Yazar "Güneser, M.T." seçeneğine göre listele
Listeleniyor 1 - 9 / 9
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe Accuracy for Diagnosis of Heart Disease Using Sim Supervisor Algorithm(American Institute of Physics Inc., 2023) Abdlkareem, M.G.; Alkhafaji, M.A.; Güneser, M.T.In this paper, a model for heart disease diagnosis using semi-supervised learning methods has been proposed. The proposed method, uses Semi-Supervised Support Vector Machine (S3VM) for heart disease diagnosis. Also, Expectation Maximization (EM) method is used for handling missing values in patient's observed data; which can improve diagnosis accuracy greatly. Thus, our proposed method for diagnosing heart disease, consists of three steps: "preprocessing by EM", "extracting features by PCA" and "disease detection using S3VM". In the evaluation of the proposed method, a real dataset containing medical information of 270 patients was used. Each data record had 13 attributes, which were reduced to 10 using the PCA algorithm. The results of the proposed model has been compared with other classification algorithms. Experimental results shows that using the proposed system, we could diagnose heart disease with an average accuracy of 83%. The results of this study show that the proposed method has better performance in terms of accuracy as well as in terms of specificity and sensitivity criteria and can be a useful tool for early heart disease diagnosis. © 2023 American Institute of Physics Inc.. All rights reserved.Öğe Design and Simulation for Triple-Band Metasurface Slot Antenna(American Institute of Physics Inc., 2023) Gatea, Q.M.; Alkhafaji, M.A.; Güneser, M.T.The proposed antenna works well in three resonant frequencies for various applications such as Wi-Fi and WiMAX, with good rejection of other frequencies to prevent interference between these applications' work and other applications operating in the same bandwidth. There are three bands: 2.7 GHz, 7.27 GHz, and 8.67 GHz, with respective gain values of 7.19 dBi, 8.96 dBi, and 1.97 dBi. The cells are created by connecting two opposed letters C of varied sizes so that the smallest gets contained within the biggest. The standard antenna was integrated with the metasurface layer using Fabry-Pérot resonating cavity theory, and there is an air gap between them. The simulation was carried out using the CST program. © 2023 American Institute of Physics Inc.. All rights reserved.Öğe Design of dual-band frequency compact microstrip antenna for UMTS and WLAN applications(Institute of Electrical and Electronics Engineers Inc., 2017) Seker, C.; Güneser, M.T.In this study, we designed multi and wide band frequency monopole antenna, consisted of FR4 as a substrate with thickness of 1.6mm. The radiating element is printed on a truncated metallic ground plane. Proposed antenna operates in UMTS and WLAN wireless communications applications at 1.9 GHz and 4.9 GHz respectively. The antenna was applied on FR4 plate with the dimensions of 42 × 42 × 1.6 mm3. This monopole antenna was designed using computer simulation technology 2015 (ANSYS HFSS: High Frequency Electromagnetic Field Simulation). The performance was examined based on return loss, radiation pattern, gain, efficiency and VSWR. © 2017 IEEE.Öğe Designing an irrigation system using photovoltaic energy by considering crop type in Fergana Valley(EDP Sciences, 2021) Kuzey, S.; Seker, C.; Elweddad, M.; Güneser, M.T.Today, the importance of energy cost and efficiency is gradually increase. The decrease in drinking water and agricultural water resources, increases the interest in drip irrigation systems in agricultural irrigation. Environmentally friendly photovoltaic drip irrigation systems (PVDIS) are the appropriate solution in regions where there is no electricity distribution network, where it is far away, or where power cuts are frequently. This study is carried out in the Fergana Valley of Uzbekistan. Regional climate data obtained from Climwat 2.0 software are processed in Cropwat 8.0 software. Crops that are both the source of livelihood of the people of the region and that can be used in this study have been determined. Annual and daily water needs are analyzed so that these crops are irrigated every seven days. A system is designed by taking the data of the crop with the highest water requirement as a reference. The drip irrigation system is set up in a PVsyst 7.1.7 simulation environment to pump 114.24 m3 of water daily from a 5-meter-deep river with a 1.8 kW photovoltaic system. The efficiency of the system is 58.7% and the efficiency of the pump is 34.5%. Crop water need is met at the rate of 98.87%. It is predicted that the designed and analyzed PVDIS will provide efficiency in energy and water resources. © The Authors.Öğe Intelligent Energy Management and Prediction of Micro Grid Operation Based On Machine Learning Algorithms and Genetic Algorithm(Gazi Universitesi, 2022) Elweddad, M.; Güneser, M.T.Micro grid energy management has become critically important due to inefficient power use in the residential sector. High energy consumption necessitates developing a strategy to manage the power flow efficiently. For this purpose, this work has been divided into two phases: The first is the "ON/OFF" operation, which has been executed using a genetic algorithm for the hybrid system, including diesel generator, solar photovoltaic (PV), wind turbine, and battery. Then, in the second phase, the output results were used as input in three algorithms to predict load and supply dispatch one month ahead. This study has two objectives; the first is to decide which energy source should meet the load one month ahead. The second is to compare the outcomes of machine-learning techniques, namely Random Forest (RF), Decision Tree (DT), and K-Nearest Neighbours (KNN), to determine the one that performs the best. The results indicated that the DT technique has the best performance in the application of classification with an accuracy of 100%. The findings also show that the RF approach gives acceptable results with an accuracy of up to 98%, and the KNN algorithm was poor in terms of accuracy with a value of 28%. © 2022, International Journal of Renewable Energy Research. All Rights Reserved.