Master Degree / Yüksek Lisans Tezleri

Permanent URI for this collectionhttps://hdl.handle.net/11147/3008

Browse

Filters

2020 - 20249

Settings

Publisher: search.filters.publisher.01. Izmir Institute of TechnologySubject: search.filters.subject.Artificial intelligence

Search Results

Now showing 1 - 9 of 9
  • Master Thesis
    Hardware acceleration with fpga Based electronic boards for machine learning
    (01. Izmir Institute of Technology, 2024) Akkuş, Batuhan; Gümüş, Abdurrahman; Apaydın, Mehmet Serkan
    Son yıllardaki makine ög˘renmesi algoritmalarındaki gelis¸meler uç cihazlardaki kullanımını da arttırmıs¸tır (Merenda et al., 2020). Makine ög˘renimi algoritmaları genel- likle GPU tabanlı bilgisayarlarda çalıs¸tırılmaktadır, bu da yüksek enerji tüketimi (De- sislavov et al., 2021), yog˘un donanım kaynag˘ı gereksinimleri ve büyük fiziksel boyutları (Liu et al., 2022) nedeniyle uç cihazlar için uygun olmamaktadır. Bu tez, donanım hızlandırıcısı olarak FPGA platformlarında makine ög˘renmesi algoritmalarının, özellikle derin sinir ag˘larının uygulanması ve çıkarım yapılmasını aras¸tırarak, düs¸ük güç tüke- timi, verimli donanım kullanımı ve yüksek çıkarım performansı elde etmeyi hedefle- mektedir. Bu sistemlerin uç cihazlara adaptasyonu için esneklig˘i ve verimlilig˘i artırmak amacıyla, CNV ag˘ının (Umuroglu et al., 2017b) daha hafif bir varyasyonu olan CNV light gelis¸tirilmis¸. Bu ag˘, PyTorch tabanlı bir araç olan Brevitas (Pappalardo et al., 2019) ile nicemleme-farkında-eg˘itim yöntemi, kullanılarak 1, 2, 4 ve 8-bit seviyelerine nicemleme yapılmıs¸tır. CNV light ag˘ı CIFAR-10, SVHN, GTSRB ve MNIST veri setleri üzerinde Brevitas ile eg˘itilmis¸tir. Modeller FINN çerçevesi (Umuroglu et al., 2017a) kullanılarak FPGA'ya sentezlenmis¸tir. Modeller en fazla, en az ve sabit FPS seviye donanım kul- lanımına göre ayarlanmıs¸tır. Xilinx XC7Z020-1CLG400C FPGA, modelin metriklerini deg˘erlendirmek ve raporlamak için kullanılmıs¸tır. GTSRB veri setinde, ikili (W1A1) nicemleme yapılmıs¸ CNV light ag˘ı, tüm donanım kullanımları için %95.12 dog˘ruluk ve en fazla donanım kullanımında 12,191 FPS performansı ve 3.20W güç tüketimi elde etti, minimum donanım kullanımı için ise 6 FPS ve 1.62W güç tüketti. Sonuçlar, FPGA'ların uç cihazlarda makine ög˘renmesi modellerini verimli ve ölçeklenebilir platformlar olarak kullanılabileceg˘ini göstermektedir.
  • Master Thesis
    Human-centric artificial intelligence systems for visual assistance and multimodal emotion analysis
    (01. Izmir Institute of Technology, 2024) Dede, İbrahim; Gümüş, Abdurrahman
    İnsan merkezli yapay zeka sistemleri, günlük yaşamı iyileştiren ve gerçek dünyadaki zorlukları ele alan teknolojiler yaratmak için çok önemlidir. Bu perspektifte, iki proje önerilmektedir. İlk proje olan Vis-Assist, görme engelli bireylere yardımcı olmak için tasarlanmış bir giyilebilir görsel yardımcı cihazdır. Nesneleri algılar ve sınıflandırır, mesafelerini ölçer ve harici sunuculara ihtiyaç duymadan entegre düşük maliyetli bir hesaplama birimi kullanarak titreşim motoru dizisi aracılığıyla gerçek zamanlı dokunsal geri bildirim sağlar. Bu cihaz, kullanıcıların 19 farklı nesne sınıfı arasında ayrım yapmasına ve güvenli bir şekilde gezinmesine olanak tanır. Geliştirilen giyilebilir cihazın performansı, dört katılımcıyla iki tür deney yoluyla değerlendirildi. Sonuçlar, kullanıcıların nesnelerin yerini belirleyebildiğini ve böylece engellerle çarpışmayı önleyebildiğini göstermektedir. Kullanıcılar ortalama olarak, 40 m²'lik boş bir alanda bir sandalye gibi önceden tanımlanmış bir nesneyi 94 saniyeden kısa bir sürede bulabilir ve nesneleri bulmak için engellerin etrafından dolaşabilir ve 121 saniyeden kısa bir sürede nesneleri bulabilir. İkinci proje, az sayıda atış öğrenmesi kullanarak çok modlu duygu sınıflandırmasına odaklanıyor. Yapay zekadaki geleneksel yöntemler, genellikle metin, görüntü, zaman serisi sinyali, ses spektrogramı gibi tek bir kaynak türünden gelen girdilere dayanır. Bu kaynaklar, modelin performansını iyileştirmek için çok modlu yaklaşımla birleştirilebilir. Bu araştırmada, OpenAI'nin CLIP çerçevesini kullanarak bir yapay zeka modeli geliştirildi ve Tip-Adapter algoritması üç tür girdiyi (metin, ses ve video) işleyecek şekilde uyarlandı. Modelin performansı, iki veri kümesi kullanılarak bir duygu sınıflandırma görevi üzerinde test edildi. Sonuçlar, çok modluluğun tek bir modalite kullanmaya kıyasla doğruluğu artırdığını göstererek, karmaşık, gerçek dünya ortamlarını anlayabilen ve bunlara yanıt verebilen insan merkezli AI sistemlerinin önemini vurguluyor.
