Browsing by Author "Maraş, Hadi Hakan"

Now showing 1 - 15 of 15

An evaluation of the relationship between physical/mechanical properties and mineralogy of landscape rocks as determined by hyperspectral reflectance
(Springer Heidelberg, 2016) Maras, Erdem Emin; Maraş, Hadi Hakan; Caniberk, Mustafa; Odabas, Mehmet Serhat; Degerli, Burcu; Maras, Suleyman Sirri; Maras, Hadi Hakan; 34410
We investigated the relationships between mineral content and the physical and mechanical properties of landscape rock using a non-destructive remote sensing method applied in the laboratory. Using this technique, the spectral properties of the landscape rock could be collected at different wavelengths without harming the samples. Differences in spectral reflectance were compared with the physical and mechanical properties of the stone. Significant correlations were observed between reflectance values and the rocks' mechanical and physical properties, with correlation coefficients of 95 to 99 %. However, establishing a correlation between two variables is not a sufficient condition to establish a causal relationship. Mineral densities and mineral content are characteristics used for the classification of landscape rock. We have concluded that although spectral signatures from landscape rock can be used for predicting which stones might have similar features when comparing two batches of stone, the high correlations we discovered cannot confirm a cause and effect relationship that would allow for the prediction of a rock's physical and mechanical properties. Although this conclusion is disappointing, the mineral content and the significant correlations discovered by hyperspectral reflectance scanning can be used as supplementary information when comparing two samples of landscape rock.
Automated Classification of Rheumatoid Arthritis, Osteoarthritis, and Normal Hand Radiographs with Deep Learning Methods
(Springer, 2022) Ureten, Kemal; Maraş, Hadi Hakan; Maras, Hadi Hakan; 34410
Rheumatoid arthritis and hand osteoarthritis are two different arthritis that causes pain, function limitation, and permanent joint damage in the hands. Plain hand radiographs are the most commonly used imaging methods for the diagnosis, differential diagnosis, and monitoring of rheumatoid arthritis and osteoarthritis. In this retrospective study, the You Only Look Once (YOLO) algorithm was used to obtain hand images from original radiographs without data loss, and classification was made by applying transfer learning with a pre-trained VGG-16 network. The data augmentation method was applied during training. The results of the study were evaluated with performance metrics such as accuracy, sensitivity, specificity, and precision calculated from the confusion matrix, and AUC (area under the ROC curve) calculated from ROC (receiver operating characteristic) curve. In the classification of rheumatoid arthritis and normal hand radiographs, 90.7%, 92.6%, 88.7%, 89.3%, and 0.97 accuracy, sensitivity, specificity, precision, and AUC results, respectively, and in the classification of osteoarthritis and normal hand radiographs, 90.8%, 91.4%, 90.2%, 91.4%, and 0.96 accuracy, sensitivity, specificity, precision, and AUC results were obtained, respectively. In the classification of rheumatoid arthritis, osteoarthritis, and normal hand radiographs, an 80.6% accuracy result was obtained. In this study, to develop an end-to-end computerized method, the YOLOv4 algorithm was used for object detection, and a pre-trained VGG-16 network was used for the classification of hand radiographs. This computer-aided diagnosis method can assist clinicians in interpreting hand radiographs, especially in rheumatoid arthritis and osteoarthritis.
Automatic Coastline Detection Using Image Enhancement and Segmentation Algorithms
(Hard, 2016) Maras, Erdem Emin; Maraş, Hadi Hakan; Caniberk, Mustafa; Maras, Hadi Hakan; 34410
Coastlines have hosted numerous civilizations since the earliest times of mankind due to the advantages they offer such as natural resources, transportation, arable areas, seafood, trade, and biodiversity. Coastal regions should be monitored vigilantly by planners and control mechanisms, and any changes in these regions should be detected with its human or natural origin, and future plans and possible interventions should be formed in these aspects to maintain ecological balance, sustainable development, and planned urbanization. Integrated coastal zone management (ICZM) provides an important tool to reach that goal. One of the important elements of ICZM is the detection of coastlines. While there are several methods to detect coastlines, remote sensing methods provide the fastest and the most efficient solutions. In this study, color infrared, grayscale, RGB, and fake infrared images were processed with the median filtering and segmentation software developed within the study, and coastal lines were detected by the edge detection method. The results show that segmentation with fake infrared images derived from RGB images give the best results.
