Yazar "Isik, Esme" seçeneğine göre listele
Listeleniyor 1 - 12 / 12
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Analysis and classification of the mobile molecular communication systems with deep learning(Springer Heidelberg, 2022) Isik, Ibrahim; Er, Mehmet Bilal; Isik, EsmeNano networks focused on communication between nano-sized devices (nanomachines) is a new communication concept which is known as molecular communication system (MCs) in literature. The researchers have generally used fixed transmitter and receiver for MCs models to analyze the fraction of received molecules and signal to interference rate etc. In this study, contrary to the literature, a mobile MC model has been used in a diffusion environment by using five bits. It is concluded that when the receiver and transmitter are mobile, distance between them changes and finally this affects the probability of the received molecules at the receiver. After the fraction of received molecules is obtained for different mobility values of Rx and Tx (Drx and Dtx), deep learning's bi-directional long short-term memory (Bi-LSTM) model is applied for the classification of Rx and Tx mobilities to find the best MC model with respect to fraction of received molecules. Finally it is obtained that when the mobilities of Rx and Tx increase, the fraction of received molecules also increases. Bi-LSTM model of Deep learning is used on a data set consisting of five classes. The suggested model's accuracy, precision, and sensitivity values are obtained as 98.05, 96.49, and 98.01 percent, respectively.Öğe Analysis and estimation of fading time from thermoluminescence glow curve by using artificial neural network(Taylor & Francis Ltd, 2021) Isik, Esme; Isik, Ibrahim; Toktamis, HuseyinThe artificial neural network (ANN) is an information processing technology inspired by the information processing technique of the human brain. The way the simple biological nervous system works is imitated with ANN. In this study, an ANN model is proposed to analyze and simulate TL intensity of experimental data of quartz crystals with respect to the fading. In this model, network type and transfer function are chosen as the feed-forward backpropagation algorithm and Tansig respectively for the training of the proposed ANN model. The optimization process is also chosen as Levenberg-Marquardt in this study. The performance criteria of the proposed method were evaluated according to the coefficient of determination (R-2) and mean-squared error (MSE) techniques. After simulation results are obtained, the TL glow curve of the prediction results of quartz crystal is obtained as a function of fading time irradiated with beta-source at 70 Gy for stored in 64 h at room temperature.Öğe Analysis of molecular communication model via diffusion with cumulative distribution functions(Gazi Univ, Fac Engineering Architecture, 2024) Isik, Ibrahim; Isik, Esme; Ates, AbdullahMolecular Communication (MOC), a novel communication method between nano-sized devices, has gained attention in recent literature. Numerous MOC models have been utilized to analyze factors such as the number of molecules reaching the receiver and the molecule-interference ratio. However, a common trend observed in the existing MOC models is the predominant use of the Normal distribution function to describe the movement of carrier molecules within the diffusion medium. In contrast to the existing literature, this study aims to thoroughly investigate alternative distribution functions for the diffusion of molecules in the medium, taking into consideration the number of received molecules, in order to identify the MOC model with optimal performance. In this study, the performance of various distribution functions including extreme value distribution (EVRND), normal distribution (NRND), t-distribution (TRND), generalized extreme value distribution (GEVRND), and generalized Pareto distribution (GPRND) were compared using different system parameters to identify the best MOC model. The analysis revealed that the GPRND distribution exhibited the highest performance, while the NRND distribution demonstrated the lowest performance. Given the prevalent use of the NRND distribution in analyzing MOC models within the literature, the significance of this study is further underscored.