Bilgisayar ve Bilişim Fakültesi Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.13091/10834

Browse

Now showing 1 - 20 of 32

A 3d U-Net Based on Early Fusion Model: Improvement, Comparative Analysis With State-Of Models and Fine-Tuning
(Konya Teknik Univ, 2024) Kayhan, Beyza; Uymaz, Sait Ali
Multi-organ segmentation is the process of identifying and separating multiple organs in medical images. This segmentation allows for the detection of structural abnormalities by examining the morphological structure of organs. Carrying out the process quickly and precisely has become an important issue in today's conditions. In recent years, researchers have used various technologies for the automatic segmentation of multiple organs. In this study, improvements were made to increase the multi-organ segmentation performance of the 3D U-Net based fusion model combining HSV and grayscale color spaces and compared with state-of-the-art models. Training and testing were performed on the MICCAI 2015 dataset published at Vanderbilt University, which contains 3D abdominal CT images in NIfTI format. The model's performance was evaluated using the Dice similarity coefficient. In the tests, the liver organ showed the highest Dice score. Considering the average Dice score of all organs, and comparing it with other models, it has been observed that the fusion approach model yields promising results.
Citation - WoS: 1
Academic Text Clustering Using Natural Language Processing
(2022) Taşkıran, Fatma; Kaya, Ersin
Accessing data is very easy nowadays. However, to use these data in an efficient way, it is necessary to get the right information from them. Categorizing these data in order to reach the needed information in a short time provides great convenience. All the more, while doing research in the academic field, text-based data such as articles, papers, or thesis studies are generally used. Natural language processing and machine learning methods are used to get the right information we need from these text-based data. In this study, abstracts of academic papers are clustered. Text data from academic paper abstracts are preprocessed using natural language processing techniques. A vectorized word representation extracted from preprocessed data with Word2Vec and BERT word embeddings and representations are clustered with four clustering algorithms.
Citation - WoS: 3
Citation - Scopus: 4
Approaches To Automated Land Subdivision Using Binary Search Algorithm in Zoning Applications
(Ice Publishing, 2022) Koç, İsmail; Çay, Tayfun; Babaoğlu, İsmail
The planned development of urban areas depends on zoning applications. Although zoning practices are performed using different techniques, the parcelling operations that shape the future view of the city are the same. Preparing the parcelling plans is an important step that has a direct impact on ownership structure and reallocation. Parcelling operations are traditionally handled manually by a technician. This is a serious problem in terms of time and cost. In this study, by taking the zoning legislation, the production of a pre-land subdivision plan has been automatically performed for a region of Konya, which is one of the major cities in Turkey. The parcelling processes have been performed in three different ways: the first parcelling technique is parcelling with edge values, the second is parcelling with area values and the third is parcelling using both edge and area values together. For the entire parcelling process, the area of the parcel has been calculated using the Gauss method. Moreover, to effectively determine the boundaries and to calculate the parcel area in the parcelling process, the binary search technique has been used in all the methods. The experimental results show that the parcelling operations were carried out very quickly and successfully.
Citation - Scopus: 1
Automatic Sleep Stage Classification for the Obstructive Sleep Apnea
(Trans Tech Publications Ltd, 2023) Özsen, Seral; Koca, Yasin; Tezel, Gülay Tezel; Solak, Fatma Zehra; Vatansev, Hulya; Kucukturk, Serkan
Automatic sleep scoring systems have been much more attention in the last decades. Whereas a wide variety of studies have been used in this subject area, the accuracies are still under acceptable limits to apply these methods to real-life data. One can find many high-accuracy studies in literature using a standard database but when it comes to using real data reaching such high performance is not straightforward. In this study, five distinct datasets were prepared using 124 persons including 93 unhealthy and 31 healthy persons. These datasets consist of time-, nonlinear-, welch-, discrete wavelet transform- and Hilbert-Huang transform features. By applying k-NN, Decision Trees, ANN, SVM, and Bagged Tree classifiers to these feature sets in various manners by using feature-selection highest classification accuracy was searched. The maximum classification accuracy was detected in the case of the Bagged Tree classifier as 95.06% with the use of 14 features among a total of 136 features. This accuracy is relatively high compared with the literature for a real-data application.