Automatic detection of spina bifida occulta with deep learning methods from plain pelvic radiographs
(2023) Maraş, Hadi Hakan; Üreten, Kemal; Maraş, Yüksel; Maraş, Hadi Hakan; Gök, Kevser; Atalar, Ebru; Çayhan, Velihan; 34410
Purpose: Spina bifida occulta (SBO), which is the most common congenital spinal deformity, is often seen in the lower lumbar spine and sacrum. In this study, it is aimed to develop a computer-aided diagnosis method that will help clinicians in the diagnosis of spina bifida occulta from plain pelvic radiographs with deep learning methods and transfer learning method. Materials and methods: The You Only Look Once (YOLO) algorithm was used for object detection, and classification was made by applying transfer learning with a pre-trained VGG-19, ResNet-101, MobileNetV2, and GoogLeNet networks. Our dataset consisted of 206 normal lumbosacral radiographs and 160 SBO lumbosacral radiographs. The performance of the models was evaluated by metrics such as accuracy, sensitivity, specificity, precision, F1 score, and area under the ROC curve (AUC) results. Results: In the detection of SBO, 85.5%, 80.8%, 89.7%, 87.5%, 84%, and 0.92 accuracy, sensitivity, specificity, precision, F1 score, and AUC results were obtained with the pre-trained VGG-19 model, respectively. The pre-trained VGG-19 model performed better than the others. Conclusion: Successful results were obtained in this study performed to the diagnosis of SBO with deep learning methods. A model that will assist physicians in the diagnosis of SBO can be developed with new studies to be conducted with a large number of spinal radiographs.
CBS Tabanlı Suç Analizi Yöntemleri
(2013) Maraş, Hadi Hakan; Maraş, Hadi Hakan; 34410
Coğrafi Bilgi Sistemleri (CBS) günlük hayatımızda önemi sürekli olarak artan uygulamalara sahiptir. CBS’nin popüler ve kritik uygulama alanlarından biri de mekânsal suç analizidir. Günümüzde suç oranları artış göstermekte ve bu yüzden suç eğilimlerini analiz etmek ve suçu önleyici tedbirler almak büyük önem arz etmektedir. Suçlar çoğu zaman mekânsal ve zamansal modeller göstermektedir. Örneğin, bazı suç türleri bazı lokasyonlarda nispeten yüksek oranlarda işlenebilmektedir. Bazıları ise gün içinde belli saat aralıklarında yüksek oranlarda olabilmektedir. Klasik suç analiz yöntemlerine coğrafi destek eklemek, tablosal veya istatistiksel metotların sunamayacağı son derece önemli ve müstesna faydalar sağlayabilir. Örneğin, belli bir suç türünün mekânsal dağılımını görmek veya farklı suç türlerinin lokasyonlarını harita üzerinde karşılaştırmak, karar verme pozisyonundaki yöneticilere kritik ve önemli ipuçları verebilir. Bu yüzden, suç analiz yöntemlerine mekânsal boyut katmak emniyet birimlerindeki çalışmalara önemli bir destek sağlamaktadır
Covariance Features for Trajectory Analysis
(Kaunas Univ Technology, 2018) Karadeniz, Talha; Maraş, Hadi Hakan; 304886; 34410
In this work, it is demonstrated that covariance estimator methods can be used for trajectory classification. It is shown that, features obtained via shrunk covariance estimation are suitable for describing trajectories. Compared to Dynamic Time Warping, application of explained technique is faster and yields more accurate results. An improvement of Dynamic Time Warping based on counting statistical comparison of base distance measures is also achieved. Results on Australian Sign Language and Character Trajectories datasets are reported. Experiment realizations imply feasibility through covariance attributes on time series.
