Browsing by Author "Saracoglu, Ridvan"

Now showing 1 - 4 of 4

Classification of Pistachio Species Using Improved K-Nn Classifier
(Mattioli 1885, 2021) Ozkan, Ilker Ali; Koklu, Murat; Saracoglu, Ridvan
In order to keep the economic value of pistachio nuts which have an important place in the agricultural economy, the efficiency of post-harvest industrial processes is very important. To provide this efficiency, new methods and technologies are needed for the separation and classification of pistachios. Different pistachio species address different markets, which increases the need for the classification of pistachio species. In this study, it is aimed to develop a classification model different from traditional separation methods, based on image processing and artificial intelligence which are capable to provide the required classification. A computer vision system has been developed to distinguish two different species of pistachios with different characteristics that address different market types. 2148 sample image for these two kinds of pistachios were taken with a high-resolution camera. The image processing techniques, segmentation and feature extraction were applied on the obtained images of the pistachio samples. A pistachio dataset that has sixteen attributes was created. An advanced classifier based on k-NN method, which is a simple and successful classifier, and principal component analysis was designed on the obtained dataset. In this study; a multi-level system including feature extraction, dimension reduction and dimension weighting stages has been proposed. Experimental results showed that the proposed approach achieved a classification success of 94.18%. The presented high-performance classification model provides an important need for the separation of pistachio species and increases the economic value of species. In addition, the developed model is important in terms of its application to similar studies.
Developing an Adaptation Process for Real-Coded Genetic Algorithms
(Tech Science Press, 2020) Saracoglu, Ridvan; Kazankaya, Ahmet Fatih
The genetic algorithm (GA) is a metaheuristic method which simulates the life cycle and the survival of the fittest in the nature for solving optimization problems. This study aimed to develop enhanced operation by modifying the current GA. This development process includes an adaptation method that contains certain developments and adds a new process to the classic algorithm. Individuals of a population will be trialed to adapt to the current solution of the problem by taking them separately for each generation. With this adaptation method, it is more likely to get better results in a shorter time. Experimental results show that this new process accelerated the algorithm and a certain solution has been reached in fewer generations. In addition, better solutions were achieved, especially for a certain number of generations.
Meteorological Risk Assessment Based on Fuzzy Logic Systems for Maritime
(Galenos Publ House, 2022) Karaca, Ismail; Soner, Omer; Saracoglu, Ridvan
In recent years, numerous casualties have been associated with a lack of safe navigation of ships. Despite advanced navigation systems and the implementation of safety management systems onboard ships, maritime safety is still one of the major concerns for the shipping industry. This research proposes a proactive modeling approach that utilizes Fuzzy Logic and Adaptive Neuro-Fuzzy Inference Systems (ANFIS). The model primarily provides continuous meteorological risk assessment for ships to improve marine navigational safety. In the study, Wind Speed, Sea Conditions, Visibility, and Day/Night Ratio are converted to meteorological risk factors using meteorological risk assessment system. Supported by ANFIS, the meteorological risk assessment system has demonstrated that the database contains details of over 180 marine casualty information involving navigation and traffic accidents. The results emphasize that environmental factors, as well as the Day/Night Ratio, significantly influence ship navigational safety. Hence, a meteorological risk assessment system can enhance navigational safety and prevent loss of life in the shipping industry. As a result, a meteorological risk assessment framework has enormous potential for preventing accidents and improving the safety and sustainability of the shipping industry. In this regard, the proposed model is a one-of-a-kind framework that will be extremely useful for mitigating and preventing the effects of maritime accidents.
Study on the Estimation of Wind Energy Generation Using Artificial Neural Networks
(Parlar Scientific Publications (p S P), 2020) Saracoglu, Ridvan; Altin, Muhammed Cihat
Reducing environmental pollution and protecting the environment is the most urgent need of our world. Since non renewable resources used to meet the energy demand in the world produce large amounts of greenhouse gases, environmental problems occures. The supply of non renewable resources will be more expensive as their reserves will decrease and become depleted in the coining years. Renewable energy sources are clean, environmentally friendly and do not require any raw materials for production. Wind power generation systems, which stand out in the production of renewable energy sources, gain importance considering the current wind energy potential. Although electricity production from wind energy has increased, it is still not considered a safe energy source for the electricity grid. Since wind is a variable (unbalanced and unbalanced) source, it is difficult to predict. Wind production estimates are needed to ensure that the energy produced does not have grid adaptation problems and to make effective use of the energy produced. In this study, a model was created to estimate wind speed using artificial neural networks based methods and meteorological data. Wind energy potentials can be calculated regionally with these and similar models. Energy production that does not harm the environment can be realized better.