Doğuş University
Discipline

Bilgisayar Bilimleri Anabilim Dalı

Doğuş University

105

Archived Theses

0

DOIs Assigned

0%

DOI Rate

Discipline

50 Theses
Master'sOpen AccessTR

Kablosuz örgü ağlarda ölçeklenebilir yönlendirme protokolü

Bu tezde, kablosuz örgü ağlarda yönlendirme işlemi ağın ölçeklenebilirliği açısından ele alınmış ve bu ağlar için ölçeklenebilir bir yönlendirme protokolü geliştirilmiştir. Geliştirilen protokol Ad-hoc on Demand Scalable Routing Protocol (ADSRP) ihtiyaç duyulduğu anda devreye girerek düğümlerdeki olası kopmalardan dolayı oluşacak paket kayıplarını engellemektedir. Ayrıca, daha az paket kayıbı ile ağın ölçeklenebilmesine imkan tanımaktadır. Benzetim aracı olarak Network Simulator 2.33 (ns-2) kullanılmıştır. Önerilen protokol C++ programlama dili kullanılarak kodlanmış ve örgü ağlarda yönlendirme protokolü olarak kullanılabilen Ad-hoc on Demand Distance Vector (AODV) ve Ad-hoc on Demand Multipath Distance Vector (AOMDV) yönlendirme protokolleriyle karşılaştırılarak benzetim sonuçları elde edilmiştir. Deneysel sonuçlar, geliştirilen protokolün örgü ağlarda başarılı olduğunu göstermiştir.

Ramazan Kocaoğlu
Gazi University · Bilişim Enstitüsü
2012
00
Master'sOpen AccessTR

Görüntü işleme algoritmalarının FPGA üzerinde gerçeklenmesi

Görüntü işleme algoritmaları; sağlık, güvenlik, savunma gibi birçok alanda kullanılmaktadır. Bu çalışmada bazı görüntü işleme algoritmaları FPGA geliştirme kartı üzerinde gerçeklenmiştir. FPGA tabanlı geliştirme kartları üzerinde gerçek zamanlı olarak görüntüde renk değiştirme, morfolojik açma ve kapama, kırmızı renkli nesne takibi, ten rengi tanıma, sobel filtresinin görüntüye uygulanması gibi bir takım tasarımlar gerçekleştirilmiştir. Bu işlemlerde donanım tanımlama dili olan Verilog kullanılmıştır. Elde edilen sonuçlar geliştirme kartına bağlanan monitör sayesinde gözlemlenmiştir. Yapılan bu çalışmanın, daha gelişmiş görüntü işleme sistemleri tasarlamak için bir temel olacağı düşünülmektedir.

FPGA
Mehmet Fatih Özçelik
Gazi University · Bilişim Enstitüsü
2012
00
Master'sOpen AccessTR

IEEE 802.11 kablosuz ağlarda güvenlik

Kablosuz ağlarda bağlantı hızının kullanıcılar için makul seviyelere çıkması kablosuz ağ kullanımını yaygınlaştırmıştır. Kablosuz ağların geniş bir şekilde kabul görmesi ve bu ağlara olan gerekliliğin artması, kablosuz ağların güvenliği ile ilgili bazı endişeleri de beraberinde getirmiştir. Kablosuz ağ güvenliği için birçok yöntem mevcuttur ve her geçen gün geliştirilmektedir. Kullanılan bu yöntemlerden bazıları güvenlik açıklarına sahiptir. Bu açıklardan dolayı kablosuz ağlar tehdit altındadır. Bu çalışmada kablosuz ağların korunması için geliştirilen IEEE güvenlik algoritmalarının açıkları anlatılmış ve bu açıklardan yararlanılarak kablosuz bir ağa nasıl dâhil olunacağı gösterilmiştir.

1-alanin desil ester hidroklorür
Mustafa Abdulkareem
Gazi University · Bilişim Enstitüsü
2012
00
Master'sOpen AccessTR

Hipermedya sistemlerinde uyarlanabilir ve uyarlanır metotları karşılaştırma ve yabancı dil öğretiminde örnek bir araç geliştirme

Bu araştırma kapsamında uyarlanır hipermedya tasarımının genel özellikleri sunulmuş ve güncel bazı uyarlanır hipermedya geliştirilme modelleri incelenmiştir. Ayrıca, uyarlanır ve uyarlanabilir hipermedya sistemleri avantaj ve dezavantajları karşılaştırılmıştır. Bu karşılaştırma sonucuna göre uyarlanır hipermedya sistemleri ile geleneksel uyarlanabilir hipermedya uygulamalarının olumlu yönlerini birleştiren faydalı bir metot ortaya koymaya yönelik örnek bir uygulama geliştirilmiştir. Bu uygulamada uyarlanır hipermedyaların en fazla uygulama alanı buldukları eğitsel uyarlanır hipermedya sistemi ve eğitim konusu olarak da yabancı dil (İngilizce) eğitimi seçilmiştir. Geliştirilen uygulama yabancı dil eğitiminde bazı dilbilgisi konularının öğrenilmesine destek sağlamaktadır.

İlker Sezer
Gazi University · Bilişim Enstitüsü
2011
00
Master'sOpen AccessTR

SDH ağları için özgün bir dcn planlama modeli

SDH ağları, geniş coğrafik alana yayılmış, optik olarak birbirine bağlanmış elemanlardan oluşmaktadır. Ağ yönetim sistemleri ile ağın konfigürasyon, hata, performans, güvenlik ve muhasebe yönetimi yapılmaktadır. Yüksek kalitede hizmet sağlamak için, ağ elemanları ile yönetim sistemleri arasında her koşulda sağlam ve güvenilir olarak çalışan bir iletişim kurmak esastır. Yönetim sistemleri tarafından, ağda yer alan her bir elemanın konfigürasyonu kontrol edilmekte ve yazılımların yeni sürümleri tüm elemanlara dağıtılmaktadır. Veri İletişim Ağı (DCN), yönetim sistemleri ile SDH elemanları arasındaki işletim mesajlarının taşınmasını sağlamaktadır. Bu çalışmada, SDH ağlarında sağlam, güvenilir bir DCN yapısının gereksinimleri belirlenmiş ve bunlara uygun DCN yapısını planlamak üzere özgün bir model geliştirilmiştir. Geliştirilen model ile ilk olarak, ağdaki eleman sayısı, elemanlarca desteklenen yığın yapıları gibi ağın genel özellikleri ele alınmakta, ardından her bir elemanın trafik bağlantıları, topolojik konumu ve yönetimsel yükü değerlendirilerek, kullanılacak yönlendirme protokolüne uygun olarak ağın DCN planlaması yapılmaktadır.

Optik ağlarSenkron sayısal hiyerarşiYönlendirme
Mehmet Şükrü Aygün
Gazi University · Bilişim Enstitüsü
2011
00
Master'sOpen AccessTR

Kablosuz tasarsız ağlarda kimlik doğrulama protokolleri

Sıradan kablolu bağlantılara göre, kablosuz ağlar kullanıcılarına birçok avantaj sunmaktadır. Fakat bunun yanısıra, kablosuz ağlar için güvenli koşulların sağlanması da oldukça gereklidir. Standart kablolu bağlantılarda, yerel ağlara müdahele etmenin daha zor olmasına rağmen, kablosuz bağlantılar bu konuda çok daha hassas kalmaktadır. Bu tez çalışmasında, günümüzde giderek daha çok yaygınlaşan kablosuz ağ teknolojileri araştırılmıştır. Ağların yapısı, özellikleri, güvenlik durumları incelenerek sunulmuştur. Ayrıca, tasarsız kablosuz ağlarda güvenlik yöntemi olarak nitelendirilen kimlik doğrulama, yetkilendirme süreçlerinin öneminden bahsedilmiş ve farklı kimlik doğrulama protokollerinin çalışma prensipleri araştırılmıştır. Çalışmanın uygulama kısmında Delphi platformu kullanılarak, ağlarda kimlik doğrulama benzetimi yapılmıştır.

Kablosuz ağlar
Rustam Babayev
Gazi University · Bilişim Enstitüsü
2011
00
Master'sOpen AccessTR

Kablosuz algılayıcı ağlarda anahtar dağıtım yöntemleri için performans değerlendirmesi

Kablosuz Algılayıcı Ağları (KAA) her bir cihaza algılayıcı düğümü adı verilen ve batarya enerjisi ile çalışan çok sayıda küçük özerk cihazlardan oluşur. Bu cihazlar bütünleşik algılayıcılar, veri işleme özellikleri ve kısa erişimli radyo haberleşme sistemleri ile donatılmıştır. Güvenilirlik, aslına uygunluk, erişebilirlik ve bütünlük KAA' nın tipik güvenlik amaçlarındandır. KAA'lar, askeri amaçlara yönelik algılama ve izleme sistemleri, çevre görüntüleme vb çok çeşitli uygulamalarda kullanılmaktadır. Güvenliğin son derece önemli olduğu düşman ortamlarda, KAA'ların güvenli haberleşmeyi sağlayabilmesi kriptografik yöntemleri kullanılmasına bağlıdır. Kriptografik yöntemler kullanılırken her zaman bir anahtar dağıtım hizmeti gereklidir. Bu çalışmada literatürde KAA'lar için önerilmiş olan anahtar dağıtım yöntemleri incelenmiştir. KAA'ların özelliklerine göre anahtar dağıtım yöntemleri için bir sınıflandırma yapılmış ve incelenen yöntemlerin güvenilir iletişim, hafıza yükü, iletişim yükü, anahtar dağıtım süresi ve düğüm yakalanmasına karşı direnç açısından performans karşılaştırması yapılmıştır.

