Halenur Sazak

Object detection technologies form the foundation of real-time performance across a broad spectrum of applications, ranging from autonomous systems to medical imaging. This study analyzes the extensive architectural evolution of the YOLO series, the benchmark for this field, from its initial version to the cur rent YOLO26 model. Throughout the paper, structural transformations in the backbone, neck, and detection head components are examined chronologically. The review focuses on critical technical milestones, including the transition from anchor-based to anchor-free systems, the integration of attention mechanisms, and optimizations to loss functions. Furthermore, by evaluating the density of literature, data labeling tools, and the wide range of applications, the study exam ines the evolutionary logic of object detection architectures and the technological framework of modern models in comprehensive detail.

Pamukkale University Journal of Engineering Sciences

Background/Objectives: Accurate detection and classification of blood cell types in microscopic images are crucial for diagnosing various hematological conditions. This study aims to develop and evaluate advanced architectures for automating blood cell detection and classification using the newly proposed YOLOv10 and YOLOv11 models, with a specific focus on identifying red blood cells (RBCs), white blood cells (WBCs), and platelets in microscopic images as a preliminary step of the complete blood count (CBC). Methods: The Blood Cell Count Detection (BCCD) dataset was enriched using data augmentation techniques to improve model robustness and diversity. Extensive experiments were performed, including complete weight initialization, advanced optimization strategies, and meticulous hyperparameter tuning for the YOLOv11 architecture. Results: The YOLOv11-l model achieved an overall mean Average Precision (mAP) of 93.8%, reflecting its robust accuracy across multiple blood cell types. Conclusions: The findings underscore the efficacy of the YOLOv11 architecture in automating blood cell classification with high precision, demonstrating its potential to enhance hematological analyses and support clinical diagnosis.

Summary: 5G and beyond (5GB) systems show a flexible characteristic to meet different user communications requirements in parallel. Multi‐numerology waveform design is an important part of this human centric characteristic, however, it is necessary to make multi‐numerology planning. In this paper, the integrated sensing and communications (ISAC) concept is used with machine learning (ML) techniques to develop an intelligent numerology control mechanism for 5GB. Thanks to the ISAC capabilities, an environment‐aware system is designed, and several useful sensing information (USI) that affect the wireless channel characteristic is utilized. It is assumed that the USI is obtained through 5GB smart city networks. At that point, synthetic data generation is performed to form a new dataset with USI‐based features. Additionally, a novel feature control algorithm is proposed in the paper. Lastly, simulation results are presented for different type of ML models including several ensemble methods.