Araştırma Makalesi
BibTex RIS Kaynak Göster

Çeşitli görüntülerin sınıflandırılması için yeni bir Evrişimsel Sinir Ağı önerisi

Yıl 2024, Cilt: 13 Sayı: 1, 262 - 278, 15.01.2024
https://doi.org/10.28948/ngumuh.1355726

Öz

Günümüzde derin öğrenme metotları robotik, ses işleme, tıp ve görüntü gibi birçok alanda yaygın kullanılmaktadır. Bu çalışmada literatürde yapılan görüntü sınıflandırma ve analizine yönelik çalışmalar detaylı bir şekilde incelenmiştir. Ayrıca yapılan çalışmada CNN kullanılarak derin öğrenme metotlarının MNIST, Fashion MNIST, CIFAR-10 ve CIFAR-100 ismindeki 4 farklı veri seti üzerinde performans analizleri yapılmıştır. Oluşturulan derin öğrenme modellerinin yapıları, eğitim için kullanılan parametre değerleri, kullanılan katmanlar, doğrulama verileri için elde edilen karmaşıklık matrisleri, doğruluk ve kayıp grafikleri ayrıntılı olarak gösterilmiştir. Çalışmamız 3 adet konvolüsyon katmanı, 3 adet batch normalizasyon katmanı, 2 adet maxpooling katmanı, 1 flatten, 2 droupout, 2 dense katmanından oluşan farklı bir ağ yapısı ile gerçekleştirilmiştir. Ayrıca önerdiğimiz modelle görüntü sınıflandırılmasının farklı veriler üzerindeki performansı artırılmıştır. Test sonunda çalışmamız çeşitli değerlendirme metriklerine göre doğruluk sonuçları karşılaştırılmıştır. Kullanılan tüm veri setleri için en iyi ve en kötü bulunan görüntüler tespit edilmiştir. Önerilen CNN modeli ile MNIST ve Fashion MNIST veri setleri için yüksek doğruluk oranları gözlemlenmiş olup bu değerler sırasıyla %99.22 ve %99.21’dir.

