Browsing by Author "Perihanoglu, Guzide Miray"

Now showing 1 - 2 of 2

Clustering Analysis of the Seismicity of Van Province and Its Surroundings Via Spatial Autocorrelation Techniques Filters
(Polska Akad Nauk, Polish Acad Sciences, 2022) Perihanoglu, Guzide Miray; Bilginer, Omer; Akyel, Elif
Destructive aftershocks such as the Mw 7.2 Van earthquake on October 23, 2011, and the Hoy (Iran) earthquake with Mw 5.9 on February 23, 2020, occurred in the province of Van and its surroundings. In earthquake studies, the issue of examining the distribution and homogeneity of earthquake incidences with Geographic Information Systems (GIS) based via spatial autocorrelation techniques is frequently investigated. Van province and its surroundings are among the areas with high earthquake risk due to its location on the East Anatolian Compressive Tectonic Block. The aim of this study is to analyze the spatial patterns of earthquakes with magnitude Mw 4 and above that occurred in the province of Van and its surroundings during the instrumental period and to determine to cluster. Spatial cluster analyses play an important role in examining the distribution of seismicity. The data used in the study have been taken from the database system of the Earthquake Department of the Republic of Turkey Ministry of Interior Disaster and Emergency Management Presidency. Moran's I and Getis-Ord Gi methods from spatial autocorrelation techniques were preferred on the earthquake data set to be used in this research. It has aimed to determine the dangerous areas by testing the earthquake distributions in clustered regions via spatial autocorrelation techniques.
Performance Evaluation of Geoai-Based Approach for Path Loss Prediction in Cellular Communication Networks
(Springer, 2024) Perihanoglu, Guzide Miray; Karaman, Himmet
Accurate signal path loss models for predictions are crucial in current cellular communication networks. Recently, numerous path loss estimation methods have been presented to improve the efficiency of networks. However, most of these existing models do not include spatial data such as land use/land cover, terrain elevation, building height, and the effect of topography. To address this issue, this study proposes a GeoAI-based technique for path loss estimation in cellular communication networks, addressing existing models' lack of spatial data integration. Support Vector Regression, K-Nearest Neighbor, Random Forest, and multi-layer perceptron (MLP) artificial neural network models are evaluated using field measurements in an urban, suburban area in Van, Turkey, across various frequencies. Among the models, MLP with three hidden layers, nine input variables, hyperbolic tangent activation function, and Adam optimization method performs best. At 900 MHz, MLP has been observed with MSE, RMSE, MAE, and R values of 0.22 dB, 0.47 dB, 0.46 dB, and 0.99 dB, respectively. Lastly, a comparison of the developed model to the Free space, COST 231, Ericsson, and SUI models revealed that the GeoAI-based path loss models outperformed the empirical models regarding prediction accuracy and generalization. This study underscores the significance of integrating spatial data into path loss prediction, particularly in diverse urban and suburban environments, for optimizing cellular communication networks.