Önder Ameen Khalil
Gazi University · Bilişim Enstitüsü
2011
00
Master'sOpen AccessTR

Fotometrik stereo tabanlı 3 boyutlu yüz tanıma

Literatürde 2B ve 3B yüz tanıma ile ilgili birçok çalışma bulunmaktadır. 2B yüz tanıma teknikleri pozdan, aydınlanmadan, yüz ifadelerinden ve makyajdan olumsuz etkilenmektedir. 3B yüz tanıma teknikleri poz, aydınlanma ve makyajdan bağımsız çalışabilmekte, diğer problemlere de kısmi çözüm getirmektedir. Gerçek uygulamalarda 3B tarayıcılarla 3B yüzlerin elde edilmesi pratik olarak gerçekleştirilememektedir. Fotometrik stereo ile farklı yönlerden aydınlatılmış en az üç adet 2B yüz görüntüsü kullanılarak 3B yüz verileri oluşturulabilmektedir. Bu yöntem, 3B yüz verilerinin hızlı bir şekilde üretilmesini sağlayan maliyet verimli ve kullanışlı yöntemlerden birisidir. Bu tezde 2B görüntülerden fotometrik stereo ile oluşturulmuş 3B veriler kullanılarak 3B yüz tanıma sistemi önerilmiştir. Yapılan deneylerde 64 farklı aydınlanma yönü altında görüntülenmiş 38 bireyin görüntülerinin bulunduğu Yale B ve genişletilmiş Yale B yüz veritabanları kullanılmıştır. Bütün 2B yüz görüntüleri maskelenerek 3B veri oluşturma işleminden önce yüz dışı bölgeler ve 3B oluşturma işleminde hata oluşturabilecek saç gibi öğeler çıkarılmıştır. Her bireyin 2B görüntülerinden deneysel olarak farklı aydınlatma açılarına sahip 3'lü 10 grup oluşturulmuş ve bu görüntüler kullanılarak 3B test yüz verileri elde edilmiştir. Ek olarak genetik algoritma ile 3B referans görüntüye yakın 3B test verisinin üretilebileceği farklı aydınlatma açılarına sahip 3'lü 5 grup seçilmiş, bu gruplar kullanılarak da 3B test yüz verileri elde edilmiştir. Yüz tanıma safhasında çeşitli algoritmalar bu 3B yüz verileri ile test edilmiştir. İlk olarak farkların karesinin toplamının karekökü ve 2B ilinti doğrudan yükseklik haritası üzerinde denenmiştir. Sonra yükseklik haritası nokta bulutuna dönüştürülerek iteratif en yakın nokta metodu uygulanmıştır. Yüzey normalleri ise test ve referans yüzlerin normalleri arasındaki açıların ortalaması alınarak yüz tanımada kullanılmıştır. Yüzey özelliklerinin tanımlanmasını sağlayan temel yüzey eğrilikleri ve türevleri; ortalama, Gaussian, eğilmişlik ve şekil indisi de yüz tanıma işleminde kullanılmıştır. Şekil indisi haritalarından SIFT tanımlayıcıları çıkarıldıktan sonra bu tanımlayıcıları eşleştirme yöntemi de yüz tanıma safhasında kullanılmıştır. Deneysel sonuçlar incelendiğinde şekil indisi haritalarının ilintisi ve farkları yöntemlerinin %99 üzerinde tanıma sonucu verdiği gözlenmiştir. Ek olarak yüz tanıma, yüzlerin herhangi bir kısmının olmadığı durumlarda herhangi bir kayıtlama işlemi uygulamadan şekil indisi haritalarından SIFT tanımlayıcılarını eşleştirme yöntemi kullanılarak yapılmıştır. Elde edilen sonuçlara göre ağız bölgesi ve burun ucunun olduğu bölge diğer yüz bölgelerine göre daha başarılı sonuçlar vermiştir. Son olarak yüz parçaları bazı açılarda döndürülerek de test edilmiştir. Sonuçlar incelendiğinde şekil indisi haritalarından çıkarılan SIFT tanımlayıcılarını eşleştirme yönteminin 90 derecelik dönmelere karşı çok az miktarda etkilendiği görülmüştür.

Fotometrik stereo yöntemiYüz tanımaÜç boyutlu yeniden yapılandırma
Ebubekir Temizkan
Gazi University · Bilişim Enstitüsü
2011
00
Master'sOpen AccessTR

Yazılım projelerinde risk yönetimi

Bu çalışmada bilgisayar yazılım projelerinin gelişimine katkı sağlayacak, yazılım projelerinin yönetimi ve yazılım projelerinde risk yönetimi ele alınmıştır. Aynı zamanda yazılım projeleri ve risklerlerin türleri incelenmiş, yapılan araştırmaların verimliliği ve hangi proje aşamasına odaklandığı gösterilmiştir. Risk yönetiminin yazılım projelerinde önde gelen konular arasında olduğu vurgulanmış, konuya daha fazla özen gösterilmesi ve yapılan risk çalışmalarının daha erken aşamalara odaklanması gerektiği gözlenmiştir. Yapılan çalışmaların büyük oranda kuram kapsamda kalması yazılımda risk tanımı ve risk azaltma işlemini pasif bırakmıştır. İnceleme sonucu bir takım bulgular ve öneriler sıralanmıştır.

Proje maliyetiProje yönetimiProjeler+10
Alaa E. Younis
Gazi University · Bilişim Enstitüsü
2011
00
Master'sOpen AccessTR

Metin madenciliği ile doküman demetleme

Günümüzde, büyük miktardaki veri Internet ortamında yer alan dokümanlar şeklinde saklanmaktadır. Buradaki esas problem bu verilerden önemli bilgileri çıkarmak ve keşfedilmemiş örüntüleri bulmaktır. Bu problemin çözümü için kullanılabilecek yöntemlerden birisi de kümeleme teknikleri ile dokümanlar arasındaki ilişkileri gruplayarak, farklı gruplar arasındaki ilişkileri ve örüntüleri bulmaktır. Kümeleme analizi, nesnelerin sınıflandırılmasını detaylı bir şekilde açıklamak hedefiyle geliştirilmiştir. Bu hedefe yönelik olarak, elamanlar içlerindeki benzerliklere göre gruplara ayrılır. Diğer bir hedef ise, benzer elemanların gruplanmasıyla veri setini küçültmektir. Bu çalışmanın amacı bölünmeli kümeleme teknikleri kullanarak İngilizce ve Türkçe metinlerde bulunan verileri belirli başlıklar altında kümeleyerek gerekli bilgiyi elde etmektir . Çalışmada metinlerin tümü Terim Frekansı ? Ters Doküman Frekansı (TF-IDF) vektörleri ile ifade edilmiştir. Daha sonra metin madenciliği konusunda, geleneksel bilgiye erişim çalışmalarının eksiklerini gideren Latin Semantic Index (LSI) yöntemi kullanılmıştır. LSI yöntemi K-Means ve K-Median algoritmalarını kullanarak gerek metinlerden gerekse bu metinlerde geçen terimlerden temel kavram vektörleri oluşturup her bir metnin ve terimin bu vektörler üzerindeki iz düşümünü hesaplar. Çalışmada TF, TF-IDF ve LSI kullanıldığında K-Means ve K-Median algoritmalarının başarıları karşılaştırılmıştır. K-Means algoritmasının kümeleme başarısı, K-Median algoritmasından daha iyi çıkmıştır. Veri seti olarak bu çalışmada oluşturulan Milliyet gazetesi veri seti ve literaturde sıklıkla kullanılan R8 ve WebKB-4 veri setleri kullanılmıştır. Milliyet gazetesi veri setinde sağlık, siyaset ve futbol adlı üç alt başlık bulunmaktadır. R8 veri seti Reuters-21578 içinde bulunmakta ve sekiz sınıf içermektedir. WebKB-4 veri seti farklı üniversitelerin bilgisayar bilimleri bölümlerinden toplanan web sayfaları kullanılarak oluşturulmuş ve dört sınıf içermektedir. Çalışma Microsoft. Net ortamında C# dili kullanılarak gerçekleştirilmiştir..

Syolai M.taha
Gazi University · Bilişim Enstitüsü
2011
00
Master'sOpen AccessTR

Veri madenciliği yöntemleri ile spam filtreleme

Ticaretin internet kanalları üzerinden gelişmesi, hızlı ve ekonomik haberleşme olması nedeni ile elektronik posta haberleşmesinin hayatımızda giderek önemini artırmıştır. İşlem maliyetinin çok düşük olması, çok büyük miktardaki verilerin çok uzak mesafelere saniyeler içinde aktarılmasına olanak sağlaması yaygınlaşmasını sağlamıştır. İnternet üzerinde aynı mesajın yüksek sayıdaki kopyasının, bu tip bir mesajı alma talebinde bulunmamış kişilere, zorlayıcı nitelikte gönderilmesi spam olarak adlandırılır. E-posta yolu ile gönderilen spam türlerinden ticari içerikli olan UCE (Unsolicited Commercial E-mail) ve UBE (Unsolicited Bulk E-mail) adından da anlaşılacağı gibi istenmediği halde size gönderilen bir ürünü ya da hizmeti tanıtıcı elektronik posta iletileridir. İstenmeyen elektronik posta problemini tamamen çözebilmiş tek bir teknik ya da tekniklerin birleşmesinden oluşan bir çözüm mevcut değildir. İstenmeyen iletilerin belirlenmesine yönelik birçok veri madenciliği çalışması da yapılmıştır. Veri madenciliği açıkça verinin bir parçası olmayan veride ilginç örüntüleri bulma sürecine denir. Spam filtrelemede iki tür yaklaşım söz konusudur. Bunlardan birincisi bilgi mühendisliği (knowledge engineering) yöntemi ile kurallar oluşturarak filtreleme yapmaktır. Diğeri ise makine öğrenimi ya da makine öğrenimi tekniklerini büyük veri setleri üzerinde uygulayarak makine öğreniminden ayrılan veri madenciliği olarak bilinen yöntemler ile önceden hazırlanmış veri setleri ile sınıflandırmanın yapılmasıdır.Bu tez kapsamında e-posta veri setleri üzerinden oluşturulmuş olan nitelik uzayı üzerinde veri madenciliği yöntemleri uygulanarak spam filtreleme yapılmıştır.

