Cagri Yardimci
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Cagri Yardimci has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Mevlüt Ersoy
Süleyman Demirel Üniversitesi
3 shared publications - Atike Ince Yardimci
Technology Transfer Office, Uşak University, Uşak, Turkey
1 shared publication - Fatih Yalçin
Usak University
1 shared publication - Hüseyin Ata Karavana
Ege University
1 shared publication - Kadir Gündoğan
Department of Material Science and Nanotechnology Engineering, Uşak University, Uşak, Turkey
1 shared publication - Yaser Acikbas
Electrical and Electronics Engineering Department, Engineering and Natural Sciences Faculty, Usak University, Usak, Turkey
1 shared publication
Latest Publications
- 23 March 2026
- Published by SAGE Publications in Journal of Ambient Intelligence and Smart Environments
- Vol. 18 (3) , 322-335
Deep learning-based forecasting of temperature and humidity in footwear using multi-sensor data
Maintaining thermal comfort and regulating humidity in footwear is critical, particularly in environments where fluctuations in temperature and moisture impact user experience. Correct estimation of these parameters is crucial in selecting suitable material, thereby improving the efficiency and comfort of the footwear. This study proposes a comparison of the deep learning models (recurrent neural networks, long short-term memory (LSTM), bidirectional LSTM, DeepAR, and hybrid model (Cay, Vassiliadis et al.)) for the forecasting of temperature and humidity inside various types of footwear based on the multi-sensor data. A foot model that mimicked the actual temperature and perspiration process of the human foot was used, and sensor readings were taken from various points of the footwear. Performance of deep learning models was evaluated using four key metrics: mean absolute error, root mean squared error, explained variance score, and mean absolute percentage error. The findings indicate that the hybrid model outperforms the other models and achieves the highest predictive accuracy across all tested footwear conditions. This research contributes to the development of artificial intelligence-based predictive modeling for footwear climate control, offering a robust approach for determining thermophysiological comfort in wearable technologies and smart-manufacturing applications.
- 23 March 2026
- Published by SAGE Publications in Journal of Ambient Intelligence and Smart Environments
- Vol. 18 (3) , 322-335
Deep learning-based forecasting of temperature and humidity in footwear using multi-sensor data
Maintaining thermal comfort and regulating humidity in footwear is critical, particularly in environments where fluctuations in temperature and moisture impact user experience. Correct estimation of these parameters is crucial in selecting suitable material, thereby improving the efficiency and comfort of the footwear. This study proposes a comparison of the deep learning models (recurrent neural networks, long short-term memory (LSTM), bidirectional LSTM, DeepAR, and hybrid model (Cay, Vassiliadis et al.)) for the forecasting of temperature and humidity inside various types of footwear based on the multi-sensor data. A foot model that mimicked the actual temperature and perspiration process of the human foot was used, and sensor readings were taken from various points of the footwear. Performance of deep learning models was evaluated using four key metrics: mean absolute error, root mean squared error, explained variance score, and mean absolute percentage error. The findings indicate that the hybrid model outperforms the other models and achieves the highest predictive accuracy across all tested footwear conditions. This research contributes to the development of artificial intelligence-based predictive modeling for footwear climate control, offering a robust approach for determining thermophysiological comfort in wearable technologies and smart-manufacturing applications.
- Open Access
- 2 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 18272-18284
A Multiscale Deep Learning Framework With Genetic Algorithm-Optimized Inception Architecture for Defect Classification of Polyacrylonitrile Nanofibers
Automating defect classification in electrospun polyacrylonitrile (PAN) nanofibers is essential for improving quality control and reducing the experimental effort required for scanning electron microscopy (SEM) based inspection. This study introduces a domain specific deep learning model for the accurate classification of nanofiber defects using a uniquely curated SEM dataset labeled into slightly defective, defective, and non-defective categories. Unlike conventional binary approaches, the proposed framework incorporates an intermediate class that captures subtle morphological deviations that are important for early stage defect recognition. A custom Nanofiber Classifier is developed and enhanced with a multiscale Inception module together with hyperparameters optimised through a genetic algorithm (GA), enabling expressive and discriminative feature extraction across heterogeneous fiber geometries. Evaluation against widely used pretrained architectures such as GoogleNet and AlexNet shows that the proposed model, although developed and trained entirely from scratch, achieves exceptional classwise performance with accuracy values of 98.64% for slightly defective, 99.16% for defective, and 99.18% for non defective samples. These findings demonstrate that a purpose built multiscale architecture provides an effective, reliable, and scalable solution for SEM based nanofiber quality assessment.
