Derin Öznitelik ve İnce-Ayar ile Aktarım Öğrenme Tabanlı Bağlantı Elemanlarının Hibrit Sınıflandırma Yaklaşımı

Year 2023, Volume: 18 Issue: 2, 461 - 475, 01.09.2023

Canan Taştimur Erhan Akın

https://doi.org/10.55525/tjst.1317713

Abstract

Son yıllarda yapılan çalışmalarda sıkça kullanılmaya başlanan derin öğrenme, birçok farklı tür ve özellikteki nesnelerin sınıflandırılması sorununun çözülmesine yardımcı olmuştur. Çoğu çalışma, sıfırdan bir evrişimsel sinir ağı (CNN) oluşturur ve eğitir. Ağı eğitmek için harcanan zaman böylece boşa harcanır. Transfer öğrenme (TL) hem veri setinin eğitilmesinden kaynaklanan zaman kaybını önlemek hem de küçük veri setlerini daha etkin bir şekilde sınıflandırmak için kullanılmaktadır. Bu çalışma, on sekiz tip bağlantı elemanı içeren bir veri seti kullanarak sınıflandırma yapmaktadır. Çalışmamız üç farklı TL senaryosu içermektedir. Bunlardan ikisi ince ayar (FT) ile TL kullanırken, üçüncüsü özellik çıkarma (FE) ile yapmaktadır. Çalışma, on sekiz farklı önceden eğitilmiş ağ modelinin (yani EfficientNet, DenseNet, InceptionResNetV2, InceptionV3, MobileNet, ResNet50, Xception ve VGGNet) sınıflandırma performansını ayrıntılı olarak karşılaştırmaktadır. Literatürdeki diğer araştırmalarla karşılaştırıldığında, birinci ve ikinci senaryolarımız TL-FT' nin iyi sonuçlarla uygulamalarını sağlarken, üçüncü senaryomuz TL-FE hibrit bir yöntem olup diğer iki senaryodan daha iyi sonuçlar üretmiştir. Ayrıca, bulgularımız literatürdeki çalışmaların çoğundan daha üstün olduğu fark edilmiştir. En iyi sonuçlara sahip modeller TL-FT1 senaryosunda 0,97 doğrulukla DenseNet169, TL-FT2'de 0,96 ile EfficientNetB0 ve TL-FE'de 0,995 ile DenseNet169'dur.

Keywords

Sınıflandırma, bağlantı elemanı, özellik çıkarma, ince ayar, Sınıflandırma, bağlantı elemanı, özellik çıkarma, ince ayar, transfer öğrenme

A Hybrid Classification Approach for Fasteners Based on Transfer Learning with Fine-Tuning and Deep Features

Abstract

Deep learning, which has seen frequent use in recent studies, has helped solve the problem of classifying objects of many different types and properties. Most studies both create and train a convolutional neural network (CNN) from scratch. The time spent training the network is thus wasted. Transfer learning (TL) is used both to prevent the loss of time due to training the dataset and to more effectively classify small datasets. This study performs classification using a dataset containing eighteen types of fastener. Our study contains three different TL scenarios. Two of them use TL with fine-tuning (FT), while the third does so with feature extraction (FE). The study compares the classification performance of eighteen different pre-trained network models (i.e., one or more versions of EfficientNet, DenseNet, InceptionResNetV2, InceptionV3, MobileNet, ResNet50, Xception, and VGGNet) in detail. When compared to other research in the literature, our first and second scenarios provide excellent implementations of TL-FT, while our third scenario, TL-FE, is hybrid and produces better results than the other two. Furthermore, our findings are superior to those of most previous studies. The models with the best results are DenseNet169 with an accuracy of 0.97 in the TL-FT1 scenario, EfficientNetB0 with 0.96 in TL-FT2, and DenseNet169 with 0.995 in TL-FE.