Detection of hand osteoarthritis from hand radiographs using convolutional neural networks with transfer learning
(2020) Maraş, Hadi Hakan; Erbay, Hasan; Maraş, Hadi Hakan; 34410
Osteoarthritis is the most common type of arthritis. Hand osteoarthritis leads to specific structural changes in the joints, such as asymmetric joint space narrowing and osteophytes (bone spurs). Conventional radiography has traditionally been the primary method of visualizing these structural changes and diagnosing osteoarthritis. We aimed to develop a computerized method that is capable of determining the structural changes seen in radiography of the hand and to assist practitioners in interpreting radiographic changes and diagnosing the disease. In this retrospective study, transfer-learning-based convolutional neural networks were trained on a randomly selected dataset containing 332 radiography images of hands from an original set of 420 and were validated with the remaining 88. Multilayer convolutional neural network models were designed based on a transfer learning method using pretrained AlexNet, GoogLeNet, and VGG-19 networks. The accuracies of the models were 93.2% for AlexNet, 94.3% for GoogLeNet, and 96.6% for VGG-19. The sensitivities of these models were 0.9167 for AlexNet, 0.9184 for GoogLeNet, and 0.9574 for VGG-19, while the specificity values were 0.9500, 0.9744, and 0.9756, respectively. The performance metrics, including accuracy, sensitivity, specificity, and precision, of our newly developed automated diagnosis methods are promising in the diagnosis of hand osteoarthritis. Our computer-aided detection systems may help physicians in interpreting hand radiography images, diagnosing osteoarthritis, and saving time.
Did satellite imagery supersede aerial imagery? A perspective from 3D geopositioning accuracy
(2016) Maraş, Hadi Hakan; Erdogan, Mustafa; Maraş, Hadi Hakan; Aktuğ, Bahadır; Maraş, Süleyman Sırrı; 34410
In this study, the geometric accuracy comparison of aerial photos and WorldView-2 satellite stereo image data is evaluated with the different number and the distribution of the ground control points (GCPs) on the basis of large scale map production. Also, the current situation of rivalry between airborne and satelliteborne imagery was mentioned. The geometric accuracy of Microsoft UltraCam X 45 cm ground sampling distance (GSD) aerial imagery and WorldView-2 data both with and without GCPs are also separately analyzed. The aerial photos without any GCP by only using global navigation satellite system (GNSS) and inertial measurement unit (IMU) data with tie points give an accuracy of +/- 1.17 m in planimetry and +/- 0.71 m in vertical that means nearly two times better accuracy than the rational polynomial coefficient (RPC) of stereo WorldView-2. Using one GCP affects the accuracies of aerial photos and WorldView-2 in different ways. While this situation distorts the aerial photo block, it corrects the shift effect of RPC in WorldView-2 and increases the accuracy. By using four or more GCPs, 1/2 pixel (similar to 0.23 m) accuracy in aerial photos and 1 pixel (similar to 0.50 m) accuracy in WorldView-2 can be achieved in horizontal. In vertical, aerial photos have 1 pixel (similar to 0.55 m) and WorldView-2 has 1.5 pixels (similar to 0.85 m) accuracy. These results show that Worldview-2 imagery can be used in the production of class I 1: 5000 scale maps according to the ASPRS Accuracy Standards for Digital Geospatial Data in terms of geometric accuracy. It is concluded that the rivalry between aerial and satellite imagery will continue for some time in the future.
