Sürdürülebilir Kalkınma Amaçları
Yayınlar
- MakaleAçık Erişim2026Real maritime measurement-driven machine learning for path loss modeling in shore-to-ship wireless links
Sağır, Nuğman; Eyüboğlu, Ekrem; Kuzulugil, Kenan; Tuğcu, Zeynep Hasırcı; Çavdar, İsmail Hakkı
Reliable propagation modeling remains a fundamental requirement for the design and deployment of maritime wireless communication systems, particularly in shore-to-ship scenarios characterized by highly variable environmental conditions. Unlike conventional empirical and deterministic models that rely on theoretical assumptions, the proposed approach is entirely measurement-driven, enabling more accurate and robust propagation modeling. Four regression algorithms—Gaussian Process Regression, Least Squares Boosting, Decision Tree, and Support Vector Regression—are evaluated using a feature set that includes transmission distance, sea state, weather conditions, and antenna configurations. Among the tested models, the Decision Tree achieves the best performance, with an RMSE of 1.18 dB and an R2 of 0.96, corresponding to an error reduction of approximately 45.6% compared to the best-performing empirical model. Feature importance analysis shows that transmission distance and antenna geometry dominate signal attenuation, while environmental variables have a limited influence at this frequency. Unlike most existing studies that emphasize deep learning or black-box models, this work demonstrates that lightweight and interpretable regression models can achieve comparable accuracy while enabling real-time link planning and practical deployment. The focus is on engineering applicability rather than proposing new learning architectures. Overall, the results indicate that measurement-driven machine learning provides accurate and interpretable solutions for shore-to-ship path loss modeling under real maritime conditions.
- MakaleAçık Erişim2024Measurement-based V2V propagation modeling in highway, suburban, and urban environments
Hasırcı Tuğcu, Zeynep; Kuzulugil, Kenan; Çavdar, İsmail Hakkı
Vehicle-to-vehicle (V2V) communication is one of the promising communication applications designed to optimize traffic conditions and has played a crucial role in the improvement of intelligent transportation technologies. Since there is still some uncertainty regarding generalized models that provide a more accurate representation of propagation environments, the existing literature emphasizes the need for additional experimental studies in various countries and propagation environments. This study aims to investigate the low-density and high-density characteristics of V2V channels for highway, suburban, and urban propagation environments in Türkiye. Thus, first, channel measurements were conducted for all propagation scenarios. Then, after the estimation of path loss parameters, the best-fitted path loss model was determined for each propagation scenario by comparing log-distance, two-ray, and log-ray models. It was observed that the log-ray model offered remarkably better performance than the two-ray model, especially in the majority of scenarios with two-ray characteristics. In addition, small-scale modeling and shadowing were also examined, and the outcomes were compared to relevant literature. Last, generalized path loss models were developed for six propagation scenarios and compared with previous studies. Providing additional experimental data on the impact of traffic and road environments that vary across countries on the V2V channel, this study not only validated and compared existing propagation models but also improved the representing accuracy and generalizability of the newly proposed propagation models. Here, all findings were presented in detail to support the motivation of the research.