Serdar Kürşat Sarıkoz
Gazi University · Bilişim Enstitüsü
2010
00
Master'sOpen AccessEN

A neural-statistical modeling approach for keystroke recognition algorithms

The main problem of the computer and information systems is the security, which is to protectthe system from the attacks of imposter or unauthorized users. In order to supply bettersecurity, it must be determined clearly while system access that if the claimed one isauthorized user known by the system or not.Recently, biometric security systems technology is developed and added to the typicalauthentication systems , which are consist of username and PIN or password query, aiming toget higher security in system access.The keystroke pattern recognition system is chosen as one of the biometric security systemand proposed to perform a classification in this thesis. In order to achieve this, a perspective isdeveloped under the knowledge of the classification algorithms used earlier in keystrokepattern recognition systems. According to this, a model is designed which uses hybridcombination of two different algorithms. One of them is the statistical algorithm which is thevery firstly used one in pattern recognition and the other one is the neural networks. In themodel, the statistical algorithm formulations are embedded into the neural networkarchitecture. Designed algorithm model is described in detail and tested with sample userdatasets and performance results are presented.When thinking about need of new approaches in the classification algorithms in keystrokepattern recognition, this study can be a starting point to further enhancements with itsperspective on the subject.

Computer securityNerve netPattern recognition+1
Özlem Güven
Doğuş University · Institute of Graduate Studies in Science
2006
00
Master'sOpen AccessEN

Service oriented architecture

I present a survey that describes service oriented architecture. I made an sample applicationon Oracle BPEL by using Oracle SOA Suite for demonstration issues using it. I maderesearches about properties of service oriented architecture, advantages and disadvantages ofit. Besides, the past studies that were made by using SOA has been analyzed. In this thesisprinciples of service oriented architecture are explained.Service oriented architecture can be used in different areas by the help of its properties andadvantages. It can be adopted to different platforms easily. The use of SOA in applicationsdecreases the development time but making services at the beginning is not good in termseffort. The main advantage of service oriented architecture is reusability, a service can beused in different applications and there is no need to make any changes on the service. Tohave the description of any service is adequate to use it. A service can be used by sending thenecessary parameters to the service.In application part, an application has been developed step by step by using the properties ofservice oriented architecture.

Extensible markup languageOracle databaseWeb services
Murat Kaya
Doğuş University · Institute of Graduate Studies in Science
2009
00
Master'sOpen AccessEN

Application of text mining on IT incident management systems

With the increase of data stored in computer systems worldwide, gaining knowledge from data became more computer dependent. Data alone is not very valuable unless there's knowledge extracted from data. This is the reason that machine learning has become a quite important topic recently. Text classification is a machine learning task which aims on classifying documents based on their content and that is the method used in this study. This study focuses on the task of classifying documents on the IT service management, mainly incident management, tools. IT service management and incident management is a hot topic in every company which serves IT services and they require human effort to manage. In ITIL framework for IT service management, it's always useful to link the incidents with configuration items, in other words the assets or components necessary to deliver IT services, and this task is managed manually by IT support technicians in many IT service management tools. The aim of the study is to remove this manual linking step by applying text classification methods and instead to provide an automatic assignment of CI's to incidents. Four text classification methods, Naïve Bayes Multinomial, k-Nearest Neighbor, Support Vector Machine and C4.5 decision tree classifiers, are used on three different sets of incidents extracted from the same database by using different filters. The impact of some pre-processing steps is compared on different sizes of datasets. It's possible to conclude from the experiments that this study achieved an acceptable accuracy on all sizes of datasets though some methods, like SVM on Dataset B, may only be used as nice-to-have as the results are not perfect. Using a model with 64.41% accuracy as a primary solution might cause time and value loss. Another conclusion from the experimental results is that SVM performs well even in such complex datasets while the classifiers like Naïve Bayes Multinomial and kNN are very sensitive to noise. Learning speed of each classifier in the evaluations has been monitored and proved that C4.5 could be problematic from speed perspective on complex datasets. Naïve Bayes Multinomial and kNN, however, does not require any time to learn because of their distance and probability approaches.

Erdal Sever İşcen
Doğuş University · Institute of Graduate Studies in Science
2019
00
DoctorateOpen AccessTR

Esnek kullanımlı avuç izi bölgesine dayalı doğrulama sistemlerinin tasarım çalışması

Tez çalışmasının ilk kısmında düşük maliyetli iki adet çevrimiçi avuç izi doğrulama sistemi proje desteğiyle oluşturulmuş ve performansları gerçek hayat koşullarında ölçülmüştür. Tasarımı yapılan sistemler, üç yıl boyunca laboratuvar girişlerinde hizmet vermiş, kayıtlı binden fazla kullanıcısıyla 20,000?i aşkın doğrulamanın gerçekleştirilmesine imkan tanımıştır. Çevrimiçi sistemlerden elde edilen yüksek başarıdan ötürü, çalışmalarımızın ikinci kısmında, kullanımdaki kısıtlamaların en aza indirildiği serbest arka planlı ve temassız sistemlerin geliştirilmesi üzerinde durulmuş, tasarımları ve çevrimdışı testleri gerçekleştirilmiştir.Bu tezde, yüksek performans veren Gabor tabanlı Çekirdek Fisher Ayırtacı yönteminin avuç izi özniteliklerini belirlemede; Aktif Görünüş Modeli yönteminin de karmaşık arka plana sahip görüntülerde avuç bölütlenmesi amacıyla avuç izi tanımada kullanımları önerilmiştir. Ayrıca, tarafımızdan geliştirilen, doğrusal olmayan regresyonun kullanıldığı model tabanlı avuç izi bölgesi belirleme yöntemi, bölütleme performans ölçümlerinde kullanılabilecek sınırlandırılmış noktanın eğriye uzaklığı ve marjin genişliği kriterleri ile model tabanlı yöntemler için oluşturulan avuç modeli yeni yaklaşımlar olarak literatüre kazandırılmıştır. Çevrimiçi sistemlerle oluşturulan, gerçek dünyada oluşabilecek senaryoları içeren büyük ölçekteki avuç veritabanları ile çok sayıda kullanım esnekliğinin simüle edildiği serbest arka planlı sistemlerden elde edilen avuç veritabanları avuç izi tanıma testleri için araştırmacıların hizmetine açılmıştır. Doğrulama performansını arttırmak için farklı doğrulama senaryolarının kullanılması ve kullanıcı tanımlı normalleştirme kavramının avuç izi biyometriğinde uygulanması, tezin sağladığı diğer katkılar olarak dikkat çekmektedir.

Murat Aykut
Karadeniz Technical University · Institute of Graduate Studies in Science
2013
00
DoctorateOpen AccessEN

Sınavda öğrenci etkinliklerinin etiketlenmesi için derin öğrenme temelli özniteliklerin çıkarılması ve sınıflandırılması

Visual monitoring study findings have improved considerably as a result of research on video description and human activity detection. Exam cheating detection is a fundamental part of any level education program. This work focuses on students' activities labeling in the exam. The framework is developed for labeling students' activities into six different classes, back- watching, front-watching, side-watching, normal, showing gestures, and suspicious. A methodology for predicting cheating activities is proposed in this study. To extract features, feature descriptors such as local binary patterns and texture features are used. The entropy and ant colony optimization (ACO) based feature selection methods are utilized separately on the acquired feature subsets having qualities of both filter and wrapper-based approaches. The features are then combined to form a powerful features subset. Those selected features are trained on several different models. SVM-based and KNN classifiers are showed promising results on the datasets. The classification system accurately labels the student activities into abnormal and normal classifications using the exam activities detection dataset. The findings show that the proposed framework for activity recognition in exams is quite effective and accurate. 92% for SVM and 94% for KNN achieved on the dataset.

Musa Dıma Genemo
Karadeniz Technical University · Institute of Graduate Studies in Science
2021
00
Master'sOpen AccessEN

Online electricity bill management system: A web application for an energy supplier company in Somalia

This thesis examines the design and development of an Online Electricity Bill Management System (OEBMS) using a structured Software Development Life Cycle (SDLC) methodology, namely the Waterfall model. This framework simplifies the process of conceptualizing, constructing, and implementing the program. Clients can effectively handle their invoices by using the online application's user-friendly interface. By using automation in the billing process, the system effectively minimizes the need for human work and significantly decreases the occurrence of mistakes. Furthermore, it eliminates the need for paper-dependent activities, hence promoting the adoption of digital workflow. The primary objective of this thesis is to centralize the management of electrical data, including details about connections, power panels, and customer information. To accomplish this task, OEBMS utilizes machine learning methodologies such as regression models and random forests. To forecast future power consumption patterns, these models use previous data. As a result, the system may provide comprehensive reports that go beyond the mere presentation of fundamental billing data. It is considered the ability to create reports that predict potential increases in demand or discover consumer segments that show trends of shifting consumption. The system uses a MySQL server as the database management system, while an Apache web server hosts the web interface for user access. Another objective of this thesis is to tackle the inefficiencies and inaccuracies that arise from human bill computations and paper-based procedures. The OEBMS aims to automate these operations to improve efficiency and accuracy.

Progressive web appsEnergy management systems
Mohamed Maawıye Hılowle
Beykoz University · Lisansüstü Programlar Enstitüsü
2024
00
Master'sOpen AccessTR