Citation - WoS: 1
Clustering Neighborhoods According To Urban Functions and Development Levels by Different Clustering Algorithms: a Case in Konya
(2022) Akar, Alı Utku; Uymaz, Sait Ali
Urban functions/activities, which emerged under the influence of the human factor and are in the process of development over time, play a crucial role in the development of neighborhoods. To ensure balanced development status among the neighborhoods, it is necessary to know the development levels of the neighborhoods in advance. This study focuses on the clustering of the 167 central neighborhoods in Konya in terms of urban functions and reveals the similarities or differences in the development status of these neighborhoods. K-means, Hierarchical (agglomerative) and OPTICS clustering analyzes were used to cluster central neighborhoods. 18 features related to urban functions were determined as input parameters in the clustering analyzes. Results showed that cluster analysis can be used in urban studies and determine the development status of cities. It is important to carry out clustering studies to make urban planning by revealing the development differences between the neighborhoods and to provide more appropriate service delivery.
Citation - WoS: 9
Citation - Scopus: 15
Clustering-Based Plane Refitting of Non-Planar Patches for Voxel-Based 3d Point Cloud Segmentation Using K-Means Clustering
(INT INFORMATION & ENGINEERING TECHNOLOGY ASSOC, 2020) Sağlam, Ali; Makineci, Hasan Bilgehan; Baykan, Ömer Kaan; Baykan, Nurdan Akhan
Point cloud processing is a struggled field because the points in the clouds are three-dimensional and irregular distributed signals. For this reason, the points in the point clouds are mostly sampled into regularly distributed voxels in the literature. Voxelization as a pretreatment significantly accelerates the process of segmenting surfaces. The geometric cues such as plane directions (normals) in the voxels are mostly used to segment the local surfaces. However, the sampling process may include a non-planar point group (patch), which is mostly on the edges and corners, in a voxel. These voxels can cause misleading the segmentation process. In this paper, we separate the non-planar patches into planar sub-patches using k-means clustering. The largest one among the planar sub-patches replaces the normal and barycenter properties of the voxel with those of itself. We have tested this process in a successful point cloud segmentation method and measure the effects of the proposed method on two point cloud segmentation datasets (Mosque and Train Station). The method increases the accuracy success of the Mosque dataset from 83.84% to 87.86% and that of the Train Station dataset from 85.36% to 87.07%.
Citation - WoS: 9
Citation - Scopus: 13
Comparison of the Effects of Mel Coefficients and Spectrogram Images Via Deep Learning in Emotion Classification
(INT INFORMATION & ENGINEERING TECHNOLOGY ASSOC, 2020) Demircan, Semiye; Örnek, Humar Kahramanlı
In the present paper, an approach was developed for emotion recognition from speech data using deep learning algorithms, a problem that has gained importance in recent years. Feature extraction manually and feature selection steps were more important in traditional methods for speech emotion recognition. In spite of this, deep learning algorithms were applied to data without any data reduction. The study implemented the triple emotion groups of EmoDB emotion data: Boredom, Neutral, and Sadness-BNS; and Anger, Happiness, and Fear-AHF. Firstly, the spectrogram images resulting from the signal data after preprocessing were classified using AlexNET. Secondly, the results formed from the MelFrequency Cepstrum Coefficients (MFCC) extracted by feature extraction methods to Deep Neural Networks (DNN) were compared. The importance and necessity of using manual feature extraction in deep learning was investigated, which remains a very important part of emotion recognition. The experimental results show that emotion recognition through the implementation of the AlexNet architecture to the spectrogram images was more discriminative than that through the implementation of DNN to manually extracted features.
