Yazar "Unver, Halil Murat" seçeneğine göre listele
Listeleniyor 1 - 20 / 21
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A Linear Time Pattern Based Algorithm for N-Queens Problem(Gazi Univ, 2022) Karabulut, Bergen; Erguzen, Atilla; Unver, Halil MuratThe n-queens problem is the placing of n number of queens on an nxn chessboard so that no two queens attack each other. This problem is important due to various usage fields such as VLSI testing, traffic control job scheduling, data routing, dead-lock or blockage prevention, digital image processing and parallel memory storage schemes mentioned in the literature. Besides, this problem has been used as a benchmark for developing new artificial intelligence search techniques. However, it is known that backtracking algorithms, one of the most frequently used algorithms to solve this problem, cannot produce all solutions in large n values due to the exponentially growing time complexity. Therefore, various methods have been proposed for producing one or more solutions, not all solutions for each n value. In this study, a pattern based approach that produces at least one unique solution for all n values (n>3) was detected. By using this pattern, a new algorithm that produces at least one unique solution for even very large n values in linear time was developed. The developed algorithm with.(n) time complexity produces quite faster solution to n-queens problem and even in some values, this algorithm produces (n-1)/2 unique solutions in linear time.Öğe A New Hybrid Approach Using GWO and MFO Algorithms to Detect Network Attack(Tech Science Press, 2023) Dalmaz, Hasan; Erdal, Erdal; Unver, Halil MuratThis paper addresses the urgent need to detect network security attacks, which have increased significantly in recent years, with high accuracy and avoid the adverse effects of these attacks. The intrusion detection system should respond seamlessly to attack patterns and approaches. The use of metaheuristic algorithms in attack detection can produce near-optimal solutions with low computational costs. To achieve better performance of these algorithms and further improve the results, hybridization of algorithms can be used, which leads to more successful results. Nowadays, many studies are conducted on this topic. In this study, a new hybrid approach using Gray Wolf Optimizer (GWO) and Moth-Flame Optimization (MFO) algorithms was developed and applied to widely used data sets such as NSL-KDD, UNSW-NB15, and CIC IDS 2017, as well as various benchmark functions. The ease of hybridization of the GWO algorithm, its simplicity, its ability to perform global optimal search, and the success of the MFO algorithm in obtaining the best solution suggested that an effective solution would be obtained by combining these two algorithms. For these reasons, the developed hybrid algorithm aims to achieve better results by using the good aspects of both the GWO algorithm and the MFO algorithm. In reviewing the results, it was found that a high level of success was achieved in the benchmark functions. It achieved better results in 12 of the 13 benchmark functions compared. In addition, the success rates obtained according to the evaluation criteria in the different data sets are also remarkable. Comparing the 97.4%, 98.3%, and 99.2% classification accuracy results obtained in the NSL-KDD, UNSW-NB15, and CIC IDS 2017 data sets with the studies in the literature, they seem to be quite successful.Öğe An Attack Detection Framework Based on BERT and Deep Learning(IEEE-Inst Electrical Electronics Engineers Inc, 2022) Seyyar, Yunus Emre; Yavuz, Ali Gokhan; Unver, Halil MuratDeep Learning (DL) and Natural Language Processing (NLP) techniques are improving and enriching with a rapid pace. Furthermore, we witness that the use of web applications is increasing in almost every direction in parallel with the related technologies. Web applications encompass a wide array of use cases utilizing personal, financial, defense, and political information (e.g., wikileaks incident). Indeed, to access and to manipulate such information are among the primary goals of attackers. Thus, vulnerability of the information targeted by adversaries is a vital problem and if such information is captured then the consequences can be devastating, which can, potentially, become national security risks in the extreme cases. In this study, as a remedy to this problem, we propose a novel model that is capable of distinguishing normal HTTP requests and anomalous HTTP requests. Our model employs NLP techniques, Bidirectional Encoder Representations from Transformers (BERT) model, and DL techniques. Our experimental results reveal that the proposed approach achieves a success rate over 99.98% and an F1 score over 98.70% in the classification of anomalous and normal requests. Furthermore, web attack detection time of our model is significantly lower (i.e., 0.4 ms) than the other approaches presented in the literature.