Hatice Doğan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Hatice Doğan has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Güleser Kalaycı Demir
Dokuz Eylül University, Faculty of Engineering
2 shared publications - Hasan Ozturk
Dokuz Eylul University
2 shared publications - Nasuf Sonmez
Department of Physics Faculty of Science Ege University 35040 Izmir Turkey
2 shared publications - Ahmet Onur Gi̇rAy
Dokuz Eylül Üniversitesi
1 shared publication Alkım Şükrü Özkan
Department of Electrical and Electronics Engineering, Dokuz Eylül University, 35390 İzmir, Turkey
1 shared publication- Anıl EREN
Dokuz Eylul University
1 shared publication
Latest Publications
- 10 June 2026
- Published by SAGE Publications in Structural Health Monitoring
Deep learning-based detection and severity classification of distributed pitting faults in helical gearboxes
Gears, which play a vital role in the transmission of power and torque between shafts in industrial machinery, can be susceptible to faults such as pitting, cracking, wear, and corrosion, caused by harsh operating conditions. Among these faults, distributed pitting, characterized by the formation of small pits on all surfaces of the teeth, is more difficult to detect. The early detection and severity assessment of such faults are crucial in preventing further damage to machinery. Deep learning methods, particularly autoencoders (AEs) and convolutional neural networks (CNNs), have demonstrated significant potential for detecting gear faults in vibration signals. This study explores the use of variational AEs (VAEs) as feature extractors to classify the severity of distributed pitting faults in helical gears. For this purpose, experiments were conducted using a test rig equipped with a two-stage industrial helical gearbox under four distinct load conditions, employing healthy gears and gears with varying pitting severities. Vibration signals, captured by accelerometers, were combined into one-dimensional time-series data and subsequently transformed into two-dimensional representations using two approaches to leverage image classification capabilities of deep learning methods. Various configurations of CNN, AE, and VAE models were evaluated for fault severity classification using different input modalities. Of all the methods tested, VAE combined with a classifier performed best in almost all load conditions. In addition, because not all fault types may be represented during model development, the study also examined the behavior of the best-performing models when one fault class was excluded from training. This additional evaluation was used to assess the generalization to unseen fault classes under incomplete fault coverage, and the VAE–classifier combination showed more reliable behavior than the competing alternatives within this evaluation setting.
- 10 June 2026
- Published by SAGE Publications in Structural Health Monitoring
Deep learning-based detection and severity classification of distributed pitting faults in helical gearboxes
Gears, which play a vital role in the transmission of power and torque between shafts in industrial machinery, can be susceptible to faults such as pitting, cracking, wear, and corrosion, caused by harsh operating conditions. Among these faults, distributed pitting, characterized by the formation of small pits on all surfaces of the teeth, is more difficult to detect. The early detection and severity assessment of such faults are crucial in preventing further damage to machinery. Deep learning methods, particularly autoencoders (AEs) and convolutional neural networks (CNNs), have demonstrated significant potential for detecting gear faults in vibration signals. This study explores the use of variational AEs (VAEs) as feature extractors to classify the severity of distributed pitting faults in helical gears. For this purpose, experiments were conducted using a test rig equipped with a two-stage industrial helical gearbox under four distinct load conditions, employing healthy gears and gears with varying pitting severities. Vibration signals, captured by accelerometers, were combined into one-dimensional time-series data and subsequently transformed into two-dimensional representations using two approaches to leverage image classification capabilities of deep learning methods. Various configurations of CNN, AE, and VAE models were evaluated for fault severity classification using different input modalities. Of all the methods tested, VAE combined with a classifier performed best in almost all load conditions. In addition, because not all fault types may be represented during model development, the study also examined the behavior of the best-performing models when one fault class was excluded from training. This additional evaluation was used to assess the generalization to unseen fault classes under incomplete fault coverage, and the VAE–classifier combination showed more reliable behavior than the competing alternatives within this evaluation setting.
- 23 October 2023
- Published by Bandirma Onyedi Eylul University in Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi
- Vol. 6 (2) , 209-222
Lane Detection for Autonomous Driving in a Video Game Environment
To ensure comfortable and safe driving, the automotive industry has accelerated the development of autonomous vehicles in recent years. In the design of autonomous vehicles, challenging problems such as lane detection need to be solved. Convolutional neural networks, which show superior performance in many fields, have also been used in the lane detection problem. The datasets required to train CNN models are too large to be collected and labeled by manual effort. In this study, a method is proposed to automatically collect a labeled data set from the video game environment to be used in the detection of highway lanes. Different CNN models such as ResNet50, VGG16, Xception, and InceptionV3 networks are trained using the Transfer Learning method with 745,823 collected images. The images captured by the front vehicle camera are used as input, the coordinates of the points in the left and right lane and the center of the lane in the 2D plane in front of the vehicle and the angle of the vehicle are used as outputs. The performances of these models are tested and compared on the images collected from a road not used in the training set. According to the performance comparisons, ResNet50 performs best.
