Lastik Kusurlarının Tespiti için Yapay Zeka Destekli Yeni Bir Hibrit Model: CTLDF+EnC

Year 2024, Volume: 17 Issue: 3, 231 - 242, 31.07.2024

Özcan Askar , Ramazan Tekin

https://doi.org/10.17671/gazibtd.1465294

Abstract

Bu çalışma, araç sürücülerinin lastiklerindeki çatlakları tespit etmek için önerilen yapay zeka tabanlı bir aşınmış lastik tespit sistemine odaklanmaktadır. Sürücüler genellikle lastik diş derinliği ve hava basıncının öneminin farkında olsalar da, lastik oksidasyonu ile ilişkili risklerin farkında değillerdir. Ancak, lastik oksidasyonu ve çatlakları sürüş güvenliğini etkileyen önemli sorunlara neden olabilir. Bu makalede, lastik çatlağı tespiti için, önceden eğitilmiş transfer öğrenme yöntemlerinden elde edilen derin özellikleri topluluk öğrenme yöntemleriyle birleştirerek kullanan yeni bir hibrit mimari olan CTLDF+EnC (Basamaklandırılmış Transfer Öğrenme Derin Özellikler + Ensemble Sınıflandırıcılar) önerilmektedir. Önerilen hibrit model, dokuz transfer öğrenme yönteminden gelen özellikleri ve İstifleme, Yumuşak ve Katı oylama topluluk öğrenme yöntemlerini içeren sınıflandırıcıları kullanmaktadır. Endüstriyel kullanıma yönelik X-Ray görüntü tabanlı uygulamalardan farklı olarak bu çalışmada önerilen model herhangi bir dijital görüntüleme cihazından elde edilen görüntülerle çalışabilmektedir. Çalışmada önerilen modeller arasında en yüksek test doğruluk değeri %76,92 olarak CTLDF+EnC ( İstifleme) hibrit modeli ile elde edilmiştir. CTLDF+EnC ( Yumuşak) ve CTLDF+EnC (Katı) modelleri ile sırasıyla %74,15 ve %72,92 doğruluk değerleri elde edilmiştir. Çalışmanın sonuçları, önerilen hibrit modellerin lastik sorunlarını tespit etmede etkili olduğunu göstermektedir. Ayrıca, düşük maliyetli ve uygulanabilir bir yapı sunulmuştur.

Keywords

Transfer Öğrenme, Derin Öznitelikler, Topluluk Öğrenme, Lastik Çatlakları

A New Hybrid Model for Artificial Intelligence Assisted Tire Defect Detection: CTLDF+EnC

Abstract

This paper focuses on an artificial intelligence based worn tire detection system proposed to detect cracks in the tires of vehicle drivers. Although drivers are generally aware of the importance of tire tread depth and air pressure, they are not aware of the risks associated with tire oxidation. However, tire oxidation and cracks can cause significant problems affecting driving safety. In this paper, we propose a new hybrid architecture for tire crack detection, CTLDF+EnC (Cascaded Transfer Learning Deep Features + Ensemble Classifiers), which uses deep features from pre-trained transfer learning methods in combination with ensemble learning methods. The proposed hybrid model utilizes features from nine transfer learning methods and classifiers including Stacking, Soft and Hard voting ensemble learning methods. Unlike X-Ray image-based applications for industrial use, the model proposed in this study can work with images obtained from any digital imaging device. Among the models proposed in the study, the highest test accuracy value was obtained as 76.92% with the CTLDF+EnC (Stacking) hybrid model. With CTLDF+EnC (Soft) and CTLDF+EnC (Solid) models, 74.15% and 72.92% accuracy values were obtained respectively. The results of the study show that the proposed hybrid models are effective in detecting tire problems. In addition, a low-cost and feasible structure is presented.

