Araştırma Makalesi
BibTex RIS Kaynak Göster

Dikkat Modülleri ile Oluşturulmuş Derin Öğrenme Modelini Kullanarak Pamuk Hastalığının Tespiti

Yıl 2021, Cilt: 36 Sayı: 3, 659 - 668, 30.09.2021
https://doi.org/10.21605/cukurovaumfd.1005343

Öz

Pamuk, dünya genelinde önemli bir endüstri sektörü olup, tarıma dayalı ülkelerde ekonomik kalkınmanın en önemli faktörlerinden biridir. Ülkemiz, pamuk tarımına elverişli ülkeler arasında yer almaktadır ve genelde Akdeniz ile Güneydoğu Anadolu bölgesinde pamuk üretimi gerçekleştirilmektedir. Pamuk bitkisinden iç ve dış etmenlerden kaynaklı birçok hastalık görülebilmektedir. Araştırmacılar, pamuk hastalığının tespitini gerçekleştirmek ve verimli bir üretim elde edebilmek için son zamanlarda yapay zekâ tabanlı çalışmalara odaklanmışlardır. Bu çalışmada kullanılan veri kümesi; hastalıklı pamuk yaprağı, hastalıklı pamuk bitkisi, sağlam pamuk yaprağı ve sağlam pamuk bitki görüntülerinden oluşmaktadır. Önerilen yaklaşımda, veri büyütme tekniği ile dikkat modüllerinden oluşan derin öğrenme modeli birlikte kullanılmıştır. Çalışmanın analizlerinde, Olasılıksal Dereceli Azalma (ODA) ve Uyarlanabilir Moment Tahmini (UMT) optimizasyon yöntemleri kullanılmıştır. Sınıflandırma sürecinde elde edilen en iyi genel doğruluk başarısı %96,56 olmuştur.

