6 results
Search Results
Now showing 1 - 6 of 6
Article Citation - WoS: 7Citation - Scopus: 10Comparison of Three Different Learning Methods of Multilayer Perceptron Neural Network for Wind Speed Forecasting(Gazi Univ, 2021) Bulut, Mehmet; Tora, Hakan; Buaisha, Dr.magdiIn the world, electric power is the highest need for high prosperity and comfortable living standards. The security of energy supply is an essential concept in national energy management. Therefore, ensuring the security of electricity supply requires accurate estimates of electricity demand. The share of electricity generation from renewables is significantly growing in the world. This kind of energy types are dependent on weather conditions as the wind and solar energies. There are two vital requirements to locate and measure specific systems to utilize wind power: modelling and forecasting of the wind velocity. To this end, using only 4 years of measured meteorological data, the present research attempts to estimate the related speed of wind within the Libyan Mediterranean coast with the help of ANN (artificial neural networking) with three different learning algorithms, which are Levenberg-Marquardt, Bayesian Regularization and Scaled Conjugate Gradient. Conclusions reached in this study show that wind speed can be estimated within acceptable limits using a limited set of meteorological data. In the results obtained, it was seen that the SCG algorithm gave better results in tests in this study with less data.Article Citation - WoS: 2Citation - Scopus: 2Risk Assessment of Sea Level Rise for Karasu Coastal Area, Turkey(Mdpi, 2023) Eliawa, Ali; Genc, Asli Numanoglu; Tora, Hakan; Maras, Hadi HakanSea Level Rise (SLR) due to global warming is becoming a more pressing issue for coastal zones. This paper presents an overall analysis to assess the risk of a low-lying coastal area in Karasu, Turkey. For SLR scenarios of 1 m, 2 m, and 3 m by 2100, inundation levels were visualized using Digital Elevation Model (DEM). The eight-side rule is applied as an algorithm through Geographic Information System (GIS) using ArcMap software with high-resolution DEM data generated by eleven 1:5000 scale topographic maps. The outcomes of GIS-based inundation maps indicated 1.40%, 6.02%, and 29.27% of the total land area by 1 m, 2 m, and 3 m SLR scenarios, respectively. Risk maps have shown that water bodies, low-lying urban areas, arable land, and beach areas have a higher risk at 1 m. In a 2 m scenario, along with the risk of the 1 m scenario, forests become at risk as well. For the 3 m scenario, almost all the territorial features of the Karasu coast are found to be inundated. The effect of SLR scenarios based on population and Gross Domestic Product (GDP) is also analyzed. It is found that the 2 and 3 m scenarios lead to a much higher risk compared to the 1 m scenario. The combined hazard-vulnerability data shows that estuarine areas on the west and east of the Karasu region have a medium vulnerability. These results provide primary assessment data for the Karasu region for the decision-makers to enhance land use policies and coastal management plans.Article Citation - WoS: 5Citation - Scopus: 5An Unrestricted Arnold's Cat Map Transformation(Springer, 2024) Turan, Mehmet; Goekcay, Erhan; Tora, HakanThe Arnold's Cat Map (ACM) is one of the chaotic transformations, which is utilized by numerous scrambling and encryption algorithms in Information Security. Traditionally, the ACM is used in image scrambling whereby repeated application of the ACM matrix, any image can be scrambled. The transformation obtained by the ACM matrix is periodic; therefore, the original image can be reconstructed using the scrambled image whenever the elements of the matrix, hence the key, is known. The transformation matrices in all the chaotic maps employing ACM has limitations on the choice of the free parameters which generally require the area-preserving property of the matrix used in transformation, that is, the determinant of the transformation matrix to be +/- 1.\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\pm 1.