LEE- Bilgisayar Mühendisliği Lisansüstü Programı
Bu topluluk için Kalıcı Uri
Gözat
Sustainable Development Goal "none" ile LEE- Bilgisayar Mühendisliği Lisansüstü Programı'a göz atma
Sayfa başına sonuç
Sıralama Seçenekleri
-
ÖgeClassification of melanoma malignancy in dermatology(Lisansüstü Eğitim Enstitüsü, 2021) Gazioğlu, Bilge Süheyla ; Kamaşak, Mustafa Ersel ; 709938 ; Bilgisayar MühendisliğiCancer has become one of the most common diseases all over the world in recent years. Approximately 40% of all incidences is skin cancer. The frequency of sightings of skin cancer has increased by 10 times in the last 50 years, and the risk of developing skin cancer is about 20%. Skin cancer has symptoms such as abnormal tissue growth, redness, pigmentation abnormalities and nonhealing wounds. Melanoma is a rare type of skin cancer with higher mortality compared to other types of skin cancers. Melanoma can be defined as a result of uncontrolled division and proliferation of melanocytes. Worldwide, melanoma is the 20th most common cancer and there are an estimated 287,723 new cases (1.6% of all cancers). In USA, more than two hundred thousand new cases of melanoma were diagnosed in 2021 and it increases more rapidly than other forms of cancer. Melanoma incidence increased up to 237% in the last 30 years. In our country, Turkey, melanoma is relatively rare compared to the other countries. Cancer cells display a rapid grow and systematic spread. As in all types of cancer, early diagnosis is of great importance for the treatment of skin cancer. Early diagnosis improves treatment success and prognosis. To detect a melanoma, changes in color, shape and structure of the skin, swelling and stains on the skin are carefully examined by the physicians. Besides the physician investigation, computer aided diagnosis (CAD) mechanisms are recommended for early diagnosis. In this thesis, deep learning models have been used to determine whether skin lesions are benign or malignant melanoma. The classification of the lesions is considered from two different points of view. In the first study, effect of objects in the image and image quality on classification performance was examined by using four different deep learning models. In addition, sensitivity of these models was tested. In the second study, it was aimed to establish a pre-diagnosis system that could help dermatologists by proposing a binary classification (benign nevi or malignant melanoma) mechanism on the ISIC dataset. In clinical settings, it is not always possible to capture flawless skin images. Sometimes skin images can be blurry, noisy, or have low-contrast. In other cases, images can have external objects. The aim of the first study is to investigate the effects of external objects (ruler, hair) and image quality (blur, noise, contrast) using widely used Convolutional Neural Networks (CNN) models. Classification performance of frequently used ResNet50, DenseNet121, VGG16 and AlexNet models are compared. Resilience of the mentioned models against external objects and image quality was examined. Distortions in the images are discussed under three main headings: Blur, noise and contrast changes. For this purpose, different levels of image distortions were obtained by adjusting different parameters. Data sets were created for three different distortion types and distortion levels. Firstly, the most common external object in skin images is hair on skin. In addition, rulers are commonly used as a scale for suspicious lesions on skin. In order to determine the effect of external objects on lesion classification, three separate test sets were created. These sets consist of images containing a ruler, hair and no external object (none). The third dataset consists only of mole (lesion) images. With the three datasets, four models were trained and their classification performances were analyzed. In fact, the best result was expected to be classified with a higher accuracy of the dataset that did not contain any object except the lesion. However, when the results are analyzed, since the image set containing hair had the highest number of images in the total dataset, the best classification performance in our system was measured by using DenseNet model on this subset. As a result of these tests, ResNet model showed a better classification performance compared to other models. Melanoma images can be better recognized under contrast changes unlike the benign images, we recommend ResNet model whenever there is low contrast. Noise significantly degrades the performance on melanoma images and the recognition rates decrease faster compared to benign lesions in noisy set. Both classes are sensitive to blur changes. Best accuracy is obtained with DenseNet model in blurred and noisy datasets. The images contain ruler has decreased the accuracy and ResNet has better performance in this set. Hairy images have the best success rate in our system since it has the maximum number of images in total dataset. We evaluated the accuracy as 89.22% for hair set, 86% for ruler set and 88.81% for none set. We can infer that DenseNet can be used for melanoma classification with image distortions and degradations. As a general result of the first study, we can conclude that DenseNet can be used for melanoma classification since it is more resistant to image distortion. In recent years, deep learning models with high accuracy values in computer aided diagnosis systems have been used frequently in biomedical image processing research area. Convolutional neural networks are also widely used in skin lesion classification to increase classification accuracy. In another study discussed in this thesis, five deep learning models were discussed in order to classify the images in the specially created skin lesions dataset. The dataset used in this study consists of images from ISIC dataset. In the dataset which is available in 2020, there are two classes of benign and malignant and three diagnosis consist of nevus, melanoma and unknown. We only considered images with nevus and melanoma diagnosis. Dataset had 565 melanoma and 600 benign lesion images in total. We separated the 115 images for the class of malignant melanoma and 120 images for the benign nevi class as our test set. The rest of the data was used for model training. With pre-processing methods such as flipping and rotation, the training dataset has divided into 5 parts and the number of images in the train set was increased. DenseNet121, DenseNet161, DenseNet169, DenseNet201, ResNet18, ResNet50, VGGNet19, VGGNet16_bn, SqueezeNet1_1, SqueezeNet1_0 and AlexNet models were trained with each subset. Using these models an ensemble system was designed. In this system, results the models were combined with the majority voting method. The accuracy of the proposed model is 95.76 % over the data set.
-
ÖgeCompression of geometry videos by 3D-SPECK wavelet coder(Lisansüstü Eğitim Enstitüsü, 2021) Bahçe Gülbak, Canan ; Bayazıt, Uluğ ; 723134 ; Bilgisayar MühendisliğiA geometry image represents a manifold surface in 3D space as an 2D array of 3D points. This involves 3 steps : First, cutting the manifold which essential defines the boundary of the square, second, defining the parametrization which defines the interior of the square and lastly, rasterizing and scan converting the geometry and applying compression to it. By representing manifold 3D objects using a global 2D parametrization (mapping) it is possible to use existing video techniques to represent 3D animations. 2D-SPECK coder, discovered by Islam and Pearlman, codes sets of DWT coefficients grouped within subbands. SPECK coder is different from the other schemes in that it does not use trees which span and also exploits the similarity accross different subbands. It makes use of sets in the form of blocks. The main idea is to exploit the clustering of energy in frequency and space in the hierarchical structures of wavelet transformed images. 3D-SPECK coder, is an extension of the 2D-SPECK algorithm for compressing 3D data with high coding efficiency. A geometry video is formed as a sequence of geometry images where each frame is a remeshed form of a frame of an animated mesh sequence. For efficiently coding geometry videos by exploiting temporal as well spatial correlation at multiple scales, this thesis proposes the 3D-SPECK algorithm which has been successfully applied to the coding of volumetric medical image data and hyperspectral image data in the past. The thesis also puts forward several postprocessing operations on the reconstructed surfaces that compensate for the visual artifacts appearing in the form of undulations due to the loss of high frequency wavelet coefficients, cracks near geometry image boundaries due to vertex coordinate quantization errors and serrations due to regular or quad splitting triangulation of local regions of large anisotropic geometric stretch. Experimental results on several animated mesh sequences demonstrate the superiority of the subjective and objective coding performances of the newly proposed approach to those of the commonly recognized animated mesh sequence coding approaches at low and medium coding rates.
