Raziye hale Topaloglu

Ms. Raziye hale Topaloglu


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 July 2021 in Turkish Journal of Engineering
Verified
Journal Article
Closed access
KAKübra Ali̇yazicioğlu
Kübra Ali̇yazicioğlu
FBFatmanur Beker
Fatmanur Beker
RTRaziye hale Topaloglu
Raziye hale Topaloglu
BBBurhan Baha Bilgilioglu
Burhan Baha Bilgilioglu
RCResul Comert
Resul Comert
Irregular urbanization causes problems such as decrease in fertile agricultural areas, irregular industrialization and urbanization. To provide a healthier life opportunity for future generations without disturbing nature, it is essential to determine the temporal changes in land use and to make land management plans accordingly. In this study, land use/land cover (LULC) change occurred in Kahramanmaras province within 30 years was investigated by remote sensing and integration of Geographic Information Systems. Landsat satellite images of 1988-1998-2008-2018 were obtained for the production of LULC maps. Each image was classified according to supervised classification approach using the support vector machines (SVMs) algorithms. The confusion matrix was created for each year to examine the accuracy of the LULC maps. The overall accuracy of the thematic maps was obtained as 91.76%, 93.56%, 86.89% and 88.29%, respectively. Also, Kappa values of thematic maps for each year were obtained as 0.88, 0.91, 0.81 and 0.84, respectively. When the results were examined, the development of industry in the city area and the construction of the airport contributed to the development of the social and economic structure of the city. The increase in the number of housing in the related regions has led to an increase in the amount of urban areas and a decrease in agricultural areas.

10 March 2023 in Journal of Environmental Planning and Management
Verified
Journal Article
Closed access
BVBeril Varol
Beril Varol
Szabó SzilárdSzabó Szilárd
Szabó Szilárd
RTRaziye hale Topaloglu
Raziye hale Topaloglu
GAGül Aslı Aksu
Gül Aslı Aksu
Elif SertelElif Sertel
Elif Sertel
This study aims to investigate the changes in landscape metrics with varying spatial resolution from Sentinel-2 (10 m), SPOT 7 (1.5 m), Pleaides (0.5 m), and Worldview-4 (0.3 m) images. We implemented Geographic Object-Based Image Analysis (GEOBIA) techniques to all images to identify 21 land use and land cover (LULC) classes, which were then used to calculate several landscape metrics. We performed the Welch hypothesis testing on the class-level landscape metrics and applied Standardized Principal Component Analysis (PCA) with the correlation matrix to reveal the multivariate pattern of landscape metrics. Our results showed that 10 m and even the 1.5 m spatial resolutions cannot guarantee the identification of all LULC classes, and class areas change with varying spatial resolution (sometimes with 200% differences). Sentinel-2 images have some limitations, specifically from the landscape ecological planning perspective; on the other hand, Pleaides and Worldview-4 seem good alternatives to understand habitats’ viability and landscape isolation/connectivity.

30 June 2023 in Mersin Photogrammetry Journal
Verified
Journal Article
Closed access
YVYunus Emre Varul
Yunus Emre Varul
HAHilal Adiyaman
Hilal Adiyaman
TBTolga Bakirman
Tolga Bakirman
BBBülent Bayram
Bülent Bayram
EAElif Alkan
Elif Alkan
RTRaziye hale Topaloglu
Raziye hale Topaloglu
The images are important components of real estate applications on the internet to inform users. There are multiple rental and sale properties and many images of these properties on the internet, and it is challenging to control the images of these real estate in terms of time, workload, and cost. Considering the requirements of the problem, Deep Learning (DL), one of the Artificial Intelligence (AI) methods, offers ideal solutions. This study aims to distinguish images that contain humans using deep learning techniques. This will also aid in not violating the privacy of people according to the Law on the Protection of Personal Data in the image content used in real estate applications. For this purpose, firstly, a dataset of real estate images with and without humans called the Real Estate Privacy (REP) dataset was created. The REP dataset was split into 70%, 20%, and 10% for training, validation, and testing, respectively. Secondly, the REP dataset was trained with Inceptionv3, ResNet-50, and DenseNet-169 architectures using transfer learning. Lastly, the performances of the architectures were evaluated by accuracy, precision, recall, and F1-score accuracy metrics. Experimental results indicate that the 52 epoch ResNet-50 architecture is the best for our datasets with 98.45% overall accuracy and 98.00% precision, 98.90% recall, and 98.44% F1-score. The Inceptionv3 model provided the best results on the 55th epoch with 98.27% accuracy, 97.81% precision, 98.71% recall, and 98.26% F1-score. Finally, the DenseNet-169 model produced the best results on the 47th epoch, with 97.81% accuracy, 97.09% precision, 98.52% recall, and 97.80% F1-score. Accuracy assessment shows that the highest accuracy among the three architectures was obtained with the ResNet-50 architecture This study shows that deep learning methods offer a perspective to image content control and can be used efficiently in real estate applications.