- 2 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 18272-18284
Open AccessA Multiscale Deep Learning Framework With Genetic Algorithm-Optimized Inception Architecture for Defect Classification of Polyacrylonitrile Nanofibers
Automating defect classification in electrospun polyacrylonitrile (PAN) nanofibers is essential for improving quality control and reducing the experimental effort required for scanning electron microscopy (SEM) based inspection. This study introduces a domain specific deep learning model for the accurate classification of nanofiber defects using a uniquely curated SEM dataset labeled into slightly defective, defective, and non-defective categories. Unlike conventional binary approaches, the proposed framework incorporates an intermediate class that captures subtle morphological deviations that are important for early stage defect recognition. A custom Nanofiber Classifier is developed and enhanced with a multiscale Inception module together with hyperparameters optimised through a genetic algorithm (GA), enabling expressive and discriminative feature extraction across heterogeneous fiber geometries. Evaluation against widely used pretrained architectures such as GoogleNet and AlexNet shows that the proposed model, although developed and trained entirely from scratch, achieves exceptional classwise performance with accuracy values of 98.64% for slightly defective, 99.16% for defective, and 99.18% for non defective samples. These findings demonstrate that a purpose built multiscale architecture provides an effective, reliable, and scalable solution for SEM based nanofiber quality assessment.
- Open Access
- 31 August 2021
- Published by International Journal of 3D Printing Technologies and Digital Industry in International Journal of 3D Printing Technologies and Digital Industry
- Vol. 5 (2) , 237-250
COMPARISON OF SOFTWARE AND HARDWARE BASED INTRUSION PREVENTION SYSTEMS
In this study, attacks in three different scenarios were organized by Nmap and Hping3 tools on the virtual Kali server to physical servers running two software-based, open source Intrusion Prevention Systems (IPS-A and IPS-B) and one hardware-based, closed-source Intrusion Prevention System (IPS-C). Although the software-based IPS-A has high packet capture performances, it has been observed that the detection/alarm results are below the average. Although the hardware-based IPS-C is an optimized appliance to put a minimum load on the processor, the detection/alarm figures are at very low levels. In this paper, it has been observed that the IPS-B which is the other software-based Intrusion Prevention System, has a processor usage of 100% but it has reached a far ahead result with very high analysis and detection/alarm performance. In this study, in all the scenarios, four different packet numbers and about twenty parameters were applied to all three IPSs that packet capture performance is quite high and 100%. All three IPSs achieved 100% detection results in attacks where a small number of packets were sent.
- 31 August 2021
- Published by International Journal of 3D Printing Technologies and Digital Industry in International Journal of 3D Printing Technologies and Digital Industry
- Vol. 5 (2) , 237-250
Open AccessCOMPARISON OF SOFTWARE AND HARDWARE BASED INTRUSION PREVENTION SYSTEMS
In this study, attacks in three different scenarios were organized by Nmap and Hping3 tools on the virtual Kali server to physical servers running two software-based, open source Intrusion Prevention Systems (IPS-A and IPS-B) and one hardware-based, closed-source Intrusion Prevention System (IPS-C). Although the software-based IPS-A has high packet capture performances, it has been observed that the detection/alarm results are below the average. Although the hardware-based IPS-C is an optimized appliance to put a minimum load on the processor, the detection/alarm figures are at very low levels. In this paper, it has been observed that the IPS-B which is the other software-based Intrusion Prevention System, has a processor usage of 100% but it has reached a far ahead result with very high analysis and detection/alarm performance. In this study, in all the scenarios, four different packet numbers and about twenty parameters were applied to all three IPSs that packet capture performance is quite high and 100%. All three IPSs achieved 100% detection results in attacks where a small number of packets were sent.