Sürdürülebilir Kalkınma Amaçları
Yayınlar
- BildiriAçık Erişim2024Cross-view Gait Recognition Based on Fine-Tuned Deep Networks
Yaprak, Busranur; Gedikli, Eyup; Bingöl, Ozkan; Dogan, Ramazan Ozgur
Gait recognition is a biometrics-based computer vision process used to identify people based on their walking styles. Compared to other types of biometrics, gait offers a more advantageous recognition process as it does not require high-resolution and close-range images and obtains without contact. But besides this, gait biometrics is highly affected by cross-view variation, and under this variation recognition performance decreases significantly. In this study, performance evaluations of fine-tuned VGG-16 and ResNet-50 deep CNN networks on the cross-view gait recognition problem are performed. For this purpose, Gait energy images (GEI) and Silhouettes obtained from CASIA-B, the most comprehensive data set in gait recognition, are given as input to the networks. The experimental results showed that the VGG-16 network achieved higher recognition rates in cross-view gait recognition.
- BildiriAçık Erişim2024High-Accuracy Hand Segmentation for Palmprint Biometric Systems Improving Auto-Encoder Techniques
Yalcin, Kadir; Dogan, Ramazan Ozgur; Dogan, Hulya; Bingol, Ozkan
Biometric technologies have been widely adopted in various commercial products, ranging from security systems to personal devices, due to their exceptional reliability and user-friendliness. Among these, palmprint biometrics has gained increasing attention for its advantages, such as ease of use, a larger surface area, and the ability to capture more features compared to other biometric methods. A typical palmprint biometric system involves five key stages: (a) Image Acquisition, (b) Hand Segmentation, (c) Pattern Generation, (d) Feature Extraction, and (e) Verification/Identification. The overall success of the system depends on the effectiveness of each stage, with hand segmentation being crucial for identifying the most relevant features for accurate verification. This study aims to achieve high-accuracy biometric recognition by segmenting hands from images captured in uncontrolled environments with complex backgrounds. Accuracy (ACC), Intersection over Union (IoU), F1-Score, and Dice Coefficient are the four critical metrics used to assess the performance of segmentation techniques. The findings demonstrate that the U-Net + ViT and MA-Net + ResNet34 techniques outperform traditional auto-encoder methods in both quantitative performance metrics and visual analysis, leading to significantly improved hand segmentation for biometric systems.
- MakaleAçık Erişim2024DL-EDOF: Novel Multi-Focus Image Data Set and Deep Learning-Based Approach for More Accurate and Specimen-Free Extended Depth of Focus
Dogan, Hulya; Dogan, Ramazan Ozgur; Ay, Ilyas; Sezen, Sena F.
Depth of focus (DOF) is defined as the axial range in which the specimen stage moves without losing focus while the imaging apparatus remains stable. It may not be possible to capture an image that includes the entire specimen in focus due to the narrow DOF in microscopic systems. Extended depth of focus (EDOF) is used to overcome this limitation in microscopic systems. Although the researchers have developed so many EDOF microscope approaches, this research field still has some crucial shortcomings such as high computational costs, complexity and execution time, requiring additional equipment, low precise characterization of curves, and edges in images, varying performance depending on the specimen and microscope, using only gray levels of input images to acquire the pixel’s focus values. In order to minimize these shortcomings and comprehensively analyze the performance of EDOF approaches, a novel multi-focus image data set is generated, and a deep learning-based EDOF microscope approach is proposed in this study. When compared with the state-of-art EDOF approaches, our study provides various crucial contributions such as the first EDOF approach based on unsupervised deep learning, providing more accurate and specimen-free EDOF, generating a novel multi-focus image data, not requiring any pre- or post-processing technique and acquiring the pixel’s focus degrees using deep features. In order to evaluate the effectiveness of the suggested approach, 20 different EDOF approaches are applied to a multi-focus image data set containing 9 image collections (4 synthetic and 5 microscope image collections) in total. Performance analysis metrics with and without requiring a reference image are preferred to identify which EDOF microscope approach can extract more essential details from the multi-focus images for the synthetic and microscope image collections, which are Root Mean Square Error (RMSE), Peak Signal Noise Ratio (PSNR), Universal Quality Index (UQI), Correlation Coefficient (CC), Perception-based Image Quality Evaluator (PIQE), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE), Extension of Universal Quality Index for N Images (UQIN), and Naturalness Image Quality Evaluator (NIQE). Objective and subjective analysis of this study demonstrates that unsupervised deep learning model is more efficient to transmit crucial details from multi-focus images. Moreover, the suggested EDOF microscope approach with highest PSNR, UQI, CC, UQIN and lowest RMSE, PIQE, BRISQUE, NIQE produces higher performance than the state-of-art approaches.