Öğe Analysis Of A Novel High Performance Induction Air Heater(Vinca Inst Nuclear Sci, 2018) Unver, Umit; Yuksel, Ahmet; Kelesoglu, Alper; Yuksel, Fikret; Unver, Halil MuratThis study represents an experimental and numerical investigation of the enhanced prototypes of the induction air heaters. For this purpose, flow field is enhanced in order to avoid turbulence. The air mass flow rate, outlet construction and the application of insulation of the outer surface of the heater were selected as the performance enhancing parameters. Depending on the exit construction, the new designed prototypes are named as K-2 and K-3. Experiments were performed under two groups for three various flow rates. In the first group, non-insulation situation is examined. In the second group tests, insulation is applied to the outside of windings and inlet-outlet flaps which constitute the boundary of the control volume for the prevention of heat losses. The increasing flow rate boosted the thermal efficiency by 9%. Each of insulation and enlarging exit cross section increased the thermal efficiency by 13%. It was observed that the thermal power transferred to air with the new prototypes increased about 246 W more than the previous designs. The thermal efficiencies of the K-2 and K-3 type heaters were calculated as 77.14% and 87.1%, respectively.Öğe Android malware detection based on image-based features and machine learning techniques(SPRINGER INTERNATIONAL PUBLISHING AG, 2020) Unver, Halil Murat; Bakour, KhaledIn this paper, a malware classification model has been proposed for detecting malware samples in the Android environment. The proposed model is based on converting some files from the source of the Android applications into grayscale images. Some image-based local features and global features, including four different types of local features and three different types of global features, have been extracted from the constructed grayscale image datasets and used for training the proposed model. To the best of our knowledge, this type of features is used for the first time in the Android malware detection domain. Moreover, the bag of visual words algorithm has been used to construct one feature vector from the descriptors of the local feature extracted from each image. The extracted local and global features have been used for training multiple machine learning classifiers including Random forest, k-nearest neighbors, Decision Tree, Bagging, AdaBoost and Gradient Boost. The proposed method obtained a very high classification accuracy reached 98.75% with a typical computational time does not exceed 0.018 s for each sample. The results of the proposed model outperformed the results of all compared state-of-art models in term of both classification accuracy and computational time.Öğe The Android malware detection systems between hope and reality(Springer International Publishing Ag, 2019) Bakour, Khaled; Unver, Halil Murat; Ghanem, RazanThe widespread use of Android-based smartphones made it an important target for malicious applications' developers. So, a large number of frameworks have been proposed to tackle the huge number of daily published malwares. Despite there are many review papers that have been conducted in order to shed light on the works that achieved in Android malware analysing domain, the number of conducted review papers do not fit with the importance of this research field and with the volume of achieved works. Also, there is no comprehensive taxonomy for all research trends in the field of analysing malicious applications targeting the Android system. Furthermore, none of the existing review papers contains a schematic model that makes it easy for the reader to know the methods and methodologies used in a particular field of research without much effort. This paper aims at proposing a comprehensive taxonomy and suggesting a new schematic review approach.To this end, a review of a large number of works that achieved between 2009 and 2019 has been conducted. The achieved study includes more than 200 papers that have different goals such as apps' behaviour analysis, automatic user interface triggers or packer/unpacker frameworks development. Also, a comprehensive taxonomy has been proposed so that most of the previous works can be classified under it. To the best of our knowledge, the suggested taxonomy is the widest and the most comprehensive in terms of the covered research trends. Moreover, we have proposed a detailed schematic model (called Schematic Review Model) illustrates the process of detecting the malignant applications of an Android in the light of the studied works and the proposed taxonomy. To our