Kaynakça

  • E. Moen, D. Bannon, T. Kudo, W. Graf, M. Covert and D.Valen, Deep learning for cellular image analysis, Nature Metots, 16(12), 1233-1246, 2019.
  • F. Cevik, Z. Kilimci, Derin öğrenme yöntemleri ve kelime yerleştirme modelleri kullanılarak Parkinson hastalığının duygu analiziyle değerlendirilmesi, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 27(2), 151-161, 2020. https:// doi: 10.5505/pajes.2020.74429.
  • Z. Pekoz and T. İnkaya, Derin öğrenme ile talep tahmini: Bir üçüncü parti lojistik firması için covid-19 döneminde vaka analizi, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 1000(1000), 1-8, 2022. https:// doi: 10.5505/pajes.2022.73537.
  • T. Karahan and V. Nabiyev, Plant identification with convolutional neural networks and transfer learning, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 27(5), 638-645, 2021. https:// doi: 10.5505/pajes.2020.84042.
  • O. Abouelnaga and H. Ali, Cifar-10: knn-based ensemble of classifiers, 2016 International Conference on Computational Science and Computational Intelligence, Las Vegas, Nevada, USA, 15-17 December 2016.
  • G. Tushar, Comparative study of various convolutional neural networks on cifar-10, International Journal for Modern Trends in Science and Technology, 6(12), 402-406, 2020.
  • H. Tien, Cifar-10 to compare visual recognition performance between deep neural networks and humans. arXiv, abs/1811.07270, 2018.
  • R. Ju, Y. Lin and T. Jian, Efficient convolutional neural networks on raspberry pi for image classification, Journal of Real-Time Image Processing, 20(2), 1-9, 2023. https://doi.org/10.1007/s11554-023-01271-1
  • A.Yahya, K. Liu, A. Hawbani and Y. Wang, A novel image classification metot based on residual network. Inception, and Proposed Activation Function. Sensors, 23(6), 2976, 2023. https:// /doi.org/10.3390/s23062976.
  • X. Zhao, P. Huang P and H. Shu, Wavelet-attention CNN for image classification, Multimedia Systems, 28(3), 915-924, 2022. https://doi.org/ 0.1007/s00530-022-00889-8.
  • K. Zhang, Y. X. Guo, J. Yuan and Q. Ding, Multiple feature reweight densenet for image classification, IEEE Access, 7, 9872-9880, 2019. https:// /doi.org/ 10.1109/ACCESS.2018.2890127.
  • H. Shao, E. Ma, M. Zhu, X. Deng, S. Zhai, Mnist handwritten digit classification based on convolutional neural network with hyperparameter optimization, Intelligent Automation & Soft Computing, 36(3), 2023. https://doi.org/ 10.32604/iasc.2023.036323.
  • E. Plesovskaya and S. Ivanov, Hierarchical classification on the mnist dataset using truncated svd and kernel density estimation, Procedia Computer Science, 212, 368-377, 2022.
  • Y. Pei and L.Ye, Cluster analysis of mnist data set, In Journal of Physics: Conference Series, 2181(1), 12-12, 2022. https://doi.org/10.1088/1742-6596/2181/1/012035.
  • A. Henrique, Classifying garments from fashion-mnist dataset through CNNs, Journal Advances in Science Technology and Engineering Systems, 6(1), 989-994, 2021. https://doi.org/ 10.25046/aj0601109.
  • Ş. Öztürk, Moda görseli sınıflandırma: düzenleyici teknikler ile evrişimsel sinir ağları uygulaması, Bilgisayar Bilimleri ve Mühendisliği Dergisi, 15(1), 66-76, 2022.https://doi.org/ 10.54525/tbbmd.1077432.
  • S. Bhatnagar, D. Ghosal and MH. Kolekar, Classification of fashion article images using convolutional neural networks. Fourth International Conference on Image Information Processing, 357-362, India, 21-23 December 2017.
  • K. Meshkini, J. Platos and H. Ghassemain, An analysis of convolutional neural network for fashion images classification (fashion-mnist). International Conference on Intelligent Information Technologies for Industry, 85-95, Ostrava–Prague, Czech Republic, 2–7 December 2019.
  • K. Greeshma and K. Sreekumar, Hyperparameter optimization and regularization on fashion-mnist classification, International Journal of Recent Technology and Engineering, 8(2), 3713-3719, 2019.https://doi.org/ 10.35940/ijrte.B3092.078219.