  • Master Thesis
    Estrus Detection in Cows With Deep Learning Techniques
    (01. Izmir Institute of Technology, 2024) Arıkan, İbrahim; Ayav, Tolga; Soygazi, Fatih
    Accurately predicting the estrus period is essential for enhancing the efficiency and lowering the costs of artificial insemination in livestock, a crucial sector for global food production. Precisely identifying the estrus period is critical to avoid economic losses such as decreased milk production, delayed calf births, and loss of eligibility for government subsidies. Since the most obvious movement that needs to be detected during the fertilization period is mounting, it is important to detect this movement. Since manual detection of this movement is difficult and costly, automated methods were needed. Therefore, it is thought that deep learning-based methods can be applied to detect the mounting moment. The proposed method detects the estrus period using deep learning and XAI (Explainable Artificial Intelligence) techniques. Deep learning-based mounting detection is performed using CNN, ResNet, VGG-19 and YOLO-v5 models. The ResNet model in this proposed study detects mounting movement with 99% accuracy. Explainability of deep learning models describes features that aid in decision-making in detecting mounting motion. Grad-CAM and Gradient Inputs models, which are XAI techniques, are used for the black box behind the proposed models. The developed deep learning models reveal that they focus on the udder and back area of the cows during the decision-making phase. In addition, how successfully the Grad-CAM and Gradient Inputs models, which are the XAI models used for the explainability of the deep learning models trained in this study, performed the explanation process was measured by calculating the 'faithfulness', 'maximum sensitivity' and 'complexity' metrics.
  • Master Thesis
    Machine-learning-assisted de novo design of molybdenum disulfide binding peptides
    (01. Izmir Institute of Technology, 2024) Öğüt, Alp Deniz; Yücesoy, Deniz Tanıl; Apaydın, Mehmet Serkan
    Kısa amino asit zincirleri, peptitler, biyolojik süreçler ve yüksek teknoloji uygulamaları için vazgeçilmez moleküllerdir. Geniş kullanım alanları arasında, moleküler tanıma özelliği ile bio-nano arayüzler oluşturmak ilgi toplayan bir araştırma konusu olmuştur. Yapılan çalışmalar sonucunda yönlendirilmiş evrim metodolojileri oluşturulmuş ve çeşitli hedeflere -enzim, antijen veya inorganik yapılar- bağlanan fonksiyonel peptit tanısı mümkün hale gelmiştir fakat bu geleneksel yaklaşım ölçeklenebilirlik ve sekans uzayındaki ilişkilerin anlaşılması konusunda zayıflıklar taşımaktadır. Bu zafiyetler, yüksek çıktılı sekanslama ve hesaplama verimlerinin artması ile beraber derin yönlendirilmiş evrim gibi daha güçlü teknolojilerinin geliştirilmesini motive etmiştir. Bu yöntemle üretilen büyük veri setleri, sekans-fonksiyon ilişkilerinin makine öğrenmesi ile modellenebilmesinin önünü açmıştır. Bu tezin amacı bu veri setlerine uygun bir makine öğrenmesi akışı oluşturmaktır. Bu düzlemde Random Forest algoritması ve derin nöral ağlar kullanılmış, eğitilen modellerin bağlanma puanı öngörüleri beraber kullanıldığında mutlak hata sırasıyla, 0.0304, Pearson korelasyon ölçütü 0.904 olarak elde edilmiştir. Bu modelleri kullanarak rastgele arama ve tekrarlayan optimizasyonlar ile güçlü bağlanan örnek bir peptit tasarlanmıştır. Bulgular alan bilgisinin makine öğrenme modeli eğitimdeki yerini vurgulamış, kullanılan örnek ağırlıklarının ve semantik amino asit vektörlerinin başarıya önemli katkıları gözlemlenmiştir. Bu çalışma çeşitli fonksiyonlara sahip peptit tasarlayabilen bir platform oluşturabilmek için temel noktaları göz önüne serer.
  • Master Thesis
    Predicting Software Size From Requirements Written in Natural Language: a Generative Ai Approach
    (01. Izmir Institute of Technology, 2024) Kennouche, Dhıa Eddıne; Demirörs, Onur