Did satellite imagery supersede aerial imagery? A perspective from 3D geopositioning accuracy
(Springer Heidelberg, 2016) Yilmaz, Altan; Maraş, Hadi Hakan; Erdogan, Mustafa; Maras, Hadi Hakan; Aktug, Bahadir; Maras, Suleyman Sirri; 34410
In this study, the geometric accuracy comparison of aerial photos and WorldView-2 satellite stereo image data is evaluated with the different number and the distribution of the ground control points (GCPs) on the basis of large scale map production. Also, the current situation of rivalry between airborne and satelliteborne imagery was mentioned. The geometric accuracy of Microsoft UltraCam X 45 cm ground sampling distance (GSD) aerial imagery and WorldView-2 data both with and without GCPs are also separately analyzed. The aerial photos without any GCP by only using global navigation satellite system (GNSS) and inertial measurement unit (IMU) data with tie points give an accuracy of +/- 1.17 m in planimetry and +/- 0.71 m in vertical that means nearly two times better accuracy than the rational polynomial coefficient (RPC) of stereo WorldView-2. Using one GCP affects the accuracies of aerial photos and WorldView-2 in different ways. While this situation distorts the aerial photo block, it corrects the shift effect of RPC in WorldView-2 and increases the accuracy. By using four or more GCPs, 1/2 pixel (similar to 0.23 m) accuracy in aerial photos and 1 pixel (similar to 0.50 m) accuracy in WorldView-2 can be achieved in horizontal. In vertical, aerial photos have 1 pixel (similar to 0.55 m) and WorldView-2 has 1.5 pixels (similar to 0.85 m) accuracy. These results show that Worldview-2 imagery can be used in the production of class I 1: 5000 scale maps according to the ASPRS Accuracy Standards for Digital Geospatial Data in terms of geometric accuracy. It is concluded that the rivalry between aerial and satellite imagery will continue for some time in the future.
Konvolusyonal Sinir Ağları Kullanılarak Normal, Romatoid Artrit ve Osteoartrit’li Direkt El Grafilerinin Ayrımı
(2019) Maraş, Hadi Hakan; 34410
Neuronavigation Skill Training Through Simulation: Insights From Eye Data
(Iated-Int Assoc Technology Education A& Development, 2016) Çağıltay, Nergiz; Tokdemir, Gül; Maraş, Hadi Hakan; Aydın, Elif; Maraş, Hadi Hakan; Tombul, Gökçen; Aydın, Elif; 17411
Neuronavigation systems are developed to support the brain surgery operations. Because of its complex anatomical structure, the neurosurgery is a risky and critical operation. The surgeon is required to perform the operation in a very small area with very restricted movements. The neuronavigation systems are developed to help the surgeon during the operation to show the current position of the surgery with respect to the 3D virtual model of the patient. In these systems, the 3D virtual model of the patient is created according to the medical data (MRI/BT) of the patient. Hence these systems work like navigations systems that are used in driving a car. The surgeon uses this system by controlling the system through a software interface and its user interface and correlates the current position of the operation with the 3D patient virtual model. In this way the surgeon checks the critical anatomical structures through this system and eliminates possible risks. Hence surgeons who will perform such operations are required to develop several skills to manage this very complicated environment. They are required to perform the operation according to the information coming from the navigation display. Additionally, in order to reach relevant information from the navigation display they have to control the navigation panel. In order to prepare surgeons to manage this very complicated environment, their required skills need to be improved during the training period. In this study, to better understand the surgeons' behaviours while managing the tasks related to the surgical navigation procedures, a simulation based environment is developed and an experimental study is conducted with 10 people. Their eye data and their performance data is recorded based on the simulated tasks. The results of the study is analysed statistically and descriptively. The results show that it is possible to control a neuronavigation display through eye movements which could be an alternative human-computer interaction option for designing the neuronavigation systems' user interfaces. Secondly, it is shown that performing a task according to the results of a second information source (neuronavigation system) lowers the general performance in terms of travelled distance with the operation tool and camera (endoscope). However the success level while performing each task and the time spent values are similar in both cases. On the other hand the number of errors is higher in the first scenario. Hence, the surgical education programs need to provide appropriate solutions to better understand and measure the skill levels of trainees on such tasks and to improve their skills through virtual practice systems.
Problems of Gaining Neuronavigation Skills on Surgical Education Programs: A case study in Turkey
(2016) Tokdemir, Gül; Maraş, Hadi Hakan; Tokdemir, Gül; Maraş, Hadi Hakan; Topallı, Damla; 17411; 34410
Neuronavigation technology is one of the important technologies that supports and guides the surgeons during the surgical procedures. Availability of this technology for the surgical education programs to gain the skills of using this technology effectively and efficiently during the surgical operations as well as availability of this technology in the operating room is critical for improving the surgical operations’ performance. In this study, the availability of this technology for the neurosurgical operations is researched through a quantitative research conducted by 220 neuro surgeons in Turkey. Based on the results of this study, suggestions for the education technology developers for creating technology enhanced education programs to increase the navigation skill levels of the candidate surgeons are developed. The results of this study aimed to improve the quality of the surgical education programs and the performance of the surgical procedures.
