7 results
Search Results
Now showing 1 - 7 of 7
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.magdi; Buaisha, 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 Implementation of Turkish Text-To Synthesis on a Voice Synthesizer Card With Prosodic Features(2017) Tora, Hakan; Uslu, İbrahim Baran; Karamehmet, Timur; Uslu, BaranThis 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 A Wavelet-Based Feature Set for Recognizing Pulse Repetition Interval Modulation Patterns(2016) Gençol, Kenan; At, Nuray; Kara, AlıThis paper presents a new feature set for the problem of recognizing pulse repetition interval (PRI) modulation patterns. The recognition is based upon the features extracted from the multiresolution decomposition of different types of PRI modulated sequences. Special emphasis is placed on the recognition of jittered and stagger type PRI sequences due to the fact that these types of PRI sequences appear predominantly in modern electronic warfare environments for some specific mission requirements and recognition of them is heavily based on histogram features. We test our method with a broad range of PRI modulation parameters. Simulation results show that the proposed feature set is highly robust and separates jittered, stagger, and other modulation patterns very well. Especially for the stagger type of PRI sequences, wavelet-based features outperform conventional histogram-based features. Advantages of the proposed feature set along with its robustness criteria are analyzed in detail.Article A Practical Distributed Lightweight Multi-Hop Time Synchronization Algorithm for Linear Wireless Sensor Networks Implemented on a Pic Based System With Realistic Experimental Analysis(Sakarya University, 2020) Erpay, A.; Al Imran, M.A.; Kara, A.; Imran, Md Abdullah AlTime synchronization is fundamental in the distributed networked systems, especially in Wireless Sensor Networks where a global time is essential to make sense of the events like collection of data and scheduled sleep/wake-up of nodes. There exists numerous time synchronization algorithms and techniques in the literature. Nonetheless, these proposed methods lack realistic experimentation of the synchronization process which is vital from the realization point of view. This study aims to bridge that gap by presenting a distributed lightweight time synchronization protocol implemented on an inexpensive PIC platform. Furthermore, PIC-based systems hadn’t been investigated before and gives an idea of the simplicity of the algorithm. Experimental analysis was done to see the performance of the protocol. The core motivation of the experiments was to the study the impact of the environment (e.g. indoor, outdoors, temperature variations and interference) on the synchronization. Our findings show that temperature indeed impedes the synchronization accuracy. © 2020, Sakarya University. All rights reserved.Article Recurrent Neural Networks for Spam E-Mail Classification on an Agglutinative Language(2020) Işık, Şahin; Kurt, Zuhal; Anagun, Yildiray; Özkan, KemalIn this study, we have provided an alternative solution to spam and legitimate email classification problem. The different deep learning architectures are applied on two feature selection methods, including the Mutual Information (MI) and Weighted Mutual Information (WMI). Firstly, feature selection methods including WMI and MI are applied to reduce number of selected terms. Secondly, the feature vectors are constructed with concept of the bag-of-words (BoW) model. Finally, the performance of system is analyzed with using Artificial Neural Network (ANN), Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (BILSTM) models. After experimental simulations, we have observed that there is a competition between detection results of using WMI and MI when commented with accuracy rates for the agglutinative language, namely Turkish. The experimental scores show that the LSTM and BILSTM give 100% accuracy scores when combined with MI or WMI, for spam and legitimate emails. However, for particular cross validation, the performance WMI is higher than MI features in terms e-mail grouping. It turns out that WMI and MI with deep learning architectures seem more robust to spam email detection when considering the high detection scores.Article Mobile Robot Navigation Using Reinforcement Learning in Unknown Environments(2019) Khan, M. U.In mobile robotics, navigation is considered as one of the most primary tasks, which becomes more challenging during local navigation when the environment is unknown. Therefore, the robot has to explore utilizing the sensory information. Reinforcement learning (RL), a biologically-inspired learning paradigm, has caught the attention of many as it has the capability to learn autonomously in an unknown environment. However, the randomized behavior of exploration, common in RL, increases computation time and cost, hence making it less appealing for real-world scenarios. This paper proposes an informed-biased softmax regression (iBSR) learning process that introduce a heuristic-based cost function to ensure faster convergence. Here, the action-selection is not considered as a random process, rather, is based on the maximum probability function calculated using softmax regression. Through experimental simulation scenarios for navigation, the strength of the proposed approach is tested and, for comparison and analysis purposes, the iBSR learning process is evaluated against two benchmark algorithms.Article Fitzhugh-Nagumo Modelleri için Çatallanma Denetimi(2018) Doruk, Reşat Özgür; Ihnısh, HamzaA theoretical bifurcation control strategy is presented for a single Fitzhugh-Nagumo (FN) type neuron. The bifurcation conditions are tracked for varying parametersof the individual FN neurons. A MATLAB package called as MATCONT is utilizedfor this purpose and all parameters of the neuron is analyzed one-by-one. Analysis byMATCONT revealed five Hopf (H) and one Limit-Point/Saddle Point (LP) bifurcation.The Hopf type of bifurcations are controlled by a washout filter supported by projectivecontrol theory. Washout filters are designed as first and second order. First order washoutfilter which is also physically applicable appeared to be more advantageous than thesecond order version. It appeared that, the LP case could not be stabilized by the aid of awashout filter. To solve this issue, a nonlinear controller is proposed. The only drawbackassociated with that is its inability to keep the original equilibrium point. Simulations arealso provided to validate the research done.