    In project management, software size measurement represents a critical process aimed at visualizing a project. This quantification is pursued independently of the specific technologies or technical decisions adopted during the project's development phase. Among the various methodologies employed for this purpose, the COSMIC Functional Size Measurement (FSM) and Event Points are used to facilitate such assessments. These methodologies are instrumental in offering a standardized approach for measuring software size, yet they inherently demand a considerable amount of manual effort. Furthermore, these methods require the manual extraction of Objects of Interest and Event Names, adding to the labor-intensive nature of the process. In response to these challenges, this thesis implements a suite of Artificial Intelligence (AI)-based methods that have dramatically transformed the measurement process. These innovative approaches encompass the creation of a Regression Model that predicts software sizes with remarkable accuracy, a Summarization Model that automates the extraction of Event Names, and a finely tuned Large Language Model (LLM) that generates Objects of Interest with a significant precision. The adoption of these AI-driven techniques has proven to be highly successful, substantially minimizing the manual effort traditionally required in software size measurement and thereby greatly enhancing both efficiency and reliability of estimation practices. Together, these AI-based methodologies represent a significant advancement in software size measurements, offering a more streamlined and efficient approach. By reducing the reliance on manual processes, these methods not only enhance the accuracy and reliability of measurements but also contribute to a more agile project management environment.
  • Master Thesis
    Analysis of Building Information Modeling (bim) Performance Using Big Data From a Construction Project
    (01. Izmir Institute of Technology, 2023) Bostan, Berkay Batuhan; Çavka, Hasan Burak
    This study aims to propose a systematical approach for evaluating BIM performance from a main contractor's perspective based on big data from a construction project. Retrospective case study is used as the research approach. Data is collected through interviews with the main contractor firm, and data from the logged project information in project databases including ACONEX and Microsoft Excel files. A framework containing performance metrics, specifically tailored to evaluate BIM performance based on big data, is developed from the combined analysis of literature review, interviews with main contractor, and overview of the project data. Collected project data and interview data are analyzed using the developed framework. Results of the data analysis are verified through follow-up interviews with the main contractor firm. Findings of the study suggest that it is possible to evaluate the BIM performance through analysis of collected BIM big data using the proposed systematical approach. Several performance problems were identified during the data analysis. Follow-up interviews revealed that identified performance problems from the data analysis largely coincided with the real-life experiences and accurate data entry is the key criterion for the analysis to yield correct results. The proposed framework should be tested in wider range of studies and may serve as a foundation for a future benchmarking system. Future work should focus on refining performance metrics, establishing a BIM big data database for benchmarking, exploring data's potential to be used for real-time performance assessment, and implementation of emerging Artificial Intelligence (AI) techniques for the analysis of big data.
  • Master Thesis
    Recognition of Counterfactual Statements in Turkish
    (01. Izmir Institute of Technology, 2023) Acar, Ali; Tekir, Selma
    Counterfactual statements describe an event that did not happen or cannot happen, and optionally the consequence of this event if it would happen. Counterfactual statements are the building blocks of human thought processes as people constantly reflect upon past happenings and consider their future implications. Counterfactual reasoning is essential for machine intelligence and explainable artificial intelligence studies. Detecting counterfactuals automatically with machine learning algorithms is very crucial for these areas. This thesis presents the development of the first-ever Turkish counterfactual detection dataset. It presents a comprehensive classification baseline and expands the scope of counterfactual detection to include the Turkish language.
