Browsing by Author "Karasakal, O."

Now showing 1 - 5 of 5

Heterogeneous Sensor Data Fusion for Target Classification Using Adaptive Distance Function
(Springer Science and Business Media Deutschland GmbH, 2021) Karasakal, E.; Karasakal, O.; Atıcı, B.
Automatic Target Recognition (ATR) systems are used as decision support systems to classify the potential targets in military applications. These systems are composed of four phases, which are selection of sensors, preprocessing of radar data, feature extraction and selection, and processing of features to classify potential targets. In this study, the classification phase of an ATR system having heterogeneous sensors is considered. We propose novel multiple criteria classification methods based on the modified Dempster–Shafer theory. Ensemble of classifiers is used as the first step probabilistic classification algorithm. Artificial neural network and support vector machine are employed in the ensemble. Each non-imaginary dataset coming from heterogeneous sensors is classified by both classifiers in the ensemble, and the classification result that has a higher accuracy ratio is chosen for each of the sensors. The proposed data fusion algorithms are used to combine the sensors’ results to reach the final class of the target. We present extensive computational results that show the merits of the proposed algorithms. © 2021, Springer Nature Switzerland AG.
Citation - Scopus: 2
A Multiple Criteria Ranking Method Based on Outranking Relations: an Extension for Prospect Theory
(Springer Science and Business Media Deutschland GmbH, 2022) Karasakal, O.; Şentürk, H.; Karasakal, E.
In this study, Prospect Theory is integrated into a well-known multiple criteria ranking method, PROMETHEE. PROMETHEE considers the outranking relations among alternatives based on the preference functions. Prospect Theory evaluates the alternatives with a difference function based on gains and losses. The preference functions of PROMETHEE are modified to capture the choice behavior of the decision maker. The proposed method is a generalization of PROMETHEE that can handle the higher loss impact case as well as the usual equal loss and gain impact. The proposed method is compared with PROMETHEE, PT-PROMETHEE that is an extension of PROMETHEE with reference alternative, and the weighted sum method using an exemplary data set and Times Higher Education (THE) World University Ranking 2019 and 2020 data. The results show that rankings of alternatives change significantly when the impact of losses is larger than gains. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
Optimization of Fleet Search on Network of Regions
(Elsevier Ltd, 2026) Yakıcı, E.; Erişkin, L.; Karatas, M.; Karasakal, O.
Unmanned Aerial Vehicles (UAVs) are widely used in modern military missions, primarily for surveillance, reconnaissance, search and detection, and air-to-ground strikes. The widespread use of UAVs in recent conflicts, such as the Russia–Ukraine war, once again highlighted their growing strategic importance. The complexity of military missions carried out by UAVs, coupled with the need for autonomous and coordinated fleet operations, requires analytical approaches to optimize deployment planning and improve operational efficiency. In this study, we address a UAV deployment planning problem for search and detection missions, in which a homogeneous fleet of UAVs is tasked with searching for hostile assets across a network of disjoint regions. Each region is characterized by an a priori probability of target presence, a search difficulty factor which affects the probability of detection, and known inter-region distances. For this purpose, we first develop a mixed-integer nonlinear programming formulation which determines the base locations of UAVs, allocates the limited search time across regions, and sequences the visits to maximize the total time-weighted detection probability mass to achieve the highest probability as much and as early as possible during the operation. Next, we apply a tangent line approximation technique to reformulate the model as a mixed-integer linear programming problem, which we solve using commercial off-the-shelf solvers. We then propose a hybrid heuristic approach based on the ant colony optimization method to generate high-quality solutions. Our computational experiments reveal that the proposed heuristic significantly reduces solution time while maintaining superior performance compared to the linear approximation model. © 2026 The Authors
Citation - Scopus: 8
A Partial Coverage Hierarchical Location Allocation Model for Health Services
(Inderscience Publishers, 2023) Karasakal, O.; Karasakal, E.; Töreyen, Ö.
We consider a hierarchical maximal covering location problem (HMCLP) to locate health centres and hospitals so that the maximum demand is covered by two levels of services in a successively inclusive hierarchy. We extend the HMCLP by introducing the partial coverage and a new definition of the referral. The proposed model may enable an informed decision on the healthcare system when dynamic adaptation is required, such as a COVID-19 pandemic. We define the referral as coverage of health centres by hospitals. A hospital may also cover demand through referral. The proposed model is solved optimally for small problems. For large problems, we propose a customised genetic algorithm. Computational study shows that the GA performs well, and the partial coverage substantially affects the optimal solutions. © 2023 Inderscience Enterprises Ltd.
Solution Approaches for the Dynamic Naval Air Defense Planning Problem
(Institute of Electrical and Electronics Engineers Inc., 2026) Arslan, C.; Karasakal, O.; Kirca, Ö.
The naval air defense planning (NADP) problem entails the defense of a naval fleet against aerial threats. This complex and dynamic problem requires real-time decision-making and adaptation to evolving warfare environment. While our previous work addressed the static NADP problem by proposing a mathematical model and heuristic solutions for sensor allocation, engagement scheduling, and ship routing, this study extends to the dynamic NADP problem. Unlike the static version, which assumes complete knowledge of future threats, the dynamic NADP problem requires continuous updates and real-time adjustments to decisions as new threats emerge and situational parameters change. We present modifications in the mathematical formulation, which is based on a mixed-integer nonlinear programming (MINLP) model, alongside a comprehensive simulation structure. We employ heuristic solution approaches that utilize a combination of a genetic algorithm, construction of an engagement graph to solve the shortest path problem, and dynamic programming (DP) techniques. Computational experiments are conducted to evaluate the effectiveness of these methods in addressing the dynamic NADP problem. The study also explores machine learning models for threat prioritization, offering innovative solutions to the challenges posed by dynamic naval air defense scenarios. © 2013 IEEE.