Öğe Analysis of thermoluminescence characteristics of a lithium disilicate glass ceramic using a nonlinear autoregressive with exogenous input model(Wiley, 2020) Isik, Esme; Toktamis, Huseyin; Isik, IbrahimDental ceramics because of their translucency exemplify the most biologically realistic restorative materials for aesthetic rehabilitation and can be used to estimate dose accumulated as a result of a nuclear accident or attack. In this study, lithium disilicate ceramic obtained from Vivadent Ivoclar, Turkey was studied for its thermoluminescence (TL) properties. The lithium disilicate glass ceramic was irradiated with a Sr-90-Y-90 beta-source from 10 Gy to 6.9 kGy and the results read on a Harshaw 3500 reader. The TL peak of lithium disilicate ceramic showed sublinearity in the range 12 Gy to 6 kGy. The area under the TL glow curve increased by about 25% by the end of 10th measurement cycle. Fading values were also considered after irradiation. Lithium disilicate ceramic samples underwent 37% fading after 1 h and 59% fading after 1 week. In addition to the experimental study, a software-based simulation study was also undertaken using a MATLAB system identification tool. Experimental studies are generally time consuming and some materials used for experiments are very expensive. In this study, experimental, and simulation results were compared and produced almost the same outcome with a similarity of more than 98%.Öğe Analyzing of Alzheimer's Disease Based on Biomedical and Socio-Economic Approach Using Molecular Communication, Artificial Neural Network, and Random Forest Models(Mdpi, 2022) Bayraktar, Yuksel; Isik, Esme; Isik, Ibrahim; Ozyilmaz, Ayfer; Toprak, Metin; Kahraman Guloglu, Fatma; Aydin, SerdarAlzheimer's disease will affect more people with increases in the elderly population, as the elderly population of countries everywhere generally rises significantly. However, other factors such as regional climates, environmental conditions and even eating and drinking habits may trigger Alzheimer's disease or affect the life quality of individuals already suffering from this disease. Today, the subject of biomedical engineering is being studied intensively by many researchers considering that it has the potential to produce solutions to various diseases such as Alzheimer's caused by problems in molecule or cell communication. In this study, firstly, a molecular communication model with the potential to be used in the treatment and/or diagnosis of Alzheimer's disease was proposed, and its results were analyzed with an artificial neural network model. Secondly, the ratio of people suffering from Alzheimer's disease to the total population, along with data of educational status, income inequality, poverty threshold, and the number of the poor in Turkey were subjected to detailed distribution analysis by using the random forest model statistically. As a result of the study, it was determined that a higher income level was causally associated with a lower risk of Alzheimer's disease.Öğe Classification of Diffusion Constants of Transmitter and Receiver and Distance Between Them Using Mobile Molecular Communication via Diffusion Model(Springer Heidelberg, 2024) Er, Mehmet Bilal; Isik, Ibrahim; Kuran, Umut; Isik, EsmeMolecular communication (MC) holds promise for enabling communication in scenarios where traditional wireless methods may be impractical or ineffective, offering unique capabilities for a range of applications in both natural and engineered systems. In this research, a novel approach to MC is explored, diverging from the standard use of stationary transmitter and receiver models typically found in the field. The study introduces a dynamic MC model, where both the transmitter and receiver are mobile within a diffusion environment. This model operates using a 5-bit system. The key finding is that the mobility of these nanodevices alters their distance, which in turn impacts the likelihood of molecule reception at the receiver. The study employs deep learning techniques, specifically a combination of Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks, to categorize the mobility patterns of the receiver (Rx) and transmitter (Tx). By analyzing various mobility rates (Drx and Dtx) and distances between the Tx and Rx, the research successfully identifies the most efficient mobile MC model in terms of molecule reception rates. The use of Linear Support Vector Machine alongside the CNN and LSTM hybrid feature vector resulted in an 87.68% accuracy in predicting diffusion coefficients. Moreover, using a Cubic Support Vector with the same hybrid feature vector, the study achieved an 88.09% accuracy in estimating the distance between the transmitter and receiver. The study concludes that an increase in the mobilities of Rx and Tx correlates with a higher rate of molecule reception.