-
ÖgeDinamik ortamlar için istatiksel metotlar kullanan çoklu evrimsel algoritmalar(Lisansüstü Eğitim Enstitüsü, 2022-09-19) Gazioğlu, Emrullah ; Uyar, Ayşe Şima ; 504152518 ; Bilgisayar MühendisligiGerçek dünyada karşılaştığımız birleşimsel (ing: combinatorial) optimizasyon problemleri doğası gereği dinamik bir yapıya sahiptir. Dinamik ortamlarda bulunması gereken optimum nokta zamanla değişeceğinden, sezgisel yaklaşımlar ancak bu ortamlara iyi adapte edilirse başarılı olabilir. Çevresel değişiklik, optimizasyon algoritmalarının her iki tarafında da (kısıtlar ve/veya amaç fonksiyonu) meydana gelebilir. Değişikliği ele almanın en basit yolu, algoritmayı yeniden başlatmaktır. Ancak, yeni optimal çözüm öncekinden çok uzak olmayabilir. Bu nedenle, yeniden başlatma fikri kullanışlı değildir. Bunun yerine, şimdiye kadar edinilen bilgiler mevcut ortama uyum sağlamak için faydalı olabilir. Bu uyarlamayı gerçekleştirmek için bazı dinamik ortam kriterleri dikkate alınmalıdır: (i): değişim sıklığı, (ii): değişikliğin şiddeti, (iii): döngü uzunluğu/döngü doğruluğu, (iv): değişimin öngörülebilirliği. Yukarıda bahsedilen problemleri ele alabilmek için literatürde hem deterministik hem de sezgisel yöntemler kullanılmıştır. Bu yöntemler yetersiz kalınca Metasezgisel algoritmalar kullanılmaya başlanmıştır. Genetik Algoritmalar, Metasezgisel algoritmaların, Evrimsel Algoritmalar alt sınıfına düşen ve türlerin doğadaki biyolojik evriminden ilham alan çok popüler optimizasyon algoritmalarıdır. GA'lar, literatürdeki büyük başarılarına rağmen, değişen ortamlarda genetik çeşitliliklerini kaybederler. Bunun nedenleri olarak şunları söyleyebiliriz: (i): faydalı çözümleri kaybetmek ve (ii): problemin değişkenleri arasındaki ilişkileri kullanamamak. Bu tezde, birinci sorun için, bir çoklu kromozom yapısı uygulanarak bir örtük bellek şeması geliştirilmiştir. İkinci sorun için, problemin değişkenleri (bir kromozomdaki genler olarak da bilinir) arasındaki ilişkilerden yararlanmak için bir Bayes Ağı kullanımıştır. Epistasis, gerçek biyolojik hayatta bir kromozomdaki genlerin etkileşimi anlamına gelir. Daha açık olarak, bir genin etkisi, başka bir genin/genlerin varlığına veya yokluğuna bağlıdır. Bu tezde, genlerin etkileşimlerinden faydalanmak için, çoklu gösterilimin yanı sıra, iyi bilinen bir Dağıtım Tahmini Algoritması olan Bayesçi Optimizasyon Algoritması, önerilen algoritmaya enjekte edilmiştir. Bu tezde, dinamik ortam optimizasyon problemleri ile baş edebilmek için GA tabanlı istatistiksel metotlar kullanan çok kromozomlu bir algoritma önerilmiştir. İlk olarak, örtük bir bellek şeması elde etmek için GA'ya çoklu gösterilim eklenmiştir. Genetik operatörler örtük bellek üzerinde icra edilirken uygunluk değeri hesaplamaları çözüm adaylarının fenotipleri üzerinden yürütülmüştür. Ayrıca, önerilen algoritmanın varyantları literatürde önceden tanıtılmış olan bazı göçmenlik yöntemleri kullanılarak oluşturulmuş, farklı parametre değerleri ile nasıl davrandıkları gözlenmiştir. Önerilen algoritmayı test etmek için üç farklı problem çözülmüştür: Ayrıştırılabilir Birleşim Tabanlı Fonksiyonlar, Dinamik Sırt Çantası Problemi ve Çok boyutlu Sırt Çantası Problemi. Ayrıştırılabilir Birleşim Tabanlı Fonksiyonlar, çeşitli karmaşıklık düzeyleri içerdikleri için dinamik optimizasyon problemlerinde sıkça kullanılan kıyaslama problemleridirler. Bu fonksiyonlarda her bir çözüm adayı dört bitlik bölümlere ayrılır ve her bölümün uygunluk değerleri ayrı ayrı hesaplandıktan sonra bulunan değerler toplanıp çözüm adayının genel uygunluk değeri bulunur. Sırt Çantası Problemi, bilgisayar bilimlerinde sıkça karşılaşılan bir problem formatıdır. Bu problemde, pahada (getirisi) ağır, yükte hafif nesnelerin toplanması hedeflenmekte ve bunu yaparken getiriyi maksimuma çıkarırken yükü minimumda tutmaya çalışılır. Gerçek dünya problemleri üzerindeki etkilerini görmek için bu problemin dinamik versiyonu çözüldü. Finansal yönetim ve endüstride, birçok gerçek dünya sorunu bu problem ile ilgilidir. Örneğin, kargo yükleme, üretim planlaması, sermaye bütçelemesi, proje seçimi ve portföy yönetimi bu problem ile çözülebilen örneklerdir. Çok boyutlu Sırt Çantası Problemi, normal versiyonundan farklı olarak, birden fazla kaynak içeren ve her bir kaynağın kendine ait kısıtları olan versiyonudur. Bu problem, tek bir kısıt yerine kaynak sayısı kadar kısıt olduğundan çözülmesi daha zordur. Yukarıda bahsedilen problemleri çözmek için iki farklı dinamik ortam yöntemi kullanılmıştır. Bunlardan birincisi XOR jeneratörü, diğer ise Normal Dağılım metotu ile yeni veri setleri oluşturmaktır. Sonuç olarak, bu tezde, dinamik optimizasyon problemlerini çözmek için hem istatistiksel bir yöntem hem de örtük bir bellek şeması kullanan bir GA önerilmiştir. Önerilen yöntemin dinamik ortamlardaki davranışını izlemek için üç farklı problem çözülmüştür. Daha sonra performansı literatürdeki en yeni bir yöntem ile karşılaştırılmıştır. Sonuçlar, önerilen yöntemin dinamik optimizasyon problemlerini çözmede oldukça etkili olduğunu göstermiştir.