Öğe Multi-objective Optimization of Combined Economic Emission Dispatch Problem in Solar PV Energy Using a Hybrid Bat-Crow Search Algorithm(Gazi Universitesi, 2021) Elbaz, A.; Güneser, M.T.This paper deals with the multi-objective fuel cost optimization of a conventional power plant (CPP) and emission minimization in CPPs and solar PV power plants (SPVPPs) using a hybrid bat-crow search algorithm. To resolve this complicated, non-convex, and excessively nonlinear problem, a variety of meta-heuristic optimization algorithms are developed and effectively employed. To handle evolutionary multi-objective algorithms’ inadequacies, such as early convergences, slowly meeting the Pareto-optimal front, and narrow trapping, applying a combination of different algorithms is unusual. This paper offers a hybrid evolutionary multi-objective optimization process based on combining the crow search optimization with the bat algorithm for dealing with the combined economic emission dispatch problem for SPVPPs. A hybrid technique combined with the proposed constriction handling method can balance exploitation and exploration tasks. Different IEEE standard bus systems were tested with the proposed hybrid method using the quadratic cost function and monitoring the transmission losses. The results of the proposed algorithm have also been compared with those of the bat, PSO, and crow search algorithms. The proposed method can be said to be effective considering the simulation results. © 2021, International Journal of Renewable Energy Research. All Rigths Reserved.Öğe Optimal sizing of a renewable energy hybrid system in Libya using integrated crow and particle swarm algorithms(ASTES Publishers, 2021) Elbaz, A.; Güneser, M.T.Sizing optimization should be used to design an efficient, sustainable, and feasible hybrid system. In this paper, a hybrid power plant consisting of an off-grid photovoltaic and wind energy system was planned to supply the demand of residential houses in Libya. To minimize installation and operational costs by sizing each part of the hybrid system, the crow search technique was applied. We optimized the number of photovoltaic modules, wind turbine power, and battery capacity and then we compared the performance of the crow algorithm with the particle swarm optimization algorithm for hybrid system design. The results of the crow algorithm suggest better efficiency for sizing lower-cost hybrid power plants consisting of photovoltaic and wind systems. © 2021 ASTES Publishers. All rights reserved.Öğe Optimization of Compact Microstrip Monopole Antenna Parameters with NS-RFO and Artificial Intelligence in Antenna Design(Institute of Electrical and Electronics Engineers Inc., 2024) Pak, S.; Güneser, M.T.; Seker, C.Developments in artificial intelligence directly affect various fields of science. This is especially important in the solution of higher-order models and systems that do not have an exact equation. Due to the difficulties in modeling electromagnetic systems, artificial intelligence-based studies have a special importance in this field. In this study, the multidimensional optimization of a compact microstrip monopole antenna that can be used in next generation communication applications is studied with a new artificial intelligence algorithm, the red fox algorithm. Thus, a compact microstrip antenna with broadband (8.75 GHz - 11.25 GHz) radiation at 10 GHz resonant frequency is designed for X-Band applications. © 2024 IEEE.Öğe A Reliable Transmission and Extraction of Textual Information Using Keyless Encryption, Steganography, and Deep Algorithm with Cuckoo Optimization(Springer Science and Business Media Deutschland GmbH, 2023) Pandey, B.K.; Pandey, D.; Alkhafaji, M.A.; Güneser, M.T.; Seker, C.The entire work postulates a fusion of an innovative keyless image encoding approach based on a chaotic map and steganography. Nearly every single picture element has been encrypted by rearranging pixel values that are then assessed by such an adapted cat map as well as steganography has been used in the suggested methodology to transmit keyless encoded textual information utilizing a cover image, with encoded textual image information inserted into cover images. But on the other hand, retrieving textual images embedded in the receiver has indeed been regarded as the most challenging process. Furthermore, a sender will indeed transfer reasoning rather than a key to the recipient, ignoring the fact that acquiring engrained textual information hidden inside the cover image to enhance efficiency would have been challenging. Steganography was easily accomplished by placing data bits of secret textual image information into the cover image’s least significant bit of picture elements. The image quality, on the other hand, suffers greatly from the inclusion of an encrypted message. Images could indeed cause some disturbances from time to time. As a consequence, non-smooth areas of the image have been regarded as smooth. Therefore, the weighted Naive Bayes algorithm (NBA) method is being used in the illustration to retrieve the appropriate textual image information from complicated deteriorated images. Normally, images comprise a small amount of noise, so the introduction of the guided filter (GF) during the initial preprocessing phase is required. A very important feature in the textual image information extraction procedure was obtained utilizing a variety of techniques, including Gabor transform (GT), weighted Naive Bayes algorithms (WNBA), and a high-quality learning procedure for standard procedure. Eventually, textual content identification and recognition are performed using a combination of DNN and cuckoo algorithms. Again, for the proposed system, the set of data IIIT5K is being used, as well as high performance has been gained with parameters such as mean square error and peak signal-to-noise ratio. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