Keywords

Transfer Learning, Deep Features, Ensemble Learning, Tire Cracks

References

• S.-L. Lin, Research on tire crack detection using image deep learning method, Sci Rep 13 (2023) 8027.
• Q. Guo, C. Zhang, H. Liu, X. Zhang, Defect detection in tire X-ray images using weighted texture dissimilarity, J Sens 2016 (2016).
• G. Zhao, S. Qin, High-precision detection of defects of tire texture through X-ray imaging based on local inverse difference moment features, Sensors 18 (2018) 2524.
• Z. Zheng, S. Zhang, B. Yu, Q. Li, Y. Zhang, Defect inspection in tire radiographic image using concise semantic segmentation, IEEE Access 8 (2020) 112674–112687.
• R. Wang, Q. Guo, S. Lu, C. Zhang, Tire defect detection using fully convolutional network, IEEE Access 7 (2019) 43502–43510.
• J. Huang, B. Kingsbury, Audio-visual deep learning for noise robust speech recognition, in: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, 2013: pp. 7596–7599.
• Y. Kaya, F. Kuncan, R. Tekin, A new approach for congestive heart failure and arrhythmia classification using angle transformation with LSTM, Arab J Sci Eng 47 (2022) 10497–10513.
• J. Liu, D. Capurro, A. Nguyen, K. Verspoor, “Note Bloat” impacts deep learning-based NLP models for clinical prediction tasks, J Biomed Inform 133 (2022) 104149.
• B. Özaydın, R. Tekin, A Hybrid Model Based on Deep Features and Ensemble Learning for the Diagnosis of COVID-19: DeepFeat-E, Turkish Journal of Science and Technology 18 (2023) 183–198.
• H. Purwins, B. Li, T. Virtanen, J. Schlüter, S.-Y. Chang, T. Sainath, Deep learning for audio signal processing, IEEE J Sel Top Signal Process 13 (2019) 206–219.
• B. Rim, N.-J. Sung, S. Min, M. Hong, Deep learning in physiological signal data: A survey, Sensors 20 (2020) 969.
• H. Tung, R. Tekin, New Feature Extraction Approaches Based on Spatial Points for Visual-Only Lip-Reading., Traitement Du Signal 39 (2022).
• D. Wang, J. Su, H. Yu, Feature extraction and analysis of natural language processing for deep learning English language, IEEE Access 8 (2020) 46335–46345.
• S.-H. Wang, S. Xie, X. Chen, D.S. Guttery, C. Tang, J. Sun, Y.-D. Zhang, Alcoholism identification based on an AlexNet transfer learning model, Front Psychiatry 10 (2019) 205.
• X. Yang, Y. Zhang, W. Lv, D. Wang, Image recognition of wind turbine blade damage based on a deep learning model with transfer learning and an ensemble learning classifier, Renew Energy 163 (2021) 386–397.
• F. Chollet, Xception: Deep learning with depthwise separable convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017: pp. 1251–1258.
• K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, ArXiv Preprint ArXiv:1409.1556 (2014).
• B. Zoph, V. Vasudevan, J. Shlens, Q. V Le, Learning transferable architectures for scalable image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018: pp. 8697–8710.
• K. He, X. Zhang, S. Ren, Deep Residual Learning for Image Recognition, Microsoft Research 45 (2015) 1951–1954. https://doi.org/10.1002/chin.200650130.
• G. Huang, Z. Liu, L. Van Der Maaten, K.Q. Weinberger, Densely connected convolutional networks, Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 2017-Janua (2017) 2261–2269. https://doi.org/10.1109/CVPR.2017.243.
• C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, Rethinking the inception architecture for computer vision, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: pp. 2818–2826.
• A.G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, H. Adam, MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, (2017). http://arxiv.org/abs/1704.04861.
• D.H. Wolpert, Stacked generalization, Neural Networks 5 (1992) 241–259.
• Z.-H. Zhou, Ensemble methods: foundations and algorithms, CRC press, 2012.
• Y. Zhang, D. Lefebvre, Q. Li, Automatic detection of defects in tire radiographic images, IEEE Transactions on Automation Science and Engineering 14 (2015) 1378–1386.
• Y. Li, B. Fan, W. Zhang, Z. Jiang, TireNet: A high recall rate method for practical application of tire defect type classification, Future Generation Computer Systems 125 (2021) 1–9.
• J. Siegel, Oxidized and non-oxidized tire sidewall and tread images, Harvard Dataverse (2021). https://doi.org/https://doi.org/10.7910/DVN/Z3ZYLI.
• J. Lu, V. Behbood, P. Hao, H. Zuo, S. Xue, G. Zhang, Transfer learning using computational intelligence: A survey, Knowl Based Syst 80 (2015) 14–23.
• P. Geurts, D. Ernst, L. Wehenkel, Extremely randomized trees, Mach Learn 63 (2006) 3–42.
• M.K. Bohmrah, H. Kaur, Classification of Covid-19 patients using efficient fine-tuned deep learning DenseNet model, Global Transitions Proceedings 2 (2021) 476–483.
• S. Erdogan, Explorative spatial analysis of traffic accident statistics and road mortality among the provinces of Turkey, J Safety Res 40 (2009) 341–351.
• C. Cai, L. He, Improved Mach–Zehnder interferometer-based shearography, Opt Lasers Eng 50 (2012) 1699–1705.
• H.L.M. Dos Reis, K.A. Warmann, Acousto-ultrasonic non-destructive evaluation of fatigue damage in steel-belted radial tires., Int J Fatigue 3 (1996) 216.
• L.E. Roemer, N. Ida, Location of wire position in tyre belting using Bayesian analysis, NDT & E International 24 (1991) 95–97.
• R. Wang, Q. Guo, S. Lu, C. Zhang, Tire defect detection using fully convolutional network, IEEE Access 7 (2019) 43502–43510.