-
ÖgeEtmen tabanlı bir anlamsal süreç çalışma ortamının geliştirilmesi(Lisansüstü Eğitim Enstitüsü, 2021) Kır, Hüseyin ; Erdoğan, Takuhi Nadia ; 672532 ; Bilgisayar MühendisliğiKurumsal bilişim sistemleri alanı, uzun bir süre boyunca, kurumsal veriyi merkeze alan ve onun yönetimine odaklanan veri odaklı bilişim sistemleri tarafından hükmedilmiştir. Fakat zamanla bilginin de diğer üretim enstrümanları gibi kurumların hedeflerine ulaşmak için tükettikleri ve ürettikleri ara ürünler olduğu, asıl odaklanılması gereken bakış açısının üretimi sağlayan işlevler olduğu algısı yaygınlaşmaya başlamıştır. Bu yaklaşım ile, kurumsal veri/bilgi önemini korurken, merkeze iş süreçleri alınarak iş süreci yönetim sistemleri (İSYS) ortaya çıkmıştır. İSYS'ler kurumsal işleyişi temsil eden süreç modellerini girdi olarak alan ve katılımcıların eş güdümlü bir şekilde çalışmasını sağlayarak üretim süreçlerinin etkinliğini ve üretkenliğini arttırmayı hedefleyen genel yazılım sistemleridir. Bu sistemler zamanla gelişerek tüm süreç yaşam döngüsünü (tasarım, işletim, izleme, analiz ve iyileştirme) destekleyecek işlevselliklere erişmiştir. Geleneksel olarak İSYS'ler yönetmelikler ile detaylı bir şekilde tanımlanmış, öngörülebilen ve tekrarlanabilen süreçlerin modellenmesine ve işletilmesine odaklanmıştır. Bu süreçlerdeki olası tüm iş akışları tamamen bilinmektedir ve süreç katılımcılarının verebileceği kararlar önceden öngörülmektedir. Halihazırda, bu tür süreçler kurumsal süreçlerin büyük çoğunluğunu oluşturmaktadır. Ne var ki, kurumların %16'sı önceden öngörülemeyen olaylardan dolayı iş süreçlerini anlık olarak değiştirmek zorunda kaldıklarını, %10'u ise bazı süreçlerinin günlük olarak değiştiğini belirtmektedir. Aslen bu süreçler, mevcut İSYS'lerin yönetmekte yetersiz kaldığı, bilgi yoğun ve sanatsal süreçlerdir. Bilgi yoğun süreçler (BYS), yürütülmesi ve yönetilmesi çeşitli bilgi güdümlü karar verme görevlerini yerine getiren bilgi çalışanlarına bağlı olan süreçlerdir. Bu süreçler genelde üst seviyede bir iş akışına sahiptirler ama bu akışın detayları, dolaylı bir şekilde, sadece iş uzmanı tarafından bilinmektedir. Bu süreçler, formal bir süreç modeli ile ifade edilememekle beraber çoğu zaman yazılı bile değillerdir. Bilgi yoğun süreçlere örnek olarak enerji uzmanının bir hidroelektrik santrali projesini değerlendirme süreci örnek verilebilir. İş uzmanı, sunulan yapılabilirlik çalışmasının değerlendirilmesi, kamulaştırmaların gerekliliği ve uygunluğu, beklenen üretim projeksiyonlarının gerçekçiliği ve talep ile tutarlılığı gibi bir çok tecrübeye dayalı incelemeyi, duruma göre diğer iş uzmanlarına da (hukuk, planlama vb.) danışarak, süreci ilerletmektedir. Sürecin akışı tamamen anlık ihtiyaçlar doğrultusunda, iş uzmanının tecrübesi ile ortaya çıkmaktadır ve her değerlendirme süreci farklı bir akışa sahip olabilmektedir. Süreç yönetimi araştırma alanı, gelecekte sanal organizasyonların kurulacağı, dünyanın farklı yerlerindeki birbirini tanımayan insanların aynı sürece dahil olarak işbirliği içerisinde üretim yapabilecekleri bir geleceği hayal etmektedir. Yaşamakta olduğumuz Covid-19 pandemi süreci de bu eğilimi hızlandırarak, uzaktan birlikte çalışmayı bir zorunluluk haline getirmiştir. Bunun sonucunda, mevcut altyapıların desteklemediği, zorlu bilgi yoğun senaryolarda da süreç odaklı yaklaşımların uygulanması bir zorunluluk olmuştur. Günümüz İSY sistemlerinin bilgi odaklı süreç yönetimi hedefini hayata geçirebilmek için işbirliği, uyarlanabilirlik ve bağlam farkındalık gibi kavramların üzerine yoğunlaşması gerekmektedir. Bunun için, mevcut İSYS'lerin, bir dizi yeni gereksinimi desteklemeye başlaması gerekmektedir. Genel olarak bu gereksinimler: tüm kurumsal ortam, veri ve kuralların modellendiği bir kurumsal bilgi tabanının geliştirilmesi ve bu bilgi modeli üzerinde bilgi ile tetiklenen, kurallar ile şekillenen, organizasyon hedeflerine hizmet eden, dinamik işbirliklerinin yapılabildiği bir çalışma ortamının oluşturulması şeklinde özetlenebilir. Bu yöndeki araştırmalar ise hala, büyük oranda, akademik seviyededir ve sadece akıllı hata kotarma problemine odaklanmış durumdadır. Ayrıca, bu çalışmaların kurumsal standartlardan uzak oluşları ve uygulanabilirliklerindeki zorluklardan dolayı endüstriyel kullanımı yaygınlaşamamıştır. Tez çalışması kapsamında geliştirilen yöntem yüksek değişkenliğe sahip bilgi yoğun iş süreçlerinin yönetimi için üç hipotezi temel almaktadır. İlk olarak, süreç tasarımı sadece görev ve kontrol akışlarının modellenmesi ile sınırlı değildir, süreç uzayını oluşturan veri, kural, hedef, iş ortamı ve iş akış perspektiflerinin bütüncül bir şekilde ele alınması gerekmektedir. İkinci olarak, kapsüllemeyi ve bileşenleştirmeyi sağlamak için, süreç işletimleri, kurumsal bilgiyi güncelleyen görev akışları ile değil, her biri kendi hedefleri, inanışları, kararları ve yaşam döngüsü olan etkileşimli özerk varlıklar (akıllı yazılım etmenleri) üzerinden yönetilmelidir. İSY sistemlerinin nihai hedefi, iş akışlarının eş güdümünü sağlamaktan, iş