Yazar "Yucedag, Ibrahim" seçeneğine göre listele
Listeleniyor 1 - 13 / 13
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Analysis of Fuzzy Logic based Textual Meaning Inference Approach for Comment Content Estimation in Social Networks(Gazi Univ, 2020) Bayrakdar, Sumeyye; Yucedag, IbrahimIn recent years, social networking has become a very popular communication tool among internet users connected by one or more relationships. Thousands or even millions of users share their experiences and opinions on different aspects of life everyday through social networking communities. The positive or negative content of the comments posted by the members of the social network can arouse great interest among the members of the social network group. Understanding social networks requires the analysis of structural relationships and interaction patterns between users. In this paper, an analysis of fuzzy logic based textual meaning inference analysis was performed for the estimation of content in social networks. The positive comments made by the members on the social networks have the positive effect for the users to read comments. In this context, our semantic inference approach is analyzed with the help of fuzzy logic where the content of comment can be positive or negative. According to the input values in the fuzzy logic system, the relevant interpretation can be positive or negative. Considering that the results of the obtained system yields highly accurate results, we think that our fuzzy logic based semantic inference approach can be used in many social networks.Öğe Automated Retinal Image Analysis to Detect Optic Nerve Hypoplasia(Kaunas Univ Technology, 2024) Çelik, Canan; Yucedag, Ibrahim; Akcam, Hanife TubaIdentification of the optic disc and fovea is crucial for automating the diagnosis and screening of retinal diseases. Based on quantitative calculations, this study presents a decision support system for doctors that automatically detect optic nerve hypoplasia. For disease diagnosis, U -Net architecture is used, which uses a pre -trained ResNet encoder to segment the optic disc and fovea structures. An important aspect of the proposed technique is that pretrained ResNet and U -Net are used together, providing robust performance in the detection of optic nerve hypoplasia. Our proposed architecture was tested on retinal images from Messidor, Diaretdb1, DRIVE, HRF, APTOS, and IDRID. In addition, a special database called ONH-NET was created based on 189 retinal images obtained from D & uuml;zce University, Department of Ophthalmology. Messidor database test images showed, 0. 9069 IOU Score, 0.9626 Sensitivity, 0.9411 Precision, 0.9974 Accuracy and 0.9505 dice -coefficient values in optic disc detection, and 0.8282 IOU score, 0.8442 sensitivity, 0.8252 precision, 0.8992 Accuracy, 0.7873 dice coefficient values were obtained in fovea detection. We computed diameter optic disc to macula radius ratios from segmented optic disc and fovea for screening optic nerve hypoplasia and achieved 100% success.Öğe DETERMINATION OF MAIN ELECTRICAL PARAMETERS OF Au-4H-n-SiC (MS) AND Au-Al2O3-4H-n-SiC (MIS) DEVICES(World Scientific Publ Co Pte Ltd, 2021) Demir, Gulcin Ersoz; Yucedag, IbrahimIn this study, Au-4H-n-SiC metal-semiconductor (MS) and Au-Al2O3-4H-n-SiC metal-insulator-semiconductor (MIS) devices were fabricated to examine the effects on the performance of electronic devices of interfacial insulating materials. In order to determine the dielectric properties, capacitance/conductance-voltage (C/G-V) measurements were realized in a wide range of voltages (-3.0 V)-(11.0 V). Current-voltage (I-V) measurements to obtain the electric properties were realized at +/- 2:5V. Moreover, both the energy distributions of surface states (N-ss) and series resistance (R-s) were obtained from the C/G-V data. Obtained results provided that series resistance originating from interfacial layer (Al2O3) was more effective on the I-V and C/G-V characteristics which must be taken into account in the calculation of main electrical parameters. The rectification ratio (RR) and shunt resistance (R-sh) of the MIS device were almost 10(3) times greater than those of the MS structure. Using Al2O3 between Au and 4H-n-SiC also led to an increase in the value of barrier height (BH) and a decrease in the value of ideality factor (n). These results confirmed that Al2O3 layer leads to an increase in the performance of MS device with respect to low values of N-ss, reverse saturation current (I-0) and n and high values of RR, R-sh and BH.Öğe An Efficient Deep Learning-based Intrusion Detection System for Internet of Things Networks with Hybrid Feature Reduction and Data Balancing Techniques(Kaunas Univ Technology, 2024) Karamollaoglu, Hamdullah; Dogru, Ibrahim Alper; Yucedag, IbrahimWith the increasing use of Internet of Things (IoT) technologies, cyber-attacks on IoT devices are also increasing day by day. Detecting attacks on IoT networks before they cause any damage is crucial for ensuring the security of the devices on these networks. In this study, a novel Intrusion Detection System (IDS) was developed for IoT networks. The IoTID20 and BoT-IoT datasets were utilized during the training phase and performance testing of the proposed IDS. A hybrid method combining the Principal Component Analysis (PCA) and the Bat Optimization (BAT) algorithm was proposed for dimensionality reduction on the datasets. The Synthetic Minority Over-Sampling Technique (SMOTE) was used to address the problem of data imbalance in the classes of the datasets. The Convolutional Neural Networks (CNN) model, a deep learning method, was employed for attack classification. The proposed IDS achieved an accuracy rate of 99.97% for the IoTID20 dataset and 99.98% for the BoT-IoT dataset in attack classification. Furthermore, detailed analyses were conducted to determine the effects of the dimensionality reduction and data balancing models on the classification performance of the proposed IDS.