Kaynakça

  • 1. Chohan, S., Perveen, R., Abid, M., Tahir, M.N., Sajid, M., 2020. Cotton Diseases and Their Management BT-Cotton Production and Uses: Agronomy. Crop Protection, and Postharvest Technologies. In: Ahmad S, Hasanuzzaman M (eds). Springer Singapore, Singapore, 239–270.
  • 2. Eski, Ö., Kayalak, S., 2018. Türkiye’de Pamuk Üretimi için Bir Öngörü Modeli: Var Yaklaşımı. ÇOMÜ Ziraat Fakültesi Dergisi, 6, 131–137. https://doi.org/10.33202/comuagri.503960.
  • 3. 2019 Pamuk Bülteni, https://www.tarimorman.gov.tr, Erişim Tarihi: 09.08.2020.
  • 4. Çoban, M., Çiçek, S., Küçüktaban, F., Yazıcı, L., Çiftçi, H., 2016. Bazı Pamuk Melezlerinin Verim ve Lif Kalite Özelliklerinin İncelenmesi. Tarla Bitkileri Merkezi Araştırma Enstitüsü Dergisi, 25(2), 112–112. https://doi.org/10.21566/tarbitderg.281873.
  • 5. Çopur, O., 2018. GAP Projesinin Türkiye Pamuk Üretimine Etkisi: Son On Yıldaki Değişimler. Adyütayam, 6(1), 11–18.
  • 6. Çelik, İ., Soysal, M., İnan, Ö., Çetinkaya, M., 2010. Antalya Bölgesinde Pamuk Solgunluk Hastalığı (Verticillium dahliae) Surveyi. Batı Akdeniz Tarımsal Araştırma Enstitüsü Derim Dergisi, 27(1), 18–32.
  • 7. Sakçı, N., Sağır, A., Temiz, M.G., 2017. Pamukta Solgunluk Hastalığı (Verticillium Dahliae Kleb.)’nın Tohumun İçeriğine Etkisinin Belirlenmesi. Bitki Koruma Bülteni, 57(1),1-11. https://doi.org/10.16955/bitkorb.299002.
  • 8. Ferro, H.M., Souza, R.M., Lelis, F.M.V., Silva, J.C.P., Medeiros, F.H.V.D., 2020. Bacteria for Cotton Plant Protection: Disease Control Crop Yield and Fiber Quality. Rev Caatinga 33(1), 43–53.
  • 9. Shah, N., Jain, S., 2019. Detection of Disease in Cotton Leaf using Artificial Neural Network. In: 2019 Amity International Conference on Artificial Intelligence, 473–476.
  • 10.Chowdhary, K.N., Nithin, Y.M., Srikanta, P., Rekha, B.S., 2018. A Machine Learning Approach for Detection of Cotton Leaf Disease. Int. J. Sci. Res. Dev., 6(3), 1902–1905.
  • 11. Pechuho, N., Khan, Q., Kalwar, S., 2020. Cotton Crop Disease Detection using Machine Learning via Tensorflow. Pakistan J. Eng. Technol., SI(1), 126-130.
  • 12. Gulhane, V.A., Gurjar, A.A., 2011. Detection of Diseases on Cotton Leaves and its Possible Diagnosis. Int J Image, 5(5), 590–598.
  • 13.Bhoi, J., 2020. Cotton Disease Dataset. In: Kaggle.https://www.kaggle.com/janmejaybhoi/ cotton-disease-dataset. Accessed 29 Oct 2020.
  • 14. Shorten, C., Khoshgoftaar, T.M., 2019. A Survey on Image Data Augmentation for Deep Learning. J. Big Data, 6(60), 1-48. https://doi.org/10.1186/s40537-019-0197-0
  • 15. Sun, S., Cao, Z., Zhu, H., Zhao, J., 2020. A Survey of Optimization Methods from a Machine Learning Perspective. IEEE Trans Cybern, 50, 3668–3681. https://doi.org/10.1109/tcyb.2019.2950779
  • 16. Kennedy, R.K.L., Khoshgoftaar, T.M., Villanustre, F., Humphrey, T., 2019. A Parallel and Distributed Stochastic Gradient Descent Implementation Using Commodity Clusters. J. Big Data, 6(16) 1-23. https://doi.org/10.1186/s40537-019-0179-2.
  • 17. Kumar, A., Sarkar, S., Pradhan, C., 2020. Malaria Disease Detection Using CNN Technique with SGD, RMSprop and ADAM Optimizers. In: Journal of Ambient Intelligenceand Humanized Computing, 211–230.
  • 18. Zhong, H., Chen, Z., Qin, C., Huang, Z., Zheng, V.W., Xu, T., Chen, E., 2020. Adam Revisited: A Weighted Past Gradients Perspective. Front Comput Sci, 14(5), 145309. https://doi.org/10.1007/s11704-019-8457-x.
  • 19.Chauhan, K., 2020. CNN-Attention: An Imagen Classifier with Attention Layers Visualized. In: GitHub.https://github.com/kapilnchauhan77/CNN-Attention. Accessed 31 Oct 2020.
  • 20. Suárez-Paniagua, V., Segura-Bedmar, I., 2018. Evaluation of Pooling Operations in Convolutional Architectures for Drug-drug Interaction Extraction. BMC Bioinformatics 19, 209. https://doi.org/10.1186/s12859-018-2195-1.
  • 21.Jiang, X., Lu, M., Wang, S.H., 2020. An Eight-layer Convolutional Neural Network with Stochastic Pooling, Batch Normalization and Dropout for Fingerspelling Recognition of Chinese Sign Language. Multimed Tools Appl 79, 15697–15715. https://doi.org/10.1007/s11042-019-08345-y.
  • 22. Yang, Y., Wu, Q.M.J., Feng, X., Akilan, T., 2020. Recomputation of the Dense Layers for Performance Improvement of DCNN. IEEE Trans Pattern Anal Mach Intell, 42, 2912–2925. https://doi.org/10.1109/tpami.2019.2917685
  • 23. Luo, Y., Wong, Y., Kankanhalli, M., Zhao, Q., 2020. Softmax: Improving Intraclass Compactness and Interclass Separability of Features. IEEE Trans Neural Networks Learn Syst, 31, 685–699. https://doi.org/10.1109/tnnls.2019.2909737
  • 24.Bello, I., Zoph, B., Le, Q.V., Vaswani, A., Shlens, J., 2019. Attention Augmented Convolutional Networks. Proc IEEE Int Conf Comput Vis 2019-Octob: 3286–3295. https://doi.org/10.1109/ICCV.2019.00338.
  • 25. Gadekallu, T.R., Khare, N., Bhattacharya, S., Singh, S., Maddikunta, P.K.R., Srivastava, G., 2020. Deep Neural Networks to Predict Diabetic Retinopathy. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-01963-7.
  • 26.Chicco, D., Jurman, G., 2020. The Advantages of the Matthews Correlation Coefficient (MCC) Over F1 Score and Accuracy in Binary Classification Evaluation. BMC Genomics, 21, 6. https://doi.org/10.1186/s12864-019-6413-7.
  • 27. Kandel, I., Castelli, M., 2020. The Effect of Batch Size on the Generalizability of the Convolutional Neural Networks on a Histopathology Dataset, ICT Express. https://doi.org/https://doi.org/10.1016/j.icte.2020.04.010