Keywords

Classification, fastener, feature extraction, fine tuning, transfer learning

References

• Pathak Y, Shukla PK, Tiwari A, Stalin S, & Singh S. Deep transfer learning based classification model for COVID-19 disease. Pattern Recognit. Lett. 2020; 152: 122-128.
• Akgun D, Kabakuş AT, Senturk Z.K, Senturk A, & Kucukkulahli E. A transfer learning-based deep learning approach for automated COVID-19 diagnosis with audio data. Turk. J. Electr. Eng. Comput. Sci. 2021; 29(SI-1): 2807-2823.
• Sravan V, Swaraj K, Meenakshi K, & Kora P. A deep learning based crop disease classification using transfer learning. Mater. Today Proc. 2020.
• Kudva V, Prasad K, & Guruvare S. Hybrid transfer learning for classification of uterine cervix images for cervical cancer screening. J. Digital Imaging 2020; 33(3): 619-631.
• Thenmozhi K, & Reddy U.S. Crop pest classification based on deep convolutional neural network and transfer learning. Comput. Electron. Agric. 2019; 164.
• Talo M, Baloglu UB, Yıldırım O, & Acharya UR. Application of deep transfer learning for automated brain abnormality classification using MR images. Cogn. Syst. Res. 2019; 154: 176-188.
• Mehrotra R, Ansari M, Agrawal R, & Anand RS. A transfer learning approach for AI-based classification of brain tumors. Mach. Learn. Appl. 2020; 2.
• Yang K, Yang T, Yao Y, & Fan SD. A transfer learning-based convolutional neural network and its novel application in ship spare-parts classification. Ocean Coastal Manage. 2021; 215.
• Ali MS, Miah M.S, Haque J, Rahman MM, & Islam MK. An enhanced technique of skin cancer classification using deep convolutional neural network with transfer learning models. Mach. Learn. Appl. 2021; 5.
• Rahman Z, & Ami AM. A transfer learning based approach for skin lesion classification from imbalanced data. In: 2020 11th International Conference on Electrical and Computer Engineering (ICECE), 2020; Dhaka, Bangladesh. pp. 65-68.
• Kumar S, & Janet B. DTMIC: Deep transfer learning for malware image classification. J. Inf. Secur. Appl. 2022; 64.
• Giraddi S, Seeri S, Hiremath P.S, & Jayalaxmi GN. Flower Classification using Deep Learning models. In: 2020 International Conference on Smart Technologies in Computing, Electrical and Electronics (ICSTCEE), 2020; Karnataka, India. pp. 130-133.
• Wang I. H. Lee KC, & Chang SL. Images Classification of Dogs and Cats using Fine-Tuned VGG Models. In: 2020 IEEE Eurasia Conference on IOT, Communication and Engineering (ECICE), 2020; Yunlin, Taiwan: IEEE. pp. 230-233.
• Lee SW. Novel classification method of plastic wastes with optimal hyper-parameter tuning of Inception_ResnetV2. In: 2021 4th International Conference on Information and Communications Technology (ICOIACT): 2021; IEEE. pp. 274-279.
• Qian Y, Li G, Lin X, Zhang J, Yan J, Xie B, & Qin J. Fresh tea leaves classification using inception-V3. In: 2019 IEEE 2nd International Conference on Information Communication and Signal Processing (ICICSP), 2019; Weihai, China: IEEE. pp. 415-419.
• Junaidi A, Lasama J, Adhinata FD, & Iskandar AR. Image Classification for Egg Incubator using Transfer Learning of VGG16 and VGG19. In: 2021 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT), 2021; Malang: IEEE. pp. 324-328.
• Rajayogi JR, Manjunath G, & Shobha G. Indian food image classification with transfer learning. In: 2019 4th International Conference on Computational Systems and Information Technology for Sustainable Solution (CSITSS9), 2019; Miami, Fla: IEEE. pp. 1-4.