uzmanlarının karar verme süreçlerine yardımcı olmaya doğru evrilmektedir. Bu doğrultuda, üçüncü hipotez olarak, bilgi çalışanlarının uzmanlıklarının en azından bir kısmı dijitalleştirilmeli ve özerk yazılım vekilleri tarafından yerine getirilmelidir. Bu amaçla, iki aşamalı bir yaklaşımla, tüm İSY yaşam döngüsünü destekleyen bir çözüm önerilmiştir. İlk olarak, iş süreçleri, kurumsal bilgi yönetimi ve çoklu etmen sistemleri modelleme paradigmalarını ve tasarım bileşenlerini kusursuz bir biçimde tümleştiren ve bir arada modellenmelerine olanak tanıyan, tümleşik bir modelleme metodolojisi geliştirilmiştir. Arttırımlı bir şekilde geliştirilen modeller organizasyon, iş ortamı, kurumsal stratejiler, işlevsellikler ve kısıtları anlamsal bir şekilde tanımlamakta ve kurumsal bilgi modelini oluşturmaktadır. Bu modellerin tasarımında, endüstride ve etmen tabanlı yazılım mühendisliğinde kullanılan standartlar ve en iyi uygulamalar, mümkün olduğunca yeniden kullanılarak, gerçek hayat problemlerinde kolay bir şekilde uygulanabilir olması hedeflenmiştir. Tez çalışmasının ikinci aşamasında, etmenlerin çalışma zamanında özerk bir şekilde hedefe yönelik ve bilgi odaklı davranış uyarlamaları yapmasına olanak tanıyan bir çoklu etmen tabanlı süreç işletim ortamı geliştirilmiştir. Geliştirilen bilgi modelini kullanan etmenler bilişsel yetenekler (hedef güdümlü planlama, kural uyumluluk, bilgi güdümlü davranışlar ve dinamik işbirlikleri gibi) sergileyerek, bilgi çalışanlarının karar verme süreçlerini desteklemeye çalışmaktadır. Bu amaçla, iş uzmanlarının karar verme yöntemlerinden esinlenerek geliştirilen buluşsal planlama yaklaşımı ile sergilenecek eylemlere çalışma zamanında, yeni bilgiler ortaya çıktıkça adım adım karar verilmekte ve hedefler ile gerçekler arasındaki boşluk kapatılmaya çalışılmaktadır. İş uzmanlarının hedefe yönelik davranış seçimi, süreç kalitesinin değerlendirilmesi, kurallara uygunluğun kontrolü, hata yönetimi ve dinamik müzakere ve işbirliği yetenekleri dijitalleştirilerek, etmenler tarafından yerine getirilebilir hale getirilmiştir. Bu sayede çalışma zamanında süreçlerin dinamik bir şekilde uyarlanabilmesi ve anlık etkileşimler ile yeniden şekillenerek organizasyon hedeflerine ulaşabilmesi sağlanmıştır. Gerçekleştirilen deneysel çalışmalar ile, süreç işletimi için yeterli kaynaklara sahip bir ortamda, tez kapsamında geliştirilen çerçevenin rastgele oluşturulan çalışma zamanı hatalarını başarılı bir şekilde kotarabildiğini ortaya koymuştur. Literatürdeki mevcut çalışmalar ile karşılaştırıldığında, geliştirilen sistemin, bilgi yoğun süreç yönetim sistemlerinin temel gereksinimlerinin büyük bir çoğunluğunu sağlayan, literatürdeki en kapsamlı çözüm olduğu ortaya konmuştur.
-
ÖgeGeneralized multi-view data proliferator (gem-vip) for boosting classification(Graduate School, 2022-08-08) Çelik, Mustafa ; Rekik, Islem ; 504131531 ; Computer EngineeringMulti-view network representation revealed multi-faced alterations of the brain as a complex interconnected system, particularly in mapping neurological disorders. Such rich data representation maps the relationship between different brain views which has the potential of boosting neurological diagnostic tasks. However, multi-view brain data is scarce and generally is collected in small sizes. Thus, such data type is broadly overlooked among researchers due to its relatively small size. Despite the existence of data proliferation techniques as a way to overcome data scarcity, to the best of our knowledge, multi-view data proliferation from a single sample has not been fully explored. Here, we propose to bridge this gap by proposing our GEneralized Multi-VIew data Proliferator (GEM-VIP), a framework aiming to proliferate synthetic multi-view brain samples from a single multi-view brain to boost multi-view brain data classification tasks. For the given Connectional Brain Template (i.e., represents an approximation of brain graphs that captures the unique connection shared by a population's subjects), we set out the proliferate synthetic multi-view brain graphs using the inverse of multi-variate normal distribution (MVND). However, one needs two crucial components, which are the mean an the covariance of a given population. As such, first, our proposed GEM-VIP framework obtains a population-representative tensor (i.e., drawn from the prior CBT) which can be mathematically regarded as a mean of the population. Second, drawing inspiration from the genetic algorithm paradigm our proposed GEM-VIP learns the covariance matrix of the population using the given CBT. Lastly, it proliferates synthetic samples using the earlier obtained representative tensor and created covariance matrix of the population on the MVND equation. We evaluate our GEM-VIP against several comparison methods. The results show that our framework boosts the multi-view brain data classification accuracy of AD/ lMCI and eMCI/ normal control (NC) datasets. In short, our GEM-VIP method boosts the diagnoses of the neurological disorders.