Citation - WoS: 1
Covid-19 Detection Using Variational Mode Decomposition of Cough Sounds
(2023) Solak, Fatma Zehra
According to the World Health Organization, cough is one of the most prominent symptoms of the COVID-19 disease declared as a global pandemic. The symptom is seen in 68% to 83% of people with COVID-19 who come to the clinic for medical examination. Therefore, during the pandemic, cough plays an important role in diagnosing of COVID-19 and distinguishing patients from healthy individuals. This study aims to distinguish the cough sounds of COVID-19 positive people from those of COVID-19 negative, thus providing automatic detection and support for the diagnosis of COVID-19. For this aim, “Virufy” dataset containing cough sounds labeled as COVID-19 and Non COVID-19 was included. After using the ADASYN technique to balance the data, independent modes were obtained for each sound by utilizing the Variational Mode Decomposition (VMD) method and various features were extracted from every mode. Afterward, the most effective features were selected by ReliefF algorithm. Following, ensemble machine learning methods, namely Random Forest, Gradient Boosting Machine and Adaboost were prepared to identify cough sounds as COVID-19 and Non COVID-19 through classification. As a result, the best performance was obtained with the Gradient Boosting Machine as 94.19% accuracy, 87.67% sensitivity, 100% specificity, 100% precision, 93.43% F-score, 0.88 kappa and 93.87% area under the ROC curve.
A Deep Learning Ensemble Approach for X-Ray Image Classification
(Konya Teknik Univ, 2024) Esme, Engin; Kıran, Mustafa Servet
The application of deep learning-based intelligent systems for X-ray imaging in various settings, including transportation, customs inspections, and public security, to identify hidden or prohibited objects are discussed in this study. In busy environments, x-ray inspections face challenges due to time limitations and a lack of qualified personnel. Deep learning algorithms can automate the imaging process, enhancing object detection and improving safety. This study uses a dataset of 5094 x-ray images of laptops with hidden foreign circuits and normal ones, training 11 deep learning algorithms with the 10-fold cross-validation method. The predictions of deep learning models selected based on the 70% threshold value have been combined using a meta-learner. ShuffleNet has the highest individual performance with 83.56%, followed by InceptionV3 at 81.30%, Darknet19 at 78.92%, DenseNet201 at 77.70% and Xception at 71.26%. Combining these models into an ensemble achieved a remarkable classification success rate of 85.97%, exceeding the performance of any individual model. The ensemble learning approach provides a more stable prediction output, reducing standard deviation among folds as well. This research highlights the potential for safer and more effective X-ray inspections through advanced machine learning techniques.
Determining the Most Powerful Features in the Design of an Automatic Sleep Staging System
(2023) Özşen, Seral; Koca, Yasin; Tezel, Gülay; Çeper, Sena; Küççüktürk, Serkan; Vatansev, Hülya
Spending too much time on manual sleep staging is tiring and challenging for sleep specialists. In addition, experience in sleep staging also creates different decisions for sleep experts. The search for finding an effective automatic sleep staging system has been accelerated in the last few years. There are many studies dealing with this problem but very few of them were conducted with real sleep data. Studies have been carried out on mostly processed and cleaned-ready data sets. In addition, there are few studies in which the data distribution in sleep stages is balanced (equal numbers of epochs from each stage are used), and it is seen that the performance of these studies is quite low compared to other studies. When the literature studies are examined, there is a wide range of studies in which many features are extracted, many feature selection methods are used, many classifiers are applied and various combinations of these are available. For this reason, to determine the best-performing features and the most powerful features, 168 features were extracted from the real EEG, EOG, and EMG signals of 124 patients. These features were selected with 7 different feature selection methods, and classification was carried out with 4 classifiers. In general, the ReliefF feature selection method has performed best, and the Bagged Tree classifier has reached the highest classification accuracy of 67.92% with the use of nonlinear features.
Citation - WoS: 2
Citation - Scopus: 2
Different Deep Learning Based Classification Models for Covid-19 Ct-Scans and Lesion Segmentation Through the Cgan-Unet Hybrid Method
(Int Information & Engineering Technology Assoc, 2023) Ngong, Ivoline C.; Baykan, Nurdan Akhan
The new coronavirus, which emerged in early 2020, caused a major global health crisis in 7 continents. An essential step towards fighting this virus is computed tomography (CT) scans. CT scans are an effective radiological method to detecting the diagnosis in early stage, but have greatly increased the workload of radiologists. For this reason, there are systems needed that will reduce the duration of CT examinations and assist radiologists. In this study, a two-stage system has been proposed for COVID-19 detection. First, a hybrid method is proposed that can segment the infected region from CT images. The reason for this is that there is not always a reference image in the datasets used in the classification. For this purpose; UNet, UNet++, SegNet and PsPNet were used both separately and as hybrids with GAN, to automatically segment infected areas from chest CT slices. According to the segmentation results, cGAN-UNet hybrid system was selected as the most successful method. Experimental results show that the proposed method achieves a segmentation success with a dice score of 92.32% and IoU score of 86.41%. In the second stage, three classifiers which include a Convolutional Neural Network (CNN), a PatchCNN and a Capsule Neural Network (CapsNet) were used to classify the generated masks as either COVID-19 or not, using the segmented images obtained from cGAN-UNet. Success of these classifiers was 99.20%, 92.55% and 73.84%, respectively. According to these results, the highest success was achieved in the system where cGAN-Unet and CNN are used together.