knowledge, this is the first time that the Android malware detection methods have been explained in this way with this amount of detail. Furthermore, the studied researches have been analysed according to multiple criteria such as used analysing method, used features, used detection method, and used dataset. Also, the features used in the studied works were discussed in detail by dividing it into multiple classes. Moreover, the challenges facing Android's malware analysing methods were discussed in detail. Finally, it has been concluded that there are gaps between the size and the goal of the conducted works and the number of malicious apps published every day, so some future works areas have been proposed and discussed.Öğe Automatic Landmark Detection through Circular Hough Transform in Cephalometric X-rays(Ieee, 2017) Duman, Elvan; Kokver, Yunus; Unver, Halil Murat; Erdem, Osman AyhanIn this paper, a knowledge based framework is proposed to detect automatically cephalometric landmarks: Porion (Po), Sella (S), Menton (Me), Pogonion (Pg) and Gnathion (Gn). In this way anomalies can be diagnosed easily by orthodontists. Our framework comprise of two main steps: (1) Adaptive Histogram Equalisation (AHE) is applied to clarify the image which is used to determine the method of treatment in orthodontics and obtained from the plain X-ray. (2) Circular Hough Transform method is used to locate the cephalometric landmarks automatically on the processed image, the method was tested on 7 cephalometric images and our framework accurately and automatically locates these 5 cephalometric landmarks.Öğe Classification Based on Structural Information in Data(Springer Heidelberg, 2022) Karabulut, Bergen; Arslan, Guvenc; Unver, Halil MuratClustering provides structural information from unlabeled data. The studies in which the structural information of the dataset is obtained through unsupervised learning approaches such as clustering and then transferred to the supervised learning are noteworthy. In this study, we propose a new preprocessing method, which obtains structural information that is expected to represent the most meaningful summary of the training dataset before applying a supervised learning strategy. To obtain this summary, the CURE clustering method was used. The proposed preprocessing method combined with SVM and a new classification method named representative points based SVM (RP-SVM) was developed. This new method was experimentally tested with various real datasets and was compared with the standard SVM, KMSVM, KNN and CART methods. The RP-SVM has significantly reduced the training size and resulted in less support vectors compared to standard SVM while achieving similar accuracy results. The RP-SVM has achieved better accuracy with less training data compared to KNN and CART. In addition, the RP-SVM has less data reduction compared to the KMSVM, but it is a more stable method that performs well in all datasets used. The results show that the proposed method can extract structural information that provides high quality for classification.Öğe DeepVisDroid: android malware detection by hybridizing image-based features with deep learning techniques(Springer London Ltd, 2021) Bakour, Khaled; Unver, Halil MuratIn this paper, a novel hybrid deep learning model called DeepVisDroid has been suggested for detecting android malware samples based on hybridizing image-based features with deep learning techniques. To this end, four grayscale image datasets have been constructed by converting some files from the source of the android applications into grayscale images. Then, two types of image-based features, namely local features and global features, have been extracted from the constructed image datasets and used for training the proposed model. The bag of visual words representation has been used for constructing one feature vector from multiple local feature descriptors extracted from each image. After that, 1D-convolutional layers-based neural network model has been proposed and trained using the extracted local and global image-based features. To the best of our knowledge, this is the first time that a convolutional neural network model is trained based on this type of features and used in the android malware detection domain. Furthermore, two classical 2D-convolutional layers-based neural network models have been proposed and two well-known deep learning models have been tested in order to compare the results of the proposed DeepVisDroid model with the results of the traditional convolutional neural network models and the results of the state-of-the-art deep learning models. The results of the proposed DeepVisDroid model are very promising, where its classification accuracy reached more than 98% with very efficient run-time overhead ranging between 0.11 and 2.02 s for each sample.