-
ÖgeHeuristic algorithms for solving chemical shift assignment problem in protein structure determination(Lisansüstü Eğitim Enstitüsü, 2021) Yılmaz Maden, Emel ; Uyar Etaner, Ayşe Şima ; Güntert, Peter, ; 709824 ; Bilgisayar MühendisliğiHeuristic algorithms have been widely used in several different hard optimization problems not only in computer science but also in several other disciplines, including natural sciences, bioinformatics, electronics, and operational research, where computational methods are needed. Heuristic algorithms search for optimal solutions by maximizing or minimizing the given objectives depending on the need while satisfying the given conditions. Heuristic algorithms find solutions in a huge search space where many different possible solution candidates exist. Due to these conditions of the search space, systematic search techniques are not feasible for such kinds of problems. In this thesis, we applied several different heuristic approaches and their combinations on the chemical shift assignment problem of the Nuclear Magnetic Resonance (NMR) spectroscopy. NMR spectroscopy is one of the methods to determine the three-dimensional structure of proteins. The three-dimensional structure of proteins provides crucial information to detect the shape, structure and function of biological macromolecules. The protein structure also demonstrates the function of proteins by illustrating the interactions of the macromolecules with other proteins or small ligands. Therefore, the three-dimensional structure of a protein can form a basis for drug design against human diseases. NMR has many advantages compared to other techniques; however, NMR spectroscopy needs very advanced computational techniques for providing the protein structure. The chemical shift assignment of the atoms is one of the most challenging problems in NMR spectroscopy. It needs a considerable amount of time by an experienced spectroscopist if the determination is done manually or by a semi-automated method. Additionally, even if the remaining parts of the structure determination methods work perfectly, it is impossible to create the protein structure if the chemical shift assignments are not done correctly. Due to this complexity, the total number of protein structures obtained from NMR spectroscopy is very few compared to its alternative methods, such as X-ray crystallography. Due to its importance in NMR experiments, the chemical shift assignment problem has recently become one of the most critical research areas in the computational techniques of NMR spectroscopy. There have been many types of research on this problem; however, they are far from perfect. Some of these techniques can provide only partial solutions by assigning only the backbone atoms or only the sidechain atoms. Some of these methods require a very long computation time. Additionally, the results of many of the existing methods have a great area for improvement. In this thesis, we developed a novel method with the heuristic algorithms that provides a fully automatic assignment of the chemical shift values of NMR experiments. First, we studied the background of the problem along with the existing methods. Secondly, we proposed our methods that solve the problem with evolutionary algorithms. Thirdly, we performed experiments on several different datasets, compared the success of our methods against the state-of-the-art solutions of the problem, and continuously improved our methods. Finally, we performed further analysis on the results and proposed further work. First, the background of the chemical shift assignment problem is comprehensively studied from the computer science point of view. The optimization processes in heuristic algorithms, stochastic local search methods, iterative improvement, simple stochastic local search methods, hybrid, and population-based stochastic local search methods are discussed in detail. The ant colony optimization and the evolutionary algorithms are analyzed as the population-based stochastic local search methods. After these evaluations, the evolutionary algorithms appeared to be a suitable candidate for solving this problem since they already work with a population, which is a set of solution candidates. We also analyzed the NMR spectroscopy hardware, principles, and experiment steps in detail because the problem is a real application from NMR spectroscopy in natural sciences. Furthermore, we had a deep dive into the chemical shift assignment problem and into the protein structure and peptide formation areas, which are the basis for the NMR spectroscopy calculations. Afterwards, the existing methods for solving this problem are discussed with their drawbacks. Secondly, we proposed our methods for solving the problem with heuristic algorithms. Our method comprises several different evolutionary algorithms and their combinations with hill climbing, with each other, and constructive heuristic methods. More conventional approach genetic algorithm, GA, and multi-objective evolutionary algorithms, NSGA2 and NSGA3, are applied to the problem. The multi-objective evolutionary algorithms investigated each objective parameter separately, whereas the genetic algorithm followed a conventional way, where all objectives are combined in one score function. While defining the methods, we first defined the problem model, along with the existing conditions and the score function. We modeled the problem as a combinatorial optimization problem, where expected peaks are mapped onto the measured peaks. The chromosome of the algorithm is an array of the expected peaks and the values inside represent their mapped measured peaks. The objectives of the problem are defined in a score function. The constraints are not separately evaluated because they are already fulfilled by the problem model implicitly. Additional fine-tuning and changes are implemented on the algorithms to apply the NMR-specific behaviors to the problem model. Then, the following improvements are realized on the algorithms: We optimized the probability of applying crossover and mutation in the methods. The population initialization is optimized with a constructive initialization algorithm, which minimizes the search space to find better initial individuals. Furthermore, we optimized the population's diversity to find the optimum solutions by escaping from local optima. We also implemented hybrid algorithms by combining a hill-climbing algorithm with our proposed algorithms. Thirdly, we performed experiments on several datasets with a set of commonly used spectra. We also compared the results of our methods with the two state-of-the-art algorithms: FLYA and PINE. In almost all of these datasets, our algorithm GA yielded better results than PINE. Our algorithm NSGA2 produced better results than PINE in almost half of the datasets. Our NSGA3 algorithm yielded less than 10% correct assignments because only two objectives out of four objectives of our problem model create trade-off. NSGA3 algorithms are known to be successful on problems with more than three objectives. Additionally, our algorithms had better runtime performance than FLYA in more than half of the datasets. Our algorithms could assign all of the atoms in all datasets, which creates a huge completeness success of the problem, whereas FLYA and PINE algorithms could not provide a complete assignment. Furthermore, we observed in our results that splitting a large protein into smaller fragments improved our algorithms' results dramatically. Finally, we performed further analysis on our results. These analyses showed us that our algorithms often assigned different atoms than FLYA and PINE. Primarily the GA algorithm can provide good results on some parts of datasets where the state-of-the-art algorithms cannot make any assignment. In order to leverage this success of our algorithms, we proposed a hierarchical method. This method combines FLYA and our algorithm GA to benefit from the different success factors of each algorithm. The results showed that this approach improved the overall success of the algorithms. In future work, the three algorithms could be combined to achieve better results. Additionally, one can focus on distinguishing atoms that can be assigned consistently and more reliably than others. The assignment is only tentative so that fewer wrong assignments are done. Furthermore, the objective function of the problem can be remodeled to improve the performance of the algorithms. Additionally, our method can be extended in further work so that large proteins are split into smaller fragments before applying our algorithms, which will improve the overall results. In this thesis, we successfully implemented a fully automatic algorithm for solving the chemical shift assignment problem of NMR spectroscopy. Our method can automatically assign a significant part of the sidechain and backbone atoms without any parameter changes or manual interactions. We produced results that are comparable to the two very well know state-of-the-art algorithms. Our approaches could provide around a 70% success rate on these datasets and assign many atoms that other methods could not assign. Our algorithm outperformed at least one of these two state-of-the-art methods almost in all of our experiments. Additionally, the whole methods are implemented on the MOEA framework, enabling the further implementation of new algorithms easily.
