Özkan CANAY

Dr. Özkan CANAY

orcid
Faculty Member of the Faculty of Computer and Information Sy...

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 February 2023 in Engineering Science and Technology, an International Journal
Verified
Journal Article
Open access
Özkan CANAYÖzkan CANAY
Özkan CANAY
ÜKÜmit Kocabıçak
Ümit Kocabıçak

26 December 2023 in Information Processing & Management
Verified
Journal Article
Closed access
Özkan CANAYÖzkan CANAY
Özkan CANAY
ÜKÜmit Kocabıçak
Ümit Kocabıçak

9 November 2024 in Knowledge-Based Systems
Verified
Journal Article
Closed access
Özkan CANAYÖzkan CANAY
Özkan CANAY
ÜKÜmit Kocabıçak
Ümit Kocabıçak

6 January 2015 in Neural Computing and Applications
Verified
Journal Article
Closed access
PDF file
TCTarik Cakar
Tarik Cakar
RKRaşit Köker
Raşit Köker
Özkan CANAYÖzkan CANAY
Özkan CANAY

6 July 2026 in Turkish Journal of Engineering
Verified
Journal Article
Closed access
CÖCem özkurt
Cem özkurt
Özkan CANAYÖzkan CANAY
Özkan CANAY
PÜPolat Üzelge
Polat Üzelge
ADAhmet Dursun
Ahmet Dursun
Mucahit SoyaslanMucahit Soyaslan
Mucahit Soyaslan
This study presents an artificial intelligence-based system for the real-time and high-accuracy detection of defects in bolts moving on a production line conveyor belt. Bolt defects are critical for product safety and production quality, while manual inspection methods remain insufficient due to their time-consuming nature, susceptibility to human error, and limited reliability. Although various approaches have been proposed in the literature, existing methods are limited in terms of small-object detection, real-time performance, and industrial integration. To address these limitations, a deep learning-based defect detection mechanism was developed and comparatively evaluated using the YOLOv9, YOLOv10, and YOLO11 architectures, with emphasis on low hardware requirements, ease of integration, and real-time capability. A custom dataset of 12,075 high-resolution conveyor belt bolt images was constructed and used to train and validate all model variants. Experimental results demonstrate that all three architectures achieved over 99% mAP50, with the YOLO11x model reaching 99.39% mAP50 and 90.90% mAP50-95, closely matched by YOLOv10x at 99.39% mAP50 and 90.91% mAP50-95. Considering both detection accuracy and inference speed, YOLO11x provides the most favorable balance for production line integration, while YOLOv10x stands out as a competitive alternative with comparable accuracy and lower computational cost. The proposed system offers a faster, more reliable, and easily integrable solution than manual inspection, with strong potential for adoption in high-precision industrial sectors such as automotive, aerospace, and defense.

28 February 2025
Verified
Book Chapter
Closed access
Özkan CANAYÖzkan CANAY
Özkan CANAY
Artificial intelligence, which is quickly helping us solve several complex problems, is centered on neural networks. This chapter gives a detailed introduction to the foundational concepts of neural networks, from perceptrons and activation functions to multilayer architectures. How networks improve their output using iterative processes is explained, with a focus on backpropagation and its associated methods. These architectures are introduced with examples from general-purpose tasks, including classification and regression, showcasing their adaptability and versatility. In addition, the chapter describes problems, such as the vanishing gradient problem, and their solutions, including advanced activation functions and training algorithms, to enhance training efficiency. The chapter presents selection strategies for problem-specific architectures which focus on both scalability and real-world applicability. It also discussed regularization methods for preventing overfitting and ensuring reliable performance across different datasets.