Detection of Cotton Disease Using Deep Learning Model Created with Attention Modules

Yıl 2021, Cilt: 36 Sayı: 3, 659 - 668, 30.09.2021
https://doi.org/10.21605/cukurovaumfd.1005343

Öz

Cotton is an important industrial sector worldwide and is one of the most important factors of economic development in countries based on agriculture. Our country is among the countries that are suitable for cotton agriculture and cotton production is generally carried out in the Mediterranean and Southeast Anatolia. Many diseases caused by internal and external factors can be seen in cotton plants. Researchers have recently focused on artificial intelligence-based studies to detect cotton disease and achieve efficient production. The dataset used in this study; it consists of diseased cotton leaf, diseased cotton plant, fresh cotton leaf and disease fresh plant images. In the proposed approach, the data augmentation technique and the deep learning model consisting of attention modules are used together. Stochastic Gradient Descent (SGD) and Adaptive Moment Estimation (ADAM) optimization methods were used in the analysis of the study. The best overall accuracy success achieved in the classification process was 96.56%.

Kaynakça

  • 1. Chohan, S., Perveen, R., Abid, M., Tahir, M.N., Sajid, M., 2020. Cotton Diseases and Their Management BT-Cotton Production and Uses: Agronomy. Crop Protection, and Postharvest Technologies. In: Ahmad S, Hasanuzzaman M (eds). Springer Singapore, Singapore, 239–270.
  • 2. Eski, Ö., Kayalak, S., 2018. Türkiye’de Pamuk Üretimi için Bir Öngörü Modeli: Var Yaklaşımı. ÇOMÜ Ziraat Fakültesi Dergisi, 6, 131–137. https://doi.org/10.33202/comuagri.503960.
  • 3. 2019 Pamuk Bülteni, https://www.tarimorman.gov.tr, Erişim Tarihi: 09.08.2020.
  • 4. Çoban, M., Çiçek, S., Küçüktaban, F., Yazıcı, L., Çiftçi, H., 2016. Bazı Pamuk Melezlerinin Verim ve Lif Kalite Özelliklerinin İncelenmesi. Tarla Bitkileri Merkezi Araştırma Enstitüsü Dergisi, 25(2), 112–112. https://doi.org/10.21566/tarbitderg.281873.
  • 5. Çopur, O., 2018. GAP Projesinin Türkiye Pamuk Üretimine Etkisi: Son On Yıldaki Değişimler. Adyütayam, 6(1), 11–18.
  • 6. Çelik, İ., Soysal, M., İnan, Ö., Çetinkaya, M., 2010. Antalya Bölgesinde Pamuk Solgunluk Hastalığı (Verticillium dahliae) Surveyi. Batı Akdeniz Tarımsal Araştırma Enstitüsü Derim Dergisi, 27(1), 18–32.
  • 7. Sakçı, N., Sağır, A., Temiz, M.G., 2017. Pamukta Solgunluk Hastalığı (Verticillium Dahliae Kleb.)’nın Tohumun İçeriğine Etkisinin Belirlenmesi. Bitki Koruma Bülteni, 57(1),1-11. https://doi.org/10.16955/bitkorb.299002.
  • 8. Ferro, H.M., Souza, R.M., Lelis, F.M.V., Silva, J.C.P., Medeiros, F.H.V.D., 2020. Bacteria for Cotton Plant Protection: Disease Control Crop Yield and Fiber Quality. Rev Caatinga 33(1), 43–53.
  • 9. Shah, N., Jain, S., 2019. Detection of Disease in Cotton Leaf using Artificial Neural Network. In: 2019 Amity International Conference on Artificial Intelligence, 473–476.
  • 10.Chowdhary, K.N., Nithin, Y.M., Srikanta, P., Rekha, B.S., 2018. A Machine Learning Approach for Detection of Cotton Leaf Disease. Int. J. Sci. Res. Dev., 6(3), 1902–1905.
  • 11. Pechuho, N., Khan, Q., Kalwar, S., 2020. Cotton Crop Disease Detection using Machine Learning via Tensorflow. Pakistan J. Eng. Technol., SI(1), 126-130.
  • 12. Gulhane, V.A., Gurjar, A.A., 2011. Detection of Diseases on Cotton Leaves and its Possible Diagnosis. Int J Image, 5(5), 590–598.
  • 13.Bhoi, J., 2020. Cotton Disease Dataset. In: Kaggle.https://www.kaggle.com/janmejaybhoi/ cotton-disease-dataset. Accessed 29 Oct 2020.