Öğe Exploiting 5G Enabled Cognitive Radio Technology for Semantic Analysis in Social Networks(Springer, 2023) Bayrakdar, Sumeyye; Yucedag, IbrahimCognitive radio is an intelligent communication system that is aware of its environment and can dynamically adapt its operating parameters with the aim of providing an efficient use of the scarce spectrum. The main advantage of cognitive radio technology is its ability to adapt and cooperate with all other wireless technologies such as fifth generation technology, 5G. 5G enabled cognitive radio technology provides accelerated communication performance in accordance with spectrum efficiency and energy efficiency. 5G enabled cognitive radio proposes system interoperability and integration of communication system through cognition. Social networking is a common communication media among internet users connected by one or more relationships. Large numbers of internet users share their experiences and thoughts through social networking web sites. Semantic analysis is defined as the process of drawing meaning from text. In this paper, a fuzzy logic based semantic analysis is performed for the estimation of comment content in 5G enabled cognitive radio based social networks. In social networks, the positive comments posted by the users have the positive influence for the members to examine related comments. The comment content posted by the users is decided to be positive or negative with the help of fuzzy logic based semantic analysis approach. In this regard, the relevant interpretation can be positive or negative based on the input parameters in the fuzzy logic system. Our 5G enabled cognitive radio technology based semantic analysis approach with fuzzy logic system can be utilized in many social networks, taking superior accuracy results of 93% into account.Öğe Hand Gesture Recognition from 2D Images by Using Convolutional Capsule Neural Networks(Springer Heidelberg, 2021) Guler, Osman; Yucedag, IbrahimObject classification and recognition are an important research area widely used in computer vision and machine learning. With the use of deep learning methods in the field of object recognition, there have been important developments in recent years. Object recognition and its sub-branches face recognition, motion recognition, and hand gesture recognition are now used effectively in devices used in daily life. Hand sign classification and recognition are an area that researchers are working on and trying to develop for human-computer interaction. In this study, a hybrid model was created by using a capsule network algorithm with a convolutional neural network for object classification. A dataset, named HG14, containing 14 different hand gestures was created. To measure the success of the proposed model in object recognition, training was carried out on HG14, FashionMnist, and Cifar-10 datasets. Also, VGG16, ResNet50, DenseNet, and CapsNet models were used to classify the images in HG14, FashionMnist, and Cifar-10 datasets. The results of the training were compared and evaluated. The proposed hybrid model achieved the highest accuracy rates with 90% in the HG14 dataset, 93.88% in the FashionMnist dataset, and 81.42% in the Cifar-10 dataset. The proposed model was found to be successful in all studies compared to other models.Öğe Investigation of effects on dielectric properties of different doping concentrations of Au/Gr-PVA/p-Si structures at 0.1 and 1 MHz at room temperature(Springer, 2020) Ersoz Demir, Gulcin; Yucedag, Ibrahim; Altindal, SemsettinIn order to improve and detailedly investigate the dielectric properties of polymer interfaces of Metal-Polymer-Semiconductor (MPS) structures, three types of MPS were fabricated by doping 1, 3 and 5% graphene (Gr) into the polyvinyl alcohol (PVA) interface material. Capacitance-Voltage (C-V) and Conductance-Voltage (G/omega-V) measurements were used to analyze the dielectric properties of three types of MPS. UsingC-Vand G/omega-V data, series resistance (R-s) affecting device performance and interface properties besides basic dielectric parameters of each structure such as both the real and imaginary components of complex dielectric constant (epsilon'and epsilon''), complex electrical modulus (M' and M''), loss tangent (tan delta), and ac electrical conductivity (sigma(ac)) were also calculated. The effect of graphene doping was examined for each parameter and obtained results were compared at both low (0.1 MHz) and high (1 MHz) frequencies. It was observed that epsilon and epsilon'' decreased with increasing graphene doping at both 0.1 and 1 MHz, while M' and M'' increased under same conditions. Moreover, both the M' and M'' vs V plots have two distinctive peaks between -2.0 V and 0.0 V due to a special density distribution of surface states between (Gr-PVA) and p-Si. The tan delta gradually increased with increasing graphene doping at only 0.1 MHz. As the doping ratio of graphene increases, the charge carriers in the structure generate more dipoles and create an earlier relaxation process. In other words, increasing the doping ratio helps to improve the series resistance effects in MPS structures. As a result, it was seen that the interfacial properties of MPS structures were improved by increasing the rate of graphene doping.