Yayınlar
Koleksiyondaki öğeler
- MakaleYalnız künye2019Scopus SJRQ3Regp: A new pooling algorithm for deep convolutional neural networks
Yildirim, O.; Baloglrf, U.B.
In this paper, we propose a new pooling method for deep convolu-tional neural networks. Previously introduced pooling methods either have very simple assumptions or they depend on stochastic events. Different from those methods, RegP pooling intensely investigates the input data. The main idea of this approach is finding the most distinguishing parts in regions of the input by investigating neighborhood regions to construct the pooled representation. RegP pooling improves the efficiency of the learning process, which is clearly visible in the experimental results. Further, the proposed pooling method outperformed other widely used hand-crafted pooling methods on several benchmark datasets.
AtıfScopus8WoS6OpenAlex9
İncele - MakaleYalnız künye2019Scopus SJRQ1Classification of myocardial infarction with multi-lead ECG signals and deep CNN
Baloglu, Ulas Baran; Talo, Muhammed; Yildirim, Ozal; Tan, Ru San; Acharya, U Rajendra
Myocardial infarction (MI), commonly known as heart attack, causes irreversible damage to heart muscles and even leads to death. Rapid and accurate diagnosis of MI is critical to avoid death. Blood tests and electrocardiogram (ECG) signals are used to diagnose acute MI. However, for an increase in blood enzyme values, a certain time must pass after the attack. This time lag may delay MI diagnosis. Hence, ECG diagnosis is still very important. Manual ECG interpretation requires expertise and is prone to inter-observer variability. Therefore, computer aided diagnosis may be useful in automatic detection of MI on ECG. In this study, a deep learning model with an end-to-end structure on the standard 12-lead ECG signal for the diagnosis of MI is proposed. For this purpose, the most commonly used technique, convolutional neural network (CNN) is used. Our trained CNN model with the proposed architecture yielded impressive accuracy and sensitivity performance over 99.00% for MI diagnosis on all ECG lead signals. Thus, the proposed model has the potential to provide high performance on MI detection which can be used in wearable technologies and intensive care units.
AtıfScopus457OpenAlex476İncele - MakaleYalnız künye2018Scopus SJRQ1Anesthetic potential of geranium (Pelargonium graveolens) oil for two cichlid species, Sciaenochromis fryeri and Labidochromis caeruleus
Can, Erkan; Kizak, Volkan; Seyhaneyildiz Can, Şafak; Özçiçek, Esin
The anesthetic potential of geranium oil (Pelargonium graveolens L.) was evaluated in two freshwater aquarium fish species, the electric blue hap (Sciaenochromis fryeri, 2.00 ± 0.61 g) and blue streak hap (Labidochromis caeruleus, 2.31 ± 0.52 g). Fish were exposed to nine concentrations of anesthetic (25, 50, 75, 100, 125, 150, 200, 250, 300 μl L−1). The induction time generally decreased significantly with increasing concentration of geranium oil for both of the fish species. The recovery time increased with the enhancing geranium oil concentration. Deep anesthesia took between 61.19 ± 7.25 s and 165.43 ± 6.78 s for S. fryeri and between 73.32 ± 8.92 s and 171.12 ± 10.74 s for L. caeruleus. Recovery occurred after 96 ± 6.87 s (L. caeruleus), with the longest being 291.45 ± 8.31 s (S. fryeri). The minimal effective concentration was 75 μl L−1 for deep anesthesia for both two species, and 50 μl L−1 was found as the minimal sedative concentration at the stage of loss of equilibrium. These findings suggested that geranium oil is a new potential anesthetic for two ornamental fish species.
