Güncel Gönderiler: Bilgisayar Mühendisliği Bölümü
Toplam kayıt 214, listelenen: 1-20
-
Shapley Patch Valuation Method for Histopathological Image Classification
(Institute of Electrical and Electronics Engineers Inc., 2025)This study introduces a patch valuation method based on Shapley values for histopathological image classification, addressing the computational challenges of processing large whole-slide images (WSIs). The proposed approach ... -
Data Valuation with Shapley-based Methods for Medical Image Classification
(Institute of Electrical and Electronics Engineers Inc., 2025)This study introduces novel approaches to data valuation in medical image classification, focusing on the Gradient Shapley and Improved Gradient Shapley methods. These methods aim to reduce data selection costs while ... -
Deep Learning-based Virtual Birefringence Imaging and Staining of Amyloid Deposits in Label-Free Tissue
(Institute of Electrical and Electronics Engineers Inc., 2025)We present virtual birefringence imaging and staining, enabling label-free detection of amyloid deposits in tissue. By transforming autofluorescence images into virtually-stained brightfield and polarization images, this ... -
Population-based Local Search Algorithms for Cross-domain Search
(Pamukkale Üniversitesi, 2025)Population-based local search is a meta-heuristic algorithm combining the principles of the population-based search and the local search. This study presents an extensive comparison of two population-based local search ... -
Derin Öğrenme ve Makine Öğrenmesi Yöntemleri ile Sosyal Medya Verilerinden Suç Tespiti
(Nigde Omer Halisdemir University, 2025)Bu çalışmada, Türkçe sosyal medya paylaşımlarındaki tehdit ve hakaret içeriklerinin tespiti amaçlanmıştır. Doğal Dil İşleme teknikleri kullanılarak sosyal medya verileri üzerinde derin öğrenme algoritmalarıyla modeller ... -
Ters Tasarımlı Ultra-Kompakt Alt/Üst/Bant Geçirgen Entegre Fotonik Filtreler
(TÜBİTAK, 2023)Günümüzde internetin de yaygınlaşmasıyla iletilen veri miktarının yüksek hızlı şekilde artması, düşük güçle çalışan ve yüksek enerji verimine sahip, ölçeklenebilir, kullanım sırasında uyarlanabilir sistemleri gerekli ... -
Depremdeki Riskli Yapıların Beton Performansının Yapay Öğrenme Yöntemleri İle Değerlendirilmesi
(IEEE, 2025)Yapı malzemelerinin dayanımını tahmin etmek günümüzde depremlere karşı önlem almak için çok hayati bir süreçtir. Bu sürecin maliyetini düşürerek etkinliğini arttırmak olası can kayıplarının önüne geçmesini sağlayabilir. ... -
Histopatoloji Görüntülerinin Sınıflandırılması için Sinir Mimarisi Arama
(IEEE, 2025)Histopatoloji görüntülerinin otomatik sınıflandırılması tıbbi tanı süreçlerinde önemli rol oynamaktadır. Son yıllarda, sinir mimarisi arama yöntemleri derin ögrenme modellerinin otomatik olarak tasarlanmasını saglayarak ... -
Beyaz Kan Hücresi Tespitinde YOLO Tabanlı Modellerin Deneysel Karşılaştırması
(IEEE, 2025)Bağışıklık sisteminin temel bileşenlerinden biri olan beyaz kan hücrelerinin tespit edilmesi, sınıflandırılması ve analizlerinin yapılması enfeksiyon ve kanser gibi hastalıkların teşhisi için büyük önem taşımaktadır. Bu ... -
Fake News Detection on Social Media Data using Community Notes with Machine Learning
(IEEE, 2025)The spread of misinformation on digital platforms has become a critical issue that requires the development of effective detection mechanisms. This study explores the use of machine learning techniques to classify fake ... -
Leukemia White Blood Cell Classification Using DenseNet121 Embeddings and Ensemble Learning
(IEEE, 2025)Leukemia diagnosis through white blood cell (WBC) classification remains challenging, requiring expert pathologists and significant time investment. This study presents a hybrid approach for leukemia WBC classification ... -
Detecting Spam Comments in Product Reviews on E-Commerce Websites
(IEEE, 2025)With the increasing use of e-commerce platforms, user reviews have become a major factor influencing customer decisions. However, the presence of spam comments—whether posted automatically or manually—negatively affects ... -
Latency-Aware and Energy-Efficient Task Offloading in IoT and Cloud Systems with DQN Learning
(MDPI, 2025)The exponential proliferation of the Internet of Things (IoT) and optical IoT (O-IoT) has introduced substantial challenges concerning computational capacity and energy efficiency. IoT devices generate vast volumes of ... -
Investigating Hepatic Fibrosis Heterogeneity by Threedimensional Imaging in Metabolic Dysfunction-Associated Steatotic Liver Disease
(Nature, 2025)Although liver biopsy is a well-established technique to assess fibrosis it has several limitations, including invasive nature, semi-quantitative assessment methods, significant sampling and observer variability, making ... -
Multi-teacher Based Knowledge Distillation for Retinal Vessel Segmentation
(Springer, 2025)Accurate segmentation of retinal vessels is crucial for the early diagnosis and management of various ocular diseases. Existing methods often struggle to segment thin vessels, leading to missed diagnoses and inaccurate ... -
Assessing the Impacts of Blockchain Technology on Supply Chain Efficiency: A Data‑Driven Integrated Decision‑Making Framework
(Springer, 2025)The digitalization of supply chains enhances efficiency and aligns with the expectations of customers and suppliers. In data-intensive industries, such as Oil and Gas (O&G), blockchain technology, a key tool for supply ... -
A multi-Strategy Chimp Optimization Algorithm for Solving Global and Constraint Engineering Problems
(Springer, 2025)The chimp optimization algorithm (ChOA) is a recently introduced metaheuristic algorithm inspired by nature. This algorithm identified four types of chimpanzee groups: attacker, barrier, chaser, and driver, and proposed ... -
A Novel Hybrid Metaheuristic Method for Efficient Decentralized LoT Network Layouts
(Elsevier, 2025)This paper introduces a Hybrid Genetic Particle Swarm Optimization (HGPSO) method focusing on optimal and efficient sensor deployment in Wireless Sensor Networks (WSNs) and Decentralized IoT (DIoT) networks. Effective ... -
Parameter Tuning for Combinatorial Bees Algorithm in Travelling Salesman Problems
(AIP Conference Proceedings, 2023)Bees Algorithm is one of the most used nature-inspired algorithms. There are five parameters applied in the basic combinatorial version of Bees Algorithm: number of scout bees, number of elite bees, number of best bees, ... -
Towards Better Sentiment Analysis in the Turkish Language: Dataset Improvements and Model Innovations
(MDPI, 2025)Sentiment analysis in the Turkish language has gained increasing attention due to the growing availability of Turkish textual data across various domains. However, existing datasets often suffer from limitations such as ...