- BildiriAçık Erişim2024An Efficient Technique Based on Deep Learning for Automatic Focusing in Microscopic System
Dogu, Fatma Tuana; Dogan, Hulya; Dogan, Ramazan Ozgur; Ay, Ilyas; Sezen, Sena F.; Seyman, M.
During microscopic examination process, experts firstly determine the most appropriate focusing point by precisely moving the microscope stage in the Z axis. This manual focusing process may cause variability in results depending on hand-eye coordination and individual experience. Therefore, the development of automatic focusing offers superior quality and consistent imaging. Many researchers have studied automatic focusing systems and proposed many focus functions to extract focus information from multi-focus images. Nevertheless, these focusing systems still consist of several significant limitations such as requiring a supplementary material, longer running time, producing different performance depending on the sample and magnification objective. In this study, an efficient technique based on deep learning is proposed to automatically determine the focused image during microscopic examination processes to minimize these limitations in the literature. This technique takes a sequence of images with the same field of view and different focuses as input and gives the image with maximum focusing as output. The proposed technique is compared with other automatic focusing techniques on the literature. In this study, novel multi-focus image sequences obtained from liver, intestine, heart, kidney, and lung samples is prepared to evaluate the performance of automatic focusing techniques. These sequences are obtained by scanning with 10× and 40× magnification objectives. Running time, accuracy, number of local maximum points, range, and noise levels are used as evaluation criteria in this study. According to evaluation criteria results obtained in this study, it has been proven that the proposed technique provides better performance than other automatic focusing techniques.
- BildiriYalnız künye2023Shape of Masses in Contrast Mammography Images and First Order Statistical Features Classification Based on
Kobya, Mehmet Emin; Ture, Hayati; Dogan, Ramazan Ozgur; Kayikcioglu, Temel; Teymur, Aykut; Kul, Sibel
Mammography is a valuable tool in the diagnosis and staging of primary breast cancer. Contrast-enhanced mammography (CEM) combines an iodinated contrast agent with traditional mammography to increase diagnostic accuracy, especially in women with more dense parenchymal background patterns. In this study, a Decision Support System (DSS) is proposed that classifies masses using radiomic features obtained from masks of benign and malignant masses in images obtained with the CEM technique. An open-access database containing 2006 CEM images was used in this study. Radiomic features obtained from these images were used to identify differences between benign and malignant masses. The DSS uses these features to classify masses using a decision tree algorithm. This study highlights the importance of the use of iodinated contrast agents to improve diagnostic accuracy in women with more dense parenchymal background patterns. Additionally, it emphasizes the potential benefits of a DSS, in combination with radiomic features, in the diagnosis and staging of breast cancer. In conclusion, this study demonstrates that the use of radiomic features in mammography images obtained with the CEM technique is an effective way to classify benign and malignant masses.The use of this technology could be an important tool in the early diagnosis and accurate classification of breast cancer.
- BildiriYalnız künye2023Deep Learning Based Focus Measurement Operator for 3D Imaging in Microscopic Systems
Dogan, Hulya; Dogan, Ramazan Ozgur
Since 3D imaging in microscopic systems makes cell and tissue structures more prominent and visible, it provides higher performance in image processing applications such as automatic segmentation, recognition, classification, alignment and stitching. For this reason, 3D imaging in microscopic systems has been one of the most comprehensive and long-studied research areas in the literature. It seems that the most frequently preferred strategy for 3D imaging is shape from focus. Shape from focus is a strategy that uses a sequence of 2D images with the same perspective and different focused regions to create the 3D shape of the sample. Focus measurement operators are applied to extract the focus properties of the input images in shape from focus strategies. These operators have several limitations, such as more precise characterization of curves and edges in images. Researchers often use a pre- or post-processing technique to minimize these limitations, rather than proposing a new focus measurement operator. In this study, a deep learning based focus measurement operator, which does not require a pre- or post-processing technique, is developed to eliminate these limitations. The qualitative and quantitative results obtained in the study show that the proposed focus measurement operator is more effective in 3D imaging than other operators in the literature.
