Yazar "Arslan A." seçeneğine göre listele
Listeleniyor 1 - 20 / 23
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe An adaptive neuro-fuzzy inference system-based approach to forecast time series of chaotic systems(Springer, 2014) Köse U.; Arslan A.Forecasting (prediction of) time series of chaotic systems is known as one of the most remarkable research areas within the Chaos Theory. As being associated with needs for more effective, efficient and accurate solution approaches, Artificial Intelligence-based techniques are used for designing forecasting systems to achieve the related objectives. In this sense, this study introduces a system, which was designed on an Adaptive Neuro-Fuzzy Inference System (ANFIS) approach. As a result of learning – reasoning infrastructure ensured by the combination of Artificial Neural Networks and Fuzzy Logic techniques, an alternative solution-based study on forecasting chaotic time series is provided for the literature. © Springer Science+Business Media Dordrecht 2014.Öğe The banded karyotype of the 2n = 58 chromosomal race of mole rats from Erzincan, Turkey(2013) Arslan A.; Zima J.In this study, the 2n = 58 chromosomal race of blind mole rats, Nannospalax xanthodon, from the Erzincan province in Turkey was investigated. Conventional chromosome staining, Ag-NOR staining and C-banding analysis were carried out in the specimens studied. The karyotype included three small or medium-sized meta/submetacentric pairs and twenty-five acrocentric pairs of autosomes of gradually diminishing size (NFa = 62). C-heterochromatin regions were found in centromeric and pericentromeric areas or in short arms of some bi-armed autosomal pairs and in pericentromeric areas of a few acrocentric autosomes. The X chromosome had a centromeric C-positive band and the short arm of the Y chromosome appeared to be C-positively stained. The NORs were localized in distal heterochromatin areas of the short arms of two pairs of biarmed and one pair of acrocentric autosomes. Within the 58 chromosome populations reported from Turkey, two groups can be recognized differing by the presence or absence of a large submetacentric autosomal pair. The populations possessing this marker chromosome occur in central and northern Anatolia, whereas populations form eastern Anatolia have no similar chromosome in their karyotype.Öğe Biochemical and sensory evaluations of Turkish delight (Lokum) enriched with black grape and sour cherry syrups(Turkiye Klinikleri Journal of Medical Sciences, 2014) Batu A.; Arslan A.Black grape and sour cherry are high in phenolic substances and anthocyanin compounds, which are important for human health. Adding black grape and sour cherry fruit syrups into Turkish delight (lokum) could make the product healthier. While the highest antioxidant activity (AA) was found in the products produced with 7.5% black grape syrup (BGS) and sour cherry fruit syrup (SCS), the lowest AA was obtained from the control sample. The AA values of Turkish delight produced with BGS and SCS increased with the increased fruit concentration. Turkish delight produced with SCS had about twice as much AA than that produced with BGS. The sensory panelists' scores showed that all the treatments were acceptable in terms of appearance, color, and aroma, but the products produced with 2.5% were evaluated as the best. In terms of overall acceptability, the 2.5% and 5.0% fruit concentrate Turkish delight samples produced approximately the same results. © TÜBİTAK.Öğe Boundary extraction in texture mosaics using discontinuity information in feature space [Özellik uzayinda devamsizlik bilgisi kullanilarak doku mozaiklerinde sinir çikarimi](2010) Öztürk A.; Arslan A.In this study, boundary extraction between textures is examined. The overall system consists of three stages. In the first stage, the gradients in feature space are estimated using a modified version of gray-level edge detection operators. For comparison purposes, both the Prewitt and Sobel operators are used. The second stage involves application of a threshold value to obtain a binary image displaying edges found in the first stage. In the last and crucial stage, some morphological post-processing operations are applied on the binary edge image to remove spurious pixels inside regions and to thin the thick edges occuring due to both rough thresholding and the use of large displacement value in edge detection. To discriminate between textures, four different features are used. The first three features are the fractal dimension (FD) of original image, constrast-strecthed image and top-hat transformed image, respectively. The fourth feature is the entropy which is a parameter obtained from the spatial gray-level co-occurrence matrix of the image. The experimental results are presented for mosaics with different number of textures from Brodatz album.