Sürdürülebilir Kalkınma Amaçları
Yayınlar
- MakaleYalnız künye2026A Dense and Sparse Attention in Vision Transformer for Remote Sensing Image Classification
Celik, Kemal
Satellite imagery plays a crucial role in various applications, such as environmental monitoring, urban planning, and disaster response. Previously, Convolutional neural networks have played a crucial role in improving remote sensing scene classification by effectively capturing spatial features. However, they often struggle with long-range dependencies and complex spectral patterns in satellite images. Recently, transformer-based architectures, initially designed for natural language processing, have been adopted in computer vision to leverage self-attention mechanisms for capturing long-range dependencies. To effectively extract the long-range dependencies and complex patterns, this paper proposes a novel method combining dense and sparse attention mechanisms to enhance remote sensing scene classification in different scales. The dense attention mechanisms capture comprehensive connections within satellite images, followed by sparse attention mechanisms applied at both tile and patch scale levels. This multi-scale attention strategy allows the model to efficiently focus on important spatial and spectral features while managing computational complexity. Extensive experimental evaluations on three benchmark datasets, such as Merced, AID, and Optimal-31, demonstrate significant improvements in classification accuracy, achieving 98.9, 97.5, and 97.8, respectively. Experimental results show that the proposed framework outperforms CNN and Transformer baselines, enhancing the accuracy and robustness of remote sensing scene classification for geospatial analysis.
- MakaleYalnız künye2026Multi level throttled attention for accurate and efficient classification of retinal diseases in OCT images
Celik, Kemal; Celik, Fatih
The classification of retinal diseases using Optical Coherence Tomography images has gained significant attention in recent years. However, due to the heterogeneity of retinal disorders, achieving high classification accuracy remains challenging. While deep learning has improved the identification of various ophthalmic conditions, accurate and early diagnosis is still critical for effective clinical decision-making. Additionally, reducing computational complexity is essential for building scalable diagnostic systems. To address these challenges, we propose a novel Multi-level Throttled Attention (MLTA) model that first applies attention to extract important features, followed by throttling to filter out redundant or less useful features. This process is applied at multiple stages, operating on both Convolutional Neural Network layers and Transformer architectures, and then fuses them finally. This approach optimizes feature selection by preserving the most informative retinal features while discarding redundant ones from multi-level feature maps. As a result, the model enhances classification performance while reducing computational overhead. We evaluate our proposed model on two benchmark OCT datasets: OCT2017 and OCTID, achieving accuracy scores of 99.59 ± 0.04% and 99.71 ± 0.03%, respectively. Our method outperforms existing CNN-based and Vision Transformer-based models, demonstrating superior accuracy and efficiency through this hierarchical attention.
- MakaleAçık Erişim2025Elipsoidin düzleme lambert konform konik tasvirinde, coğrafi ve düzlem koordinatlar arasında dönüşüm, jeodezik temel problem çözümü
Celik, Kemal; Kaya, A
Yeryüzünde yapılan ölçülerin değerlendirilmesinde, referans yüzeye ihtiyaç duyulur. Bu yüzey, çalışma alanı büyüklüğüne göre; düzlem, küre ya da elipsoid olarak seçilir. Elipsoid üzerinde yapılacak jeodezik hesaplamaların, düzlem hesabına göre daha zor yapıya sahip olması nedeniyle; yüzey üzerindeki bilgilerin düzleme geçirilmesi yoluna gidilir. Bu çalışmada elipsoidin düzleme tasvirinde kullanılan metotlardan biri olan Lambert Konform Konik (LKK) tasvir incelenmiştir. LKK tasvirinde, elipsoid üzerindeki bilgiler bir yardımcı yüzey aracılığı ile düzleme taşınır. LKK’da, yardımcı yüzey olarak koni kullanılır. Bu çalışmada sözkonusu tasvirin temel yapısı tanımlandıktan sonra, elipsoid coğrafi koordinatları ile düzlem koordinatları arasındaki dönüşümler için kapalı formüller incelenmiş sayısal örnekler verilmiştir. Ayrıca bu tasvir koordinatlarıyla, elipsoid çözüme eşdeğer jeodezik temel problem çözüm formülleri de sayısal çözümlerle incelenmiştir. Bir noktanın koordinatları ile koordinatı bilinmeyen noktayı birleştiren jeodezik eğri ve bu eğrinin azimutu bilindiği durumda ikinci noktanın koordinatları ve azimutun hesaplanması yapılmıştır. Bilinen iki noktanın koordinatlarından jeodezik eğri uzunluğu ve bu eğrinin iki ucundaki azimutların hesaplaması yapılmıştır.
- MakaleAçık Erişim2025Optimizing Land Image Classification: A Deep Learning Approach with ResNet-101 on the EuroSAT Dataset
Celik, Fatih; Celik, Kemal
The classification of image is essential to make LULC (Land Use Land Cover) maps. However, the classification of land cover plays a vital role for studying and modernizing the land areas. Recently, deep learning (DL) techniques have achieved outstanding performance in the classification of high-resolution images. Different techniques have been employed in traditional methods to identify LULC due to its complex and ever-changing nature. However, these studies have shown improved outcomes despite some restrictions such as inaccuracies and reduced performance. To address these problems, the proposed study introduces a Squeeze Synchronization Layer (SSL) and a Convolve Craft Focus Module (CCFM) where, SSL reduces input data complexity by removing noise and irrelevant information from images using pooling and convolutional operations also, CCFM enhances feature extraction to improve land classification accuracy. The EUROSAT land image dataset is utilized for the evaluation of the introduced model. Whereas, the dataset comprises of 64x64 images, which are captured by satellite Sentinel-2A in ResNet 101 input layer. Although, a SSL is suggested, and a CCFM is implemented in the convolutional layer for classifying land images. However, the efficiency of the system is evaluated by measuring performance metrics such as recall, F1score, precision, and accuracy values of the proposed system. The accuracy value of the proposed system is 96% of accuracy, 100% of precision, 100% of recall, and 100% of F1-score, signifies the superior efficiency of the proposed model.