- BildiriYalnız künye2023Anomaly Detection in Predicted Water Treatment Data using Hybrid CNN-LSTM Network Model
Özgenç, Busra; Ayas, Selen; Dogan, Ramazan Ozgur; Çavdar, Bora; Sahin, Ali Klvanc; Ayas, Mustafa Sinasi
Water treatment systems are among the industrial control systems where it is essential to detect anomalies accurately and efficiently due to the potential threat to public health. With advances in computer science, machine learning models have been successfully used in the anomaly detection process in recent years. In this paper, a hybrid CNN-LSTM network model is proposed to detect anomalies in water systems. Using a statistical window-based anomaly detection approach, the performance of the proposed model in detecting different types of attacks is analyzed on the open SWaT dataset. Experimental results show that the precision, recall and F1-score values of the proposed model are 0.994, 0.973 and 0.983, respectively, and can be successfully used to detect anomalies in water treatment systems.
- BildiriYalnız künye2023An Extensive Study: Creation of A New Inverted Microscope Image Data Set and Improving Auto-Encoder Models for Higher Accuracy Segmentation of HaCaT Cell Culture Line
Sevim, Zeynep; Dogan, Hulya; Demir, Zeynep; Sezen, Feride Sena; Dogan, Ramazan Ozgur
In cell culture investigations, it is assumed that the number of cells is counted automatically without the need for forward planning, additional tools, or consumables. The automatic cell counting process is greatly facilitated and made functional by the segmentation of cell culture lines. Many studies with high-accuracy results have been developed for cell or tissue segmentation in images acquired from microscopic systems, but this success cannot be achieved for segmentation of cell culture line (especially in images acquired from inverted microscope). There are still restrictions in segmentation of cell culture line studies in inverted microscope systems. In this context, a new inverted microscope image data set is created and higher accuracy auto-encoder models are developed for segmentation of HaCat cell culture line. The analyzes of the developed auto-encoder models are evaluated using four different performance evaluation procedures which are Accuracy, Sensitivity, Specificity and Jaccard. In terms of the performance evaluation procedures used in this study, the achievements of the auto-encoder models are clearly satisfactory for the automated segmentation of the HaCat cell culture line.
- BildiriYalnız künye2023An Efficient 1D Autoencoder-Based Approach for R-Peaks Detection in Electrocardiogram Signals
Dogan, Ramazan Ozgur; Dogan, Hulya; Kayikcioglu, Temel
Electrocardiogram (ECG) signal which is composition of multiple segments such as P-wave, QRS complex and T-wave plays a crucial role in evaluating human heart cardiac diagnosis. For an analysis of cardiac diagnosis, it is required that clinicians scan the ECG signal for R-peaks (the highest peak of the QRS complex) detection, which relies on their expertise and takes enormous time. In order to provide more realistic treatment of cardiovascular diseases in the ECG signal with noises and different characteristics, computer-based R-peaks detection approaches have been actively developed in the research article for many years and generally compose of two major operations; preprocessing and decision. Contrary to previous approaches which require high computational costs and complexity, appropriate initial parameters, a novel CNN based approach is presented for R-peaks detection in this paper. Both qualitative and quantitative analysis are performed in the real ECG signal taken from typical MIT-BIH arrhythmia database. In order to validate the success of the recommended approach, total 18 different R-peaks detection approaches reported in the literature are compared by utilizing performance evaluation metrics. Average values of sensitivity, positive predictivity, error rate, accuracy and f-score are computed as 99,96%, 99,95%, 0,09%, 99,90% and 99,95% respectively, which are the best values among well-established studies for R-peaks detection. It is demonstrated with qualitative and quantitative results that better performance is achieved by our suggested approach.
- BildiriYalnız künye2023A Hybrid CNN-LSTM Framework for Unsupervised Anomaly Detection in Water Distribution Plant
Sahin, Ali Kivanc; Cavdar, Bora; Dogan, Ramazan Ozgur; Ayas, Selen; Ozgenc, Busra; Ayas, Mustafa Sinasi
To reduce potential threats to public health and economic losses, water distribution systems, which are critical parts of industrial control systems, require accurate and effective anomaly detection. The successful incorporation of machine learning models into anomaly detection procedures has been made possible by recent developments in computer science. In this research, a hybrid CNN-LSTM framework for anomaly detection in water distribution systems is presented using Python programming language in the JupyterLab environment. The performance of the proposed CNN-LSTM network model is carefully evaluated on the publicly available WADI dataset, which contains several types of attacks for a water distribution testbed, using a statistical window-based anomaly detection approach. The experimental results show acceptable precision, recall and F1 scores of 0.8619, 0.7041, and 0.775, respectively, demonstrating the efficiency of the framework in detecting anomalies in the water distribution system.