AtıfScopus33WoS29OpenAlex34İncele - MakaleYalnız künye2018Scopus SJRQ1A new Fine-Kinney-based risk assessment framework using FAHP-FVIKOR incorporation
Gul, Muhammet; Guven, Busra; Guneri, Ali Fuat
The most crucial step of a risk assessment process that follows identifying the scope of assessment and hazards is the initial risk assessment, particularly with a risk scoring system. The Fine–Kinney method is a comprehensive method for quantitative evaluations to aid in controlling hazards. In this risk assessment method, the risk value is calculated by considering the parameters of the consequence of an accident (C), the exposure or frequency of occurrence of a hazard event that could lead to an accident (E) and the probability of a hazardous event (P). The classical Fine–Kinney method has a limitation in that it assigns an equal weight to these three parameters. Therefore, we propose a new risk assessment method incorporating a fuzzy analytic hierarchy process (FAHP) with fuzzy VIKOR (FVIKOR). FAHP was used in weighting these risk parameters derived from the Fine–Kinney method. The priority orders of hazards were determined by a FVIKOR method. The proposed method enables group decision-making in assessing hazards and uses relative importance among three risk parameters by pair-wise comparison of Buckley's FAHP. Owing to the difficulty in evaluating C, E and P, linguistic terms are used in the proposed method. In addition, a case study of the evaluation of risks in the arms industry is used to illustrate the proposed method. A comparison with the classical method and fuzzy technique for order preference by similarity of an ideal solution (FTOPSIS) is discussed. The results show that the proposed method is effective in helping stakeholders to determine the risk control policies to validate the effectiveness of their risk controls.
AtıfScopus106WoS84OpenAlex124İncele - MakaleAçık Erişim2019AHP–TOPSIS integration extended with Pythagorean fuzzy sets for information security risk analysis
Ak, M. Fatih; Gul, Muhammet
Risk analysis (RA) contains several methodologies that object to ensure the protection and safety of occupational stakeholders. Multi attribute decision-making (MADM) is one of the most important RA methodologies that is applied to several areas from manufacturing to information technology. With the widespread use of computer networks and the Internet, information security has become very important. Information security is vital as institutions are mostly dependent on information, technology, and systems. This requires a comprehensive and effective implementation of information security RA. Analytic hierarchy process (AHP) and technique for order preference by similarity to ideal solution (TOPSIS) are commonly used MADM methods and recently used for RA. In this study, a new RA methodology is proposed based on AHP–TOPSIS integration extended with Pythagorean fuzzy sets. AHP strengthened by interval-valued Pythagorean fuzzy numbers is used to weigh risk parameters with expert judgment. Then, TOPSIS with Pythagorean fuzzy numbers is used to prioritize previously identified risks. A comparison of the proposed approach with three approaches (classical RA method, Pythagorean fuzzy VIKOR and Pythagorean fuzzy MOORA) is also provided. To illustrate the feasibility and practicality of the proposed approach, a case study for information security RA in corrugated cardboard sector is executed.
AtıfScopus152WoS128OpenAlex167İncele - MakaleYalnız künye2020Scopus SJRQ1Impact of mechanical properties of historical masonry bridges on fundamental vibration frequency
Onat, Onur
The fundamental frequency of a historical monument like a masonry bridge or any other structure provides a better and detailed seismic assessment of its demand to provide protection against unexpected seismic ground motion. On this basis, this paper aims to develop an empirical formulation to fit the ambient vibration frequency of historical masonry bridges using a nonlinear regression model. For this purpose, data series were collected from the literature especially focused on both ambient vibration measurement and finite element models of historical masonry bridges modeled on a full scale to get the first global natural frequency. The first approach is to forecast the natural vibration frequency by using only physical characteristics of the historical masonry bridges obtained from the literature-based experimental ambient vibration frequency data. The second approach consists of forecasting the first natural vibration frequency considering the unit weight and elasticity modulus of the dominant construction material based on the homogenization approach. In addition to mechanical characteristics, physical properties of historical masonry bridges were used, such as the length, height, width, and Main Arch Span (MAS) length of the masonry bridge, to predict the first natural vibration frequency. Among the proposed equations, a maximum accuracy of 58% was reached with the literature-based experimental approach. Moreover, an empirical formulation with 81% accuracy was proposed by using both physical characteristics and mechanical properties of the bridges on the basis of finite element model results. Also, this study highlights that this accuracy decreases to 35% if the modulus of elasticity and unit weight are ignored. In addition, the developed formulations are compared with other empirical formulations using the Mean Square Error (MSE), as a measure of the average of the squares of the errors. Consequently, the smallest MSE value of 1.95 was obtained with the proposed equation, whose accuracy was 81% in this study.
