Scopus İndeksli Yayınlar Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12573/395
Browse
6 results
Search Results
Article Citation - WoS: 55Citation - Scopus: 65Neuro-Fuzzy Model Predictive Energy Management for Grid Connected Microgrids(MDPI, 2020-05-28) Ulutas, Ahsen; Altas, Ismail Hakki; Onen, Ahmet; Ustun, Taha SelimWith constant population growth and the rise in technology use, the demand for electrical energy has increased significantly. Increasing fossil-fuel-based electricity generation has serious impacts on environment. As a result, interest in renewable resources has risen, as they are environmentally friendly and may prove to be economical in the long run. However, the intermittent character of renewable energy sources is a major disadvantage. It is important to integrate them with the rest of the grid so that their benefits can be reaped while their negative impacts can be mitigated. In this article, an energy management algorithm is recommended for a grid-connected microgrid consisting of loads, a photovoltaic (PV) system and a battery for efficient use of energy. A model predictive control-inspired approach for energy management is developed using the PV power and consumption estimation obtained from daylight solar irradiation and temperature estimation of the same area. An energy management algorithm, which is based on a neuro-fuzzy inference system, is designed by determining the possible operating states of the system. The proposed system is compared with a rule-based control strategy. Results show that the developed control algorithm ensures that microgrid is supplied with reliable energy while the renewable energy use is maximized.Article Citation - WoS: 4Citation - Scopus: 7Network Anomaly Detection Using Deep Autoencoder and Parallel Artificial Bee Colony Algorithm-Trained Neural Network(PeerJ Inc, 2024-10-08) Hacilar, Hilal; Dedeturk, Bilge Kagan; Bakir-Gungor, Burcu; Gungor, Vehbi CagriCyberattacks are increasingly becoming more complex, which makes intrusion detection extremely difficult. Several intrusion detection approaches have been developed in the literature and utilized to tackle computer security intrusions. Implementing machine learning and deep learning models for network intrusion detection has been a topic of active research in cybersecurity. In this study, artificial neural networks (ANNs), a type of machine learning algorithm, are employed to determine optimal network weight sets during the training phase. Conventional training algorithms, such as back- propagation, may encounter challenges in optimization due to being entrapped within local minima during the iterative optimization process; global search strategies can be slow at locating global minima, and they may suffer from a low detection rate. In the ANN training, the Artificial Bee Colony (ABC) algorithm enables the avoidance of local minimum solutions by conducting a high-performance search in the solution space but it needs some modifications. To address these challenges, this work suggests a Deep Autoencoder (DAE)-based, vectorized, and parallelized ABC algorithm for training feed-forward artificial neural networks, which is tested on the UNSW-NB15 and NF-UNSW-NB15-v2 datasets. Our experimental results demonstrate that the proposed DAE-based parallel ABC-ANN outperforms existing metaheuristics, showing notable improvements in network intrusion detection. The experimental results reveal a notable improvement in network intrusion detection through this proposed approach, exhibiting an increase in detection rate (DR) by 0.76 to 0.81 and a reduction in false alarm rate (FAR) by 0.016 to 0.005 compared to the ANN-BP algorithm on the UNSWNB15 dataset. Furthermore, there is a reduction in FAR by 0.006 to 0.0003 compared to the ANN-BP algorithm on the NF-UNSW-NB15-v2 dataset. These findings underscore the effectiveness of our proposed approach in enhancing network security against network intrusions.Article Citation - WoS: 34Citation - Scopus: 37Green Building Envelope Designs in Different Climate and Seismic Zones: Multi-Objective ANN-Based Genetic Algorithm(Elsevier, 2022-10) Himmetoglu, Salih; Delice, Yilmaz; Aydogan, Emel Kizilkaya; Uzal, Burak; Kızılkaya Aydoğan, EmelIn recent years, the major component of green building designs adopted by governments in order to reduce CO2 emissions as well as energy consumption is the green building envelope. The green envelope has the most important share in terms of thermal energy consumption, environment, and indoor comfort criteria. Determining the most suitable building envelope combination in the building life cycle is an important problem for designers. This study presents a new multi-objective approach that determines the most suitable green envelope designs for the buildings in different climate and earthquake zones, taking into account CO2 emissions, heating/cooling energy consumption, and material cost in terms of life cycle cost analysis. To this end, EnergyPlus building performance simulation program, artificial neural network (ANN), and genetic algorithm are used together. After the heating and cooling energy consumption, CO2 emissions, and material cost values are obtained for a certain number of the envelope alternatives with the EnergyPlus, ANN models that learn the working mechanism of EnergyPlus are trained according to these values. An ANN-based genetic algorithm procedure is developed to search the whole envelope alternative space by using the trained ANN models with EnergyPlus. The proposed approach allows searching in a very short time the whole alternative space, which is almost impossible to scan with EnergyPlus by reducing the time spent and the number of alternatives required for the design and simulation processes of the green building envelope. The proposed approach is performed for a design-stage city hospital structure in Turkey. Window type, the internal/external plaster, wall, and insulation materials along with the thicknesses of these materials, which consist of 46 different variables, are determined as envelope attributes for four different climate and seismic zones. The green building envelope designs obtained with the proposed approach are entered into EnergyPlus and the consistency of the results is compared. ANN models with an average accuracy of over 97% are developed. Without the CO2 emission cost in the life cycle cost, the mean absolute percent