Öğe Design and implementation of smart and automatic oven for food drying(Sage Publications Ltd, 2021) Tumay, Mehmet; Unver, Halil MuratFruits and vegetables ripen at certain times of the year and must be ripe for consumption. However, in the short-term ripening period, some of the fresh vegetables and fruits that are more than the consumable amount deteriorate before they can be consumed. Picking up fruits and vegetables when they are ripe and drying the surplus for later use is the most common storage method. In recent years, where technology has developed rapidly, instead of drying in the sun, solutions are produced in which the drying processes are managed automatically by using the drying kinematics of the products. The most recent techniques manage the drying process by measuring the weight of the wet and dried products during heating. Also, different types of ovens such as microwave ovens are tried to increase the efficiency of the drying process. These are rather complex solutions. In this study, a smart system that manages the drying process in real-time by using the humidity in the environment instead of weight together with the drying kinematics of the product is designed. So the complexity of the system is simplified. Also, the total duration of the drying process is exactly estimated by using the moisture content in the environment and the drying model of the product. In the study, firstly, data on the drying stage were collected with the experiments made for each product. These data were processed in a Matlab environment and a drying model with a curve fitting method was developed for each product. The drying models developed in the study were loaded into the processor of the smart oven and the entire drying process was managed in real-time. With the developed system solution, when the process is started, the drying time is estimated according to the amount processed and the type of product, and the drying time of the drying process is estimated by using the moisture content in the environment and the drying model of the product. In this way, pre-drying and post-drying stages can be planned.Öğe Detection of tibial fractures in cats and dogs with deep learning(Ankara Univ Press, 2021) Baydan, Berker; Unver, Halil MuratThe aim of this study is to classify tibia (fracture/no fracture) on whole/partial body digital images of cats and dogs, and to localize the fracture on fracture tibia by using deep learning methods. This study provides to diagnose fracture on tibia more accurately, quickly and safe for clinicians. In this study, a total of 1488 dog and cat images that were obtained from universities and institutions were used. Three different studies were implemented to detect fracture tibia. In the first phase of the first study, tibia was classified automatically as fracture or no fracture with Mask R-CNN. In the second phase, the fracture location in the fracture tibia image that obtained from the first phase was localized with Mask R-CNN. In the second study, the fracture location was directly localized with Mask R-CNN. In the third study, fracture location in the fracture tibia that obtained from the first phase of first study was localized with SSD. The accuracy and F1 score values in first phase of first study were 74% and 85%, respectively and F1 score value in second phase of first study was 84.5%. The accuracy and F1 score of second study were 52.1% and 68.5%, respectively. The F1 score of third study was 46.2%. The results of the research showed that the first study was promising for detection of fractures in the tibia and the dissemination of the fracture diagnosis with the help of such smart systems would also be beneficial for animal welfare.Öğe Detection of Web Attacks Using the BERT Model(IEEE, 2022) Seyyar, Yunus Emre; Yavuz, Ali Gokhan; Unver, Halil MuratThis paper presents a web intrusion detection system that addresses security threats with the increasing use of web applications in almost all domains, as well as the increase in attacks against web applications. Our web intrusion detection system consists of a model that can distinguish between normal and abnormal URLs. In the URL analysis phase, our model uses the BERT model of Transformers, a prominent natural language processing technique. In the classification phase, we use a CNN model, which is a popular deep learning technique. We utilize the CSIC 2010, FWAF, and HttpParams datasets for training and testing. The experimental results show that our model performs the classification of normal and abnormal requests in 0.4 ms, which is an extremely fast detection time when compared to the reported results in the literature and an accuracy of over 96%.