- 23 October 2023
- Published by Bandirma Onyedi Eylul University in Akıllı Ulaşım Sistemleri ve Uygulamaları Dergisi
- Vol. 6 (2) , 209-222
Lane Detection for Autonomous Driving in a Video Game Environment
To ensure comfortable and safe driving, the automotive industry has accelerated the development of autonomous vehicles in recent years. In the design of autonomous vehicles, challenging problems such as lane detection need to be solved. Convolutional neural networks, which show superior performance in many fields, have also been used in the lane detection problem. The datasets required to train CNN models are too large to be collected and labeled by manual effort. In this study, a method is proposed to automatically collect a labeled data set from the video game environment to be used in the detection of highway lanes. Different CNN models such as ResNet50, VGG16, Xception, and InceptionV3 networks are trained using the Transfer Learning method with 745,823 collected images. The images captured by the front vehicle camera are used as input, the coordinates of the points in the left and right lane and the center of the lane in the 2D plane in front of the vehicle and the angle of the vehicle are used as outputs. The performances of these models are tested and compared on the images collected from a road not used in the training set. According to the performance comparisons, ResNet50 performs best.
- 12 June 2023
- Published by Springer Nature in International Applied Mechanics
- Vol. 58 (6) , 1-12
Dynamic Stability of Diamond Frame Structures
- 12 June 2023
- Published by Springer Nature in International Applied Mechanics
- Vol. 58 (6) , 1-12
Dynamic Stability of Diamond Frame Structures
- 20 June 2022
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics A
- Vol. 37 (17)
Light charged Higgs search with deviation neural networks
- 20 June 2022
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics A
- Vol. 37 (17)
Light charged Higgs search with deviation neural networks
- 15 April 2022
- Published by Turkish Journal of Engineering in Turkish Journal of Engineering
- Vol. 6 (2) , 166-177
Design and implementation of a cost effective vacuum cleaner robot
Robot vacuum cleaners are among the first service robots to enter daily life. However, robot vacuum cleaners are currently inaccessible to many due to their high cost. In order for these robots to become widespread, they must be cheap and functional. In this study, the design and production of a low-cost, high-performance vacuum cleaner robot that can be controlled by smartphones is presented. This autonomous robot moves around the obstacles, vacuums the dust from the floor, performs basic navigation and also it is manually controllable. Designing of a vacuum cleaner robot is divided into three parts which are the mechanical, electrical and software design. In the mechanical design; the robot chassis and cleaning system have been designed and realized. In the electrical design; the electrical components such as batteries, motors, drivers, sensors and microcontroller have been selected and the power system has been designed by considering electrical requirements. In the software design; an easy to use Android application for remote control has been created, autonomous algorithms such as random walk and snake algorithms have been designed. Remote controlling of the robot has been provided by using Bluetooth connection between the Raspberry Pi and Android smartphone.
- 15 April 2022
- Published by Turkish Journal of Engineering in Turkish Journal of Engineering
- Vol. 6 (2) , 166-177
Design and implementation of a cost effective vacuum cleaner robot
Robot vacuum cleaners are among the first service robots to enter daily life. However, robot vacuum cleaners are currently inaccessible to many due to their high cost. In order for these robots to become widespread, they must be cheap and functional. In this study, the design and production of a low-cost, high-performance vacuum cleaner robot that can be controlled by smartphones is presented. This autonomous robot moves around the obstacles, vacuums the dust from the floor, performs basic navigation and also it is manually controllable. Designing of a vacuum cleaner robot is divided into three parts which are the mechanical, electrical and software design. In the mechanical design; the robot chassis and cleaning system have been designed and realized. In the electrical design; the electrical components such as batteries, motors, drivers, sensors and microcontroller have been selected and the power system has been designed by considering electrical requirements. In the software design; an easy to use Android application for remote control has been created, autonomous algorithms such as random walk and snake algorithms have been designed. Remote controlling of the robot has been provided by using Bluetooth connection between the Raspberry Pi and Android smartphone.
- 29 December 2021
- Published by Elsevier in Applied Acoustics
- Vol. 189, 108577
Speech protected noise cancellation system in noise dominated environments
- 29 December 2021
- Published by Elsevier in Applied Acoustics
- Vol. 189, 108577
Speech protected noise cancellation system in noise dominated environments
- 26 July 2019
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in Turkish Journal of Electrical Engineering and Computer Sciences
- Vol. 27 (4) , 3247-3257
Importance-based signal detection and parameter estimation with applications tonew particle search
- 26 July 2019
- Published by The Scientific and Technological Research Council of Turkey (TUBITAK-ULAKBIM) - DIGITAL COMMONS JOURNALS in Turkish Journal of Electrical Engineering and Computer Sciences
- Vol. 27 (4) , 3247-3257
Importance-based signal detection and parameter estimation with applications tonew particle search
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Traffic sign recognition with hierarchical Convolutional Neural Network
Convolutional Neural Network (CNN) becomes one of the most preferred deep learning method because of achieving superior success at solution of important problems of machine learning like pattern recognition, object recognition and classification. With CNN, high performance has been obtained in traffic sign recognition which is important for autonomous vehicles. In this work, two-stage hierarchical CNN structure is proposed. Signs are separated into 9 main groups at the first stage by using structure similarity index. And then classes of each main group are subclassed with CNNs at the second stage. Performance of the network is measured on 43-classes GTSRB dataset and compared with other methods.
- 1 May 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Traffic sign recognition with hierarchical Convolutional Neural Network
Convolutional Neural Network (CNN) becomes one of the most preferred deep learning method because of achieving superior success at solution of important problems of machine learning like pattern recognition, object recognition and classification. With CNN, high performance has been obtained in traffic sign recognition which is important for autonomous vehicles. In this work, two-stage hierarchical CNN structure is proposed. Signs are separated into 9 main groups at the first stage by using structure similarity index. And then classes of each main group are subclassed with CNNs at the second stage. Performance of the network is measured on 43-classes GTSRB dataset and compared with other methods.