Optimization of Charge/Discharge Coordination to Satisfy Network Requirements Using Heuristic Algorithms in Vehicle-to-Grid Concept
| Autor: | Ahmet Burak Doğan, Mustafa Alçi, Serkan Bahçeci, Ferhat Daldaban |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
lcsh:Computer engineering. Computer hardware
General Computer Science Computer science Heuristic (computer science) 020209 energy 020208 electrical & electronic engineering lcsh:TK7885-7895 02 engineering and technology Grid Thresholding Image (mathematics) genetic algorithms Smart grid heuristic algorithms 0202 electrical engineering electronic engineering information engineering In vehicle smart grids lcsh:Electrical engineering. Electronics. Nuclear engineering Electrical and Electronic Engineering Tuberculosis Disease Charge discharge Algorithm optimization lcsh:TK1-9971 electric vehicles |
| Zdroj: | Advances in Electrical and Computer Engineering, Vol 18, Iss 1, Pp 121-130 (2018) |
| ISSN: | 1844-7600 1582-7445 |
| Popis: | Image thresholding is the most crucial step in microscopic image analysis to distinguish bacilli objects causing of tuberculosis disease. Therefore, several bi-level thresholding algorithms are widely used to increase the bacilli segmentation accuracy. However, bi-level microscopic image thresholding problem has not been solved using optimization algorithms. This paper introduces a novel approach for the segmentation problem using heuristic algorithms and presents visual and quantitative comparisons of heuristic and state-of-art thresholding algorithms. In this study, well-known heuristic algorithms such as Firefly Algorithm, Particle Swarm Optimization, Cuckoo Search, Flower Pollination are used to solve bi-level microscopic image thresholding problem, and the results are compared with the state-of-art thresholding algorithms such as K-Means, Fuzzy C-Means, Fast Marching. Kapur's entropy is chosen as the entropy measure to be maximized. Experiments are performed to make comparisons in terms of evaluation metrics and execution time. The quantitative results are calculated based on ground truth segmentation. According to the visual results, heuristic algorithms have better performance and the quantitative results are in accord with the visual results. Furthermore, experimental time comparisons show the superiority and effectiveness of the heuristic algorithms over traditional thresholding algorithms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|