AtıfScopus17WoS19OpenAlex21İncele - MakaleYalnız künye2020Scopus SJRQ1A deep convolutional neural network model for automated identification of abnormal EEG signals
Yıldırım, Özal; Baloglu, Ulas Baran; Acharya, U. Rajendra
Electroencephalogram (EEG) is widely used to monitor the brain activities. The manual examination of these signals by experts is strenuous and time consuming. Hence, machine learning techniques can be used to improve the accuracy of detection. Nowadays, deep learning methodologies have been used in medical field to diagnose the health conditions precisely and aid the clinicians. In this study, a new deep one-dimensional convolutional neural network (1D CNN) model is proposed for the automatic recognition of normal and abnormal EEG signals. The proposed model is a complete end-to-end structure which classifies the EEG signals without requiring any feature extraction. In this study, we have used the EEG signals from temporal to occipital (T5–O1) single channel obtained from Temple University Hospital EEG Abnormal Corpus (v2.0.0) EEG dataset to develop the 1D CNN model. Our developed model has yielded the classification error rate of 20.66% in classifying the normal and abnormal EEG signals.
AtıfScopus164OpenAlex211İncele - MakaleAçık Erişim2018Scopus SJRQ3Design, analysis, and control of in-wheel switched reluctance motor for electric vehicles
Omaç, Z.; Polat, M.; Öksüztepe, E.; Yıldırım, M.; Yakut, O.; Eren, H.; Kaya, M.; Kürüm, H.
Estimation of dimension parameters for an electric machine has great importance before assembling on production line. As a matter of fact, researchers should find optimum solution once they decide to perform analytical design of an electric machine. In this study, we have tried to find dimensional and electrical parameters via derived mathematical equations for in-wheel switched reluctance motor (IW-SRM), and the motor has been manufactured. Moreover, an experimental setup is designed, and the speed and torque control of IW-SRM is carried out. The motor tests including both standstill and running test are performed by using the experimental setup. Initial size parameters are intuitively provided as motor analysis is conducted by software package. Then, numerous trials are examined to get optimum results. In fact, this motor is employed by an electric vehicle whose design is ongoing. Therefore, optimum motor parameters for required base speed and torque have been estimated by solving generated equations for IW-SRM with 18/12 poles via MATLAB. Considering parameters estimated, analysis of IW-SRM has been performed by Ansoft Maxwell 15.0 Software Package based on 3D finite element method (3D-FEM). Consequently, the estimated parameters have been validated by the results of Maxwell 3D FEM. Experimental results of the motor manufactured are obtained via the motor driver designed; also have been validated by Maxwell 3D.
AtıfScopus14WoS15OpenAlex24İncele - MakaleAçık Erişim2020Scopus SJRQ2New national and regional bryophyte records, 63
Ellis, L.T.; Afonina, O.M.; Czernyadjeva, I.V.; Konoreva, L.A.; Potemkin, A.D.; Kotkova, V.M.; Alataş, M.; Blom, H.H.; Boiko, M.; Cabral, R.A.