  • M. Kayed, A. Anter and H. Mohamed, Classification of garments from fashion mnist dataset using cnn lenet-5 architecture. International Conference on Innovative Trends in Communication and Computer Engineering, 238-243, Aswan, Egypt, 8-9 February 2020.
  • T. Hur, L. Kim and D. Park, Quantum convolutional neural network for classical data classification, Quantum Machine Intelligence, 4(3), 1-18, (2022). https://doi.org/10.1007/s42484-021-00061-x.
  • Y. Seo and K. Shin, Hierarchical convolutional neural networks for fashion image classification, Expert Systems with Applications, 116, 328-339, 2019. https://doi.org/ 10.1016/j.eswa.2018.09.022.
  • OM. Khanday, S. Dadvandipour S and MA. Lone, Effect of filter sizes on image classification in cnn: a case study on cfar10 and fashion-mnist datasets, International Journal of Artificial Intelligence, 10(4), 872-878, 2021. https:// doi: 10.11591/ijai.v10.i4.pp872-878 .
  • O. Nocentini, J. Kim and F. Cavallo, İmage classification using multiple convolutional neural networks on the fashion-mnist dataset, Sensors, 22(23), 9544, 2022. https:// doi: 10.3390/s22239544 .
  • A. Vijayaraj, V. Raj and R. Dhanagopal, Deep learning image classification for fashion design, Wireless Communications and Mobile Computing, 2022, 1-10, 2022. https://doi.org/ 10.1155/2022/7549397.
  • AC. Cleber, A novel multi-objective grammar-based framework for the generation of convolutional neural networks, Expert Systems With Applications, 212, 2023. https://doi.org/ 10.1016/j.eswa.2022.118670.
  • R. Elyas, A. Akbari and B. Nasersharif, Uncertainty handling in convolutional neural networks. Neural Computing and Applications, 34, 16753-16769, 2022. https://doi.org/ 10.1007/s00521-022-07313-2.
  • O. Güler and İ. Yücedağ, Hand gesture recognition from 2d images by using convolutional capsule neural networks, Arabian Journal for Science and Engineering, 47, 1211-1225, 2022. https://doi.org/ 10.1007/s13369-021-05867-2.
  • G. Ryu and D. Choi, A hybrid adversarial training for deep learning model and denoising network resistant to adversarial examples, Applied Intelligence, 53, 1-14, 2022.
  • AT. Silva and RS. Siebert, Densenet-dc: optimizing densenet parameters through feature map generation control, Revista de Informática Teórica e Aplicada, 27, 25-39, 2020.
  • F. Assunção, N. Lourenço and P. Machado, Denser: deep evolutionary network structured representation, Genetic Programming and Evolvable Machines, 20, 5-35, 2019.
  • AM. Hafiz, RA. Bhat RA and M. Hassaballah, Image classification using convolutional neural network tree ensembles, Multimedia Tools and Applications, 82(5), 6867-6884, 2023. https://doi.org/ 10.1007/s11042-022-13604-6.
  • H. Gürkan ve A. Hanilçi, Evrişimsel sinir ağı ve qrs imgeleri kullanarak ekg tabanlı biyometrik tanıma yöntemi, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 26(2), 318-327, 2020.
  • P. Shinde ve S. Shah, A review of machine learning and deep learning applications, 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), Pune, India, 16-18 August 2018.
  • G. Ciaburro and B. Venkateswaran, Neural Networks with R: Smart Models using CNN, RNN, Deep Learning, and Artificial Intelligence Principles, Packt Publishing Ltd, Birmingham, 2017.
  • M. Khishe and A. Safari, Classification of sonar targets using an mlp neural network trained by dragonfly algorithm, Wireless Personal Communications, 108(4), 2241-2260, 2019. https://doi.org/ 10.1007/s11277-019-06520-w.
  • P. Zhang, J. Xue, C. Lan, W. Zeng, Z. Gao and N. Zheng, Eleatt-rnn: adding attentiveness to neurons in recurrent neural networks, IEEE Transactions on Image Processing, 29, 1061-1073, 2019. https://doi.org/ 10.1109/TIP.2019.2937724.
  • CIFAR-10 and CIFAR-100, https://yann.lecun.com/exdb/MNIST/ (10. 05.2023)
  • H. Xiao, R. Kashif and R.Vollgraf, Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747, 2017.
  • MNIST and Fashion MNIST, https://www.cs.toronto.edu/~kriz/cifar.html (10. 05.2023)