Öğe Enhancing high sensitive hydrogen detection of Bi2O3 nanoparticle decorated TiO2 nanotubes(Elsevier Science Sa, 2024) Isik, Esme; Tasyurek, Lutfi Bilal; Tosun, Emir; Kilinc, NecmettinAn electrochemical anodization technique was used to create a hydrogen gas sensor based on TiO2 nanotubes decorated with bismuth oxide (Bi2O3). Bismuth nitrate pentahydrate (Bi(NO3)3 center dot 5H2O) was employed as the source material for Bi2O3. The resulting nanotubes were annealed at 500 degrees C, revealing an amorphous structure with a mixed phase of rutile and anatase. Platinum (Pt) electrodes, with a thickness of 100 nm, were coated onto the Bi2O3@TiO2/Ti and TiO2/Ti structures for sensor testing. Energy dispersive X-ray spectroscopy (EDS), X-ray diffraction (XRD), X-ray photoelectron spectroscopy (XPS), and field emission scanning electron microscopy (FESEM) were used to examine the structural, morphological, and surface properties of the Bi2O3@TiO2 and TiO2 nanotubes. The hydrogen sensing properties of the Pt/Bi2O3@TiO2/Ti and Pt/TiO2/Ti devices were evaluated at room temperature, with hydrogen concentrations ranging from 1000 ppm to 10 %. The I-V characterization of the sensor devices under 1 % H2 exhibited typical Schottky-type behavior. Remarkably, the Pt/Bi2O3@TiO2/Ti structure demonstrated a sensor response 1 x 107 times higher than that of in a dry air environment when the same voltage was applied under up to 1 % H2 conditions. The uniform dispersion of Bi2O3 nanoparticles throughout the structure contributed to the enhanced sensor response in the presence of H2.Öğe Enhancing the performance of TiO2 nanotube-based hydrogen sensors through crystal structure and metal electrode(Pergamon-Elsevier Science Ltd, 2024) Tasyurek, Lutfi Bilal; Isik, Esme; Isik, Ibrahim; Kilinc, NecmettinIn this research, the effect of metal electrodes and crystalline phase on gas detection of titanium dioxide (TiO2) nanotube-based hydrogen (H2) sensors was investigated. TiO2 nanotubes were produced using glycerol-based electrolyte and annealed at 300 degrees C and 700 degrees C to change the anatase and rutile crystalline phases, respectively. TiO2 nanotubes were coated by platinum (Pt), palladium (Pd), gold (Au) and silver (Ag) electrodes to fabricate metal/TiO2 nanotubes Ti H2 sensor devices and then the current-voltage (I-V) characteristics were investigated at room temperature. The structural properties of TiO2 nanotubes were characterized by SEM, FE-SEM, XRD, and Raman techniques. The H2 detection properties of the sensors were examined at the 1000 ppm - 5% H2 concentration range. The crystal structure and metal electrodes are the main factors that affect the H2 sensing properties of TiO2 nanotube-based sensors. The effect of crystal forms on sensitivity was not the same as for metal electrodes. The underlying sensing mechanisms for different types of metal electrodes and crystal structures are discussed and the relevance of their sensing performance to nanotubes and electronic properties is investigated. In addition, discussion of each metal electrode and crystal structure will make important contributions to the development of H2 sensors. The Pd-coated device annealed at 700 degrees C showed the best detection performance.(c) 2023 Hydrogen Energy Publications LLC. Published by Elsevier Ltd. All rights reserved.Öğe Interference and molecule reception probability analysis in nano/micro scale communication systems using Fick's diffusion law(Gazi Univ, Fac Engineering Architecture, 2022) Isik, Ibrahim; Tagluk, Mehmet Emin; Isik, EsmeRecently, too much afford has been conducted toward development of novel communication techniques (biological inspired) for implementing in nano and micro scale systems inspired from electro-chemical communication systems that naturally used by living beings. One of these techniques is known as nano/micro scale communication (NMSC) in which chemical signals are used as carriers for transmission of information through fluid media. The information carrier particles used in such communication systems consist of biological components such as DNA and protein components. Studies regarding NMSC are considered to highly contribute to the developments in the field of nano-technology which can be used to detect and treatment of the some unsolved illness yet. Therefore, in this study, software based a new NMSC model that could potentially be used in nano-scale systems were developed and analysed in terms of communication performance. Firstly, Diffusion constant which affect the communication performance of the software based NMSC model is derived using some Physics laws such as Fick's. Secondly, different forms of receivers such as sphere, cube and rectangular prism topologies have been tried for increasing the rate of molecule reception and reducing the inter symbol interference of the receiver. It was observed that the signal transmission rate increased and the interference decreased with the use of a cube receiver model. The results obtained from the proposed NMSC model encourages one to think that such receiver models might have the potential for Alzheimer and many illness which cause missing and/or wrong communication of the cells.