Öğe The categorical distinction annexations to maximal associations discovered from web database by rough set theory to increase the quality(2008) Ülker E.; Siramkaya E.; Arslan A.[Abstract not Available]Öğe Chaotic systems and their recent implementations on improving intelligent systems -- 2(IGI Global, 2015) Köse U.; Arslan A.Chaos Theory is a kind of a scientific approach/research effort which is based on examining behaviors of nonlinear dynamical systems which are highly sensitive to their initial conditions. Currently, there are many different scientific studies based on the Chaos Theory and the related solution approaches, methods, or techniques for problems of this theory. Additionally, the theory is used for improving the introduced studies of different fields in order to get more effective, efficient, and accurate results. At this point, this chapter aims to provide a review-based study introducing recent implementations of the Chaos Theory on improving intelligent systems, which can be examined in the context of the Artificial Intelligence field. In this sense, the main research way is directed into the works performed or introduced mostly in years between 2008 and 2013. By providing a review-based study, the readers are enabled to have ideas on Chaos Theory, Artificial Intelligence, and the related works that can be examined within intersection of both fields. At this point, the chapter aims to discuss not only recent works, but also express ideas regarding future directions within the related implementations of chaotic systems to improve intelligent systems. The chapter is generally organized as a reference guide for academics, researchers, and scientists tracking the literature of the related fields: Artificial Intelligence and the Chaos Theory. © 2015, IGI Global. All rights reserved.Öğe Cytogenetic studies on european brown hare, lepus europaeus pallas, 1778 (lagomorpha: Leporidae) in Turkey(Veteriner Fakultesi Dergisi, 2010) Arslan A.In this study, the karyotype, C-heterochromatin blocks, and nucleolar organizer regions (NORs) of four specimens of Lepus europaeus from Turkey were examined. The diploid number of chromosomes (2n), the fundamental number of chromosome arms (FN), and the number of autosomal arms (FNa) were determined as 48, 90, and 86, respectively. All of the chromosomes have been determined to be possessed of centromeric constitutive heterochromatin, except of the pair no. 10. The X chromosome had centromeric heterochromatin and Y chromosome had pericentromeric heterochromatin. There were no distal C-bands in any chromosome of samples. The NORs have been determined to be located in the terminal regions of the long arms of three subtelocentric chromosomes (nos. 15, 16, and 18). Any relation was not determined between the localization of the NORs and C-positive regions of autosomes.Öğe Design and development of a chaos-based image encryption system(Springer, 2014) Köse U.; Arslan A.In the context of cryptography applications, using Chaos-based approaches, methods and techniques for image-based data have become an efficient and important way to design and develop strong security solutions, in especially recent years. At this point, many different scientific research studies are performed in or-der to provide newer cryptographic systems and ensure effective directions for obtaining more secure data storing and sharing. In parallel, this study introduces a basic, simple Chaos-based image encryption system, which employs chaotic systems to form a mathematical and algorithmic infrastructure for data security. © Springer Science+Business Media Dordrecht 2014.Öğe A diagnostic fuzzy rule-based system for congenital heart disease(2011) Kaya E.; Oran B.; Arslan A.In this study, fuzzy rule-based classifier is used for the diagnosis of congenital heart disease. Congenital heart diseases are defined as structural or functional heart disease. Medical data sets were obtained from Pediatric Cardiology Department at Selcuk University, from years 2000 to 2003. Firstly, fuzzy rules were generated by using medical data. Then the weights of fuzzy rules were calculated. Two different reasoning methods as "weighted vote method" and "singles winner method" were used in this study. The results of fuzzy classifiers were compared.Öğe Earning weights of fuzzy rules by using gravitational search algorithm(2013) Kaya E.; Koçer B.; Arslan A.The fuzzy rules are the most important factor which affects the success in fuzzy rule-based systems. Performance of a fuzzy rule-based classifier can be improved by weighting fuzzy rules. There are different methods for weighting fuzzy rules. In this study, weights of fuzzy rules which are generated from datasets in fuzzy rule-based classifiers are determined by using Gravitational Search Algorithm. Gravitational search algorithm is a new algorithm for optimization problems. The aim of the GSA in the proposed method is to find rule weight values which maximize classification accuracy. The proposed method was tested with six different data sets. The simulation results are compared by the other method. The proposed method mostly provided better results than the other method compa red. © 2013 ICIC International.