Öğe Determining the Location of Tibial Fracture of Dog and Cat Using Hybridized Mask R-CNN Architecture(Kafkas Univ, Veteriner Fakultesi Dergisi, 2021) Baydan, Berker; Barisci, Necaatti N.; Unver, Halil MuratThe aim of this study is to hybridize the original backbone structure used in the Mask R-CNN framework, and to detect fracture location in dog and cat tibia fractures faster and with higher performance. With the hybrid study, it will be ensured that veterinarians help diagnose fractures on the tibia with higher accuracy by using a computerized system. In this study, a total of 518 dog and cat fracture tibia images that obtained from universities and institutions were used. F1 score value of this study on total dataset was found to be 85.8%. F1 score value of this study on dog dataset was found to be 87.8%. F1 score value of this study on cat dataset was found to be 77.7%. With the developed hybrid system, it was determined that the localization of the fracture in an average tibia image took 2.88 seconds. The results of the study showed that the hybrid system developed would be beneficial in terms of protecting animal health by making more successful and faster detections than the original Mask R-CNN architecture.Öğe Diagnosis of Pediatric Pneumonia with Ensemble of Deep Convolutional Neural Networks in Chest X-Ray Images(Springer Heidelberg, 2022) Ayan, Enes; Karabulut, Bergen; Unver, Halil MuratPneumonia is a fatal disease that appears in the lungs and is caused by viral or bacterial infection. Diagnosis of pneumonia in chest X-ray images can be difficult and error-prone because of its similarity with other infections in the lungs. The aim of this study is to develop a computer-aided pneumonia detection system to facilitate the diagnosis decision process. Therefore, a convolutional neural network (CNN) ensemble method was proposed for the automatic diagnosis of pneumonia which is seen in children. In this context, seven well-known CNN models (VGG-16, VGG-19, ResNet-50, Inception-V3, Xception, MobileNet, and SqueezeNet) pre-trained on the ImageNet dataset were trained with the appropriate transfer learning and fine-tuning strategies on the chest X-ray dataset. Among the seven different models, the three most successful ones were selected for the ensemble method. The final results were obtained by combining the predictions of CNN models with the ensemble method during the test. In addition, a CNN model was trained from scratch, and the results of this model were compared with the proposed ensemble method. The proposed ensemble method achieved remarkable results with an AUC of 95.21 and a sensitivity of 97.76 on the test data. Also, the proposed ensemble method achieved classification accuracy of 90.71 in chest X-ray images as normal, viral pneumonia, and bacterial pneumonia.Öğe Diagnosis of Pneumonia from Chest X-Ray Images using Deep Learning(Ieee, 2019) Ayan, Enes; Unver, Halil MuratPneumonia is a disease which occurs in the lungs caused by a bacterial infection. Early diagnosis is an important factor in terms of the successful treatment process. Generally, the disease can be diagnosed from chest X-ray images by an expert radiologist. The diagnoses can be subjective for some reasons such as the appearance of disease which can be unclear in chest X-ray images or can be confused with other diseases. Therefore, computer-aided diagnosis systems are needed to guide the clinicians. In this study, we used two well-known convolutional neural network models Xception and Vgg16 for diagnosing of pneumonia. We used transfer learning and fine-tuning in our training stage. The test results showed that Vgg16 network exceed Xception network at the accuracy with 0.87%, 0.82% respectively. However, the Xception network achieved a more successful result in detecting pneumonia cases. As a result, we realized that every network has own special capabilities on the same dataset.Öğe Improving detection and classification of diabetic retinopathy using CUDA and Mask RCNN(Springer London Ltd, 2023) Erciyas, Abdussamed; Barisci, Necaattin; Unver, Halil Murat; Polat, HuseyinDiabetic retinopathy (DR) is an eye disease caused by diabetes and can progress to certain degrees. Because DR's the final stage can cause blindness, early detection is crucial to prevent visual disturbances. With the development of GPU technology, image classification and object detection can be done faster. Particularly on medical images, these processes play an important role in disease detection. In this work, we improved our previous work to detect diabetic retinopathy using Faster RCNN and attention layer. In the detection phase, firstly non-used area of DR image was extracted using compute unified device architecture with gradient-based edge detection method. Then Mask RCNN was used instead of faster region-based convolutional neural networks (Faster RCNN) to detect lesion areas more successful. With the proposed method, more successful results were obtained than the our previous work in DenseNet, MobileNet and ResNet networks. In addition, more successful results were obtained than other works in the literature in ACC and AUC metrics obtained by using VGG19.