-
ÖgeHybrid reciprocal recommendation with advanced feature representations(Graduate Institute, 2021) Yıldırım, Ezgi ; Öğüdücü, Şule ; 674767 ; Department of Computer EngineeringOver the last few decades, with the rise of online web services such as Facebook, Amazon, and Netflix, Recommender Systems (RecSys) have taken an indisputable place in our daily lives. The application domain of RecSys has an extensive range from e-commerce to online advertisement that aims to suggest to users the right contents matching their preferences, and it is not limited to one-way interacting platforms. In some challenging application domains, RecSys are developed to serve multiple users at each decision, to mutually satisfy the accompanying parties. Where a matching problem occurs and the satisfaction of both parties is the key to success, those recommender systems are called Reciprocal Recommenders (Rec2) in literature. Differing from traditional one-directional recommendation problems, the reciprocal recommendation has more adversity to overcome, which outlines its characteristics. In this study, based on gradual research, we first seek the key points of a strong recommender system, and then, by the learned lessons from this part, focus on the reciprocal recommendation. For this purpose, we first seek answers to these questions in a general recommender system: • How can auxiliary data affect recommendation quality? • How can we easily integrate different data sources and different approaches to empower a recommender system? Then, in the second part, we shift our research focus towards reciprocal recommendation and try to answer the following research questions: • How can we effectively solve reciprocal recommendation problems without detriment to system performance? • How can we avoid vagueness of recommendations and explain conceptual associations of requested and offered characteristics? In recent years, deep learning has gained indisputable success in computer vision, speech recognition, and natural language processing. After its rising success in these challenging areas, it has been studied on recommender systems as well, but mostly to include content features into traditional methods. In the initial part of this thesis, we introduce a generalized neural network-based recommender framework that offers an easy-to-use platform to combine different data sources, approaches, and methods into a single recommender system. This framework, Neural Hybrid Recommender (NHR), also allows us to exploit the same data sources to find out more elaborate information by different learning functions. In our experiments, we have worked on item prediction problems, however, with a single change on the loss function, the framework can be used for rating prediction problems as well. To evaluate the effect of such a framework, we have tested our approach on benchmark and not yet experimented datasets; movie reviews and job applications of job-seekers from an online recruitment platform. The results in these real-world datasets show the superior performance of our approach in comparison with the state-of-the-art deep learning methods in Click-Through-Rate (CTR) prediction. With the use of auxiliary data in different forms, NHR models perform better than collaborative filtering methods that depend on interaction data only. On the movie recommendation task, based on the average of a group of experiments, NHR models achieve 2.03% relative improvements on HR@10 score and 2.51% on NDCG@10 over the most successful baseline used in the evaluation. With the same setup, the improvements on the job recommendation task become even higher; 2.60% and 2.91% on HR@10 and NDCG@10, relatively. Having more promising results on job recommendation with auxiliary data is since this task is far more complex than the movie recommendation task due to the multi-variate socio-economic dependencies in job applications. Our further experiment that investigates the effect of predictive factors, which define the predictive capability in neural networks, also verifies that. Increasing the model complexity without changing the other parameters did not deteriorate the success of models in job recommendation because complex problems are less prone to over-fit, which can usually result from high model complexity. In the latter part of this thesis, we propose a multi-objective learning approach for online recruiting. Online recruiting and online dating are the most known reciprocal recommendation problems. However, the reciprocal recommendation has gained little attention in the literature due to the lack of public datasets. We aim to resolve this shortage in our study. Since the satisfaction of both candidates and companies is indispensable for successful hiring as opposed to traditional recommenders, online recruiting should respect to expectations of all parties and meet their common interests as much as possible. For this purpose, we integrated our multi-objective learning approach into various state-of-the-art methods, whose success has been proven on similar prediction problems, and we achieved encouraging results. We propose one of the prominent architectures as a prototype of our multi-objective learning approach, however, our approach applies to any recommender system employing neural networks as its final decision-maker. Our multi-objective prototype has achieved 12.15% lower LogLoss and 6.37% higher AUC than its single-objective counterpart. Besides the predictive performance, our multi-objective approach has reduced the training and testing times by half. This speedup contributes to overcoming the time constraint that complex models suffer from, so critical in the era of deep learning. Furthermore, our prototype offers explainable recommendations thanks to its Factorization Machines (FM) component. Since explainability has recently gained importance with the global changes and for ethical reasons, we have paid special attention to the selection of our base model for prototyping. Consequently, our prototype offers the reasoning behind the recommendations, so that companies can use it when requested or needed. The explainable recommendation can create a transparent hiring process and so a fair and trustworthy environment for job-seekers. This can increase the turnover rate of users and thereby help to alleviate sparsity.
-
ÖgeIdentification of object manipulation anomalies for service robots(Lisansüstü Eğitim Enstitüsü, 2021) Altan, Doğan ; Uzar Sarıel, Sanem ; 709912 ; Bilgisayar MühendisliğiRecent advancements in artificial intelligence have resulted in an increase in the use of service robots in many domains. These domains include households, schools and factories to facilitate daily life in domestic tasks. Characteristics of such domains necessitate the intense interaction of robots with humans. These interactions necessitate extending the abilities of service robots to deal with safety and ethical issues. Since service robots are usually assigned to complex tasks, unexpected deviations of task state are highly probable. These deviations are called anomalies, and they need to be continually monitored and handled for robust execution. After an anomaly case is detected, it should be identified for effective recovery. For the identification task, a time series analysis of onboard sensor readings is needed since some anomaly indicators are observed long before the detection of the anomaly. These sensor readings need to be fused effectively for correct interpretations as they are generally taken asynchronously. In this thesis, the anomaly identification problem of everyday object manipulation scenarios is addressed. The problem is handled from two perspectives by considering the feature types that are processed. Two frameworks are investigated: the first one takes into account domain symbols as features while the second framework considers convolutional features. Chapter 5 presents the first framework to address this problem by analyzing symbols as features. It combines and fuses auditory, visual and proprioceptive sensory modalities with an early fusion method. Before they are fused, a visual modeling system generates visual predicates and provides them as inputs to the framework. Auditory data are fed into a support vector machine (SVM) based classifier to obtain distinct sound classes. Then, these data are fused and processed within a deep learning architecture. The architecture consists of an early fusion scheme, a long short-term memory (LSTM) block, a dense layer and a majority voting scheme. After the extracted features are fed into the designed architecture, the occurred anomaly is classified. Chapter 6 presents a convolutional three-stream anomaly identification (CLUE-AI) architecture that fuses visual, auditory and proprioceptive sensory modalities. Visual convolutional features are extracted with convolutional neural networks (CNNs) from raw 2D images gathered through an RGB-D camera. These visual features are then fed into an LSTM block with a self-attention mechanism. After attention values for each image in the gathered sequence are calculated, a dense layer outputs the attention-enabled results for the corresponding sequence. Mel frequency cepstral coefficients (MFCC) features are extracted from the auditory data gathered through a microphone in the auditory stage. This is followed by feeding these auditory features into a CNN block. The position of the gripper and the force applied by it are also fed into a designed CNN block. These resulting sensory modalities are then concatenated with a late fusion mechanism. Afterward, the resulting feature vector is fed into fully connected layers. Finally, the anomaly type is revealed. The experiments are conducted on real-world everyday object manipulation scenarios performed by a Baxter robot equipped with an RGB-D head camera on top and a microphone placed on the torso. Various investigations including comparative performance evaluations, parameter and multimodality analyses are studied to show the validity of the frameworks. The results indicate that the presented frameworks have the ability to identify anomalies with f-scores of 92% and 94%, respectively. As these results indicate, the CLUE-AI framework outperforms the other in classifying occurred anomaly types. Due to the requirements that the frameworks necessitate, the CLUE-AI framework does not require additional external modules such as a scene interpreter or a sound classifier as the other one does and provides better results compared to the symbol-based solution.
