Search

Open-finance systems increasingly compose portfolio models, data services, and execution interfaces supplied by different parties. This modularity is useful only if the executed wealth path can be checked independently of the model that proposed it. We study a…

We developed a series of financial social media sentiment analysis models starting with PyFin-Sentiment, a recent state-of-the-art domain-specific large language model for the financial domain. We focused on label accuracy and improvements in the quality and q…

This paper explores the role of archival study in exploring site integrity within the Historic Urban Landscape (HUL) framework, using the case of Islamic heritage sites in Java, Indonesia. In contexts where material traces have been lost or obscured, archival …

Afet risklerinin azaltılmasında, fiziksel zarar görebilirlik düzeylerinin mekânsal olarak belirlenmesi ve görselleştirilmesi, kentsel dayanıklılığın artırılması açısından kritik bir öneme sahiptir. Bu çalışma, Amasya kent merkezinde afet kaynaklı fiziksel kırı…

The rapid growth of city populations and the increasing complexity of managing city infrastructure have led to the emergence of smart cities, which rely on advanced technologies to optimise urban services. However, one of the key challenges facing smart cities…

Peyzaj mimarlığında simetri, kullanıcıların çevresel algısını ve etkileşimini yönlendiren bir tasarım ilkesidir. Bu bağlamda, simetrinin gözlemci davranışına etkisini incelemek amacıyla Konya kentinde bir çalışma yürütülmüştür. Çalışmada, göz izleme yöntemi ku…

Sunulan çalışmada, kalp hastalığı riskinin erken ve güvenilir biçimde tahmin edilmesini sağlayan makine öğrenmesi tabanlı bir mobil uygulama geliştirilmiştir. Dokuz farklı algoritma değerlendirilmiş, en yüksek doğruluğa (%86,81) sahip olan k-NN modeline rağmen…

Accurate and transparent blood glucose forecasting is crucial for effective diabetes management. This paper presents an interpretable deep learning (DL) framework based on multi-task learning (MTL) for forecasting glucose levels at multiple prediction horizons…

Efficient semantic segmentation and compression of 3D point cloud data are essential for enabling scalable, real-world applications involving large-scale LiDAR environments. This work presents a lightweight hybrid framework that integrates point transformer v3…

In this study, a classification problem is discussed to predict whether individuals' annual income levels are above $50,000. The UCI Adult Income Dataset, which is derived from the 1994 US Census (Census) data and is widely used in the field of machine learnin…

Generative Artificial Intelligence is gaining popularity every day and uses contextual data to personalize and enhance user experiences. This paper explores music generation that is conditioned on weather. It influences musical compositions by connecting MIDI …

In this study, diabetes prediction was conducted using XGBoost, Support Vector Machines (SVM), and a Multilayer Artificial Neural Network (ANN). Attributes that cannot be biologically ‘0’ (e.g. glucose, BMI) were first marked as NaN. After filling the missing …

Bu çalışmada, el yazısı karakterlerin tanınmasına yönelik derin öğrenme tabanlı bir model geliştirilmiştir. Model, farklı sayıda çıkış sınıfı (karakter) için test edilmiş; yalnızca 10 karakterin sınıflandırıldığı senaryoda %96 doğruluk oranı elde edilirken, sı…

Robust object detection and classification in dynamic industrial scenarios is still a challenge, in particular if the system has to work in real-time on mid-ranged hardware. Classical vision-based methods have difficulties to cope with low/weak illumination, r…

Ortahisar Kalesi ve çevresindeki troglodit (kaya) mekânlar, hem mimari hem de hukuki açıdan önemli sorunlar barındırmaktadır. Bu çalışmada Ortahisar Kalesi ve çevresindeki trogloditlerin mekânsal özleri, mimarlık kuramındaki tanımları ve hukuksal hak-mülkiyet…

The unlimited nature of consumption and needs contrasts with the scarcity of usable resources, necessitating the optimal use of available resources. Alongside the careful protection of the environment and human health, it is crucial to meet needs with maximum …

E-commerce is evolving rapidly, creating a more competitive market environment. With this development, gaining a competitive advantage has become even more crucial. Companies implement various strategic moves to maintain their position in this competitive mark…

Hareket sırasında dairesel alanları tarayan sistemlerde, hareket hızını ölçmek için yaygın olarak jiroskoplar, takometreler ve kodlayıcılar kullanılır. Bu çalışmada, manyetometre, jiroskop ve ivmeölçer içeren BNO055 sensörü açısal hareketi ölçmek için kullanıl…

Sleep disorders such as insomnia, sleep bruxism, narcolepsy, and sleep-disordered breathing have different sleep quality parameters such as cyclic alternating pattern phases and A subtype phases. This study aims to analyze and predict the A phase subtypes from…

This study employs a supervised learning approach for the Stock Portfolio Selection (SPS) problem. The proposed approach solves three problems defined in the literature review: the narrow period selection problem, the proper objective selection problem, and th…