Beyin - bilgisayar etkileşimi verilerin analizi ve uygulamaları

Vücudun ana kontrol mekanizması olan beyin, anlaşılması zor bir yapıya sahiptir. İnsan beyni üzerinde incelemeler yapılmaya başladığından beri günümüze dek farklı metotlarla, beynin hareketli yapısını anlaşılır hale getirmek için birçok çalışma yapılmıştır. Elektroensefalografi (EEG), bu yöntemler arasında beyin aktivitesini görüntülemeye yarayanlardan bir tanesidir. Beyin – Bilgisayar Etkileşimi, gelişmekte olan ve üzerinde çok fazla sayıda çalışma yapılmamış bir alandır. Yalnızca düşünceler aracılığıyla teknolojik cihazlarla konuşabilme fikri pek çok yeni ufuklar doğurur. Çalışmada kullandığımız Emotiv Epoc+ adlı cihaz, EEG sinyallerini okunabilir hale getirmek için faydalanılan araçlardan bir tanesidir. Kafatasında farklı loblara göre özelleşmiş olarak kendine has bölgelere yerleştirilen 14 farklı elektrot sayesinde bu cihaz aracılığıyla beyinsel aktivite gözlemlenir. Bu tez çalışmasında kullanılan EEG verileri, bahsedilen araç ve yazılım kullanılarak elde edilmiştir. Ayrıca çalışmayı desteklemek amaçlı kullanılan sınıflandırma algoritmalarının testi de UCI veritabanından alınan onaylanmış EEG verileri üzerinde gerçekleştirilmiştir. Beyinde üretilen dalgaların üst üste çakışmasıyla EEG sinyalleri meydana gelir. Bu çalışmada, kullanılan cihaz ve yazılım aracılığıyla bilgisayara aktarılan EEG verileri dosyaya yazdırılmıştır. Verilerin tutulduğu dosyalara gerekli önişleme operasyonları uygulanarak, kullandığımız programlama ortamı olan Visual C# 2015 de veriler ayrıştırılarak okunabilir hale getirilmiştir. Sınıflandırma aşamasında ise K-En Yakın Komşuluk, C x K – En Yakın Komşuluk, Naive Bayesian kullanılmıştır. Sınıflandırma algoritmalarının uzaklık ölçüm yöntemleri içinde ise Öklid, Bray- Curtis, Hellinger ve Cosine benzerlik ölçümleri bulunmaktadır. v Gerçekleştirdiğim tez çalışmasında, aynı denekten temin edilen anlık EEG sinyalleri kullanılmıştır. Deneğe deney sırasında dört temel ana yön (sağ, sol, yukarı, aşağı) gösterilen bir bilgisayar arayüzü sunulmuştur. Bu gösterilen dört yönden fare imlecinin yalnızca birine gitmesinin deneğin zihninde imgelenmesi istenmiştir. Deneğin bu düşünsel süreci EEG ölçüm cihazı yardımıyla kaydedilmiştir. Her bir yön düşüncesi ilgili yön ismiyle etiketlenip dört farklı sınıfa ayrılmıştır. Bu şekilde gruplanan EEG sinyalleri farklı sınıflandırma algoritmaları kullanarak sınıflandırma doğruluk oranlarını karşılaştırmıştır. Nispeten başarılı oran veren algoritma, hangi yönün düşünüldüğünün bilinmediği EEG verileri üzerinde uygulanarak incelenmiştir.

Alican Doğan
Dokuz Eylül University · Institute of Graduate Studies in Science
2018
00
Master'sOpen AccessTR

Uzaktan eğitimde veritabanı tasarımı ve örnek uygulama

Türkiye uzaktan eğitim uygulamasına yeni adapte olmuş ve hızlı bir şekilde gündemine alarak kullanıma başlamıştır. Şimdiye kadar belirli bir ders yada uygulama modülü için birçok veritabanı tasarımı yapılmış ancak evrensel değerde bir eğitim kurumunu oluşturabilecek seviyede geniş çaplı bir çalışma henüz yayınlanmamıştır. Üniversiteler bu uygulamanın en çok yapıldığı eğitim kurumlarından biridir, ancak her bir kurum kendi uzaktan eğitim modeli için bir veritabanı hazırlamaktadır.?Uzaktan Eğitimde Veritabanı Tasarımı ve Örnek Model? adlı çalışmada her kurum ve kuruluşa uyumlu, her ders için uyarlanabilir, gelişmiş, yönetimi kolay 153 tablo ve bu tabloların birbirleri ile tam ilişki içerisinde olduğu bir veritabanı tasarımı yapılmıştır. Veritabanı tasarımında Microsoft SQL Server 2005 veritabanı tasarım yazılımı kullanılmıştır. Veritabanı 38 ana modülden oluşmakta, farklı seviyelerde kullanıcılar tanımlanmakta ve bu kullanıcılara farklı erişim seviyeleri verilmektedir. Sistem bir bütün olarak farklı akademik ve idari personel tarafından yönetilmektedir.Tasarlanan veritabanı ister Windows form ara-yüzüne istenirse web formu ara-yüzüne uyarlanabilmekte ve kullanıcı isteğine göre geliştirilebilmektedir.Anahtar kelimeler: Eğitim Öğretim Yönetim Sistemi (LMS), SQL Server, Veritabanı, İlişkisel Tasarım, Uzaktan Eğitim

SQLUzaktan eğitimVeri tabanı
Yılmaz Sarpkaya
Afyon Kocatepe University · Institute of Graduate Studies in Science
2008
00
Master'sOpen AccessTR

SCORM uyumlu modüler öğrenim yönetim sisteminin tasarımı ve gerçekleştirilmesi

Günümüzde çoğu üniversite ve eğitim kurumu ders materyallerini internet ortamına aktararak öğrencilerine uzaktan eğitim vermek için programlar hazırlamaktadırlar. Fakat programların başarılı bir şekilde işleyebilmesi ve etkin bir eğitimin verilebilmesi için eğitim içeriklerinin internet ortamına aktarılması yeterli değildir. Eğitim içeriklerini internet ortamına hazır hale getirmek ve yayınlamak önemli bir aşama olsa da, içeriklerin ve diğer tüm işlemlerin kontrolü ve denetimini yapacak bir sisteme ihtiyaç vardır.Öğrenim Yönetim Sistemi (Learning Management System - LMS) de bu noktada ortaya çıkan bir kavramdır. Bir öğrencinin programa kayıt aşamasından mezuniyet belgesini aldığı döneme kadar olan bütün süreçlerin etkin ve güvenli bir şekilde yürütülmesinden Öğrenim Yönetim Sistemi sorumludur.Bu tez çalışmasında, geleneksel eğitime göre daha az maliyet ve daha fazla imkân sağlayan web tabanlı uzaktan öğretimin yükseköğretimde kullanımı amacıyla SCORM uyumlu ve modüler bir yapıda geliştirilen Öğrenim Yönetim Sistemi (LMS) anlatılmıştır.

LMSModüler programlarModülerlik+6
Fatih Bayram
Afyon Kocatepe University · Institute of Graduate Studies in Science
2009
00
Master'sOpen AccessTR

PDA tabanlı gerçek zamanlı EKG görüntüleme sistemi

Teletıp, ?elektronik bilgi ve haberleşme teknolojilerinin? sağlık hizmeti sağlamak ve destek sistemi olarak kullanılmasıdır. Acil yardım hizmetleri, gerekli müdahalenin zamanında ve uygun bir şekilde yapılması durumunda, servise ihtiyaç duyan kişinin hayatını kurtaracak bir etkiye sahip olduğu için çok büyük öneme sahiptir. Kalp krizi hem dünyada hem de ülkemizde en önemli sağlık problemlerinden biridir. Kalp krizinin üzerinden geçen her dakika, kalp adalesindeki hasarı arttırmakta, ne kadar erken müdahale edilirse adale o kadar az zarar görmektedir. Önemli miktarda kalp adalesinin zarar görmesi de geriye dönülmez bir tablo oluşturmaktadır. Bu nedenle kalp krizi durumunda hastaya erken müdahale edebilmek için, erken teşhis büyük önem taşımaktadır.Bu çalışmada, kalp krizi geçiren bir hasta ambulansa alındıktan sonra 12 derivasyonlu EKG cihazından alınan EKG işaretlerini, 230.4 Kbps hızında uzman doktorun PDA'sına aktaran 112 Acil Servis EKG İletim Programı tasarlanmış ve gerçekleştirilmiştir. Hazırlanan yazılım ile GPRS Modem, EDGE üzerinden internete bağlanarak PC ekranındaki EKG bilgilerini sorumlu kişilere MMS mesajı ile 90 sn de ulaştırmıştır. Bu sistem sayesinde uzman doktora ulaşmak kolaylaşmıştır. Ambulans nerede olursa olsun, GSM şebekesi mevcut olduğu sürece, sistemin EKG verilerini iletmesinin mümkün olduğu görülmüştür. Özellikle ulaşımın zor olduğu köy sağlık ocaklarında bu sistem kurulduğu takdirde, doğru teşhis ve müdahale için zaman kaybedilmeyecektir. Hastanelerde gece nöbetçi kalp hastalıkları doktoru bulunmaması durumunda, tasarlanan sistem sayesinde hastanın EKG grafiği kolaylıkla icapçı doktora iletilebilecektir. Bu sistem PC üzerinde çalışan diğer programlardan ve donanımdan bağımsız olduğundan dolayı her sisteme kolaylıkla entegre olabildiği için teletıbbın diğer alanlarında da kullanılabilir.

Tayfun Burak Aktürk
Afyon Kocatepe University · Institute of Graduate Studies in Science
2009
00
Master'sOpen AccessEN

Araştırma tabanlı testler baz alınarak model tabanlı testler için modeller geliştirme

Model-based testing facilitates automatic generation of test cases by means of models of the system under test. Correctness and completeness of these models determine the effectiveness of the generated test cases. Critical faults can be missed due to omissions in the models, which are primarily created manually. In practice, these faults are usually detected with exploratory testing performed manually by experienced test engineers. In this thesis, we propose an approach for refining system models based on the experience and domain knowledge of these test engineers. Our toolset analyzes the execution traces that are recorded during exploratory testing activities and identifies the omissions in system models. The identified omissions guide the refinement of models to be able to generate more effective test cases. We applied our approach in the context of two industrial case studies to improve the models for model-based testing of a Digital TV system. After applying our approach, three and four critical faults were detected for the first and second case studies, respectively. These faults were not detected by the initial set of test cases and they were also missed during the exploratory testing activities.

Ceren Şahin Gebizli
Özyegin University · Institute of Graduate Studies in Science
2014
00
Master'sOpen AccessEN

HDTVler için yüksek performanslı düşük karmaşıklıklı gömülü sıkıştırma

HDTV video processors need to keep one or more previously scanned frames as they process streaming video when performing tasks such as frame rate conversion, deinterlacing, and other video enhancement techniques. Reading and writing frames require high bandwidth at HD resolutions. This bandwidth can be reduced by applying compression. Video compression methods do not address this problem as they reduce network traffic while adding extra memory traffic. What is needed is high-performance, low-complexity, and lossless (or near-lossless) image compression. This type of compression method is called Embedded Compression (EC). We propose a novel end-to-end embedded memory compression solution. It can support 4K Ultra HD video streams at 30 Hz with a single core implemented in 180nm ASIC technology, which amounts to a per-core pixel rate twice the competition.