AtıfScopus21OpenAlex23İncele - MakaleAçık Erişim2018Scopus SJRQ3Performance comparison between ARIMAX, ANN and ARIMAX-ANN hybridization in sales forecasting for furniture industry; [Usporedba performansi modela ARIMAX, ANN i hibridizacije ARIMAX-ANN u predviđanju prodaje za industriju namještaja]
Yucesan, Melih; Gul, Muhammet; Celik, Erkan
Manufacturing firms aim to increase their profits and reduce costs in a competitive and rapidly changing market. One of the most important ways to reach these goals is to forecast sales correctly. Furniture manufacturing, which is considered a prosperous and growing industry in Turkey, has an increasing trend related to the growth in construction and associated industries, increase in urban migration and increase in per capita income. Accuracy of sales forecasting in furniture industry is affected by external factors, such as consumer confidence index, producer price index, month of the year and number of vacation days as well as the time factor itself. This study aims to develop an Autoregressive Integrated Moving Average with external variables (ARIMAX) to forecast the total monthly sales of furniture products of a well-known manufacturer in Turkey. As a follow up study, a performance comparison between ARIMAX, artificial neural networks (ANNs) and ARIMAX-ANN hybridization is performed. In conclusion, results of performance measures demonstrate that hybrid model developed for each amount of product sales give better accuracy values than single methods. Overall, it is proved that using the ARI-MAX and hybridization of this method with ANN are applicable for forecasting monthly sales of furniture products.
AtıfScopus7WoS5OpenAlex20İncele - BildiriAçık Erişim2021Control of automatic fire extinguishing operation for 5 forest areas with SCADA
Ustundag, Aybike; Gencer, Cetin
The number of forest fires has increased significantly in recent years. Interventions to forest fires from air and land are very difficult and dangerous. In addition, since these interventions are time-consuming, forest fire can spread to a much wider area. In this study, an automatic fire extinguishing system was designed using SCADA for 5 forest regions up to 5 hectares. In the event of a fire in the system, the smoke sensor in the fire area becomes active and the IP camera image in this area is displayed on the screen. The pressurized water flushing tap, which automatically rotates 360 degrees, works in the area. If desired, automatic operation can be canceled and manually adjusted water flushing tap can be operated. The system gives a warning when the tank water drops below 1 ton. The aim of this study is to automatically intervene early in any fire that may occur in the forest and to control the fire before it spreads.
AtıfScopus1OpenAlex1İncele - MakaleYalnız künye2018Scopus SJRQ1Analytical solution to continuous contact problem for a functionally graded layer loaded through two dissimilar rigid punches
Polat, Alper; Kaya, Yusuf; Özşahin, Talat Şükrü
A continuous contact problem of functionally graded layer resting on an elastic semi-infinite plane, which is loaded with through two different blocks is addressed in this study. The elasticity theory and integral transformation techniques are used in solution of the problem. The problem is reduced to a system of singular integral equations, and solved numerically by the aid of appropriate Gauss–Chebyshev integration formula. It is assumed that the elastic semi-infinite homogeneous plane is isotropic and all surfaces are frictionless and continuous. The shear modulus and the mass density of the FG layer vary exponentially along the thickness direction.
AtıfScopus19WoS18OpenAlex15İncele - MakaleYalnız künye2021Scopus SJRQ2Homoploid hybrids of Origanum (Lamiaceae) in Turkey: morphological and molecular evidence for a new hybrid
Arabaci, Turan; Çelenk, Sevcan; Özcan, Taner; Martin, Esra; Yazici, Türker; Açar, Mikail; Üzel, Devrim; Dirmenci, Tuncay
In this study, three hybrids of Origanum (Lamiaceae) were examined in detail using morphological, karyological, palynological and molecular approaches. One of the three hybrids, O. × aytacii, is here described for the first time, and is compared with its putative parents, O. sipyleum and O. vulgare subsp. hirtum. In addition to morphological, karyological and palynological features, we also examined nuclear ribosomal DNA (ITS) sequences of O. × intermedium (O. onites × O. sipyleum), O. × intercedens (O. onites × O. vulgare subsp. hirtum) and their purported parental species that share the same area with the new hybrid. Pollen grains were hexacolpate and isopolar. The range of Polar/Equatorial ratio (P/E) of pollen for investigated taxa varied from 0.74 to 0.99. All investigated taxa are diploid with a chromosome number as 2n = 30. According to molecular results, O. × aytacii was the most polymorphic taxon. In addition, DNA sequences showed that O. × intercedens was more similar to O. vulgare subsp. hirtum than to O. onites, and O. × intermedium was more similar to O. onites than to O. sipyleum. Furthermore, O. onites and O. vulgare subsp. hirtum have many different ITS haplotypes, probably resulting from backcrossing with different individuals. Results obtained in this study demonstrate that hybridization has played a major role in the process of Origanum speciation.