Risk Assessment of Sea Level Rise for Karasu Coastal Area, Turkey
(Mdpi, 2023) Eliawa, Ali; Maraş, Hadi Hakan; Genc, Asli Numanoglu; Tora, Hakan; Maras, Hadi Hakan; 34410
Sea Level Rise (SLR) due to global warming is becoming a more pressing issue for coastal zones. This paper presents an overall analysis to assess the risk of a low-lying coastal area in Karasu, Turkey. For SLR scenarios of 1 m, 2 m, and 3 m by 2100, inundation levels were visualized using Digital Elevation Model (DEM). The eight-side rule is applied as an algorithm through Geographic Information System (GIS) using ArcMap software with high-resolution DEM data generated by eleven 1:5000 scale topographic maps. The outcomes of GIS-based inundation maps indicated 1.40%, 6.02%, and 29.27% of the total land area by 1 m, 2 m, and 3 m SLR scenarios, respectively. Risk maps have shown that water bodies, low-lying urban areas, arable land, and beach areas have a higher risk at 1 m. In a 2 m scenario, along with the risk of the 1 m scenario, forests become at risk as well. For the 3 m scenario, almost all the territorial features of the Karasu coast are found to be inundated. The effect of SLR scenarios based on population and Gross Domestic Product (GDP) is also analyzed. It is found that the 2 and 3 m scenarios lead to a much higher risk compared to the 1 m scenario. The combined hazard-vulnerability data shows that estuarine areas on the west and east of the Karasu region have a medium vulnerability. These results provide primary assessment data for the Karasu region for the decision-makers to enhance land use policies and coastal management plans.
Türk beyin cerrahlarının teknolojiye ulaşım imkanları
(2016) Çağıltay, Nergiz; Tokdemir, Gül; Maraş, Hadi Hakan; Maraş, Hadi Hakan; 17411; 34410
Two Majority Voting Classifiers Applied to Heart Disease Prediction
(Mdpi, 2023) Karadeniz, Talha; Maraş, Hadi Hakan; Karadeniz, Talha; Maras, Hadi Hakan; Tokdemir, Gül; Tokdemir, Gul; Ergezer, Halit; Ergezer, Halit; 34410; 293396
Two novel methods for heart disease prediction, which use the kurtosis of the features and the Maxwell-Boltzmann distribution, are presented. A Majority Voting approach is applied, and two base classifiers are derived through statistical weight calculation. First, exploitation of attribute kurtosis and attribute Kolmogorov-Smirnov test (KS test) result is done by plugging the base categorizer into a Bagging Classifier. Second, fitting Maxwell random variables to the components and summating KS statistics are used for weight assignment. We have compared state-of-the-art methods to the proposed classifiers and reported the results. According to the findings, our Gaussian distribution and kurtosis-based Majority Voting Bagging Classifier (GKMVB) and Maxwell Distribution-based Majority Voting Bagging Classifier (MKMVB) outperform SVM, ANN, and Naive Bayes algorithms. In this context, which also indicates, especially when we consider that the KS test and kurtosis hack is intuitive, that the proposed routine is promising. Following the state-of-the-art, the experiments were conducted on two well-known datasets of Heart Disease Prediction, namely Statlog, and Spectf. A comparison of Optimized Precision is made to prove the effectiveness of the methods: the newly proposed methods attained 85.6 and 81.0 for Statlog and Spectf, respectively (while the state of the heart attained 83.5 and 71.6, respectively). We claim that the Majority Voting family of classifiers is still open to new developments through appropriate weight assignment. This claim is obvious, especially when its simple structure is fused with the Ensemble Methods' generalization ability and success.