- Derleme MakaleYalnız künye2023A Comprehensive Review of Computer-based Techniques for R-Peaks/QRS Complex Detection in ECG Signal
Dogan, Hulya; Dogan, Ramazan Ozgur
Electrocardiogram (ECG) signal, which is composite of multiple segments such as P-wave, QRS complex and T-wave, plays a crucial role in the treatment of cardiovascular disease. For an analysis of cardiac diagnosis, it is required that clinicians scan the ECG signal for QRS complex or R-peaks (the highest peak of the QRS complex) detection, which relies on their expertise and takes enormous time. In order to provide more realistic treatment of cardiovascular diseases, so many computer-based techniques detecting R-peaks/QRS complex in the ECG signal with noises and different characteristics have been actively developed in research article for many years. Moreover, researchers have created various data sets for R-peaks/QRS complex detection. Although R-peaks/QRS complex detection is one of the notable research areas with so many computer-based techniques and ECG data sets, no comprehensive review paper have been published recently. The main aim of this study is to present a wide range of computer-based techniques proposed for detection of R-peaks/QRS complex. First of all, in this study, computer-based techniques proposed in the literature for the detection of R-peaks/QRS complex and their stages are introduced in detail. The generalization ability of these techniques is investigated deeply. Details are given about the most preferred ECG data sets produced in the literature for the analysis of computer-based techniques. Finally, the performances of computer-based techniques and generalization abilities are analyzed for each data set created in the literature by giving the results of the evaluation metrics.
- BildiriYalnız künye2022Segmentation of Pectoral Muscle Region in MLO Mammography Images by Backboned U-Net
Dogan, Ramazan Ozgur; Türe, Hayati; Kayikçioglu, Temel
The pectoral muscle region on MLO mammography images appears prominently similar to suspicious areas. For this reason, Computer-Aided Detection (CAD) systems remove this region to reduce false-positive rates in the mass detection process. In some cases, the pectoral muscle region is exposed to distortions due to the superposition effects caused by the mammography technique. As a result, segmentation error rates of the pectoral muscle region, whose characteristic features are deteriorated, appear. In this study, a method to identify impaired pectoral muscle regions with MobileNetV2 backboned U-Net Deep Learning method is proposed. The proposed method was tested on 84 and 201 mammography images taken from both MIAS and InBreast databases and segmented with 1.81% and 1.92% false-negative (FN) and 0.25% and 0.37% false positive (FP) rates, respectively. Particularly for distorted pectoral muscle regions, the proposed method has been shown to outperform some pioneering studies in this area.
- MakaleAçık Erişim2021A Two-Phase Approach using Mask R-CNN and 3D U-Net for High-Accuracy Automatic Segmentation of Pancreas in CT Imaging
Dogan, Ramazan Ozgur; Dogan, Hulya; Bayrak, Coskun; Kayikcioglu, Temel
Background and objective: The size, shape, and position of the pancreas are affected by the patient characteristics such as age, sex, adiposity. Owing to more complex anatomical structures (size, shape, and position) of the pancreas, specialists have some difficulties in the analysis of pancreatic diseases (diabetes, pancreatic cancer, pancreatitis). Therefore, the treatment of the disease requires enormous time and depends on the experience of specialists. In order to decrease the rate of pancreatic disease deaths and to assist the specialist in the analysis of pancreatic diseases, automatic pancreas segmentation techniques have been actively developed in the research article for many years. Methods: Although the rapid growth of deep learning and proving satisfactory performance in many medical image processing and computer vision applications, the maximum Dice Similarity Coefficients (DSC) value of these techniques related to automatic pancreas segmentation is only around 85% due to complex structure of the pancreas and other factors. Contrary to previous techniques which are required significantly higher computational power and memory, this paper suggests a novel two-phase approach for high-accuracy automatic pancreas segmentation in computed tomography (CT) imaging. The proposed approach consists of two phases; (1) Pancreas Localization, where the rough pancreas position is detected on the 2D CT slice by adopting Mask R-CNN model, (2) Pancreas Segmentation, where the segmented pancreas region is produced by refining the candidate pancreas region with 3D U-Net on the 2D sub-CT slices generated in the first phase. Both qualitative and quantitative assessments of the proposed approach are performed on the NIH data set. Results: In order to evaluate the achievement of the recommended approach, a total of 16 different automatic pancreas segmentation techniques reported in the literature are compared by utilizing performance assessment procedures which are Dice Similarity Coefficient (DSC), Jaccard Index (JI), Precision (PRE), Recall (REC), Pixel Accuracy (ACC), Specificity (SPE), Receiver Operating Characteristics (ROC) and Area under ROC curve (AUC). The average values of DSC, JI, REC and ACC are computed as 86.15%, 75.93%, 86.27%, 86.27% and 99.95% respectively, which are the best values among well-established studies for automatic pancreas segmentation. Conclusion: It is demonstrated with qualitative and quantitative results that our suggested two-phase approach creates more favorable results than other existing approaches.