- MakaleAçık Erişim2025Kurtun Dam oscillate characterization with landslide possible effect detection using InSAR observations
Celik, Fatih; Sanli, Fusun Balik; Celik, Kemal; Celik, Ayse
Observing and analyzing areas prone to landslides is crucial due to the extensive destructive capacity of landslides. To monitor landslide activities across diverse areas, remote sensing data and image processing methods are employed. This study proposes a method that integrates Multi-temporal Interferometric Synthetic Aperture Radar and advanced temporal tracking technologies to intensify surveillance of the Kurtun Dam and its valley. According to Sentinel-1 A data, the net displacement rates of the dam crest varied between − 12 and 2 mm/year (LOS). InSAR technology surveys the entire dam catchment area, detecting critical infrastructure such as slopes, spillways, and access roads. The crest of the Kurtun Dam experiences oscillatory deformation during filling activities, but the lateral slopes and downstream abutment remain stable. As reservoir water levels rise, the dam structure exhibits downstream deformations, whereas declining water level results in upstream displacements. Monitoring points located the opposite Ozkurtun settlement and within the reservoir area, both facing the dam, exhibited displacement rates of up to -50 mm monthly. In regions susceptible to landslides, the greatest annual displacement rates were observed to be -54 and − 127 mm/year. This study suggests that integrating 3D modeling with InSAR technology into dam monitoring systems can significantly enhance their effectiveness. At Kurtun Dam and other crucial locations within the catchment area, the integrated approach combined with topographic monitoring, ensures reliable landslide detection and analysis. By advancing monitoring technology for embankment dams, this strategy prioritizes safety and structural integrity assessments.
- MakaleAçık Erişim2025Lightweight Transformer Model for Agricultural Land Use and Land Cover Classification
Celik, Kemal
Observing agricultural land use via remote sensing images is essential for ensuring food security, estimating yields and planning efficient exports nonetheless precise classification continues to be difficult because of the varied and evolving characteristics of agricultural environments. This research aims to evaluate and optimize advanced deep learning architectures particularly Vision Transformer (ViT) models for agricultural land-use classification tasks. Specifically, we employed ViT-Base-16 and other lightweight models DeiT-Tiny and EfficientNet-B0 applying techniques such as model layer compression and advanced data augmentation CutMix and Cutout to achieve high accuracy while significantly reducing computational complexity. Evaluation was performed using three benchmark remote sensing datasets EuroSAT, NWPU-RESISC45 and SIRI-WHU which include diverse spatial resolutions and agricultural classes relevant for practical monitoring. Findings indicate that the optimized ViT algorithm is highly effective in recognizing global spatial connections, consistently achieving remarkable classification accuracy exceeding 99% on a newly assembled dataset containing around 200 samples of Google Earth imagery. Furthermore, for the first time in agricultural image classification compressing the ViT-Base model by pruning 50% of its layers significantly reduced complexity maintaining competitive accuracy 97.9% on SIRI-WHU. The resulting models are particularly suitable for deployment on devices with limited computational resources supporting real-world operational agricultural monitoring systems. This study emphasizes the revolutionary possibilities and practical use of optimized transformer-based models that offer scalable and efficient solutions specifically designed for precision agriculture applications.
- MakaleAçık Erişim2022Gayrimenkul değerlemesinde geleneksel yöntemler
Celik, Kemal
Gayrimenkul değerlemesi, gayrimenkul veya ilişik hakların belirlenen zaman periyodunda muhtemel değerinin gerçeğe yakın olarak belirlenmesidir. Gayrimenkul piyasasının güvenli işleyebilmesi, gayrimenkullerin güncel ve gelecekteki rayiç değerlerinin bilinmesine bağlıdır. Gayrimenkullerin gerçek değerlerinin bilinmemesi, alım-satım işlemleri, emlak vergisi, kentsel dönüşüm uygulamaları vb. işlemlerde sorun oluşturmaktadır. Gayrimenkullerden güncel değere göre vergi alınmaması ekonomik kayıplara neden olmaktadır. Günümüzde nominal değerleme, çoklu regresyon ve yapay sinir ağları, bulut CBS vb. farklı birçok kitlesel değerleme yöntemleri taşınmaz değerleme işlemlerinde kullanılmaktadır. Ülkemizde geleneksel tekil değerleme yöntemi olarak kullanılmakta olan maliyet yöntemi, gelir yöntemi ve emsal karşılaştırma yöntemleri bu çalışmada örnek değerleme çalışması eşliğinde tartışılmıştır. Yapılan bu örnek değerleme çalışmasında arazi, arsa tanımları üzerinde durularak, esasen konut alanı ve sanayi alanına isabet eden alanlarda karşılaştırma yöntemi kullanılarak değerleme yapılmıştır. Samsun İli, Atakum İlçesi, Büyükkolpınar Mahallesi ve Gümüşhane İli, Merkez, Bağlarbaşı Mahallesi sırasıyla konut ve sanayi alanı değerlemesi çalışması için pilot bölge seçilmiş ve buna uygun olarak parsel alanı, imar hakkı, satış tarihi, satış değeri verileri elde edilmiştir. Kentteki konut alanına isabet eden arsalar ile sanayi alanı tanımlı arsaların değerlerinin değerleme birimleri (alan/hacim) açısından farklı olduğu tartışılmıştır.