Öğe Modeling of Induction Fluid Heater via Transformer Equivalent Circuit(Institute of Electrical and Electronics Engineers Inc., 2023) Kelesoglu, Alper; Unver, Halil Murat; Unver, UmitIn air conditioning systems where electrical energy is used as input, resistance and infrared heating systems are effectively used today. Due to its advantages, induction heating systems are a technology in the development stage as an alternative to these two technologies. In this study, the electromagnetic performance of an induction gas heater operating at grid frequency is investigated experimentally and theoretically. A mathematical method is developed to determine the conversion efficiency of electrical power to heat on conductive material. The results obtained are compared with experimental findings. © 2023 University of Split, FESB.Öğe Skin Lesion Segmentation in Dermoscopic Images with Combination of YOLO and GrabCut Algorithm(Mdpi, 2019) Unver, Halil Murat; Ayan, EnesSkin lesion segmentation has a critical role in the early and accurate diagnosis of skin cancer by computerized systems. However, automatic segmentation of skin lesions in dermoscopic images is a challenging task owing to difficulties including artifacts (hairs, gel bubbles, ruler markers), indistinct boundaries, low contrast and varying sizes and shapes of the lesion images. This paper proposes a novel and effective pipeline for skin lesion segmentation in dermoscopic images combining a deep convolutional neural network named as You Only Look Once (YOLO) and the GrabCut algorithm. This method performs lesion segmentation using a dermoscopic image in four steps: 1. Removal of hairs on the lesion, 2. Detection of the lesion location, 3. Segmentation of the lesion area from the background, 4. Post-processing with morphological operators. The method was evaluated on two publicly well-known datasets, that is the PH2 and the ISBI 2017 (Skin Lesion Analysis Towards Melanoma Detection Challenge Dataset). The proposed pipeline model has achieved a 90% sensitivity rate on the ISBI 2017 dataset, outperforming other deep learning-based methods. The method also obtained close results according to the results obtained from other methods in the literature in terms of metrics of accuracy, specificity, Dice coefficient, and Jaccard index.Öğe Statistical Edge Detection and Circular Hough Transform for Optic Disk Localization(Mdpi, 2019) Unver, Halil Murat; Kokver, Yunus; Duman, Elvan; Erdem, Osman AyhanAccurate and efficient localization of the optic disk (OD) in retinal images is an essential process for the diagnosis of retinal diseases, such as diabetic retinopathy, papilledema, and glaucoma, in automatic retinal analysis systems. This paper presents an effective and robust framework for automatic detection of the OD. The framework begins with the process of elimination of the pixels below the average brightness level of the retinal images. Next, a method based on the modified robust rank order was used for edge detection. Finally, the circular Hough transform (CHT) was performed on the obtained retinal images for OD localization. Three public datasets were used to evaluate the performance of the proposed method. The optic disks were successfully located with the success rates of 100%, 96.92%, and 98.88% for the DRIVE, DIARETDB0, and DIARETDB1 datasets, respectively.Öğe The Do's and Don'ts for Increasing the Accuracy of Face Recognition on VGGFace2 Dataset(Springer Heidelberg, 2021) Erbir, Muhammed Ali; Unver, Halil MuratIn this study, developments in face recognition are examined. Some methods are presented to increase the accuracy rate in face recognition by using transfer learning with VGGFace2 dataset and 4 different CNN models. While some of these tested offers decreased the accuracy rate, some of them increased. Effects of histogram balancing, expanding the training data, extracting the effect of non-facial portions of images and vertically aligning images on the accuracy rate were determined and compared to the accuracy rates of original images. As the optimal solution, transfer learning from the InceptionV3 model was preferred, vertical positioning was made, and an accuracy rate of 95.47% was achieved when 10% of the images were used for testing and 90% for training in a 100 people subset of VGGFace2 dataset. In LFW, one of the widely used datasets in the literature, an accuracy rate of 100% has been achieved by exceeding the highest accuracy achieved so far and all images in the LFW database have been recognized without any problems.