A new Convolutional Neural Network proposal for classifying various images

Yıl 2024, Cilt: 13 Sayı: 1, 262 - 278, 15.01.2024
https://doi.org/10.28948/ngumuh.1355726

Öz

Nowadays, deep learning methods are widely used in many fields such as robotics, sound processing, medicine and imagery. In this study, studies on image classification and analysis in the literature were examined in detail. In addition, performance analyzes of deep learning methods were carried out using CNN on 4 different data sets named MNIST, Fashion MNIST, CIFAR-10 and CIFAR-100. The structures of the created deep learning models, the parameter values used for training, the layers used, the complexity matrices obtained for the validation data, accuracy and loss graphs are shown in detail. Our study was carried out with a different network structure consisting of 3 convolution layers, 3 batch normalization layers, 2 maxpooling layers, 1 flatten, 2 droupout, 2 dense layers. In addition, the performance of image classification on different data has been increased with our proposed model. At the end of the test, the accuracy results of our study were compared according to various evaluation metrics. For all the data sets used, the best and worst images were determined. With the proposed CNN model, high accuracy rates were observed for MNIST and Fashion MNIST datasets, with these values being 99.22% and 99.21%, respectively.

Kaynakça

  • E. Moen, D. Bannon, T. Kudo, W. Graf, M. Covert and D.Valen, Deep learning for cellular image analysis, Nature Metots, 16(12), 1233-1246, 2019.
  • F. Cevik, Z. Kilimci, Derin öğrenme yöntemleri ve kelime yerleştirme modelleri kullanılarak Parkinson hastalığının duygu analiziyle değerlendirilmesi, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 27(2), 151-161, 2020. https:// doi: 10.5505/pajes.2020.74429.
  • Z. Pekoz and T. İnkaya, Derin öğrenme ile talep tahmini: Bir üçüncü parti lojistik firması için covid-19 döneminde vaka analizi, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 1000(1000), 1-8, 2022. https:// doi: 10.5505/pajes.2022.73537.
  • T. Karahan and V. Nabiyev, Plant identification with convolutional neural networks and transfer learning, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 27(5), 638-645, 2021. https:// doi: 10.5505/pajes.2020.84042.
  • O. Abouelnaga and H. Ali, Cifar-10: knn-based ensemble of classifiers, 2016 International Conference on Computational Science and Computational Intelligence, Las Vegas, Nevada, USA, 15-17 December 2016.
  • G. Tushar, Comparative study of various convolutional neural networks on cifar-10, International Journal for Modern Trends in Science and Technology, 6(12), 402-406, 2020.
  • H. Tien, Cifar-10 to compare visual recognition performance between deep neural networks and humans. arXiv, abs/1811.07270, 2018.
  • R. Ju, Y. Lin and T. Jian, Efficient convolutional neural networks on raspberry pi for image classification, Journal of Real-Time Image Processing, 20(2), 1-9, 2023. https://doi.org/10.1007/s11554-023-01271-1
  • A.Yahya, K. Liu, A. Hawbani and Y. Wang, A novel image classification metot based on residual network. Inception, and Proposed Activation Function. Sensors, 23(6), 2976, 2023. https:// /doi.org/10.3390/s23062976.
  • X. Zhao, P. Huang P and H. Shu, Wavelet-attention CNN for image classification, Multimedia Systems, 28(3), 915-924, 2022. https://doi.org/ 0.1007/s00530-022-00889-8.
  • K. Zhang, Y. X. Guo, J. Yuan and Q. Ding, Multiple feature reweight densenet for image classification, IEEE Access, 7, 9872-9880, 2019. https:// /doi.org/ 10.1109/ACCESS.2018.2890127.
  • H. Shao, E. Ma, M. Zhu, X. Deng, S. Zhai, Mnist handwritten digit classification based on convolutional neural network with hyperparameter optimization, Intelligent Automation & Soft Computing, 36(3), 2023. https://doi.org/ 10.32604/iasc.2023.036323.
  • E. Plesovskaya and S. Ivanov, Hierarchical classification on the mnist dataset using truncated svd and kernel density estimation, Procedia Computer Science, 212, 368-377, 2022.
  • Y. Pei and L.Ye, Cluster analysis of mnist data set, In Journal of Physics: Conference Series, 2181(1), 12-12, 2022. https://doi.org/10.1088/1742-6596/2181/1/012035.
  • A. Henrique, Classifying garments from fashion-mnist dataset through CNNs, Journal Advances in Science Technology and Engineering Systems, 6(1), 989-994, 2021. https://doi.org/ 10.25046/aj0601109.
  • Ş. Öztürk, Moda görseli sınıflandırma: düzenleyici teknikler ile evrişimsel sinir ağları uygulaması, Bilgisayar Bilimleri ve Mühendisliği Dergisi, 15(1), 66-76, 2022.https://doi.org/ 10.54525/tbbmd.1077432.
  • S. Bhatnagar, D. Ghosal and MH. Kolekar, Classification of fashion article images using convolutional neural networks. Fourth International Conference on Image Information Processing, 357-362, India, 21-23 December 2017.