$$\end{document} This reduces the number of possible set of keys which leads to discovering the ACM matrix in encryption algorithms using the brute-force method. Additionally, the period obtained is small which also causes the faster discovery of the original image by repeated application of the matrix. These two parameters are important in a brute-force attack to find out the original image from a scrambled one. The objective of the present study is to increase the key space of the ACM matrix, hence increase the security of the scrambling process and make a brute-force attack more difficult. It is proved mathematically that area-preserving property of the traditional matrix is not required for the matrix to be used in scrambling process. Removing the restriction enlarges the maximum possible key space and, in many cases, increases the period as well. Additionally, it is supplied experimentally that, in scrambling images, the new ACM matrix is equivalent or better compared to the traditional one with longer periods. Consequently, the encryption techniques with ACM become more robust compared to the traditional ones. The new ACM matrix is compatible with all algorithms that utilized the original matrix. In this novel contribution, we proved that the traditional enforcement of the determinant of the ACM matrix to be one is redundant and can be removed.Article Yalıtık Sözcüklü Bir Türkçe Konuşma Tanıma Sisteminin Yapay Veri Artırımı ile Tasarımı ve Gerçekleştirimi(2020) Uslu, İbrahim Baran; Tora, Hakan; Sümer, Emre; Türker, MustafaBu çalışmada toplamda doksan iki adet sesli komuttan oluşan bir yalıtık sözcüklü Türkçe konuşmatanıma sistemi tasarlanmış ve gerçekleştirilmiştir. Sistem, destek vektör makinesi (SVM) tabanlı olup,eğitimde kullanılan veri kümesi kaydedilen konuşmaların yapay olarak çeşitlendirilip artırılmasıyla eldeedilmiştir. Farklı yapay veri oranlarının tanıma başarımı üzerindeki etkisi incelenmiştir. Akustik öznitelikolarak, mel frekansı kepstral katsayıları (MFCC) kullanılmıştır. Ayrıca, ses aktivitesi tespitinin ve MFCCkatsayılarının tanıma başarımına etkileri de irdelenmiştir. Sonuçta doksan iki yalıtık komut için ortalama%92.6’lık doğrulukla çalışan bir konuşma tanıma sistemi geliştirilmiştirArticle Implementation of Turkish Text-To Synthesis on a Voice Synthesizer Card With Prosodic Features(2017) Tora, Hakan; Uslu, İbrahim Baran; Karamehmet, TimurThis study is on hardware implementation of the Turkish text-to-speech (TTS) synthesis with a voice synthesizer card. Here, a fully functional TTS system, capable of synthesizing every Turkish text, including abbreviations, numbers, etc. is designed and implemented. The system is additionally enriched by applying some prosodic attributes for more intelligible and natural speech production. A set of rules required for proper pronunciation and stress patterns are precisely defined in a lexicon utilized for synthesizing Turkish speech. Performance of the developed system is assessed by the Mean Opinion Score (MOS) test. An average score of 3.29 out of 5 is achieved.It indicates that the proposed synthesizer can be successfully integrated to many practical Turkish TTS applications.Article Citation - Scopus: 1Two-Stage Feature Generator for Handwritten Digit Classification(Mdpi, 2023) Pirim, M. Altinay Gunler; Tora, Hakan; Oztoprak, Kasim; Butun, IsmailIn this paper, a novel feature generator framework is proposed for handwritten digit classification. The proposed framework includes a two-stage cascaded feature generator. The first stage is based on principal component analysis (PCA), which generates projected data on principal components as features. The second one is constructed by a partially trained neural network (PTNN), which uses projected data as inputs and generates hidden layer outputs as features. The features obtained from the PCA and PTNN-based feature generator are tested on the MNIST and USPS datasets designed for handwritten digit sets. Minimum distance classifier (MDC) and support vector machine (SVM) methods are exploited as classifiers for the obtained features in association with this framework. The performance evaluation results show that the proposed framework outperforms the state-of-the-art techniques and achieves accuracies of 99.9815% and 99.9863% on the MNIST and USPS datasets, respectively. The results also show that the proposed framework achieves almost perfect accuracies, even with significantly small training data sizes.