A Discrete Particle Swarm Algorithm With Symmetry Methods for Discrete Optimization Problems
(2023) Baş, Emine; Yıldızdan, Gülnur
Particle Swarm Optimization (PSO) is a commonly used optimization to solve many problems. The PSO, which is developed for continuous optimization, is updated to solve discrete problems and Discrete PSO (DPSO) is obtained in this study. With DPSO, the Traveling Salesman Problem (TSP), which is well-known in the literature as a discrete problem, is solved. In order to improve the results, the swap method, the shift method, and the symmetry method are added to DPSO. The symmetry method is a new and successful method. The variations of the DPSO occurred according to the selected method type (DPSO1 (swap method), DPSO2 (shift method), DPSO3 (swap and shift methods), DPSO4 (symmetry method), DPSO5 (swap, shift, and symmetry methods), DPSO6 (swap, shift, symmetry, and 2-opt methods)). The effect of each method on the performance of the DPSO has been studied in detail. To demonstrate the success of the variations of the DPSO, the results are additionally compared with many well-known and new discrete algorithms in the literature. The results showed that the performance of DPSO has improved with the symmetry method and it has achieved better results than the discrete heuristic algorithms recently proposed in the literature.
Citation - WoS: 3
Citation - Scopus: 4
Effects of Training Parameters of Alexnet Architecture on Wound Image Classification
(Int Information & Engineering Technology Assoc, 2023) Eldem, Hüseyin; Ülker, Erkan; Işıklı, Osman Yasar
Deep learning is more extensively used in image analysis-based classification of wounds with an aim to facilitate the monitoring of wound prognosis in preventive treatments. In this paper, the classification success of AlexNet architecture in pressure and diabetic foot wound images is discussed. Optimizing training parameters in order to increase the success of Convolutional Neural Network (CNN) architectures is a frequently discussed problem. This paper comparatively examines the effects of optimization of the training parameters of CNN architecture on classification success. The paper examines how the optimizer algorithm, mini-batch size (MBS), maximum epoch number (ME), learning rate (LR), and LearnRateSchedule (LRS) parameters, which are among the training parameters used in combination in architectural training, perform at different values. The best results were obtained with an accuracy of 95.48% at the 10e-4 value of the LR parameter. When the changes in the evaluation metrics during the parameter optimization experiments were examined, it was seen that the LR parameter produced optimum values at 10e-4. As a result, when the Accuracy metric and standard deviations were examined, it was determined only with the LR parameter. No general conclusion could be reached regarding the other parameters.
Citation - WoS: 1
Citation - Scopus: 1
Empirical Evaluation of Leveraging Named Entities for Arabic Sentiment Analysis
(ZARKA PRIVATE UNIV, 2020) Mulki, Hala; Haddad, Hatem; Gridach, Mourad; Babaoglu, İsmail
Social media reflects the attitudes of the public towards specific events. Events are often related to persons, locations or organizations, the so-called Named Entities (NEs). This can define NEs as sentiment-bearing components. In this paper, we dive beyond NEs recognition to the exploitation of sentiment-annotated NEs in Arabic sentiment analysis. Therefore, we develop an algorithm to detect the sentiment of NEs based on the majority of attitudes towards them. This enabled tagging NEs with proper tags and, thus, including them in a sentiment analysis framework of two models: supervised and lexicon-based. Both models were applied on datasets of multi-dialectal content. The results revealed that NEs have no considerable impact on the supervised model, while employing NEs in the lexicon-based model improved the classification performance and outperformed most of the baseline systems.
