https://hdl.handle.net/20.500.12809/9548 2026-04-05T18:05:27Z 2026-04-05T18:05:27Z Yılmaz, Selim Şen, Sevil https://hdl.handle.net/20.500.12809/10752 2023-05-31T13:16:16Z 2023-01-01T00:00:00Z

Metaheuristic approaches for solving multiobjective optimization problems Yılmaz, Selim; Şen, Sevil Multiobjective optimization problems (MOOPs) require optimizing two or more, often conflicting objectives. The wide application of MOOPs has attracted the attention of researchers in academics and industry; therefore, a great deal of effort has been made to develop effective approaches toward solving MOOPs. In this chapter, we introduce a new metaheuristic approach called multiobjective electric fish optimization (MOEFO). The proposed approach is based on the Electric Fish Optimization (EFO) algorithm, a recently proposed metaheuristic algorithm for single-objective problems. Since EFO has achieved significant performance on solving different types of problems such as constrained and unconstrained problems, it is extended here for solving MOOPs efficiently. The proposed approach is compared with well-known meta-heuristics in the literature, and the experimental results show that MOEFO is among the best algorithms for solving MOOPs within a competitive running time. Moreover, it becomes very competitive for solving challenging Many-objective optimization problems (MaOPs) having four or more objectives.

2023-01-01T00:00:00Z Deveci, Ali Yılmaz, Selim Şen, Sevil https://hdl.handle.net/20.500.12809/10741 2023-05-30T12:34:55Z 2023-01-01T00:00:00Z

Evolving Lightweight Intrusion Detection Systems for RPL-Based Internet of Things Deveci, Ali; Yılmaz, Selim; Şen, Sevil With the integration of efficient computation and communication technologies into sensory devices, the Internet of Things (IoT) applications have increased tremendously in recent decades. While these applications provide numerous benefits to our daily lives, they also pose a great potential risk in terms of security. One of the reasons for this is that devices in IoT-based networks are highly resource constrained and interconnected over lossy links that can be exposed by attackers. The Routing Protocol for Low-Power and Lossy Network (RPL) is the standard routing protocol for such lossy networks. Despite the efficient routing built by RPL, this protocol is susceptible to insider attacks. Therefore, researchers have been working on developing effective intrusion detection systems for RPL-based IoT. However, most of these studies consume excessive resources (e.g., energy, memory, communication, etc.) and do not consider the constrained characteristics of the network. Hence, they might not be suitable for some devices/networks. Therefore, in this study, we aim to develop an intrusion detection system (IDS) that is both effective and efficient in terms of the cost consumed by intrusion detection (ID) nodes. For this multiple-objective problem, we investigate the use of evolutionary computation-based algorithms and show the performance of evolved intrusion detection algorithms against various RPL-specific attacks.

2023-01-01T00:00:00Z Tülay, Emine Elif Yıldırım, Ebru Aktürk, Tuba Güntekin, Bahar https://hdl.handle.net/20.500.12809/10658 2023-04-18T09:07:37Z 2023-01-01T00:00:00Z

Classification of Parkinson’s disease with dementia using phase locking factor of event-related oscillations to visual and auditory stimuli Tülay, Emine Elif; Yıldırım, Ebru; Aktürk, Tuba; Güntekin, Bahar Objective. In the last decades, machine learning approaches have been widely used to distinguish Parkinson’s disease (PD) and many other neuropsychiatric diseases. They also speed up the clinicians and facilitate decision-making for several conditions with similar clinical symptoms. The current study attempts to detect PD with dementia (PDD) by event-related oscillations (EROs) during cognitive processing in two modalities, i.e. auditory and visual. Approach. The study was conducted to discriminate PDD from healthy controls (HC) using event-related phase-locking factors in slow frequency ranges (delta and theta) during visual and auditory cognitive tasks. Seventeen PDD and nineteen HC were included in the study, and linear discriminant analysis was used as a classifier. During classification analysis, multiple settings were implemented by using different sets of channels (overall, fronto-central and temporo-parieto-occipital (TPO) region), frequency bands (delta-theta combined, delta, theta, and low theta), and time of interests (0.1-0.7 s, 0.1-0.5 s and 0.1-0.3 s for delta, delta-theta combined; 0.1-0.4 s for theta and low theta) for spatial-spectral-temporal searchlight procedure. Main results. The classification performance results of the current study revealed that if visual stimuli are applied to PDD, the delta and theta phase-locking factor over fronto-central region have a remarkable contribution to detecting the disease, whereas if auditory stimuli are applied, the phase-locking factor in low theta over TPO and in a wider range of frequency (1-7 Hz) over the fronto-central region classify HC and PDD with better performances. Significance. These findings show that the delta and theta phase-locking factor of EROs during visual and auditory stimuli has valuable contributions to detecting PDD.

2023-01-01T00:00:00Z Yiğit, Hasan Karayahşi, Kutlu https://hdl.handle.net/20.500.12809/10586 2023-03-14T10:42:47Z 2023-01-01T00:00:00Z

A novel model-based technique to improve design processes for microstrip antennas Yiğit, Hasan; Karayahşi, Kutlu The present work aims to prove the concept of a novel approach to designing microstrip antennas with desired radiation patterns without time-consuming trials and simulations. While it is pretty straightforward to design a microstrip antenna operating at a specific frequency, it requires repetitive trials to design an antenna with a specific radiation pattern. For this purpose, a unique model-based design technique is applied using the cavity model expressions in the present work. The behaviors and mutual influences of various parameters in the intended design problem are described by two graph models. The “employer model” oversees the limitations and freedoms of the antenna's parameters, while the “employee model” uses graph theory and machine learning to define the relationships between graph nodes. These two models have a dynamic structure that changes every calculation step to minimize design error. After two models are constructed, these models suggest physical parameter values according to the cavity model for the desired antenna radiation pattern. Then, the results for examples are demonstrated, and the validity of the proposed technique is proven. Finally, the developability of the method and its further works are discussed

2023-01-01T00:00:00Z