  • 14. Shorten, C., Khoshgoftaar, T.M., 2019. A Survey on Image Data Augmentation for Deep Learning. J. Big Data, 6(60), 1-48. https://doi.org/10.1186/s40537-019-0197-0
  • 15. Sun, S., Cao, Z., Zhu, H., Zhao, J., 2020. A Survey of Optimization Methods from a Machine Learning Perspective. IEEE Trans Cybern, 50, 3668–3681. https://doi.org/10.1109/tcyb.2019.2950779
  • 16. Kennedy, R.K.L., Khoshgoftaar, T.M., Villanustre, F., Humphrey, T., 2019. A Parallel and Distributed Stochastic Gradient Descent Implementation Using Commodity Clusters. J. Big Data, 6(16) 1-23. https://doi.org/10.1186/s40537-019-0179-2.
  • 17. Kumar, A., Sarkar, S., Pradhan, C., 2020. Malaria Disease Detection Using CNN Technique with SGD, RMSprop and ADAM Optimizers. In: Journal of Ambient Intelligenceand Humanized Computing, 211–230.
  • 18. Zhong, H., Chen, Z., Qin, C., Huang, Z., Zheng, V.W., Xu, T., Chen, E., 2020. Adam Revisited: A Weighted Past Gradients Perspective. Front Comput Sci, 14(5), 145309. https://doi.org/10.1007/s11704-019-8457-x.
  • 19.Chauhan, K., 2020. CNN-Attention: An Imagen Classifier with Attention Layers Visualized. In: GitHub.https://github.com/kapilnchauhan77/CNN-Attention. Accessed 31 Oct 2020.
  • 20. Suárez-Paniagua, V., Segura-Bedmar, I., 2018. Evaluation of Pooling Operations in Convolutional Architectures for Drug-drug Interaction Extraction. BMC Bioinformatics 19, 209. https://doi.org/10.1186/s12859-018-2195-1.
  • 21.Jiang, X., Lu, M., Wang, S.H., 2020. An Eight-layer Convolutional Neural Network with Stochastic Pooling, Batch Normalization and Dropout for Fingerspelling Recognition of Chinese Sign Language. Multimed Tools Appl 79, 15697–15715. https://doi.org/10.1007/s11042-019-08345-y.
  • 22. Yang, Y., Wu, Q.M.J., Feng, X., Akilan, T., 2020. Recomputation of the Dense Layers for Performance Improvement of DCNN. IEEE Trans Pattern Anal Mach Intell, 42, 2912–2925. https://doi.org/10.1109/tpami.2019.2917685
  • 23. Luo, Y., Wong, Y., Kankanhalli, M., Zhao, Q., 2020. Softmax: Improving Intraclass Compactness and Interclass Separability of Features. IEEE Trans Neural Networks Learn Syst, 31, 685–699. https://doi.org/10.1109/tnnls.2019.2909737
  • 24.Bello, I., Zoph, B., Le, Q.V., Vaswani, A., Shlens, J., 2019. Attention Augmented Convolutional Networks. Proc IEEE Int Conf Comput Vis 2019-Octob: 3286–3295. https://doi.org/10.1109/ICCV.2019.00338.
  • 25. Gadekallu, T.R., Khare, N., Bhattacharya, S., Singh, S., Maddikunta, P.K.R., Srivastava, G., 2020. Deep Neural Networks to Predict Diabetic Retinopathy. J Ambient Intell Humaniz Comput. https://doi.org/10.1007/s12652-020-01963-7.
  • 26.Chicco, D., Jurman, G., 2020. The Advantages of the Matthews Correlation Coefficient (MCC) Over F1 Score and Accuracy in Binary Classification Evaluation. BMC Genomics, 21, 6. https://doi.org/10.1186/s12864-019-6413-7.
  • 27. Kandel, I., Castelli, M., 2020. The Effect of Batch Size on the Generalizability of the Convolutional Neural Networks on a Histopathology Dataset, ICT Express. https://doi.org/https://doi.org/10.1016/j.icte.2020.04.010
Toplam 27 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Mühendislik
Bölüm Makaleler
Yazarlar

Mesut Toğaçar Bu kişi benim 0000-0002-8264-3899

Yayımlanma Tarihi 30 Eylül 2021
Yayımlandığı Sayı Yıl 2021 Cilt: 36 Sayı: 3

Kaynak Göster

APA Toğaçar, M. (2021). Dikkat Modülleri ile Oluşturulmuş Derin Öğrenme Modelini Kullanarak Pamuk Hastalığının Tespiti. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 36(3), 659-668. https://doi.org/10.21605/cukurovaumfd.1005343