HardwareImage compressionDigital video+2
Okan Palaz
Özyegin University · Institute of Graduate Studies in Science
2014
00
Master'sOpen AccessEN

Yazılım tanımlamalı ağlar üzerine çoklu betimlenmiş video çoğa gönderim akışı

Video has become one of the most prominent applications of the Internet. Many of the video streaming applications involve the distribution of content from a CDN source to a large population of interested clients. However, widespread support of IP-Multicast has been unavailable to a large extent due to technical and economical reasons, all stemming from the non-programmable nature of today's Internet. As a solution, streaming multicast video is commonly operated using application level multicast. However, this technique introduces excessive delays for the clients and increased traffic load for the network. This thesis is concerned with the introduction of a SDN based framework that allows the network controller to not only deploy IP-Multicast between a source and subscribers, but also control, via a simple northbound interface, the distributed set of sources where multiple-description coded video content is available. Standard and premium users are envisioned. While standard subscribers are to receive one of the descriptions of the video, premium subscribers will receive multiple descriptions, each from a different source, simultaneously and combine these descriptions prior to playback for increased video quality. In the framework, the controller constructs and maintains a dynamic multicast tree from each source and formulates the associated multicast routes. An experimental testbed has been setup on Mininet to assess the performance of the SDN-based streaming multicast video application using QoS performance metrics on a well-known test videos. We observe that for medium to heavily loaded networks, relative to todays solution of application layer multicast in a non-SDN network, the SDN-based streaming multicast video framework increases the PSNR of the received video significantly, from a level that is practically unwatchable to one that has good quality.

Kyoomars Alizadeh Noghani
Özyegin University · Institute of Graduate Studies in Science
2014
00
Master'sOpen AccessEN

Alana özel uyarlanabilir hizmet gözetimi

We propose an adaptive and domain-specific service monitoring approach to detect partner service errors in a cost-effective manner. Hereby, we not only consider generic errors such as file not found or connection timed out, but also take domain-specific errors into account. The detection of each type of error entails a different monitoring cost in terms of the consumed resources. To reduce costs, we adapt the monitoring frequency for each service and for each type of error based on the measured error rates and a cost model. We introduce an industrial case study from the broadcasting and content-delivery domain for improving the user-perceived reliability of Smart TV systems. We demonstrate the effectiveness of our approach with real data collected to be relevant for a commercial TV portal application. We present empirical results regarding the trade-off between monitoring overhead and error detection accuracy. Our results show that each service is usually subject to various types of errors with different error rates and exploiting this variation can reduce monitoring costs by up to 30\% with negligible compromise on the quality of monitoring.

Arda Ahmet Ünsal
Özyegin University · Institute of Graduate Studies in Science
2014
00
Master'sOpen AccessEN

Açık dünya politika muhakemesi için akıllı bilgi toplama

Policies play an important role in autonomous multi-agents systems where each agent aims to achieve its own goals. Policies and related mechanisms allow authority or society to regulate the actions of agents to prohibit malicious and undesirable activities. Without policies, society could be harmed by irresponsible and malicious activities of its members. On the other hand, reasoning with policies is not trivial; it requires extensive knowledge about the environment. If the knowledge is incomplete or missing, reasoning with policies may not be possible. In this thesis, we propose a proactive approach for gathering information to reason with policies. While our approach can be used in various settings, we provide two case-studies; one in social networking domain and the other in on-line advertisement domain. Through experiments we demonstrated that our approach allows high rate of success during policy reasoning when the knowledge bases is not complete.

Information gatheringLogical reasoning
İrfan Can Büyükyıldız
Özyegin University · Institute of Graduate Studies in Science
2015
00
Master'sOpen AccessEN

Eylem anlama ve duyguların beyin mekanizmalarına hesapsal yaklaşımlar

Through evolution living beings have gained unique features to deal with apparently easy but computationally expensive problems such as mate selection, learning sensorimotor skills and decision making. Thus, understanding how a biological system can process sensory information, interpret the probable results and find a solution in relatively short time to faced problems have become an attractive research area for computational neuroscience, artificial intelligence (AI) and robotics. In this thesis we focused on mirror neurons in the ventral premotor cortex (area F5) and the functional aspects of emotions from a computational but biologically plausible way. In the former part, the raw neural firing data from area F5 of macaque monkeys are analyzed to undercover neural representation using a decoding framework. For this, we propose two methods to detect mirror neurons by using machine learning and statistical analysis techniques. In the later part, we present that higher level emotions (those that have putatively evolved after the basic emotions of fear, anger etc.) are the behavioral manifestation of self-regulation mechanisms of computational (neuronal) energy expenditure for cognitive processing. To realize this proposal, we chose a tractable computational mechanism that may be considered as a model of neural computation mechanisms of the brain and deploy it on a robotic platform (Darwin-OP).

Murat Kırtay
Özyegin University · Institute of Graduate Studies in Science
2015
00
Master'sOpen AccessEN

Dinamik hareket birimleri ile insan hareketi tanıma

Dynamic Movement Primitives (DMPs)-originally a method for movement trajectory generation has been also used for recognition tasks. However there has not been a systematic comparison between other recognition methods and DMPs using human movement data. We have implemented a movement recognition method based on DMPs with Gaussians centered equally spaced in phase variable and scaled one-nearest-neighbor weight comparison. Furthermore, in thesis, we presented a comparison of commonly used Hidden Markov Model (HMM) based recognition with our implementation of DMP based recognition using human generated letter trajectories. As the working principles of these two methods are very different, in addition to the performance, the numbers of adaptable parameters that are used in each method and, process time were compared. The results indicate that DMP gives better results than HMM in the tests with noiseless data, noisy data and derogated data with given human movement dataset.

Handwriting recognitionPattern recognition
Alp Burak Pehlivan
Özyegin University · Institute of Graduate Studies in Science
2015
00
Master'sOpen AccessEN

Etkin beceri sentezi için eşzamanlı insan-robot öğrenmesi

It is generally expected that robots and autonomous agents will become a part of our daily lives in the coming decades. However, it is not feasible to program robots in advance for all possible tasks using classical robot programming. Therefore, intuitive and easy robot programming is one of the active research areas in robotics. We propose and implement a human-in-the loop robot skill synthesis that involves simultaneous adaptation of the human and the robot. In this framework, the human demonstrator learns to control the robot in real-time to make it perform a given task. At the same time, the robot learns from the human guided control creating a non-trivial coupled dynamical system. The research question we address is how this system can be tuned to facilitate faster skill transfer or improve the performance level of the transferred skill. At the beginning of the skill transfer session, the human demonstrator controls the robot exclusively as in teleoperation. As the task performance improves the robot takes increasingly more share in control, eventually reaching to full autonomy. The proposed framework is implemented and shown to work on some tasks such as physical cart-pole setup, cart-pole balance simulation, and mountain car. To assess whether simultaneous learning has advantage over the standard sequential learning (where the robot learns from the human observation but does not interfere with the control) experiments with two groups of subjects were performed. Moreover, reinforcement learning is applied to model a human demonstrator to verify simultaneous framework. The results indicate that the final autonomous controller obtained via simultaneous learning has a higher performance in the mentioned tasks.

Mohammad Alı Zamani
Özyegin University · Institute of Graduate Studies in Science
2015
00
Master'sOpen AccessEN

PL/SQL programları için otomatik prosedür gruplama

Large software systems have to be decomposed into separate, modular units for providing appropriate abstractions and improving maintainability. There exist clustering techniques that are applied to provide such abstractions by automatically grouping system modules based on dependencies among them. Hereby, dependency is usually measured as the extent to which a module refers to elements of another module. This approach cannot be directly applied for all types of programs. Some programs involve modules that are indirectly coupled. For instance, PL/SQL programs include procedures that are in most cases coupled due to their database operations although they do not make calls to each other. In this thesis, we provide an approach and a tool that supports automated modularization of software systems by considering this type of dependencies We also extend this approach for multiple, different types of dependencies. We construct several dependency matrices each of which captures a different type of dependency among the system modules. First, we perform clustering according to each of these matrices separately. Then, we perform cluster aggregation (meta clustering) on the obtained clustering results to propose a packaging structure to the designer. We performed two industrial case studies on real PL/SQL programs from the telecommunications domain. Many unexisted packages were proposed by our tool and the accuracy of the results were confirmed by domain experts.

Metin Altınışık
Özyegin University · Institute of Graduate Studies in Science
2016
00
Master'sOpen AccessEN

Boolean fonksiyonların işaret gösterimindeki terimlerin sıfırlanma düzenleri

Boolean functions (BF) are one of the fundamental concepts in discrete mathematics. It is possible to represent any BF by a unique polynomial when one takes -1 as True and 1 as False. Coefficients of the polynomial representing the given BF can be found with Lagrange interpolation. When the exact interpolation criterion is replaced with the signmatch criterion, one can find infinitely many sign representing polynomials for a given truth table. The problem of finding a minimum number of monomial set that is sufficient to represent a BF is a difficult mathematical problem. This thesis aims to contribute to its solution by investigating the zeroability patterns of monomials. To this end, we asked which monomials must be in a minimum sign representing polynomial. This question drove us to make numerical investigations on the BFs in lower dimensions. For all 3- and 4-variable BFs, we found all the monomial subsets, whose elements can be zeroed and we introduced a graph representation indicating whether particular pairs of monomials could be absent from any sign representation. In addition to the numerical investigations, we have also proved that if a three-element monomial set S, could not be absent altogether from the sign representation of a BF, then there must be at least a two element subset of S which could not be absent in any sign representation of that BF. We expect these results will give support to the development of heuristic algorithms to construct close-to-minimum number of monomial sign representing polynomials for BFs.

Boolean functions
Oytun Yapar
Özyegin University · Institute of Graduate Studies in Science
2017
00
Master'sOpen AccessEN

Sinerjik görev uygulaması için insan-robot işbirliği

There is great potential for human and robot to work together as a team, since this collaboration can take advantage of both human and robot capabilities, cover their weakness and yield a higher performance. We propose and implement a human-robot collaboration framework where, while the human tries to perform a task, the robot infers the human intention and assists the human in achieving the inferred goal. We explore how the human is influenced when (s)he interact with machine autonomy, and whether there is any advantage in task performance when human shares control with an autonomous agent. In particular, we investigate whether interacting with autonomy can aid humans to improve their performance in shorter time. We realized this collaboration system by designing a ball balancing task in which the goal is to move and balance the ball on a target position on a tray held by a robotic arm. The human performs the task by controlling the robotic arm with an interface which tilts the tray and moves the ball while the robot infers the target ball position by observing the trajectory of the ball, and augments the human control commands for assisting in task execution. The length of ball movement trajectory, completion time and positional error were chosen as the measures to evaluate the task performance. To assess the impact of our system on human learning and task execution a set of experiments were conducted under two conditions, human control condition where human performs the task alone and share control condition where both human and robot are involved in performing the task. 20 naive subjects were volunteered to perform the experiment in four continuous days. The result of these experiments suggests that not only the task execution can be improved in collaboration with robot compare to when the humans perform the task alone but also this collaboration system can make the human learning to progress faster.

