Runge Kutta (RUN) is an up-to-date and well-founded metaheuristic algorithm. The RUN algorithm aims to find the global best in solving problems by going beyond the traps of metaphors. For this purpose, enhanced solution quality mechanism is used to avoid local optimum solutions and increase the convergence speed. Although the RUN algorithm offers promising solutions, it is seen that this algorithm has shortcomings, especially in solving high dimensional multimodal problems. In this study, the solution candidates that guide the search process in the RUN algorithm are developed using the Fitness-Distance Balance (FDB) method. Thus, using the FDB-based RUN algorithm, the global optimum value of many optimization problems will be obtained in the future. CEC 2020 which has current benchmark problems was used to test the performance of the developed FDB-RUN algorithm. 10 different unconstrained benchmark problems taken from CEC 2020 were designed by arranging them in 30/50/100 dimensions. Experimental studies were carried out using the designed benchmark problems and analyzed with Friedman and Wilcoxon statistical test methods. According to the results of the analysis, it was seen that the FDB-RUN variations showed a superior performance compared to the base algorithm (RUN) in all experimental studies. In particular, it has been shown to provide more effective results for the continuous optimization of high-dimensional problems.
31 December 2021 in Düzce Üniversitesi Bilim ve Teknoloji Dergisi
In this study, the performance of Slime-Mould-Algorithm (SMA), a current Meta-Heuristic Search algorithm, is improved. In order to model the search process lifecycle process more effectively in the SMA algorithm, the solution candidates guiding the search process were determined using the fitness-distance balance (FDB) method. Although the performance of the SMA algorithm is accepted, it is seen that the performance of the FDB-SMA algorithm developed thanks to the applied FDB method is much better. CEC 2020, which has current benchmark problems, was used to test the performance of the developed FDB-SMA algorithm. 10 different unconstrained comparison problems taken from CEC 2020 are designed by arranging them in 30-50-100 dimensions. Experimental studies were carried out using the designed comparison problems and analyzed with Friedman and Wilcoxon statistical test methods. According to the results of the analysis, it has been seen that the FDB-SMA variations outperform the basic algorithm (SMA) in all experimental studies.
30 December 2022 in Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji
Lung cancer is a very deadly disease. However, early diagnosis and detection is an essential factor in overcoming this deadly disease. Tumors formed in this disease's initial stage are divided into benign and malignant. These can be visualized using a computed tomography (CT) scan. Thanks to machine learning and deep learning, cancer stages can be detected using these images. In our study, the best and most promising results in the literature were obtained by using a hybrid learning architecture. The data mining techniques we use in obtaining these results also play a significant role. The best accuracy result we obtained belongs to the CNN+GBC hybrid algorithm, which we recommend with 99.71%.
Buried mines pose great dangers to humans and animals around the world, which means thousands of people die each year from buried mines. Detecting and destroying these mines without harming people is an important issue. Today, these landmines are detected using different methods such as Ground Effect Radar, Electromagnetic induction, Infrared and Nuclear Quadrupole Resonance and active sensors are generally used in most of these methods. Although active sensor-based landmine detectors are often used for performance reasons, they can cause unintentional landmine explosions because they operate with transmitted and reflected signals. On the other hand, there is no such obstacle that can perform better in passive sensor-based landmine detectors depending on the design criteria. Therefore, in this study, a prototype design including passive sensor with magnetic anomaly method has been developed and shown. For the performance analysis of this detector, real landmines are used and the designed system is tested with different distance values in different soil types. The results show that the prototype produced successfully detects different types of landmines, is assertive in its lightness and only 1750 grams with its battery, providing sensitivity as well as advantages such as ease of use and low cost. It also shows the feature of being the first handheld landmine detector based on magnetic anomaly.
This study presents a unified semantic segmentation framework for UAV-based multispectral crop stress mapping, focusing on the integration of water stress and rust disease conditions within a common label space. Unlike conventional approaches that address individual stress factors independently, the proposed framework harmonizes heterogeneous datasets with different annotation schemes into a single multi-class segmentation problem. To achieve this, UAV multispectral orthomosaics are processed using a patch-based strategy and a multi-head UNet++ architecture incorporating segmentation, edge-aware, and Signed Distance Transform (SDT) branches. In addition, a physics-informed output-space refinement module based on fractional partial differential equations (FPDE) is introduced to enhance spatial coherence and boundary preservation in the predicted maps. Experimental results demonstrate the effectiveness of the proposed framework within the evaluated dataset setting, particularly in terms of boundary delineation, spatial consistency, and minority-class detection. The study highlights the feasibility of integrating heterogeneous stress conditions into a unified segmentation framework and provides a foundation for future research on scalable multi-source agricultural monitoring systems.