Öğe Effects of hippophae rhamnoides extract on oxidative mucosal injury induced by cisplatin in rat jejunum(Scientific Publishers of India, 2018) Arslan A.; Ozcicek F.; Cimen F.K.; Nalkiran H.S.; Gulaboglu M.; Cetin N.; Coban T.A.Objectives: We aimed to assess the effect of Hippophae rhamnoides extract (HR) on oxidative stress induced by cisplatin (Cis) in rat small intestine tissue by evaluating the biochemical and gene expression levels and histopathological changes. Materials and methods: The control group and Cis group received distilled water, while the HR25+cisplatin (HR25+Cis) group and the HR50+cisplatin (HR50+Cis) group were given HR 25 and 50 mg/kg, respectively, orally for seven days. HR25+Cis, HR50+Cis, Cis groups were injected with a single dose of intraperitoneal cisplatin on the first day. After sacrifice, the jejunum of each rat was removed for the assessment of oxidants and antioxidants. Analyses of the gene expression (for IL-1ß and TNF-?) and histopathological changes evaluated. Results: HR significantly inhibited the increase of oxidants and the decrease of antioxidants caused by cisplatin in the jejunal tissue. IL-1? and TNF-? gene expression levels were almost the same in both the HR50+Cis and the control groups. HR better prevented increase of the serum levels of IL-1? and TNF-? in animals at 50 mg/kg dose compared to 25 mg/kg dose. We confirmed that HR prevented the histopathological changes caused by cisplatin. Conclusions: It was concluded that oxidative stress caused by cisplatin may be preventable by co-administered HR. © 2018, Scientific Publishers of India. All rights reserved.Öğe G- and C-banded karyotype of Cricetulus migratorius Pallas, 1773 (Mammalia: Rodentia) in Central Anatolia(2008) Arslan A.; Akan Ş.The present study reports the banding patterns (G- and C-banding) of chromosomes of Cricetulus migratorius from Central Anatolia. Karyotype of C. migratorius comprised (2n) 22 chromosomes. The number of chromosomal arms (FN) was 44 and the number of autosomal arms (FNa) was 40. Subtelocentric X and Y chromosomes were very similar in size, but they differed on G- and C-banding patterns. Most autosomes in this species were C-negative. Pair no. 4 had very small centromeric C-bands, autosome no 8 possessed an under-centromeric heterochromatin block, and the distal part of chromosome no 9 had a C-positive band. The Y chromosomes had an entirely heterochromatic long arm. The X chromosome possessed a very large under-centromeric block of heterochromatin. © TÜBİTAK.Öğe Improving classification accuracy with discretization on datasets including continuous valued features(2011) Hacibeyoglu M.; Arslan A.; Kahramanli S.This study analyzes the effect of discretization on classification of datasets including continuous valued features. Six datasets from UCI which containing continuous valued features are discretized with entropy-based discretization method. The performance improvement between the dataset with original features and the dataset with discretized features is compared with k-nearest neighbors, Naive Bayes, C4.5 and CN2 data mining classification algorithms. As the result the classification accuracies of the six datasets are improved averagely by 1.71% to 12.31%.Öğe A karyotypic study on the indian crested porcupine, hystrix indica (kerr, 1792), in turkey (mammalia: Rodentia)(2006) Arslan A.A study of two Hystrix indica females revealed that the diploid number of chromosomes (2n) is 66, with a fundamental number (FN) of 116. The number of autosomal arms (NFa) is 112. The X chromosome is metacentric and is the largest. © 2006 Taylor & Francis Group, LLC.Öğe On the Indian crested porcupine, Hystrix indica (Kerr, 1792) in Turkey (Mammalia: Rodentia)(2008) Arslan A.This study presents some data about ecological, biological and taxonomical characteristics of Hystrix indica (Kerr, 1792) from Turkey. For this purpose characteristics of burrow, skull, tooth and measurements of external and cranial characters of two female H. indica from Turkey were investigated. It was concluded that our specimens are between the Middle East and Indian sub-region specimens in terms of morphometrical. It was also determined that there were roots in stomach contents of specimens. © 2008 Asian Network for Scientific Information.Öğe Prostatic urethral duplication: An unusual form of vertical symmetric duplication(Elsevier B.V., 1994) Kilinc M.; Arslan A.; Arslan M.; Yilmaz K.; Semercioz A.Urethral duplication is a rare anomaly that manifests itself in various ways. We present a case with a prostatic urethral duplication without incontinence. To our knowledge this is the first case to be reported and has been discussed within Effmann's classification.