Robot controlRobotics
Negın Amırshırzad
Özyegin University · Institute of Graduate Studies in Science
2017
00
Master'sOpen AccessEN

Robotik bir el üzerinde çevik manipülasyon

In robotics, flexible and the dexterous manipulation are one of the most desired type of skills. To this end, we investigate dexterous manipulation skills on an anthropomorphic robot hand. In the first part of the study, a sensorless grasping method is described. Although the high-precision sensing is highly relevant for precise grasps, precision is often not necessary to perform power grasps. An alternative approach is proposed for robotic grasping tasks based on external force estimation. Estimation accuracy is confirmed using a force sensor and the estimations are found to be useful for creating soft/power grasp behavior. In the second part, human-in-the-loop heterogeneous control for dexterous manipulation is investigated on a setup with a robotic hand and a robotic arm. The goal of the study is to experimentally verify that in tasks where the manual and explicit trajectory tuning is not possible, the autonomous movement can be learned by giving a basic policy to a robotic system, after which a human can learn and transfer an orthogonal complex part of the policy. The approach is shown on a ball swapping task in which a robotic arm is controlled by the human and a robotic hand is given an initial basic policy. In the results, we experimentally show that, in certain tasks, complex autonomous policies can be constructed by delegating the complex learning part to a human, the simple part to an autonomous agent, finally creating an autonomous control policy by recombining the parts.

Robot controlRobot handRobot arm+2
Osman Kaya
Özyegin University · Institute of Graduate Studies in Science
2017
00
Master'sOpen AccessEN

Çok ölçekli ikili benzerlik yüz tanıma için yerel ikili örüntü varyantı

Face recognition problem has been studying for more than four-decade, and many descriptors and neural network architectures were proposed. The aim is simple, extract features from the same subjects for training and test face image sets, if the proposed method was accurate, the extracted features categorized under the same label. However, the problem starts with the illumination effect on the images; the illumination effect may cause the extracted features for the same subject to be classified with the different labels. Therefore, illumination and other environmental impacts should be removed for accurate classification. One solution for eliminating environmental effect is using Local Binary Pattern (LBP) descriptor. LBP is an illumination invariant, computationally simple, and highly discriminative visual descriptor. Therefore, LBP based descriptors have been developing for more than a two-decade for solving face recognition problem. LBP′s computationally simple property make it applicable to different types of computer vision problems, also there are many examples of LBP variants either achieved state-of-the-art results in a particular application or complementary to the LBP. Having been inspired from the results, in this thesis, an LBP variant descriptor, Multi-scale Binary Similarity approach is proposed. MSBS encodes face image characteristic by analyzing the pixel relationships in selected components. The encoded features of the MSBS trained with Support Vector Machines (SVM) and tested with AT&T, Extended Yale B, Georgia Tech and MNIST datasets. The results show that MSBS outperforms most of the proposed approaches in the literature.

Support vector machinesImage classificationPrincipal components analysis+5
Ahmet Tavlı
Özyegin University · Institute of Graduate Studies in Science
2018
00
DoctorateOpen AccessEN

Nesnelerin interneti için semantik düzenleyici kurallar sistemi

With the proliferation of technology, connected and interconnected devices (hence- forth referred to as IoT) are fast becoming a viable option to automate the day-to-day interactions of users with their environments. However, with the explosion of IoT de- ployments we have observed in recent years, manually managing the interactions between humans-to-devices, and especially devices-to-devices, is an impractical task, if not an impossible task. This is because devices have their own obligations and prohibitions in context, and humans are not equipped to maintain a bird's-eye-view of the interaction space. Motivated by this observation, in this thesis, we propose a semantic policy framework that (a) supports representation of high-level and expressive user policies to govern the devices and services in the environment; (b) provides efficient procedures to refine and reason about policies to automate the management of interactions; and (c) delegates similar capable devices to fulfill the interactions, when conflicts occur. We then describe how to combine ontology-based policy reasoning mechanisms with in-use IoT applications to customize and automate device behaviors and discuss how the policy framework can be extended with data federation to handle diverse and distributed data sources. We demonstrate that smart devices and sensors can be orchestrated through policies in diverse settings, from smart home environments to hazardous workplaces, such as coal mines. Lastly, we evaluate our approach using real applications with real data and demonstrate that our approach is scalable under high load of data and devices.

Multiagent systems
Emre Göynügür
Özyegin University · Institute of Graduate Studies in Science
2018
00
Master'sOpen AccessEN

A unified framework for benchmarking sparse matrix-vector multiplication methods

Sparse matrix-vector multiplication (SpMV) is an important sparse linear algebra kernel that has a wide range of application domains, including computational science, graph analytics, machine learning and many more. Due to its significance, numerous studies have been conducted and are still being proposed to improve the performance of SpMV. Most of the studies evaluate the performance of their method in a custom experimental environment, which weakens the reproducibility of the empirical results, and also makes it hard to compare the proposed method to a wide range of existing methods. In this study, we address this problem by introducing an easy-to-integrate benchmarking framework that is able to unify SpMV methods in a single experimental environment to obtain consistent evaluation results. As a proof-of-concept, we have integrated several state-of-the-art CPU and GPU-based SpMV methods in our framework. We make the framework available as an open-source software for the convenience of researchers.

Erdem Sarılı
Özyegin University · Institute of Graduate Studies in Science
2019
00
DoctorateOpen AccessEN

Finite element analysis in a cloud computing environment

In this thesis, the challenges faced and lessons learned while establishing a large-scale high performance cloud computing service that enables online mechanical structural analysis and many other scientific applications using the finite element analysis (FEA) technique, will be described. Within an High Performance Computing (HPC) environment, several jobs with different demands can co-exist thus it becomes a challenge for the service provider to efficiently utilize its own resources while also satisfying the quality expectations of job submitters. Such a service is intended to process many independent and loosely-dependent tasks concurrently. In order to reach optimal job scheduling metrics each job type that can be submitted to the cluster must be carefully examined, its space and time characteristics must be well-understood and quantified. Challenges faced include accurate characterization of complex FEA jobs, handling of many-task mixed jobs, sensitivity of task execution to multi-threading parameters, effective multi-core scheduling within a single computing node, and achieving seamless scaling across multiple nodes. It is found that significant performance gains in terms of both job completion latency and throughput are possible via dynamic or "smart" batch partitioning and resource-aware scheduling compared to the naive Shortest Job First (SCF) and aggressively-parallel scheduling techniques. Chapter 3 of this thesis present an end-to-end discussion on the technical issues related to the design and implementation of a new cloud computing service for finite element analysis (FEA). Several design choices for HPC services at different layers of the cloud computing architecture are investigated to simplify and broaden its use cases. Investigations start with the software-as-a-service (SaaS) layer and compare parallel linear equation solvers. In order to minimize job latency and maximize the overall job throughput, several matrix characteristics are perceived. Developing such an understanding is also crucial for HPCaaS systems to automatically select the amount of computing resources per job. In following sections, the design of a ''smart'' scheduler that can dynamically select some of the required parameters, partition the workload and schedule it in a resource-aware manner will be demonstrated. Results showing that an up to 7.53x performance improvement over an aggressive scheduler using mixed FEA loads, will be presented. In addition to the performance studies, a complementary discussion on critical issues related to the data privacy, security, accounting, and portability of the cloud service will also be given. The new trend in engineering is to solve complex computational problems in the cloud over HPC services provided by different vendors. To further deepen the analyses of workloads representing HPC-related tasks in science and engineering, in chapter 4, performances of direct vs. iterative linear equation solvers are compared to help with the development of job schedulers that can automatically choose the best solver type and tune them (e.g. precondition the matrices) according to job characteristics and workload conditions that are frequently encountered on HPC cloud services. As a proof of concept, three classical elasticity problems will be used, namely a Cantilever beam, Lame problem and Stress Concentration Factor (SCF). These models theoretically represent many real-life mechanical situations in structural engineering, namely aerospace, automotive, construction and machinery industries. The representative linear problems are meshed with increasing granularities, which leads to various matrix sizes; largest having 1 billion non-zero elements. Detailed finite element analyses over an IBM HPC cluster are executed. First, a multi-frontal parallel is used, sparse direct solver and evaluate its performance with Cholesky and LU decompositions of the generated matrices with respect to memory usage, and multi-core, multi-node execution performances. As for the iterative solver, the PETSc library is used and carried out computations with several Krylov subspace methods (CG, BiCG, GMRES) and preconditioner combinations (BJacobi, SOR, ASM, None). Later in Chapter 4, the direct and iterative solver results are compared and contrasted in order to find the most suitable algorithm for varying cases obtained from numerical modeling of these three-dimensional linear elasticity problems. In addition to aforementioned studies, as a supplementary research, infrastructure-as-a-service (IaaS) layer for HPC is examined and characteristics like application performance, load isolation, and deployment speed issues using application containers (Docker) are observed. These characteristics are also compared to physical and virtual machines (VM) over a public cloud. For this purpose, HPC-specific deployment using application containers technology is evaluated and performance metrics are examined in order to contribute to evaluation of these technologies for job schedulers to be used on Cloud Computing infrastructures. This phase of the research focuses on the understanding the behavior of cloud computing infrastructures under circumstances where deployment and utilization of containers (Docker) with a chosen software is necessary. To summarize, this multi-disciplinary doctoral thesis covers most of the critical aspects and computational challenges of providing FEA in the cloud for structural mechanics including ease of deployment, batch-level performance, job-level isolation, financial accounting and content security. It utilizes several modern software tools and techniques, while also contributing new ones to the literature.