Citation - WoS: 3
Citation - Scopus: 4
Encoder-Decoder Semantic Segmentation Models for Pressure Wound Images
(Taylor & Francis Ltd, 2023) Eldem, Huseyin; Ülker, Erkan; Işıklı, Osman Yasar
Segmentation of wound images is important for efficient wound treatment so that appropriate treatment methods can be recommended quickly. Wound measurement, is subjective for an overall assessment. The establishment of a high-performance automatic segmentation system is of great importance for wound care. The use of machine learning methods will make performing wound segmentation with high performance possible. Great success can be achieved with deep learning, which is a sub-branch of machine learning and has been used in the analysis of images recently (classification, segmentation, etc.). In this study, pressure wound segmentation was discussed with different encoder-decoder based segmentation models. All methods are implemented on the Medetec pressure wound image dataset. In the experiments, FCN, PSP, UNet, SegNet and DeepLabV3 segmentation architectures were used on a five-fold cross-validation. Performances of the models were measured in the experiments and it was demonstrated that the most successful architecture was MobileNet-UNet with 99.67% accuracy.
Finger Vein Recognition Based on Multi-Features Fusion
(Int Information & Engineering Technology Assoc, 2023) Titrek, Fatih; Baykan, Ömer K.
Biometric Recognition Systems allow individuals to be automatically authenticated or identified by using their unique characteristics. Finger vein (FV), widely used for this purpose, has a crucial place among biometric systems because of its advantages, which are user-friendliness, ability to detect living tissue, high reliability, low system cost, and less area requirement in installation. It has a wide usage area, especially in places where personal safety is at the forefront. In this study, we examine the effect of the Horizontal and Vertical Total Proportion (HVTP) feature extraction algorithm on the success rate when the fusion technique is applied. Homomorphic Filter (HF) and Perona-Malik Anisotropic Diffusion (PMAD) are used to remove the noise and light scattering issue in the FV databases, and Gray Level Run Length Matrices (GLRLM), Gray Level Co-occurrence Matrices (GLCM), Segmentation-based Fractal Texture Analysis (SFTA), Horizontal Total Proportion (HTP), and Vertical Total Proportion (VTP) methods are applied to describe texture features. The fusion of multiple features instead of using only one type of feature can improve the accuracy of FV recognition systems. The novelty of the study is the fusion of HTP and VTP with the GLRLM, GLCM, and SFTA features by using Yang finger vein databases (Database_1) and MMCBNU_6000 (Database_2). Experimental results reveal that the HTP and VTP significantly improved the classification success in these FV image databases. The best success rate achieved in the Ensemble classifier is 99.7% using Database_1 and 97.6% using Database_2.
Citation - WoS: 4
Citation - Scopus: 4
Finger Vein Recognition by Combining Anisotropic Diffusion and a New Feature Extraction Method
(INT INFORMATION & ENGINEERING TECHNOLOGY ASSOC, 2020) Titrek, Fatih; Baykan, Ömer Kaan
In recent years, Finger Vein (FV) Recognition System is frequently used where personal security is required. Image distortion caused by light scattering in the tissue is one of the major problems about the visibility of the FV. In this study, Homomorphic Filter and Anisotropic Diffusion are used for removing the light scattering problem in our captured FV image and to increase the visibility of the veined region. Novelty of the study is proposing two new features: Horizontal Total Proportion (HTP) and Vertical Total Proportion (VTP). These two new features were used together with both spatial and frequency domain features and it was observed that the success rates obtained by our attributes were significantly increased. Experimental results demonstrate that the proposed HTP and VTP features are effective and reliable to improve the classification success in FV recognition problem. According to the experiments, the use of Perona-Malik and Homomorphic Filter together has been shown to reduce the light scattering problem and improve vascular visibility by removing the noise in the finger vein image. In this study, four different classifiers are used: Complex Tree, Ensemble, Support Vector Machines (SVM), K-Nearest Neighbors (KNN). The best success rate was achieved by using the KNN classifier.