error (MAPE) values for each region are 0.67%, 0.6%, 0.58%, and 1.78%, respectively. With the CO2 emission cost in life cycle cost, the MAPE values for each region are 0.96%, 0.88%, 0.86%, and 0.43%, respectively. According to the obtained results, there is a consistency of over 99% between EnergyPlus and the proposed approach.Article Citation - WoS: 4Citation - Scopus: 4Beneficiation of Low-Grade Iron Ore Using a Dry-Roll Magnetic Separator and Its Modeling via Artificial Neural Network(Springer, 2025-02-24) Fariss, Abdourahman Hassan Brahim; Ibrahim, Ahmedaljaali Ibrahim Idrees; Ozdemir, Ali Can; Top, Soner; Kursunoglu, Sait; Altiner, MahmutThe beneficiation of low-grade iron ore (39.5% Fe-(T) grade) using a dry-roll magnetic separator was investigated. The ore was characterized using Mineral Liberation Analysis (MLA). It was determined that the ore was composed of iron oxide (goethite and hematite), quartz, chlorite, muscovite, plagioclase, and other minerals. The effect of particle size (PS, - 1 + 0.500 mm, - 0.500 + 0.300 mm, and - 0.300 + 0.125 mm), splitter position (SP, 43 degrees and 58 degrees), cleaning stage (CS, 1 and 2), conveyor speed (CoS, 3, 5, and 7 Hz), magnetic field strength (MFS, 0.2 T and 0.4 T) on the recovery of the magnetic product was investigated. Experimental results show that the product (- 1 + 0.500 mm) with the Fe-(T) grade of 67.67% can be obtained, but its recovery was not at an acceptable value (< 30%). Furthermore, the Fe-(T) grade of the product (- 0.500 + 0.300 and - 0.300 + 0.125 mm) could not reach satisfactory levels<bold>.</bold> The artificial neural network (ANN) method was conducted on the results of experimental studies. Three different training algorithms were employed for modeling, and their performance was assessed using statistical evaluation criteria. The results demonstrate that Bayesian Regularization (BR) algorithm exhibited better performance compared to others in predicting both Fe(T) grade and recovery rate during the testing phase. These findings support the notion that ANN algorithms can be a powerful modeling and prediction tool in the field of mineral processing.Article Citation - WoS: 3Citation - Scopus: 3Accelerated Artificial Bee Colony Optimization for Cost-Sensitive Neural Networks in Multi-Class Problems(Wiley, 2025-04-10) Hacilar, Hilal; Dedeturk, Bilge Kagan; Ozmen, Mihrimah; Celik, Mehlika Eraslan; Gungor, Vehbi CagriMetaheuristics are advanced problem-solving techniques that develop efficient algorithms to address complex challenges, while neural networks are algorithms inspired by the structure and function of the human brain. Combining these approaches enables the resolution of complex optimization problems that traditional methods struggle to solve. This study presents a novel approach integrating the ABC algorithm with ANNs for weight optimization. The method is further enhanced by vectorization and parallelization techniques on both CPU and GPU to improve computational efficiency. Additionally, this study introduces a cost-sensitive fitness function tailored for multi-class classification to optimize results by considering relationships between target class levels. It validates these advancements in two critical applications: network intrusion detection and earthquake damage estimation. Notably, this study makes a significant contribution to earthquake damage assessment by leveraging machine learning algorithms and metaheuristics to enhance predictive models and decision-making in disaster response. By addressing the dynamic nature of earthquake damage, this research fills a critical gap in existing models and broadens the understanding of how machine learning and metaheuristics can improve disaster response strategies. In both domains, the ABC-ANN implementation yields promising results, particularly in earthquake damage estimation, where the cost-sensitive approach demonstrates satisfactory outcomes in macro-F1 and accuracy. The best results for macro-F1, weighted-F1, and overall accuracy provides best results with the UNSW-NB15 and earthquake datasets, showing values of 64%, 72%, 68%, and 60%, 80%, and 79%, respectively. Comparative performance evaluations reveal that the proposed parallel ABC-ANN model, incorporating the novel cost-sensitive fitness function and enhanced by vectorization and parallelization techniques, significantly reduces training time and outperforms state-of-the-art methods in terms of macro-F1 and accuracy in both network intrusion detection and earthquake damage estimation.Article Citation - WoS: 7Citation - Scopus: 7A Combined Application of Two Soft Computing Algorithms for Weathering Degree Quantification of Andesitic Rocks(Elsevier, 2022-12) Koca, Tumay Kadakci; Koken, Ekin; Kadakci Koca, TümayUnderstanding the variations in physical and mechanical behavior of rock materials due to progressive weathering is vital to carry on time and cost-effective engineering projects. Up to date, soft computing algorithms have been established to quantify the weathering degree (WD) of various rocks due to better prediction performance and problem-solving capability. However, the complexity of the weathering process does not allow the use of a single weathering quantification model for a wide range of rock types. Therefore, this study aims to provide a practical, quantitative, and effective framework for predicting the WD of andesitic rocks. To fulfill the aims of this study, a wide range of cases were collected from the previous studies to establish a predictive model based on dry unit weight (gamma d), effective porosity (ne), and uniaxial compressive strength (UCS). Consequently, a combined application of fuzzy inference system (FIS) and artificial neural network (ANN) was introduced to assess the WD of the investigated andesitic rocks. The WD ratings were presented as four different weathering classes (from fresh (W0) to highly weathered (W3)). Since most soft computing algorithms are black-box models that cannot be efficiently utilized in any other study, an explicit neural network formulation was firstly developed for WD prediction in this study. As a result, the proposed formulation will provide a practical and straightforward assessment of WD for andesitic rocks. However, to improve the reliability and consistency of the proposed model, different datasets should be used in the explicit neural network formulation proposed.