Öğe Parkinson's detection based on combined CNN and LSTM using enhanced speech signals with Variational mode decomposition(Elsevier Sci Ltd, 2021) Er, Mehmet Bilal; Isik, Esme; Isik, IbrahimParkinson's disease (PD) can cause many non-motor and motor symptoms such as speech and smell. One of the difficulties that Parkinson's patients can experience is a change in speech or speaking difficulties. Therefore, the right diagnosis in the early period is important in reducing the possible effects of speech disorders caused by the disease. Speech signal of Parkinson patients shows major differences compared to normal people. In this study, a new approach based on pre-trained deep networks and Long short-term memory (LSTM) by using melspectrograms obtained from denoised speech signals with Variational Mode Decomposition (VMD) for detecting PD from speech sounds is proposed. The proposed model consists of four steps. In the first step, the noise is removed by applying VMD to the signals. In the second step, mel-spectrograms are extracted from the enhanced sound signals with VMD. In the third step, pre-trained deep networks are preferred to extract deep features from the mel-spectrograms. For this purpose, ResNet-18, ResNet-50 and ResNet-101 models are used as pre-trained deep network architecture. In the last step, the classification process is occurred by giving these features as input to the LSTM model, which is designed to define sequential information from the extracted features. Experiments are performed with the PC-GITA dataset, which consists of two classes and is widely used in the literature. The results obtained from the proposed method are compared with the latest methods in the literature, it is seen that it has a better performance in terms of classification performance.Öğe Role of the Health System in Combating Covid-19: Cross-Section Analysis and Artificial Neural Network Simulation for 124 Country Cases(Routledge Journals, Taylor & Francis Ltd, 2021) Bayraktar, Yuksel; Ozyilmaz, Ayfer; Toprak, Metin; Isik, Esme; Buyukakin, Figen; Olgun, Mehmet FiratIn the fight against Covid-19, developed countries and developing countries diverge in success. This drew attention to the discussion of how different health systems and different levels of health spending are effective in combating Covid-19. In this study, the role of the health system in the fight against Covid-19 is discussed. In this context, the number of hospital beds, the number of doctors, life expectancy at 60, universal health service and the share of health expenditures in GDP were used as health indicators. In the study, firstly 2020 data was estimated by using the Artificial Neural Networks simulation method and this year was used in the analysis. The model, with the data of 124 countries, was estimated using the cross-sectional OLS regression method. The estimation results show that the number of hospital beds, number of doctors and life expectancy at the age of 60 have statistically significant and positive effects on the ratio of Covid-19 recovered/cases. Universal health service and share of health expenditures in GDP are not significant statistically on the cases and recovered. Hospital bed capacity is the most effective variable on the recovered/case ratio.Öğe Synthesis and analysis of TiO2 nanotubes by electrochemical anodization and machine learning method for hydrogen sensors(Elsevier, 2022) Isik, Esme; Tasyurek, Lutfi Bilal; Isik, Ibrahim; Kilinc, NecmettinThe conductometric hydrogen gas sensors were used to explore TiO2 nanotubes in this study. TiO2 nanotubes are synthesized by anodization of the titanium foils using a neutral 0.5% and 1% (wt) NH4F in glycerol solution depending on anodization time and anodization voltage at the temperature of 20 degrees C. The amorphous, rutile and anatase phases of TiO2 are observed for as-prepared TiO2 nanotubes, annealed at 700 and 300 degrees C, respectively. The diameters of the nanotubes grow as the anodization time and voltage increase, according to scanning electron microscopy (SEM) images. The inner diameter of nanotubes is changed between similar to 70 nm to similar to 225 nm. Hydrogen sensing properties of Ti/TiO2 nanotubes/Pd device has been tested at room temperature under concertation range from 0.5% to 10% depending on the crystalline phase. The highest sensor response is observed for anatase crystalline TiO2 nanotubes. Typical Schottky-type behavior is observed from the I-V measurement. All the fabricated nanotube diameters are also simulated by using Support Vector Machine and Artificial Neural Network models. And also, some of the nanotube diameters which are not obtained experimentally (anodization voltage of 70 V) are estimated using the Support Vector Machine and Artificial Neural Network models. In addition, an analytical model is also proposed using Jacobi numeric analysis method alternative to the simulation model for the nanotube diameter. Finally, the analytical, simulation, and experimental results are compared, and the best result is obtained using the 1 Hidden Layer Artificial Neural Network model.