• Espejo-Garcia B, Malounas I, Mylonas N, Kasimati A, & Fountas S. Using EfficientNet and transfer learning for image-based diagnosis of nutrient deficiencies. Comput. Electron. Agric. 2022.
• Ribani R, & Marengoni M. A survey of transfer learning for convolutional neural networks. In: 2019 32nd SIBGRAPI Conference on Graphics, Patterns and Images Tutorials (SIBGRAPI-T), 2019; Rio de Janeiro, Brazil: IEEE. pp. 47-57.
• Krishna ST, & Kalluri HK. Deep learning and transfer learning approaches for image classification. Int J Recent Technol Eng. 2019; 7(5S4): 427-432.
• Simonyan K, and Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv Prepr. 2014; arXiv1409.1556.
• Szegedy C, Vanhoucke V, Ioffe S, Shlens J, and Wojna Z. Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016; Las Vegas, NV, USA: IEEE. pp. 2818–2826.
• Ucar M. Diagnosis of Glaucoma Disease using Convolutional Neural Network Architectures. Dokuz Eylul Uni. Fac. of Eng. J. of Sci. and Eng. 2021; 23(68): 521-529.
• Nguyen LD, Lin D, Lin Z, & Cao J. Deep CNNs for microscopic image classification by exploiting transfer learning and feature concatenation. In: 2018 IEEE International Symposium on Circuits and Systems (ISCAS), 2018; Floransa, İtaly: IEEE. pp. 1-5.
• Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, and Adam H. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv Prepr. 2017; arXiv /1704.04861.
• Zeren MT. Comparison of ssd and faster r-cnn algorithms to detect the airports with data set which obtained from unmanned aerial vehicles and satellite images. MSc, Beykent University, Istanbul, Turkey, 2020.
• Baydilli YY. Polen Taşıyan Bal Arılarının MobileNetV2 Mimarisi ile Sınıflandırılması. Eur. J. Eng. Sci. Tech. 2021; 21: 527-533.
• Huang G, Liu Z, Maaten LVD, & Weinberger KO. Densely Connected Convolutional Networks. In; IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017; Hawaii, ABD: IEEE.
• Aktas A. Image processing applications with deep learning methods. MSc, Marmara University, Istanbul, Turkey, 2020.
• Bayram B, Kilic B, Özoğlu F, Erdem F, Bakirman T, Sivri S, & Delen A. A Deep learning integrated mobile application for historic landmark recognition: A case study of Istanbul. Mersin Photogramm. J. 2020; 2(2): 38-50.
• Tan M, and Le QV. EfficientNet: Rethinking model scaling for convolutional neural networks. In: 36th Int. Conf. Mach. Learn. ICML, 2019; pp. 10691–10700.
• Bayram B, Kılıc B, Ozoglu F, Erdem F, Sivri S, Delen A, Bayrak OC. A study on object recognition with deep learning. In: 10. Turkiye Ulusal Fotogrametri ve Uzaktan Algılama Birligi Teknik Sempozyumu (TUFUAB 2019) 2019; Aksaray, Turkey.
• He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016; Las Vegas, NV, USA: IEEE. pp. 770-778.
• Dandil E, and Serin Z. Breast Cancer Detection on Histopathological Images Using Deep Neural Networks. Eur. J. Eng. Sci. Tech. 2020; Special Issue: 451-463.
• Chollet F. Xception: Deep learning with depthwise separable convolutions. In: IEEE conference on computer vision and pattern recognition 2017; Los Alamitos, California: IEEE.
• Sivari E. Güzel M. S. Bostanci E. & Mishra A. A Novel Hybrid Machine Learning Based System to Classify Shoulder Implant Manufacturers. Healthc. (Basel) 2022; 10(3), MDPI.
• Kalkan M. Bostancı GE. Güzel MS. Kalkan B. Özsarı Ş. Soysal Ö. & Köse G. Cloudy/clear weather classification using deep learning techniques with cloud images. Comput. Electr. Eng. 2022; 102, 108271.