  • Master Thesis
    Application of Artificial Neural Networks To Structural Reliability Problems
    (01. Izmir Institute of Technology, 2023) Köroğlu, Fahri Baran; Aktaş, Engin; Maguire, Marc
    The contemporary approach in structural engineering indirectly addresses uncertainties arising from load and resistance parameters by using safety factors. To consider these uncertainties in structural engineering, it is necessary to incorporate their statistical properties into the analysis and design process. However, this approach requires the calculation of challenging multi-fold probability integrals. Approximate methods known as FORM and SORM have been developed as an alternative to calculating those integrals. Unfortunately, these methods might have accuracy and convergence problems depending on the problem at hand. Simulation-based structural reliability methods have been developed to overcome the problems associated with approximate methods. The main problem with these methods is that they are often computationally expensive when along with finite element analysis, or it is hard to implement them when a more specific method is chosen to reduce computational costs. In this study, artificial neural networks have been applied to structural reliability problems to obtain accurate probability estimates with low computational cost. A special type of learning algorithm called Bayesian Regularization was used in the training of artificial neural networks. Additionally, details of the application of artificial neural networks to structural reliability problems are provided. At the end of the study, the advantages and disadvantages of applying artificial neural networks to structural reliability problems are presented and compared with other known structural reliability methods. Additionally, a new convergence criterion and an adaptive algorithm have been developed. It was observed that applying artificial neural networks to structural reliability problems provides both efficient and accurate probability estimates.
  • Master Thesis
    Classification of Contradictory Opinions in Text Using Deep Learning Methods
    (01. Izmir Institute of Technology, 2020) Oğul, İskender Ülgen; Tekir, Selma
    Natural language inference (NLI) problem aims to ensure consistency as well as accuracy of propositions while making sense of natural language. Natural language inference aims to classify the relationship between two given sentences as contradiction, entailment or neutrality. To accomplish the classification task, sentences or words must be translated into mathematical representations called vectors or embedding. Vectorization of a sentence is as important as the complexity of the classification model. In this study, both pre-trained (Glove, Fasttext, Word2Vec) and contextual word embedding methods (BERT) were used for comparison and acquire the best result. One of the natural language processing tasks NLI, is highly complex and requires solutions. Conventional machine learning methods are insufficient to carry out natural language processing solutions. Therefore, more advanced solutions are required. This study used deep learning methods to perform the classification task. Unlike conventional machine learning approaches, deep learning approaches reduce errors while increasing accuracy by repeating the data many times. Opinion sentences have complex grammatical structures that are difficult to classify. This study used Decomposable Attention and Enhanced LSTM for natural language inference to perform NLI classification task. Using the advanced LSTM deep learning method and Bert contextual vectors for natural language extraction on the SNLI dataset, an accuracy result 88.0% very close state of the art result 92.1% was obtained. In order to show the usability of the developed solution in different NLI tasks, an accuracy of 80.02% was obtained in the studies performed on the MNLI data set.