AtıfScopus21OpenAlex18İncele - MakaleYalnız künye2018Scopus SJRQ1Experimental investigation of the flow around a simplified ground vehicle under effects of the steady crosswind
Tunay, Tural; Firat, Erhan; Sahin, Besir
Crosswinds which stem from on-road flow conditions can deteriorate a ground vehicle's driving performance. In spite of the numerous studies investigating aerodynamics of the ground vehicles in the previous literature, there is still a need for thorough understanding of the underlying flow phenomena related to crosswind sensitivity of the ground vehicles. Therefore, the present study is aimed to investigate characteristics of the flow features around the ground vehicles under steady crosswind conditions within a range of yaw angles 0° ≤ β ≤ 15° using the Ahmed vehicle model with rear slant angles of α = 25° and 35°. Throughout the investigations, flow visualizations using dye injection technique and velocity measurements using particle image velocimetry PIV technique are conducted. The Reynolds number of the flow which is based on the free stream flow velocity U = 200 mm/s and height of the model H = 72 mm is ReH= 1.4 × 104. Results are presented in terms of time-averaged vorticity <ω> contours and streamline <ψ> patterns together with velocity magnitude ((<u>2+<w>2)1/2/U) of the flow fields. Additionally, turbulence quantities such as Reynolds stresses <u'w'>/U2 and turbulent kinetic energy TKE are presented and discussed in details. Results of the present study show that characteristics of the flow features in the near wake region downstream of the Ahmed model are very sensitive to the effects of the crosswind.
AtıfScopus36WoS35OpenAlex39İncele - MakaleYalnız künye2019Scopus SJRQ2Tsallis holographic dark energy in Bianchi type-III spacetime with scalar fields
Korunur, Murat
In this paper, we study one of the new dark energy models named Tsallis holographic dark energy (THDE) model considering the Bianchi type-III spacetime model. Considering deceleration parameter, transition from deceleration to acceleration phase happens at z = 0.256. The equation of state (EoS) parameter has been found using the Granda-Oliveros (GO) scale. It is found that for > 2 values, EoS parameter behaves like the quintessence era; for < 2, EoS parameter behaves like the phantom dark energy and approaches CDM model at late-time cosmic acceleration phase. Also, we reconstructed a correspondence between THDE model and some well-known scalar fields, such as tachyon, quintessence and K-essence. In addition, we evaluated equation of state parameter, kinetic energy and scalar potential versus time.
AtıfScopus28WoS28OpenAlex29İncele - MakaleAçık Erişim2021Scopus SJRQ2New national and regional bryophyte records, 67
Ellis, L.T.; Alataş, M.; Álvaro Alba, W.R.; Charry Giraldo, A.M.; Amatov, V.; Batan, N.; Becerra Infante, D.A.; Burghardt, M.; Czernyadjeva, I.V.; Yu. Kuzmina, E.
AtıfScopus19OpenAlex19İncele - MakaleYalnız künye2018Scopus SJRQ3Investigation of dose and development time for thin e-beam resist poly(methyl methacrylate) for large area dense nanopattern applications
Göktaş, Oktay; Çakıroğlu, Dilek; Yıldırım, Özal; Göktaş, Nebile Işık
With the advance of nanotechnology, the demand for very dense nanopatterns over large areas continuously increases. Electron beam lithography is one of the main tools to realise this type of nanopattern. In this study we investigate the effect and interrelation of dose and development time for electron beam resist poly(methyl methacrylate) (PMMA) for the realisation of very large area and very dense nanopatterns. For this purpose a pattern consisting of a lattice of holes with radius of 80 nm and lattice constant of 200 nm has been designed, electron beam lithography is realised on a thin resist and a detailed SEM image inspection of the pattern is recorded. Hough transform, a pattern recognition method for the digital images, is applied to SEM images to measure the radii of the holes on the images. Interrelation between dose and development time is investigated. It is found that for a very large area of dense nanopatterns the lithographic process works better for development times shorter than typically used ones.