  • K. Meshkini, J. Platos and H. Ghassemain, An analysis of convolutional neural network for fashion images classification (fashion-mnist). International Conference on Intelligent Information Technologies for Industry, 85-95, Ostrava–Prague, Czech Republic, 2–7 December 2019.
  • K. Greeshma and K. Sreekumar, Hyperparameter optimization and regularization on fashion-mnist classification, International Journal of Recent Technology and Engineering, 8(2), 3713-3719, 2019.https://doi.org/ 10.35940/ijrte.B3092.078219.
  • M. Kayed, A. Anter and H. Mohamed, Classification of garments from fashion mnist dataset using cnn lenet-5 architecture. International Conference on Innovative Trends in Communication and Computer Engineering, 238-243, Aswan, Egypt, 8-9 February 2020.
  • T. Hur, L. Kim and D. Park, Quantum convolutional neural network for classical data classification, Quantum Machine Intelligence, 4(3), 1-18, (2022). https://doi.org/10.1007/s42484-021-00061-x.
  • Y. Seo and K. Shin, Hierarchical convolutional neural networks for fashion image classification, Expert Systems with Applications, 116, 328-339, 2019. https://doi.org/ 10.1016/j.eswa.2018.09.022.
  • OM. Khanday, S. Dadvandipour S and MA. Lone, Effect of filter sizes on image classification in cnn: a case study on cfar10 and fashion-mnist datasets, International Journal of Artificial Intelligence, 10(4), 872-878, 2021. https:// doi: 10.11591/ijai.v10.i4.pp872-878 .
  • O. Nocentini, J. Kim and F. Cavallo, İmage classification using multiple convolutional neural networks on the fashion-mnist dataset, Sensors, 22(23), 9544, 2022. https:// doi: 10.3390/s22239544 .
  • A. Vijayaraj, V. Raj and R. Dhanagopal, Deep learning image classification for fashion design, Wireless Communications and Mobile Computing, 2022, 1-10, 2022. https://doi.org/ 10.1155/2022/7549397.
  • AC. Cleber, A novel multi-objective grammar-based framework for the generation of convolutional neural networks, Expert Systems With Applications, 212, 2023. https://doi.org/ 10.1016/j.eswa.2022.118670.
  • R. Elyas, A. Akbari and B. Nasersharif, Uncertainty handling in convolutional neural networks. Neural Computing and Applications, 34, 16753-16769, 2022. https://doi.org/ 10.1007/s00521-022-07313-2.
  • O. Güler and İ. Yücedağ, Hand gesture recognition from 2d images by using convolutional capsule neural networks, Arabian Journal for Science and Engineering, 47, 1211-1225, 2022. https://doi.org/ 10.1007/s13369-021-05867-2.
  • G. Ryu and D. Choi, A hybrid adversarial training for deep learning model and denoising network resistant to adversarial examples, Applied Intelligence, 53, 1-14, 2022.
  • AT. Silva and RS. Siebert, Densenet-dc: optimizing densenet parameters through feature map generation control, Revista de Informática Teórica e Aplicada, 27, 25-39, 2020.
  • F. Assunção, N. Lourenço and P. Machado, Denser: deep evolutionary network structured representation, Genetic Programming and Evolvable Machines, 20, 5-35, 2019.
  • AM. Hafiz, RA. Bhat RA and M. Hassaballah, Image classification using convolutional neural network tree ensembles, Multimedia Tools and Applications, 82(5), 6867-6884, 2023. https://doi.org/ 10.1007/s11042-022-13604-6.
  • H. Gürkan ve A. Hanilçi, Evrişimsel sinir ağı ve qrs imgeleri kullanarak ekg tabanlı biyometrik tanıma yöntemi, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 26(2), 318-327, 2020.
  • P. Shinde ve S. Shah, A review of machine learning and deep learning applications, 2018 Fourth International Conference on Computing Communication Control and Automation (ICCUBEA), Pune, India, 16-18 August 2018.
  • G. Ciaburro and B. Venkateswaran, Neural Networks with R: Smart Models using CNN, RNN, Deep Learning, and Artificial Intelligence Principles, Packt Publishing Ltd, Birmingham, 2017.
  • M. Khishe and A. Safari, Classification of sonar targets using an mlp neural network trained by dragonfly algorithm, Wireless Personal Communications, 108(4), 2241-2260, 2019. https://doi.org/ 10.1007/s11277-019-06520-w.
  • P. Zhang, J. Xue, C. Lan, W. Zeng, Z. Gao and N. Zheng, Eleatt-rnn: adding attentiveness to neurons in recurrent neural networks, IEEE Transactions on Image Processing, 29, 1061-1073, 2019. https://doi.org/ 10.1109/TIP.2019.2937724.
  • CIFAR-10 and CIFAR-100, https://yann.lecun.com/exdb/MNIST/ (10. 05.2023)
  • H. Xiao, R. Kashif and R.Vollgraf, Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747, 2017.
  • MNIST and Fashion MNIST, https://www.cs.toronto.edu/~kriz/cifar.html (10. 05.2023)
Toplam 40 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Derin Öğrenme
Bölüm Araştırma Makaleleri
Yazarlar