-
ÖgeNovel methodology for construction and decoding of color data codes(Lisansüstü Eğitim Enstitüsü, 2022-06-30) Sirmen, Refik Tanju ; Üstündağ, Burak Berk ; 509892015 ; Computer EngineeringColors can be employed as efficient sources of data conveyance as all their scalar descriptive attributes are transferred in the same spatial component. Although there is a great deal of ongoing research on each aspect of the process, palette construction (which establishes the basis of the whole practice) and decoding (which is the ultimate goal) issues deserve extra emphasis. The term palette herein states the combination of specific colors to be included in the symbology, disregarding the permutation order. That is, the number of colors to be used is the main determinant of the conveyance capacity, while the selection of colors strongly affects the decoding reliability. These two issues constitute the main dealings of this dissertation. In this context, 3D barcodes have been chosen as the exemplary application area, mainly because of their ubiquity and relatively easier implementation. The term 3D or 3-Dimensional describes herein a barcode utilizing more than two colors. As a machine-readable representation method of data, barcode technology provides one of the most recognized and cost-effective solutions to the quest for dispatching information with higher density and consistency. Hence, introducing colors to barcodes has been an attractive field of research for years, mainly with the motive to increase information density. A significant amount of work attempts to design a variety of 3D barcodes; nevertheless, only a few focalize on the issue of construction of the palette in particular. Even the existing ones appear either suboptimal or specific rather than generic. Although increasing the number of colors will directly leverage the capacity, in the presence of various disruptive effects it would further hamper distinguishability. In this respect, the palette structure and decoding approach should be in close accordance, considering the estimated characteristics of the anticipated distortion. This conception points out the main axes of this dissertation. In this direction, first, the peculiarities of a generic 3D-barcoding practice and the properties of field-specific interference were identified. In line with the derived operational barcode color acquisition model, the need for a plausible methodology for constructing robust color palettes was thus addressed. Along with, relevant techniques and metrics were devised to evaluate and compare pallets. Furthermore, a novel decoding schema has been developed as the consequential objective. It is acknowledged that selecting colors in the reference space as farthest apart as possible improves the expected performance of authentication. Therefore, the palette construction issue was worked out here as the inverse formulation of the well-known sphere-packing problem. The proposed methodology, as well as the comparison metrics (such as the accuracy-requirement cost, efficiency, cost-effectiveness, or palette quality), can be applied axiomatically to any number of colors. Also, the approach taken is independent of the coding system, operational conditions, or devices so that it can be generalized for the favored color space. Further, the 'iterative decoding with predictive convergence' (IDPC) method developed herein presents a novel concatenated scheme, which was not fully available in the congener methods used in 3D barcodes. As a derivative of the iterative decoding, the convergence step of the IDPC tries to reach the local error minima estimate by establishing a coaction between the inner and outer layers of the schema. To achieve optimal iteration implementation, the uncertainty measure presented here was utilized, which seems to be suitable to exploit in diverse congruent areas as well. Numerous palettes (of 3 ≤ N ≤ 100) were designed, analyzed, and compared with some of the known counterparts, along with the study. Results show that constructing more efficient palettes can be realized through the proposed methodology. The methods developed were further tested and evaluated through computer simulations and real-life experiments. Simulations were conducted mainly to examine the influence of the palette selection on color authentication, as well as the contribution of the proposed predictive convergence to the decoding performance. In this framework, a novel interleaving technique was also devised and applied. In addition to the simulations, comprehensive experiments were performed in different environments. The observed average performance of the suggested decoding method was over 99% in the tests conducted; besides it was confirmed that exercising the convergence provided the resolution of most (i.e. over 84%) of the errors remaining from the previous step. We can propound that, although the importance of color selection was emphasized in several previous studies, the need for a generic methodology proposal for robust palette construction, moreover, explicit metrics for evaluating and comparing palettes were not thoroughly afforded. This dissertation aims to contribute to the efforts to fulfill this highlighted need. Furthermore, the proposed decoding algorithm promises better performances through the revealed convergence implementation. It is also envisaged that the depicted concepts, methods, and findings would be instrumental as well for the other application areas of using colors for information representation and transfer, beyond 3D barcodes.
-
ÖgeSoftware defect prediction with a personalization focus and challenges during deployment(Lisansüstü Eğitim Enstitüsü, 2021) Eken, Beyza ; Kühn Tosun, Ayşe ; 723330 ; Bilgisayar MühendisliğiOrganizations apply software quality assurance techniques (SQA) to deliver high-quality products to their customers. Developing defect-free software holds a critical role in SQA activities. The increasing usage of software systems and also their rapidly evolving nature in terms of size and complexity raise the importance of effectiveness in defect detection activities. Software defect prediction (SDP) is a subfield of empirical software engineering that focuses on building automated and effective ways of detecting defects in software systems. Many SDP models have been proposed in two decades, and current state-of-the-art models mostly utilize artificial intelligence (AI) and machine learning (ML) techniques, and product, process, and people-related metrics which are collected from software repositories. So far now, the people aspect of the SDP has been studied less compared to the algorithm (i.e., ensembling or tuning machine learners) and data aspects (i.e., proposing new metrics). While the majority of people-focused studies incorporate developer or team related metrics into SDP models, recently personalized SDP models have been proposed. On the other hand, the majority of the SDP research so far now focuses on building SDP models that produce high rates of prediction performance values. Real case studies in industrial software projects and also the number of studies that research the applicability of SDP models in practice are relatively few. However, for an SPD solution to be successful and efficient, its applicability in real life is as important as its prediction accuracy. This thesis focus on two main goals: 1) assessing people factor in SDP to understand whether it helps to improve the prediction accuracy of SDP models, and 2) prototyping an SDP solution for an industrial setting and assessing its deployment performance. First, we made an empirical analysis to understand the effect of community smell patterns on the prediction of bug-prone software classes. The ''community smell'' term is recently coined to describe the collaboration and communication flaws in organizations. Our motivation in this part is based on the studies that show the success of incorporating community factors, i.e., sociotechnical network metrics, into prediction models to predict bug-prone software modules. Also, prior studies show the statistical association of community smells with code smells (which are code antipatterns) and report the predictive success of using code smell-related metrics in the SDP problem. We assess the contribution of community smells on the prediction of bug-prone classes against the contribution of other state-of-the-art metrics (e.g., static code metrics) and code smell metrics. Our analysis on ten open-source projects shows that community smells improve the prediction rates of baseline models by 3% in terms of area under the curve (AUC), while the code smell intensity metric improves the prediction rates by 17%. One reason for that is the existing ways of detecting community smell patterns may not be rich in terms of capturing communication patterns of the team since it only mines patterns through mailing archives of organizations. Another reason is that the technical code flaws (code smell intensity metric) are more successful in representing defect related information compared to community smells. Considering the challenging situation in extracting community patterns and the higher success of the code small intensity metric in SDP, we direct our research to focus on the code development skills of developers and the personalized SDP approach. Second, we investigate the personalized SDP models. The rationale behind the personalized SDP approach is that different developers tend to have different development patterns and consequently, their development may have different defect patterns. In the personalized approach, there is an SDP model for each developer in the team which is trained with the developer's own development history solely and its