- MakaleAçık Erişim2018Scopus SJRQ2Bright, dark optical and other solitons to the generalized higher-order NLSE in optical fibers
Baskonus, Haci Mehmet; Sulaiman, Tukur Abdulkadir; Bulut, Hasan
In this paper, we study the generalized higher-order nonlinear Schrödinger equation analytically. We use two integral schemes for conducting this study. Dark, bright, combined dark–bright optical, singular soliton, soliton-like and trigonometric function solutions are successfully constructed. We give the constraint conditions for the existence of valid solutions. The 2D, 3D and the contour graphs for the dark and bright solitons are plotted.
AtıfScopus32OpenAlex35İncele - MakaleYalnız künye2019Scopus SJRQ2A fuzzy-based model for risk assessment of routes in oil transportation
Gul, M.; Guneri, A.F.; Nasirli, S. Miralp
The transportation of oil is the final step that the oil is taken before it is distributed to consumer. Road transport is a type of oil transportation methods, and transfers between facilities of primary and secondary bases are carried out by tanker trucks. A particular advantage of tanker trucks is that they provide direct travel from the source to the destination. However, road transport involves possible hazards for population and environment. At this point, this study presents a fuzzy-based risk assessment model for the routes in an oil transportation company. Fuzzy analytic hierarchy process, which is a commonly used multi-criteria decision-making method, is applied in weighting nine criteria related to the road characteristics. Then, risk scores for eleven different routes which the tanker trucks of the company followed are determined by using a basic multi-criteria scoring method. Results of the case study emerge that the most important criterion is narrow road. The riskiest route for the company has been determined. In order to reduce risks to an acceptable level, a number of control measures are suggested such as to assign experienced drivers for this route, provide regular training for drivers, make regular vehicle maintenance and transport large quantities at one time as possible. To demonstrate validity, a comparison is also provided between the proposed approach and Pythagorean fuzzy analytic hierarchy process-based risk scoring model. In conclusion, this study contributes to the applicability of fuzzy analytic hierarchy process to assess riskiness for routes in oil transportation.
AtıfScopus36WoS28OpenAlex46İncele - MakaleYalnız künye2018Scopus SJRQ1The Effect of Therapeutic Clowning on Handwashing Technique and Microbial Colonization in Preschool Children
Arıkan, Duygu; Gürarslan Baş, Nazan; Kurudirek, Fatma; Baştopcu, Ayşe; Uslu, Hakan
Purpose: This study aimed to determine the effect of therapeutic clowning on handwashing technique and microbial colonization in preschool children. Design: This randomized controlled trial was conducted using pre-test and post-test experimental and control groups. Methods: The study was conducted between March and June 2016 in two kindergartens in eastern Turkey. The study was completed with a total of 195 students, including 90 students in the experimental group and 105 students in the control group. A questionnaire was used for data collection. This questionnaire included sections about the subjects’ descriptive characteristics and the results of the bacterial cultures of their hand swabs. For the collection of these swabs, the subjects were informed in advance, and samples were collected at predetermined times. The swabs were analyzed to determine the bacterial colonization of the subjects’ hands. Clowns and video activities were used as intervention tools in the study. Findings: In the post-test, the microbial growth was ≤103 in 68.9% and >103 in 31.1% of the subjects in the experimental group. In contrast, the growth was ≤103 in 34.3% and >103 in 65.7% of the control group subjects. The difference in the post-test microbial growths of the two groups was statistically significant (p <.000). Conclusions: The hygienic handwashing technique taught in the therapeutic clowning and videos reduced the bacterial colonization on the preschool children's hands by 50%. Moreover, this method was effective in reducing the growth rate of coliform bacteria that indicate undesirable, poor hygiene of the hands. Clinical Relevance: Considering these results, we recommend that pediatric healthcare professionals use entertaining methods such as those involving clowns to teach and guide children regarding hygienic handwashing techniques.
AtıfScopus11WoS10OpenAlex12
İncele