Nitel Muhtaroğlu
Özyegin University · Institute of Graduate Studies in Science
2019
00
DoctorateOpen AccessEN

Scalable analysis of large-scale system logs for anomaly detection

System logs provide information regarding the status of system components and various events that occur at runtime. This information can support fault detection, diagnosis and prediction activities. However, it is a challenging task to analyze and interpret a huge volume of log data, which do not always conform to a standardized structure. As the scale increases, distributed systems can generate logs as a collection of huge volume of messages from several components. Thus, it becomes infeasible to monitor and detect anomalies efficiently and effectively by applying manual or traditional analysis techniques. There have been several studies that aim at detecting system anomalies automatically by applying machine learning techniques on system logs. However, they offer limited efficiency and scalability. We identified three shortcomings that cause these limitations: i)Existing log parsing techniques do not parse unstructured log messages in a parallel and distributed manner. ii)Log data is processed mainly in offline mode rather than online. That is, the entire log data is collected beforehand, instead of analyzing it piece-by-piece as soon as more data becomes available. iii)Existing studies employ centralized implementations of machine learning algorithms. In this dissertation, we address these shortcomings to facilitate end-to-end scalable analysis of large-scale system logs for anomaly detection. We introduce a framework for distributed analysis of unstructured log messages. We evaluated our framework with two sets of log messages obtained from real systems. Results showed that our framework achieves more than 30% performance improvement on average, compared to baseline approaches that do not employ fully distributed processing. In addition, it maintains the same accuracy level as those obtained with benchmark studies although it does not require the availability of the source code, unlike those studies. Our framework also enables online processing, where log data is processed progressively in successive time windows. The benefit of this approach is that some anomalies can be detected earlier. The risk is that the accuracy might be hampered. Experimental results showed that this risk occurs rarely, only when a window boundary cross-cuts a session of events. On the other hand, average anomaly detection time is reduced significantly. Finally, we introduce a case study that evaluates distributed implementations of PCA and K-means algorithms. We compared the accuracy and performance of these algorithms both with respect to each other and with respect to their centralized implementations. Results showed that the distributed versions can achieve the same accuracy and provide a performance improvement by orders of magnitude when compared to their centralized versions. The performance of PCA turns out to be better than K-means, although we observed that the difference between the two tends to decrease as the degree of parallelism increases.

Open source softwareCloud computingBig data+5
Merve Astekin
Özyegin University · Institute of Graduate Studies in Science
2019
00
Master'sOpen AccessEN

Clothing image retrieval with triplet capsule networks

Clothing image retrieval has become more important after some major developments in Computer Science and the emergence of e-commerce. Recent studies generally attack this problem by using Convolutional Neural Networks (CNNs). Despite their popularity, CNNs, by nature, have some intrinsic limitations such as losing the hierarchical spatial relationship between the parts of an image, and not being robust to affine transformations. Most recently proposed network architecture, namely Capsule Networks, has the ability to overcome these limitations by preserving the part-whole relationship and pose information in the images. In this thesis, we investigate in-shop clothing retrieval performance of densely-connected Capsule Networks with dynamic routing. To achieve this, we propose Triplet-based designs of Capsule Network architecture with two different feature extraction methods: Stacked-convolutional (SCCapsNet) and Residual-connected (RCCapsNet) Capsule Networks. Experimental results of our proposed designs on in-shop clothing retrieval show that SCCapsNet achieves 32.1\% Top-1, 81.8\% Top-20, and 90.0\% Top-50 recall-at-K scores; whereas RCCapsNet has even better performance with 33.9\% Top-1, 84.6\% Top-20, and 92.6\% Top-50 recall-at-K scores. These figures demonstrate that both of our designs outperform the baseline study and the earlier approaches by a wide margin without using any extra supportive information besides to the images. Moreover, when compared to the SOTA architectures on clothing retrieval, our proposed Triplet Capsule Networks achieve comparable recall rates with only half of the parameters used in the SOTA architectures. In the future, our designs may inherit extra performance boost due to advances in the relatively new Capsule Network research.

Image retrievalDigital image processingArtificial neural networks+1
Osman Furkan Kınlı
Özyegin University · Institute of Graduate Studies in Science
2019
00
Master'sOpen AccessEN

Teşvik odaklı ve mahremiyete dayalı bilgi paylaşımı için etmen temelli müzakere

While customizing their services, companies usually use their users' data. According to the new regularization, it is required to get the permission of their users to be able to store and share their users' private data. The current approaches rely on requesting access rights by providing some incentives. The customers can only accept or reject the possible incentive offered by the companies exchange for giving access rights. This thesis introduces an agent-based, incentive-driven, and privacy-preserving information sharing framework. One of the main contributions of this thesis is to give the data provider agent an active role in the information sharing process and to change the currently asymmetric position between the provider and the requester of data and information (DI) to the favor of the DI provider. Instead of a binary yes/no answer to the requester's data request and the incentive offer, the provider may negotiate about excluding from the requested DI bundle certain pieces of DI with high privacy value, and/or ask for a different type of incentive. We show the presented approach on a use case and conduct a user experiment. Questionnaire responses showed that participants like the idea of negotiation on their information sharing policies with the companies. Furthermore, this thesis proposes an acceptance strategy using deep reinforcement learning for automated negotiating agents. In the automated negotiation literature, most of the acceptance strategies are based on some predefined rules. In contrast, this thesis proposes to use reinforcement learning in order to learn when to accept opponent's offer. Our experimental evaluation shows that the developed acceptance strategy performed as well as AC-Next acceptance strategy.

Yousef Razeghı
Özyegin University · Institute of Graduate Studies in Science
2019
00
Master'sOpen AccessEN

Embedding-based clustering for target specific stances

We propose an unsupervised user stance detection method to capture fine grained divergences in a community across various topics. We employ pre-trained universal sentence encoders to represent users based on the content of their tweets on a particular topic. User vectors are projected onto a lower dimensional space using UMAP, then clustered using HDBSCAN. Our method performs better than previous approaches on two datasets in different domains, achieving precision and recall scores ranging between 0.89 and 0.97. We compiled a dataset of more than 300k tweets about UEFA Super Cup's 2019 final, and tagged 12k users as Liverpool FC or Chelsea FC fans. We utilized our method to analyze the stances of Twitter users noting a correlation between user stances towards various polarizing issues. We used the resultant clusters to quantify the polarization in various topics, and analyze the semantic divergence between clusters.

Ammar Raşid
Özyegin University · Institute of Graduate Studies in Science
2020
00
Master'sOpen AccessEN

A novel method for automatic fish counting based on machine learning using morphological features

This thesis offers a machine learning based computer vision approach for counting fish in a non-stop running narrow water stream (or equally on a conveyor belt or similar mechanism) in a fish farm. We call this "continuous operation". Such setup requires that counting is done extremely fast, which we call "real-time" operation. To our knowledge, our fish counting solution is the only such method, namely, continuous and real-time. The hardest subproblem here is correctly counting "overlapped fish" and yet be flexible in terms of fish sizes. Most of the previous works are not real-time due to their inefficient approach to counting overlapped fish. Our superiority in speed mostly stems from selecting fewer and computationally less expensive morphological features (which we feed to machine learning). Although the state-of-the-art is pretty accurate (98.9%), we were able to improve it to 99.4% for even very difficult test cases. Since our solution is continuous unlike previous work in the literature, we had to also solve the problem of "merging fish" (overlapped or not) lying at the boundary of consecutive frames.

Image processing-computer assistedDigital image processing
Ahad Aghapour
Özyegin University · Institute of Graduate Studies in Science
2020
00
Master'sOpen AccessEN

Familiarity effect on human-agent negotiations

Artificial Intelligence has changed our world in various ways. People have started to interact with a variety of intelligent systems on a daily basis. As the interaction between human and AI systems increases day by day, the factors influencing their communication have become more and more important especially in the field of human-agent negotiation. Therefore, it is necessary to study the factors affecting human-human negotiation while designing agents negotiating with their human counterparts. As familiarity is one of these factors, this work aims to investigate the effect of familiarity on human-agent negotiation so that we can design more effective negotiation systems. Being familiar to other party may influence how we interact and hence the process and outcome of the negotiation. Our hypothesis is that negotiating with a familiar opponent would create a difference in terms of negotiation process and outcome. In order to study this effect in human-agent negotiations, we developed negotiation framework in which human participants negotiate with an avatar in a bilateral fashion. To measure the effect of the appearance familiarity in negotiation, two control variables are defined: negotiating with a celebrity avatar and negotiating with a non-celebrity avatar. In order to avoid the learning effect, we adopt a between-subject experiment design. We recruited 67 participants and analyzed their negotiation data elaborately as well as their subjective opinions specified in the questionnaires. Our experimental results showed that being familiar with the opponent affected both negotiation process and outcome. Particularly, human participants had a tendency to be more collaborative when their opponent is a celebrity avatar versus a non-celebrity avatar.

Intelligent agentsHuman-computer interaction course
Berkay Türkgeldi
Özyegin University · Institute of Graduate Studies in Science
2020
00
Master'sOpen AccessEN

X-ray analysis prediction of BGA components in PCBA production with neural networks

Printed circuit boards are the most important part of all electronic devices used today, and the production of these boards consists of many critical processes. Assembly production lines include different inspection machines such as Solder Paste Inspection (SPI), Automatic Optical Inspection (AOI), X-Ray Inspection Device to detect defects and misplaced components on the circuit boards. SPI and AOI machines determine these problems by checking that different measurement values remain between certain threshold values, but these machines cannot provide a perfect detection mechanism since threshold values are determined by a maintenance technician by trial and error. Therefore, the circuit boards are also controlled by X-Ray Inspection machines, thus the solder paste that cannot be inspected visually by human can be easily inspected. This project aims to create a neural networks model that uses SPI and AOI measurement parameters as input features and predicts potentially defective boards before the boards go through X-Ray inspection. This model allows suspicious circuit boards to be tested in X-Ray Inspection machine, instead of testing of some circuit boards randomly. Thus, the number of X-ray devices required to test the boards is reduced, the circuit boards to be selected for sampling are selected from the boards that are likely to be defective rather than randomly selected. By virtue of this model, suspicious solders and components will be marked on the boards that will be sent to X-Ray test station as suspicious and the operator will be prevented from missing the defects that may occur in these areas. It is foreseen that this system will also identify contact without connection defects, also known as head-in-pillow defects, which cannot be detected in SPI, AOI and Functional Verification Test (FVT) processes, thus the quality of the boards produced is likely to increase. The data will be collected for 17MB170R4 model circuit boards, which are the main board of televisions, produced in one of the production lines at Vestel Electronics Factory, and the model will be applied for four BGA elements on this board. In this project, it is aimed to work on BGA elements because the solder areas of these elements cannot be inspected visually after the component is placed on the board. Due to the model, it is possible to detect most of the defective boards by applying X-Ray testing to only 1% of all circuit boards produced.