Yeşim Tiraki 0000-0001-5330-8656

Hasan Temurtaş 0000-0001-6738-3024

Soydan Serttaş 0000-0001-8887-8675

Çiğdem Bakır 0000-0001-8482-2412

Erken Görünüm Tarihi 3 Ocak 2024
Yayımlanma Tarihi 15 Ocak 2024
Gönderilme Tarihi 5 Eylül 2023
Kabul Tarihi 4 Aralık 2023
Yayımlandığı Sayı Yıl 2024 Cilt: 13 Sayı: 1

Kaynak Göster

APA Tiraki, Y., Temurtaş, H., Serttaş, S., Bakır, Ç. (2024). Çeşitli görüntülerin sınıflandırılması için yeni bir Evrişimsel Sinir Ağı önerisi. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 13(1), 262-278. https://doi.org/10.28948/ngumuh.1355726
AMA Tiraki Y, Temurtaş H, Serttaş S, Bakır Ç. Çeşitli görüntülerin sınıflandırılması için yeni bir Evrişimsel Sinir Ağı önerisi. NÖHÜ Müh. Bilim. Derg. Ocak 2024;13(1):262-278. doi:10.28948/ngumuh.1355726
Chicago Tiraki, Yeşim, Hasan Temurtaş, Soydan Serttaş, ve Çiğdem Bakır. “Çeşitli görüntülerin sınıflandırılması için Yeni Bir Evrişimsel Sinir Ağı önerisi”. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi 13, sy. 1 (Ocak 2024): 262-78. https://doi.org/10.28948/ngumuh.1355726.
EndNote Tiraki Y, Temurtaş H, Serttaş S, Bakır Ç (01 Ocak 2024) Çeşitli görüntülerin sınıflandırılması için yeni bir Evrişimsel Sinir Ağı önerisi. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi 13 1 262–278.
IEEE Y. Tiraki, H. Temurtaş, S. Serttaş, ve Ç. Bakır, “Çeşitli görüntülerin sınıflandırılması için yeni bir Evrişimsel Sinir Ağı önerisi”, NÖHÜ Müh. Bilim. Derg., c. 13, sy. 1, ss. 262–278, 2024, doi: 10.28948/ngumuh.1355726.
ISNAD Tiraki, Yeşim vd. “Çeşitli görüntülerin sınıflandırılması için Yeni Bir Evrişimsel Sinir Ağı önerisi”. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi 13/1 (Ocak 2024), 262-278. https://doi.org/10.28948/ngumuh.1355726.
JAMA Tiraki Y, Temurtaş H, Serttaş S, Bakır Ç. Çeşitli görüntülerin sınıflandırılması için yeni bir Evrişimsel Sinir Ağı önerisi. NÖHÜ Müh. Bilim. Derg. 2024;13:262–278.
MLA Tiraki, Yeşim vd. “Çeşitli görüntülerin sınıflandırılması için Yeni Bir Evrişimsel Sinir Ağı önerisi”. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, c. 13, sy. 1, 2024, ss. 262-78, doi:10.28948/ngumuh.1355726.
Vancouver Tiraki Y, Temurtaş H, Serttaş S, Bakır Ç. Çeşitli görüntülerin sınıflandırılması için yeni bir Evrişimsel Sinir Ağı önerisi. NÖHÜ Müh. Bilim. Derg. 2024;13(1):262-78.

download