Citation - WoS: 3
Citation - Scopus: 6
A Hierarchical Approach Based on Aco and Pso by Neighborhood Operators for Tsps Solution
(WORLD SCIENTIFIC PUBL CO PTE LTD, 2020) Eldem, Hüseyin; Ülker, Erkan
It is known that some of the algorithms in optimization field have originated from inspiration from animal behaviors in nature. Natural phenomena such as searching behavior of ants for food in a collective way, movements of birds and fish groups as swarms provided the inspiration for solutions of optimization problems. Traveling Salesman Problem (TSP), a classical problem of combinatorial optimization, has implementations in planning, scheduling and various scientific and engineering fields. Ant colony optimization (ACO) and Particle swarm optimization (PSO) techniques have been commonly used for TSP solutions. The aim of this paper is to propose a new hierarchical ACO- and PSO-based method for TSP solutions. Enhancing neighboring operators were used to achieve better results by hierarchical method. The performance of the proposed system was tested in experiments for selected TSPLIB benchmarks. It was shown that usage of ACO and PSO methods in hierarchical structure with neighboring operators resulted in better results than standard algorithms of ACO and PSO and hierarchical methods in literature.
Hybrid the Arithmetic Optimization Algorithm for Constrained Optimization Problems
(Konya Technical University, 2021) Baş, Emine
Since many real-world problems can be designed as optimization problems, heuristic algorithms are increasingly preferred by researchers. The Arithmetic Optimization Algorithm (AOA) is a newly developed heuristic algorithm. It uses four arithmetic operations in its structure. The addition and subtraction operators enhanced the AOA's local search capability, while the multiplication and division operators enhanced the AOA's global search capability. It has been hybridized with the Tree Seed Algorithm (TSA) to increase the success of AOA. Thus, hybrid AOA-TSA (HAOA) has been proposed. The seed production mechanism of TSA is placed in the random walking stage of AOA. New candidate solutions (seeds) have been produced with the arithmetic operators involved in AOA and the candidate solutions have been compared with the existing solutions. Thus, the performance of AOA has increased. In this study, the success of AOA and HAOA was tested in thirteen constrained optimization problems. The success of AOA and HAOA has been tested for their performance in six different population sizes. The Wilcoxon Signed-Rank test was applied to the obtained results and its success has been proved statistically. The results proved the superiority of HAOA. HAOA has been compared with other heuristic methods in the literature and the success of HAOA has been shown. Additionally, AOA and HAOA have also been tested on three different engineering design problems. The results are discussed and evaluated.
Citation - WoS: 6
Citation - Scopus: 6
Identification of Apnea-Hypopnea Index Subgroups Based on Multifractal Detrended Fluctuation Analysis and Nasal Cannula Airflow Signals
(INT INFORMATION & ENGINEERING TECHNOLOGY ASSOC, 2020) Göğüş, Fatma Zehra; Tezel, Gülay; Özşen, Seral; Küççüktürk, Serkan; Vatansev, Hülya; Koca, Yasin
The diagnosis of obstructive sleep apnea hypopnea syndrome (OSASH) and making decision of treatment necessity with positive airway pressure (PAP) therapy are time consuming and costly processes. There were different approaches in literature to accomplish these processes successfully and as soon as possible by using physiological signals with selected feature extraction and machine learning techniques. To reach fastest and true result, selection of optimal physiological signal(s), feature extraction and learning techniques is important. This study aimed to identify apnea hypopnea index (AHI) subgroups of 120 subjects and thus diagnose of OSASH and determine the need for PAP therapy by applying Multifractal Detrended Fluctuation Analysis (MDFA) as a feature extraction technique to only single channel nasal cannula airflow signals. After the extracted features from airflow signals with MDFA were gone through feature selection phase, the selected features were evaluated in Random Forest classifier. With the implementation of all processes, OSAHS patients were discriminated from healthy subjects with 95.83% accuracy, 96.88% sensitivity and 93.75% specificity. 93.75% sensitivities and 93.75%, 100% and 96.88% specificities were obtained for 15 <= AHI (PAP therapy necessary), 5 <= AHI<15 (require additional information for PAP therapy decision) and AHI <5 (not require PAP therapy) subgroups, respectively.

Browse

Browsing Bilgisayar ve Bilişim Fakültesi Koleksiyonu by WoS Q "Q4"