özlem Özcan Şimşek

Collabus: Music Recommendation System for Groups

In this decade, the music industry had a paradigm shift to digital distribution through online music stores and music streaming services, like Spotify, Apple Music, Amazon Music and SoundCloud.

Students: Ekrem Öztürk, Seha Yiğit Güryol

Advisors: Ali Taylan Cemgil

Compiling a lexicon of Turkish multi-word expressions

A multi-word expression (MWE) is a lexeme (term) made up of a sequence of two or more lexemes that has properties that are not predictable from the properties of the individual lexemes or their normal mode of combination.

Students:

Advisors: Tunga Güngör

Controller Synchronization Algorithm for Distributed SDN Control Mechanism

The main focus of this project is on synchronization of SDN controllers.

Students: Necip Fazıl Ergün, Ramazan Kani Türkmen

Advisors: Cem Ersoy

Country Prediction of Users on Social Media Using Machine Learning

The aim of our project is to predict home country of social media users who do not specify it explicitly.

Students: Taha Küçükkatırcı, Yaşar Fatih Enes Yalçın

Advisors: Ali Taylan Cemgil

Designing Target Delivery Structures for Nanonetworking

Nanonetworking is an emerging technology that attracts significant attention in the research community.

Students: Melike Ermiş

Advisors: Tuna Tuğcu

Educational Visualizations

Educational Visualizations

Students:

Advisors: Haluk O. Bingöl

Emotion Recognition

Communication is an important feature of HCI systems.

Students: Murat Karaman

Advisors: Fikret Gürgen

Employee Recommendation System for Companies through CV Analysis

In today’s job search, there are some problems.

Students: Tuna Kağan Yılmaz, Emre Kahreman

Advisors: Taflan Gündem

etherXChange : Archiving Financial Data on Ethereum Blcokchain

Decentralized systems have always been a question and also a chance for humanity.

Students: Furkan Erdem Perşembe, Ceyhun Uzunoğlu

Advisors: Can Özturan

Extractive Text Summarization

The aim of the text summarization is to extract the most important pieces of information from the text.

Students: Hilal Dönmez

Advisors: Tunga Güngör

Extractive Text Summarization with Image Captions

The goal of this research is to investigate effects of image captions in text summarization.

Students: Abdullatif Köksal

Advisors: Arzucan Özgür, Lale Akarun

Integrating an Ethernet Device to a Real Time Operating System

This project consists of understanding the capabilities of an ethernet device, learning how to use these capabilities and integrating these capabilities to a Real Time Operating System.

Students: Mahmut Karaca

Advisors: Arda Yurdakul

IPFS and Blockchain Based Archival System for Open Academic Data

Open academic data such as course syllabi and degree programs are very valuable and need to be preserved in time stamped fashion.

Students: Mehmet Sefa Balık, Oğuzhan Göller, Batuhan Demir

Advisors: Can Özturan

Load Balancing and Multi-source Routing in ICN

Information-Centric Networking is still an incomplete paradigm which introduces a large variety of new topics and approaches over the traditional networking.

Students: Nihal Ezgi YUCETURK, Kutay CANDAN

Advisors: Tuna Tuğcu, Şükrü Kuran

Machine Learning Algorithms Used in Recommendation Systems

Recommendation systems help people by recommending items which suit their preferences.

Students: Haluk Alper Karaevli

Advisors:

Machine Learning Methods for Music Transcription

Music transcription is the transformation of a musical signal into either a human-readable, or a machine-readable form.

Students: Onur Orhan

Advisors: Ali Taylan Cemgil

Management Tool For Software Laboratories

Dealing with large number of computers sequentially in software laboratories (in terms of maintenance and performing other tasks) is time and energy consuming.

Students: Kayahan Taşyaran

Advisors: Tuna Tuğcu

Micelle-based Targeted Transmission in Molecular Communication

Molecular communication is a biologically inspired networking paradigm for communication among biological nanomachines.

Students: Melike Ermiş

Advisors: Tuna Tuğcu

NeuroBoun: An approach to gain insight regarding specific academic contributions

NeuroBoun is an approach for advanced search services.

Students: Mehmet Gülşen, Ahmet Mert Yavuz

Advisors: Suzan Üsküdarlı

Offloading Decision Mechanism for iOS Based Devices

Mobile Devices has become more powerful since the first smartphone released.

Students: Özcan Burak Tomruk, Korhan Çağın Geboloğlu

Advisors: Cem Ersoy, Ahmet Cihat Baktır

Optimization of Machine Learning Algorithms on Large Datasets

Students: Ali Göksu Özkan

Advisors: Ali Taylan Cemgil

Path Finding with AR Drone and Mobile Robot in the Campus

Unmanned aerial vehicles (UAV), known as drones, first arose from military purposes but through the last years it became very popular among the people.

Students: İsmet Koralay, Harun Zengin

Advisors: H. Levent Akın

Personalization of Supermarket Product Recommendations

Grocery shopping is a daily activity for most people.

Students: Atakan Güney, İlkay Ramazan Pala, Sait Talha Nişancı

Advisors: Ali Taylan Cemgil

Phenotype Prediction using Machine Learning based on Genomic Data

The human genome contains valuable information about the person and its hand analysis is cumbersome since it consists of billions of nucleotides.

Students: Rıza Özçelik

Advisors: Arzucan Özgür

Proposing players for basketball teams

Each year thousands of transfers are happening in the sports industry and most of them are happening under the influence of managers who are not the part of the actual community.

Students: Güney Dündar, Seçkin Tayfun Çağlayan

Advisors: Taflan Gündem

Recovering cost function behind dexterous manipulation actions using inverse reinforcement learning

Learning complex tasks which require dexterous manipulations is a very challenging task in robotics.

Students: Pınar Baki

Advisors: Emre Uğur

SDN Controller Load Balancing

The use of multiple controllers in SDN can be due to performance improvements, scalability, and reliability.

Students: Aykut Bozkurt

Advisors: Cem Ersoy

SERVE: See - Listen - Plan - Act

Serve: See – Listen – Plan – Act project enables human-robot interaction by speech recognition and object detection.

Students: Abdullah Muaz Ekici, Özer Biber

Advisors: Emre Uğur

Stance Classification and Rumour Verification on Twitter

As social media has become widespread, it is increasingly used as a way of gathering and conveying information about news and controversial issues.

Students: Gökçe Uludoğan

Advisors: Arzucan Özgür

Turkish Sentiment Analysis on Twitter

My project is about analyzing current status of a person or institution or organization on society by using Twitter.

Students: Furkan Şenharputlu

Advisors: Ali Taylan Cemgil

Tweet Categorization for Customer Agents

I propose a categorization technique for topic modeling in Twitter, which train models using Latent Dirichlet Allocation (LDA) on datasets consisting of tweets and their responses.

Students: Doğa Can Dorum

Advisors: Arzucan Özgür

Visualization of Time Series Data

In this project, I implemented a visualizing tool for time-series data.

Students: Orbay Altuntoprak

Advisors: Ali Taylan Cemgil

Website Classification

This project is basically an automatized classification of websites into one of the predefined categories according to their topics.

Students: Furkan İlısu, Giray Eryılmaz

Advisors: Suzan Üsküdarlı