Öğe Investigation of the Performance of Poly(Methyl-Acrylate) as a Gate Dielectric in Organic Thin-Film Transistors(Springer, 2020) Yardim, Tayfun; Demir, Ahmet; Alli, Sema; Alli, Abdulkadir; Yucedag, IbrahimIn this study, we present two regioregular poly(3-hexylthiophene-2,5-diyl) (rr-P3HT)-based top-gate bottom-contact configured organic thin-film transistors (OTFTs) using poly(alpha-methyl acrylate) (PMA) and poly(methyl methacrylate) (PMMA) polymers separately as gate insulators for comparison. In order to compare only the performance of the dielectrics, the other parts of the devices were kept qualitatively and quantitatively identical. Unlike PMMA, PMA is flexible, and flexibility is a desirable property for an OTFT. Thus, utilizing PMA can be advantageous if it supports higher performance of the transistor. In this respect, the electronic parameters of the fabricated devices were extracted from transfer and output characteristics to determine the performance of PMA in OTFT applications. Results showed that the mobility of the OTFT with PMA (PMA-OTFT) was nearly three times greater than that of the OTFT with PMMA (PMMA-OTFT), while the PMA-OTFT threshold voltage (V-TH) was slightly less than that of the PMMA-OTFT, which was likely because of the greater effective capacitance (C-EFF) of the PMA layer compared to that of the PMMA layer. This is the main advantage of the PMA. On the other hand, the major downside is found in the reduced on-to-off current (I-ON/I-OFF) and increased subthreshold swing originating from a huge off-current (I-OFF), implying the existence of a large gate leakage current. Increasing the thickness of the PMA layer could reduce such large gate leakage current. However, this would lead to additional increase in the OTFT operating voltage. Therefore, further studies are required to improve the insulating property of the PMA polymer in order to substitute it for the PMMA.Öğe Investigation of the variation of dielectric properties by applying frequency and voltage to Al/(CdS-PVA)/p-Si structures(Elsevier, 2021) Azizian-Kalandaragh, Yashar; Yucedag, Ibrahim; Demir, Gulcin Ersoz; Altindal, SemsettinIn this study, the effect of frequency and voltage on the dielectric properties of Al/(CdS-PVA)/p-Si structures prepared using cadmium sulfide (CdS)-polivinyl alcohol (PVA) interface material was investigated. For this purpose, real and imaginary permittivity (epsilon' and epsilon ''), dissipation factor (tan delta), ac electrical conduction mechanism (sigma(ac)), real and imaginary part of electric modulus (M' and M) were obtained by using capacitance-conductance (C-G/omega) measurements at frequency between 5kHz - 5MHz and at voltage between (-1V) - (+1V). All parameters were found to depend considerably on the frequency and voltage. epsilon' and epsilon '' reach higher values at low frequencies due to surface states (N-ss) which can easily monitor ac signal, dipolar polarization and interfacial polarization. Short-range mobility of charge carriers caused the increase of both electrical modulus and sigma(ac) with increasing frequency. Moreover, M '' exhibited a peak behavior which shifts to higher frequency with increasing voltage. Peak behavior could be ascribed to both decrease in polarization and surface states. (C) 2020 Elsevier B.V. All rights reserved.Öğe A non-invasive continuous cuffless blood pressure estimation using dynamic Recurrent Neural Networks(Elsevier Sci Ltd, 2020) Senturk, Umit; Polat, Kemal; Yucedag, IbrahimCardiovascular diseases (CVD) have become the most important health problem of our time. High blood pressure, which is cardiovascular disease, is a risk factor for death, stroke, and heart attack. Blood pressure measurement is commonly used to limit blood flow in the arm or wrist, with the cuff. Since blood pressure cannot be measured continuously in this method, the dynamics underlying blood pressure cannot be determined and are inefficient in capturing symptoms. This paper aims to perform blood pressure estimation using Photoplethysmography (PPG) and Electrocardiography (ECG) signals that do not obstruct the vascular access. These signals were filtered and segmented synchronously from the R interval of the ECG signal, and chaotic, time, and frequency domain features were subtracted, and estimation methods were applied. Different methods of machine learning in blood pressure estimation are compared. Dynamic learning methods such as Recurrent Neural Network (RNN), Nonlinear Autoregressive Network with Exogenous Inputs Neural Networks NARX-NN and Long-Short Term Memory Neural Network (LSTM-NN) used. Estimation results have been evaluated with performance criteria. Systolic Blood Pressure (SBP) error mean +/- standard deviation = 0.0224 +/- (2.211), Diastolic Blood Pressure (DBP) error mean +/- standard deviation = 0.0417 +/- (1.2193) values have been detected in NARX artificial neural network. The blood pressure estimation results are evaluated by the British Hypertension Society (BHS) and American National Standard for Medical Instrumentation ANSI/AAMI SP10: 2002. Finding the most accurate and easy method in blood pressure measurement will contribute to minimizing the errors. (C) 2020 Elsevier Ltd. All rights reserved.