- BildiriYalnız künye2018R-peaks Detection with Convolutional Neural Network in Electrocardiogram Signal
Dogan, Ramazan Ozgur; Kayikçioglu, Temel
The performance of electrocardiogram applications is closely related to the succesful detection of R-peaks. Therefore, successful detection of R-peaks is of high importance. Electrocardiogram signals vary from person to person, so detection of R-peaks is getting difficult. In this study, Evolutionary Neural Network which is a deep learning model and imitates human vision, is used to detect R-peaks. The MIT-BIH Arrhythmia Database with 48 different records was used as the database and experimental results with very high accuracy were obtained.
- BildiriYalnız künye2017Real Time Sending and Monitoring Electronic Health Records
Dogan, Ramazan Ozgur; Kayikçioglu, Temel; Yagci, Yavuz
Innovations in the field of health increase with the developing technology nowadays. These technological advances in the health field have enabled us to meet with telemedicine applications. Telemedicine is the use of computer technologies and the Internet infrastructure so that we can access health services without going to the hospital. In telemedicine applications, patients can access past electronic health records of patients can be accessed as well as access real-time instant electronic health records is provided. Real-time telemedicine applications usually aim to provide remote access to the biological signs of the patient and to diagnose them through these signals. In this study, it is mentioned how a real time telemedicine application can be performed, which features should be provided, and which performance criteria should be taken into consideration while developing. In addition, performance values are examined for a sample implementation.
- BildiriYalnız künye2016Remote Patient Monitoring and Electronic Health Record System Based on Web Services
Dogan, Ramazan Ozgur; Kayikçioglu, Temel
Because of the increase in the number of people, medical problems increase and chronic diseases become more common. Medical data transfer between remote patients and health center can be provided by using information technology and telemedicine. In this study a system based web services is improved to monitor chronic patient with telemedicine. The system makes health personal offer Electronic Health Recording (EHR) consisting of biological signals and physiological parameters. This study with server-client construction consists of patient monitor software, web service and an interface allowing remote health personal to access web service.
- BildiriYalnız künye2015Virtual Mouse Control with Hand Gesture Information Extraction and Tracking
Dogan, Ramazan Ozgur; Dogan, Hulya; Köse, Cemal
Virtual mouse implemented with hand gesture tracking based on image is one of studies in human-computer interaction. In this study that human-computer interaction is implemented with virtual mouse is purposed. This study consists of three main steps that are hand gesture tracking, features of hand region extraction and classification of these features. In this study hand gesture tracking is generated with Camshift (Continuously Adaptive Mean Shift) algorithm, features of hand gestures are extracted with bag of visual words and these features are classified with support vector machines. Detailed tests are performed to compare success of tracking, features extraction and classisfication methods and that this system works successfully is shown.
- MakaleYalnız künye2015NEURAL NETWORK BASED SCALAR SPEED CONTROL OF LINEAR PERMANENT MAGNET SYNCHRONOUS MOTOR
Otkun, Ozcan; Dogan, Ramazan Ozgur; Akpinar, Adem Sefa
Nowadays, Artificial Neural Networks (ANN), in different applications, have been used in solving many problems of non-linear. In this study, ANN based Scalar (V / f) speed control of Linear Permanent Magnet Synchronous Motor (LPMSM) was carried out experimentally. For scalar control, variable frequency drive that is product of model LG-SV022IG5A-4 are used. This drive is controlled by the frequency of the C # programming language prepared by the ANN and the motor speed control was performed. Obtained experimental results by running LPMSM at different speed and load conditions were presented and analysis of success in motor speed control was performed.
- BildiriYalnız künye2014COMPUTER MONITORING AND CONTROL WITH HAND MOVEMENTS
Dogan, Ramazan Ozgur; Köse, Cemal
The devices such as mouse, keyboard used for controlling of computer have various limitations. The users must make physical contact with the devices and have a restricted away because of connection with wire to control computer by using these devices. Traditional communication devices for computer-person can't provide user wireless computer control without any physical. Inthis study, Computer monitoring and controlling with hand movements are implemented by using image proccesing and computer vision techniques to minimize these limitations. In proposed study, firstly it is expected that the user enters camera's field of view using computer camera. face of user entering the camera's field of view is detected with Haar Classifier. Hand region is detected by finding the dynamic range of skin color in YCbCr color space from the facial region. The hand region is tracked with Biggest Blob Tracking Technique, and features of hand are extracted by using Convexity Defect-Hull during tracking. Finally, position of mouse is controlled according to features of hand region, and Computer monitoring and controlling with hand movements are implemented bu tracking hand gestures.