Bayram Yurdakurban
Özyegin University · Institute of Graduate Studies in Science
2021
00
Master'sOpen AccessEN

Uncertainty assessment for speaker verification systems using a bayesian approach

The Automatic Speaker Verification (ASV) systems are developed to discriminate the genuine speakers from the spoofing attacks and they are also used as a security application in various industries (e.g., Banking and telephone-based systems). The spoofing countermeasure systems (SCS) are important for the ASV systems to protect themselves against spoofing attacks. In general, the SCSs are developed using the cross entropy loss function and the softmax classification layer to perform the best classification scores. Even though the softmax function is popularly used as a classification layer for the deep neural network tasks, it increases the uncertainty of the estimated class probabilities by squishing the probabilistic predictions of the predictive models. The aim of this work was to decrease uncertainty of the conventional cross entropy metrics and softmax function SCS by using the Bayesian approach. To accomplish this, multiple SCSs were developed to outperform the base system of the Automatic Speaker Verification Spoofing and Countermeasures 2017 Challenge. The Bayesian approach was applied to the best model (e.g., the model which performed the lowest EER score) to decrease the uncertainty of the conventional cross entropy metrics and softmax function SCS. The uncertainty of the both systems were compared with the probability distribution function, AUC value and the ROC curve. As it can be observed from the ROC curve, the Bayesian network decreased the uncertainty of the conventional cross entropy metrics and softmax function SCS by increasing AUC value 14%. Also the Bayesian network has provided the lowest EER score (16.79%) by outperforming the base system of the ASV spoof 2017 challenge.

Çağıl Süslü
Özyegin University · Institute of Graduate Studies in Science
2021
00
Master'sOpen AccessEN

Sparse voxel based 3D object detectionfrom RGB-D data

Accurate and fast 3D object detection plays a role of paramount importance for safe and capable autonomous machines. LiDAR point cloud based methods have demonstrated impressive results, yet expensive LiDAR sensors make such approaches infeasible for wide-scale adaptation. Camera based methods on the other hand are performing sub-optimally given safety and accuracy requirements. Traditionally, camera based 3D object detection is performed by generating pseudo-LiDAR point clouds from RGB-D data and using point-cloud based methods, however, irregular nature of point cloud data representation makes it challenging to exploit spatial local correlations on 3D space and point cloud based methods generally suffer from this. We propose Sparse Voxel based 3D Object Detection, our approach differs from traditional approaches by converting point cloud information to sparse voxel grid and utilizing sub-manifold sparse convolutions to extract information instead of PointNet based models. Our approach not only outperforms its point-cloud based counterparts with a wide margin but also comes with the advantage of being efficient to compute.

Eren Balatkan
Özyegin University · Institute of Graduate Studies in Science
2021
00
Master'sOpen AccessEN

Otomatikleştirilmiş ikili pazarlıklarda ilişkisel ve frekansçı rakip modelleme yaklaşımları

This thesis mainly focuses on the problem of learning opponent's preferences during the negotiation in bilateral automated negotiation in which agents negotiate with each other to reach an agreement. Accordingly, it addresses the problems with the classical frequentist approach and advances the state-of-the-art in opponent modeling in automated negotiation by introducing a novel frequency opponent modeling mechanism, which updates some of the assumptions introduced by classical frequency approaches. Moreover, this thesis also proposes adopting association rule mining techniques to learn the opponent's preferences in bilateral negotiation. An extensive evaluation of those proposed approaches shows that the proposed approaches outperform the classical frequency model. In addition, this thesis argues that while optimizing one's utility function is essential, agents in a society should not ignore the opponent's utility in the final agreement to improve the agent's long-term interests in the system. It aims to show whether or not it is possible to design a social agent (i.e., one that aims to optimize both sides' utility functions) while performing efficiently in an agent society. Accordingly, we propose a social agent supported by a portfolio of strategies, a novel tit-for-tat concession mechanism, and a frequency-based opponent modeling mechanism capable of adapting its behavior according to the opponent's behavior and the state of the negotiation. The results show that the proposed social agent does not only maximize social metrics such as the distance to the Nash bargaining point or the Kalai point but also is shown to be a pure and mixed equilibrium strategy in some realistic agent societies.

Multiagent systems
Okan Tunalı
Özyegin University · Institute of Graduate Studies in Science
2021
00
Master'sOpen AccessEN

Acil sağlık sistemleri için blockchain tabanlı güvenlik mekanizması

Elektronik sağlık kayıtları (ESK'ler) günümüz sağlık endüstrisinde çok önemli bir rol oynamaktadır, bu kayıtlar güvenlik ve gizliliğin ihlaline açık hassas ve özel sağlık veri varlıklarını içermektedir. Bu olası veri ihlallerinin hastanın mahremiyetinin ihlali, ESK'ye yetkisiz erişim, veri değişikliği ve hastanın hayatını tehlikeye atma gibi birçok sonucu olabilir. Son zamanlarda önerilen ESK sistemleri, hastanın güvenliğini korumak için güçlü güvenlik özellikleri ile birlikte geliyor. Ancak, Kişisel Sağlık Kayıtlarına (KSK'ler) erişim kontrolü yönetimi ile ilgili hala sorunlar bulunmaktadır. Daha önce sunulan sistemlerde, sisteme erişimi kontrol etmede hasta ana rolü oynar, ve bu acil durumlarda bir belirsizliğe yol açarken, hasta herhangi bir erişim izni veremez. Bu çalışmada, Hyperledger Sawtooth blockzincir ile tasarlanan güvenli ve özel bir erişim kontrol mimarisi sunarak acil durumlarda tıbbi sağlık kayıtlarının (TSK'ler) tutulması için yeni bir çerçeve öneriyoruz. Blok zincirinin benzersiz özelliklerinden yararlanan sistemimiz, acil bir senaryoda hastanın tıbbi verilerine kısa sürede güvenli bir erişim sağlar. Simülasyonumuzun sayısal sonuçları, yanıt süresi, bellek tüketimi, verim, genel gizlilik ve güvenlik açısından benzer sağlık sistemleriyle karşılaştırıldığında önerilen mimarimizin performansının daha iyi olduğunu ve kullanılabilirleğini gösterir.

Elnaz Dadvar
Özyegin University · Institute of Graduate Studies in Science
2021
00
Master'sOpen AccessEN

Motor kontrol ve beynin bilişsel karar verme mekanizmalarını analiz etmek üzere tersine pekiştirmeli öğrenme ile keşifler

Reinforcement Learning is a framework for generating optimal policies given a task and a reward/punishment structure. Likewise, Inverse Reinforcement Learning, as the name suggests, is used for recovering the reasoning behind an optimal policy based on demonstrations from an expert. We set out to explore whether recent Reinforcement Learning and Inverse Reinforcement Learning methods can serve as a computational tool for investigating optimality principles of motor control and cognitive decision-making mechanisms of the brain. For this purpose, we have targeted several different tasks involved with different parts of the sensorimotor learning mechanism of the brain. We aim to recover the optimality principles employed by the brain for various control and decision-making tasks. If this is achieved, we can analyze, understand, mimic and improve demonstrated behavior with less bias, which we hope is a step forward in understanding the process of learning in both human-based and artificial systems. For the scope of this thesis, we have evaluated two tasks. The first task was investigating the applicability of perceptual development for Reinforcement Learning. For this task, we have proposed a perceptual development based learning regime for a Reinforcement Learning agent, and the results obtained suggest that a suitable perceptual development regime may improve the learning progress and yield better-performing agents. The second task was to predict reward function parameters of a provided trajectory in a standing up under perturbation scenario. For this task, we have proposed two different Inverse Reinforcement Learning approaches. Our results indicate that we were able to infer valid reward parameters on synthetic data.

Machine learningArtificial neural networksArtificial intelligence
Emir Arditi
Özyegin University · Institute of Graduate Studies in Science
2021
00
Master'sOpen AccessEN

Kendinden denetimli derin öğrenme ile multispektral görüntü eşleştirme

This thesis presents a self-supervised deep learning framework for multispectral image matching, addressing the core challenges posed by nonlinear radiation distortions (NRDs), viewpoint variations across spectral modalities, and the scarcity of annotated datasets. Existing methods often exhibit strong modality dependence and rely heavily on costly supervision, such as depth maps or calibrated camera poses, thereby limiting their generalizability across diverse spectral domains. The framework introduces an improved self-supervision strategy—Improved Multispectral Homographic Adaptation—that enhances pseudo ground truth keypoint generation in cross-spectral settings while ensuring invariance to viewpoint changes. By incorporating a spectrum-aware windowing rule, this method increases both the repeatability and the density of detected keypoints under spectral differences, thereby improving matching performance. This enhancement ultimately leads to more accurate multispectral image registration and is validated on UAV-acquired visible–thermal datasets. Building on this self-supervision strategy, the XPoint framework is proposed as a modular and fully self-supervised image matching architecture. It integrates a pretrained VMamba encoder for robust, modality-invariant feature extraction, alongside lightweight decoder heads for keypoint detection, feature description, and homography regression. This design enables efficient, label-free learning from aligned image pairs and facilitates rapid adaptation across diverse spectral modalities. The framework is designed to be scalable and easily adaptable, requiring no additional supervision beyond image pair alignment. The approach is evaluated across five public benchmarks spanning VIS-TH, VIS-NIR, VIS-LWIR, VIS-SAR datasets. Experimental results demonstrate competitive or superior performance in feature matching and multispectral image registration tasks, while maintaining high computational efficiency. This progression—from spectrum-aware self-supervision to a generalizable matching framework—positions XPoint as a practical solution for real-world multispectral applications, particularly in environments characterized by limited supervision and high spectral variability.

İsmail Can Yağmur
Özyegin University · Institute of Graduate Studies in Science
2025
00