predictions target only the developer. Whereas in the traditional approach, there is a single SDP model that is trained with the whole team's development history, and its predictions target anyone in the team. Prior studies report promising results on the personalized SDP models. Still, their experimental setup is very limited in terms of data, context, model validation, and further explorations on the characteristics that affect the success of personalized models. We conduct a comprehensive investigation of personalized change-level SDP on 222 developers from six open-source projects utilizing two state-of-the-art ML algorithms and 13 process metrics collected from software code repositories that measure the development activity from size, history, diffusion, and experience aspects. We evaluate the model performance using rigorous validation setups, seven assessment criteria, and statistical tests. Our analysis shows that the personalized models (PM) predict defects better than general models (GM), i.e., increase recall by up to 24% for the 83% of developers. However, PM also increases the false alarms of GM by up to 12% for 77% of developers. Moreover, PM is superior to GM for those developers who contribute to the software modules that have been contributed by many prior developers. GM is superior to PM for the more experienced developers. Further, the information gained from various process metrics in prediction defects differs among individuals, but the size aspect is the most important one in the whole team. In the third part of the thesis, we build prototype personalized and general SDP models for our partner from the telecommunication industry. By using the same empirical setup that we use for the investigation of personalized models in open-source projects, we observe that GM detects more defects than PM (i.e., 29% higher recall) in our industrial case. However, PM gives 40% lower false alarms than GM, leading to a lower code inspection cost than GM. Moreover, we observe that utilizing multiple data sources such as semantic information extracted from commit descriptions and latent features of development activity and applying log filtering on metric values improve the recall of PM by up to 25% and lowers GM's false alarms by up to 32%. Considering the industrial team's perspective on prediction success criteria, we pick a model to deploy that produces balanced recall and false alarm rates: the GM model that utilizes the process and latent metrics and log filtering. Also, we observe that the semantic metrics extracted from the commit descriptions do not seem to contribute to the prediction of defects as much as process and latent metrics. In the fourth and last part of the thesis, we deploy the chosen SDP prototype into our industrial partner's real development environment and share our insights on the deployment. Integrating SDP models into real development environments has several challenges regarding performance validation, consistency, and data accuracy. The offline research setups may not be convenient to observe the performance of SDP models in real life since the online (real-life) data flow of software systems is different than offline setups. For example, in real life, discovering bug-inducing commits requires some time due to the bug life cycle, and this causes a data label noise in the training sets of an online setup. Whereas, an offline dataset does not have that problem since it utilizes a pre-collected batch dataset. Moreover, deployed SDP models need a re-training (update) with the recent commits to provide consistency in their prediction performance and to keep up with the non-stationary nature of the software. We propose an online prediction setup to investigate the deployed prototype's real-life performance under two parameters: 1) a train-test (TT) gap, which is a time gap between the train and test commits used to avoid learning from noisy data, and 2) model update period (UP) to include the recent data into the model learning process. Our empirical analysis shows that the offline performance of the SDP prototype reflects its online performance after the first year of the project. Also, the online prediction performance is significantly affected by the various TT gap and UP values, up to 37% and 18% in terms of recall, respectively. In deployment, we set the TT gap to 8-month and UP to 3-day, since those values are the most convenient ones according to the online evaluation results in terms of prediction capability and consistency over time. The thesis concludes that using the personalized SDP approach leads to promising results in predicting defects. However, whether PM should be chosen over GM depends on factors such as the ML algorithm used, the prediction performance assessment criteria of the organization, and developers' development characteristics. Future research in personalized SDP may focus on profiling developers in a transferable way instead of building a model for each software project. For example, collecting developer activity from public repositories to create a profile or using cross-project personalized models would be some options. Moreover, our industrial experience provides good insights regarding the challenges of applying SDP in an industrial context, from data collection to model deployment. Practitioners should consider using online prediction setups and conducting a domain analysis regarding the team's practices and prediction success criteria and project context (i.e., release cycle) before making deployment decisions to obtain good and consistent prediction performance. Interpretability and usability of models hold a crucial role in the future of SDP studies. More researchers are becoming interested in such aspects of SDP models, i.e., developer perceptions of SDP tools and actionability of prediction outputs.
-
ÖgeVisual attention and visual distortion sensitivity based regional rate allocation in JPEG2000(Lisansüstü Eğitim Enstitüsü, 2021) Pak, Mesut ; Bayazıt, Uluğ ; 662856 ; Bilgisayar MühendisliğiThis thesis study proposes a regional bit allocation method for improving the subjective quality for image encoding. This bit allocation method jointly uses the visual attention and visual distortion sensitivity levels of image regions for decreasing the perceptual distortions. Visual attention levels of image regions are estimated by using an exponential model of fixation durations. The human visual system is more sensitive to the distortions in structured regions than the distortions in complex textured regions. Therefore, a method for estimating distortion sensitivity, that distinguishes the structured regions from complex textures by using uniform distribution of gradient directions and connected sets of pixels having same gradient directions, is also proposed. The estimates for the visual attention level and the distortion sensitivity level are jointly used to modify the distortion contribution of each codeblock in bit allocation. The exponential model used to obtain the visual attention map of an image inputs the average of fixation duration maps of all viewer subjects. The fixation duration maps are based on eye-tracking experiments. For optimizing the perceptual quality by bit allocation, the encoder should decrease the perceptual distortions in visually conspicuous regions. The distortions in structured regions, such as object contours or letters, are very noticeable. Therefore, the distortion sensitivity estimation should determine the image regions containing true edges with significant lengths regardless of the edges' gradient magnitudes. The second visual distortion sensitivity issue is determining whether a region is complex textured or not. The complex textured regions can conceal distortions caused by lossy compression whereas in smooth regions such distortions are easily perceptible. The proposed method compares the entropy of the orientations of gradients within an image block against a threshold for classifying it as complex textured. The visual quality achieved by the proposed bit allocation method is compared with those achieved by well-known bit allocation methods (post-compression rate-distortion optimization, saliency map, foveation of fixations, and foveated just-noticeable-difference map) in order to validate the proposed method. Additionally, to assess the contribution of the use of visual distortion sensitivity to the perceived quality achieved by the proposed method, the reconstructed images resulting from bit allocation based on only the visual attention maps are also compared against those resulting from the proposed bit allocation method. The performance comparisons are primarily based on the paired comparison method developed by ITU-T that evaluates the subjective qualities of the images. In the pairwise comparative evaluation facilitated by a web page, the evaluator subjects are presented with the decoded images for different bit allocation methods pair by pair and vote for the differential quality of each pair. In addition to subjective evaluation, a more objective perceptual quality assessment method, known as Masked MS-SSIM, is also used. This assessment method calculates a similarity index between the reconstructed image and the original image for regions of interest. The plausibility of the subjective and objective comparison results are verified by using statistical hypothesis tests. In summary, the proposed bit allocation method has been experimentally shown to yield a substantially higher perceptual visual quality than the other well-known bit allocation methods. The method is conceivable for use in media server applications where the server processes the eye fixation data collected by the clients to obtain the visual attention map.