Öğe A Novel Blood Pressure Estimation Method with the Combination of Long Short Term Memory Neural Network and Principal Component Analysis Based on PPG Signals(Springer International Publishing Ag, 2020) Senturk, Umit; Polat, Kemal; Yucedag, IbrahimThe worldwide high blood pressure-related mortality rate is increasing. Alternative measurement methods are required for blood pressure measurement. There are similarities between blood pressure and photoplethysmography (PPG) signals. In this study, a novel blood pressure estimation methods based on the feature extracted from the PPG signals have been proposed. First of all, 12-time domain features have extracted from the raw PPG signal. Secondly, raw PPG signals have been applied to Principal Component Analysis (PCA) to obtain 10 new features. The resulting features have been combined to form a hybrid feature set consisting of 22 features. After features extraction, blood pressure values have automatically been predicted by using the Long Short Term Memory Neural Network (LSTM-NN) model. The prediction performance measures including MAE, MAPE, RMSE, and IA values have been used. While the combination of 12-time domain features from PPG signals and LSTM has obtained the MAPE values of 0,0547 in the prediction of blood pressures, the combination of 10-PCA coefficients and LSTM has achieved the MAPE value of 0,0559. The combination model of all features (22) and LSTM has obtained the MAPE values of 0,0488 in the prediction of blood pressures. The achieved results have shown that the proposed hybrid model based on combining PCA and LSTM is very promising in the prediction of blood pressure from PPG signals. In the future, the proposed hybrid method can be used as a wearable device in the measurement of blood pressure without any calibration.Öğe A novel mathematical model including the wetness parameter as a variable for prevention of pressure ulcers(Sage Publications Ltd, 2021) Demircan, Fadime Ogulmus; Yucedag, Ibrahim; Toz, MetinPressure ulcers are injuries caused by external conditions such as pressure, friction, shear, and humidity resulting from staying in the same position for a long time in bedridden patients. It is a serious problem worldwide when assessed in terms of hospital capacity, nursing staff employment and treatment costs. In this study, we developed a novel mathematical model based on one of our previous models to prevent pressure ulcers or delay injuries. The proposed model uses a human thermal model that includes skin temperature, hypothalamus temperature, regional perspiration coefficient, and unconsciously loss of water amount. Moreover, in our model, we defined a variable wetness parameter in addition to the parameters, pressure, temperature, and humidity. The proposed model is mathematically defined in detail and tested for a wide range of parameters to show the model's effectiveness in determining the pressure ulcer formation risk. The model is also compared with a model from the literature that based on only the general parameters, pressure, temperature, and humidity. The obtained results showed that the model determines the risk of the occurrence of the pressure ulcer more precisely than the compared one.Öğe Semantic analysis on social networks: A survey(Wiley, 2020) Bayrakdar, Sumeyye; Yucedag, Ibrahim; Simsek, Mehmet; Dogru, Ibrahim AlperAs social networks are getting more and more popular day by day, large numbers of users becoming constantly active social network users. In this way, there is a huge amount of data produced by users in social networks. While social networking sites and dynamic applications of these sites are actively used by people, social network analysis is also receiving an increasing interest. Moreover, semantic understanding of text, image, and video shared in a social network has been a significant topic in the network analysis research. To the best of the author's knowledge, there has not been any comprehensive survey of social networks, including semantic analysis. In this survey, we have reviewed over 200 contributions in the field, most of which appeared in recent years. This paper not only aims to provide a comprehensive survey of the research and application of social network analysis based on semantic analysis but also summarizes the state-of-the-art techniques for analyzing social media data. First of all, in this paper, social networks, basic concepts, and components related to social network analysis were examined. Second, semantic analysis methods for text, image, and video in social networks are explained, and various studies about these topics are examined in the literature. Then, the emerging approaches in social network analysis research, especially in semantic social network analysis, are discussed. Finally, the trending topics and applications for future directions of the research are emphasized; the information on what kind of studies may be realized in this area is given.