Öğe Rough set based categorical association rule mining in web database(2007) Ülker E.; Siramkaya E.; Arslan A.One of the most studied fields in data mining is association rules field and studied on this field more than database communications recently. In existed methods of association rules discovery, studying of objects as an only one category provides deficiency of algorithms which provide finding of categorical associations. Online text documents on internet provide adequate information sources. In this paper, meaningful and important information from text documents on internet have been tried to discover. Firstly, a preprocessing is applied to these data to reduce data with noisy and after that only adequate data are saved to database to use. In the study, relations are discovered based on person-place-event-date categories. In this paper, it is investigated to how the categorical association rules can be discovered using rough sets and presented as an application.Öğe A rough sets approach for diagnostic M-mode evaluation in newborn with congenital heart diseases(2010) Kaya E.; Oran B.; Arslan A.This paper presents a methodology based on rough set theory that can be used to identify those newborn with congenital heart diseases for which performing the test is redundant or superfluous. Pawlak introduced rough set theory in the early 1980s as a tool for representing and reasoning about imprecise or uncertain information. Our method depends on cardiac morphologic measurement algorithms for diagnosis template for neonatal congenital heart diseases accuracy. In this study, relationship between cardiac morphologic measurement and diagnosis of neonatal congenital heart diseases is analysed. Examples of echocardiographic M-mode values application for prediction of diagnosis for newborn infant with congenital heart diseases are given. Furthermore, the methodology enables one to automatically construct a set of descriptive and minimal if-then rules that model the patient group in need of the test. A reanalysis of a previously published real-world dataset of patients with normal cardiovascular system is used as this study. This may be helpful in supporting decisions concerning diagnosis of congenital heart diseases in newborn babies using rough set techniques. In addition, medical rough set techniques can discover novel diagnostic facility and associations that are useful to paediatric cardiologists. © 2010 IEEE.Öğe A support vector machine using the lazy learning approach for multi-class classification(2006) Çomak E.; Arslan A.Support vector machines can be used in a new machine learning technique based on statistical learning. In this paper, we develop least squares support vector machines (LS-SVMs) using the lazy learning approach to classify data in unclassifiable regions in the case of multi-class classification. LS-SVMs use a set of linear equations while SVMs use a quadratic programming problem. The lazy learning approach is a local and memory-based technique. Therefore, it is an alternative technique to fuzzy inference systems. Our studies show that LS-SVMs with the lazy learning approach can give comparable results to fuzzy LS-SVMs for multi-class classification. © 2006 Taylor & Francis.Öğe Texture segmentation using fractal dimension and second order statistics [Fraktal boyut ve i?kinci sevlye i?statistik yöntemleri i?le doku bölütlemesi](2007) Öztürk A.; Arslan A.In this study, segmentation of textured images using four different textural features is examined. The first three features are fractal dimension (FD) of the original image, contrast-stretched image and top-hat transformed image, respectively. Contrast-stretching and top-hat transform are known as detail enhancement techniques in the presence of shading or poor illumination, thus it is assumed that the hidden structures in textures will be apparent after these transformations. The fourth feature, e.g. entropy, is one of the parameters estimated from spatial gray level co-occurence matrix statistics. For comparison purposes, two different feature smoothing methods are applied to the feature space before running k-ortalama clustering. The median smoothing gives more accurate segmentation results than EPNSQ (Edge Preserving Noise Smoothing Quadrant) approach. The experimental results are obtained by applying the proposed method on various natural texture mosaics. For mosaics of four textures the average segmetation accuracies are %96.8 and %96 for median smoothing and EPNSQ approach, respectively. The average segmentation accuracy for five textured mosaics is %95.5 with median smoothing, while it is %89 with EPNSQ approach. The experiments carried out with median smoothing for six and nine textured images give the segmentation accuracies as %94 and %92, while they are %84 and %87 with EPNSQ approach.
