Öcal, Aysun

Profile URL:
Job Title:Arş. Gör. Uzm.
Email Address:aocal@ktun.edu.tr
Main Affiliation:02.04. Department of Electrical and Electronics Engineering
Status: Current Staff
Website: https://www.ktun.edu.tr/tr/Universite/PersonelBilgi/?prsnl=XW7GiExfHtWhB+4F5Sra6qoB492FxE09uZqYH6ph9nNxx30q7RJV2Y4Nk15YSMfFnyMEm98jol1sFcr4m2vtiw==
ORCID:ORCID Profile0009-0008-8214-5532
YÖK Akademik: 7FF56CDB10BF91E7
Google Scholar:Google Scholar ProfileoHHP7DQAAAAJ
Web of Science ID:Web of Science ProfileKXI-0512-2024
Name Variants:
Ocal, Aysun Öcal, A.
Full item page
Author of Publication: search.filters.isAuthorOfPublication.f9dff66d-2494-497e-a574-a354951cbd95

Scholarly Output Search Results

Now showing 1 - 2 of 2
  • Conference Object
    Citation - Scopus: 3
    Optimum Design of Flapping Wing Flying Robot by Modified Social Group Optimization
    (Institute of Electrical and Electronics Engineers Inc., 2022-10-03) Öcal, A.; Koyuncu, H.
    Constrained optimization is very often appealed to handle challenging design problems in engineering area. Herein, heuristic methods are frequently preferred to solve these design problems. For the best design of an engineering problem, the robustness of optimization algorithm occupies an important place.In this paper, a recent engineering problem is handled which evaluates the optimum design of a flapping wing flying robot / ornithopter. Concerning the issue, main function and constrained functions are combined using penalty function to define the problem encountered as a single objective optimization problem. The design problem is evaluated by four recent and promising algorithms that are chaotic dynamic weight particle swarm optimization (CDW-PSO), crystal structure algorithm (CryStAl), adaptive strategy particle swarm optimization (ASPSO), and modified social group optimization (MSGO). The best fitness, processing time and average best fitness evaluations are considered to objectively reveal the most appropriate method for optimum design. Consequently, MSGO and ASPSO achieve the optimum results and outperforms CDW-PSO and CryStAl algorithms for the best fitness-based experiments. Moreover, MSGO yields a remarkable performance than ASPSO by presenting a more robust behavior for average best fitness-based comparisons. © 2022 IEEE.
  • Conference Object
    Optimizing Hyperparameters of Resnet50 for 3t2fts-Based Tumor Grading
    (Institute of Electrical and Electronics Engineers Inc., 2024-11-20) Öcal, A.; Koyuncu, H.
    Three-dimensional (3D) MR imaging allows for a comprehensive assessment of crucial factors like brain tumor volume and location. Also, two-dimensional (2D) analysis comprises more methods than 3D-based analysis to be applied for tumor classification, e.g. high-grade glioma (HGG) vs low-grade glioma (LGG). Regarding this, to accurately classify between HGG and LGG glioma types, each slice of 3D MR images can be analyzed using 3D to 2D feature transformation methods. In this paper, we utilize optimized-ResNet50 models to accurately classify 2D identity information (2D-ID) of HGG-and LGG-typed tumors that is the output of a 3D to 2D feature transformation strategy (3t2FTS). At this point, state-of-the-art algorithms including crystal structure algorithm (CSA), chaotic dynamic weight-particle swarm optimization (CDW-PSO), and modified social group optimization (MSGO) are compared to tune the hyperparameters of ResNet50, i.e. continuous & discrete optimization problem. The experimental results indicate that the ResNet50-CSA model achieves the highest accuracy (91.23%) on the 3t2FTS-based data. Furthermore, ResNet50-MSGO provides 87.72 % accuracy, and its operation time is nearly half of the time belonging to ResNet50-CSA. As a result, MSGO and especially CSA, demonstrate significant performance to catch a tradeoff between searching capacity (convergence capability), accuracy and operation time. © 2024 IEEE.

Research Topics

Domains
Physical SciencesHealth Sciences
Fields
Computer ScienceMedicine
Subfields
Artificial IntelligenceRheumatologyRadiology, Nuclear Medicine and Imaging
Specific Research Areas
Metaheuristic Optimization Algorithms Research
Osteoarthritis Treatment and Mechanisms
Rheumatoid Arthritis Research and Therapies
Medical Imaging Techniques and Applications
AI in cancer detection

Sustainable Development Goals

SDG data is not available
This researcher does not have a Scopus ID.
Documents

3

Citations

6

Go to WoS profile

Publication Collaboration

Affiliation Name Count
Konya Technical University 3
1 / 1
Data obtained from OpenAlex
JournalCount
2022 13th International Conference on Computing Communication and Networking Technologies, ICCCNT 20221
2024 8th International Conference on System Reliability and Safety, ICSRS 2024 -- 8th International Conference on System Reliability and Safety, ICSRS 2024 -- 20 November 2024 through 22 November 2024 -- Sicily -- 2079861
Current Page: 1 / 1
Scholarly Output

2

Articles

0

Views / Downloads

1/0

Supervised MSc Theses

0

Supervised PhD Theses

0

WoS Citation Count

0

Scopus Citation Count

3

Patents

0

Projects

0

WoS Citations per Publication

0.00

Scopus Citations per Publication

1.50

Open Access Source

0

Supervised Theses

0

Scopus Quartile Distribution

Quartile distribution chart data is not available

Competency Cloud

GCRIS Competency Cloud