Araştırma Makalesi
BibTex RIS Kaynak Göster

Derin Öğrenme Modelleri ve Veri Ön İşleme Yöntemleri ile Çeltik Yaprak Hastalıklarının Erken Teşhisi

Yıl 2023, , 807 - 817, 18.10.2023
https://doi.org/10.21605/cukurovaumfd.1377763

Öz

Son yıllarda tarım sektöründe, derin öğrenme temelli bilgisayar destekli sistemler büyük bir önem kazanmış ve farklı uygulama alanlarında etkili bir rol oynamıştır. Bu sistemler sadece hastalıkların erken teşhisine katkı sağlamakla kalmamış, aynı zamanda tarım profesyonellerine önemli bir destek sunmuştur. Bu bağlamda, bu çalışma çeltik yapraklarında mevcut hastalıkların erken teşhisinde derin öğrenme yöntemlerinin etkinliğini araştırmayı amaçlamaktadır. Bu araştırma için, 13 farklı çeltik hastalığına ait toplam 4160 görüntü içeren Paddy Doctor veri kümesi kullanılmıştır. Veri kümesi üzerinde beş farklı transfer öğrenme modeli titizlikle değerlendirilmiştir. Elde edilen sonuçlar, Xception modelinin %93,37'lik doğruluk oranı ile en üstün performansı gösterdiğini açıkça ortaya koymaktadır. Ayrıca, bu çalışma veri ön işleme ve veri artırma tekniklerini optimize etme konusuna da değinerek veri kümesini zenginleştirmeyi ve teşhis doğruluğunu artırmayı amaçlamıştır. Başarılı bulunan modelin çeltik yaprak hastalıklarını teşhis etmedeki performansı ayrıntılı bir şekilde değerlendirilmiştir. Bu değerlendirme sonucunda, modelin en başarılı olduğu hastalık sınıfları belirlenmiş ve aynı şekilde modelin en zorlandığı veya en düşük doğruluk oranına sahip hastalık sınıfları da tespit edilmiştir. Bu bulgular, çeltik hastalıklarının erken teşhisinde transfer öğrenme modellerinin potansiyelini vurgulayarak tarım sektöründe etkili otomatik teşhis sistemlerinin geliştirilmesine olanak tanımaktadır. Bu yaklaşım, tarım sektöründe mahsul verimini artırma ve pestisit kullanımını azaltma yolunda umut vadetmektedir. Ayrıca, daha sağlıklı ve sürdürülebilir tarım uygulamalarını teşvik etme odaklı bu araştırma, gelecekteki stratejilere de katkı sağlayabilir.

Kaynakça

  • 1. T.C. Tarım ve Orman Bakanlığı Yayınları, 2007. Çeltik Hastalık ve Zararlıları ile Mücadele, https://www.tarimorman.gov.tr/ GKGM/Belgeler/Uretici_Bilgi_Kosesi/Dokumanlar/celtik.pdf Erişim Tarihi: 16.05.2023, Ankara.
  • 2. Taşlıgil, N., Şahin, G., 2011. Türkiye’de Çeltik (Oryza Sativa L.) Yetiştiriciliği ve Coğrafi Dağılımı. Adıyaman Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 4(6), 182-204.
  • 3. Amritha, H., Jeena, T., Ebin D,R., 2023. Deep Learning System for Paddy Plant Disease Detection and Classification. Environmental Monitoring and Assessment, 195, 1(2023),1–28.
  • 4. Leelavathy, B., Rao Kovvur, R.M., 2020. Prediction of Biotic Stress in Paddy Crop Using Deep Convolutional Neural Networks. In Proceedings of International Conference on Computational Intelligence and Data Engineering. Springer Singapore, 337-346.
  • 5. Shrivastava, V.K., Pradhan, M.K., Minz, S., Thakur, M.P., 2019. Rice Plant Pisease Classification Using Transfer Learning of Deep Convolution Neural Network. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences XLII-3/W6 (July 2019), 631-635.
  • 6. Ramesh, S., Vydeki, D., 2020. Recognition and Classification of Paddy Leaf Diseases Using Optimized Deep Neural Network with Jaya Algorithm. Information Processing in Agriculture, 7(2), 249-260.
  • 7. Bhagawati, R., Bhagawati, K., Singh, A.K.K., Nongthombam, R., Sarmah, R., Bhagawati, G., 2015. Artificial Neural Network Assisted Weather Based Plant Disease Forecasting System. International Journal on Recent and Innovation Trends in Computing and Communication, 3(6), 4168-4173.
  • 8. Lu, R., 2004. Multispectral Imaging for Predicting Firmness and Soluble Solids Content of Apple Fruit. Postharvest Biology and Technology, 31(2), 147-157.
  • 9. Prajapati, H.B., Shah, J.P., Dabhi, V.K., 2017. Detection and Classification of Rice Plant Diseases. Intelligent Decision Technologies, 11(3), 357-373.
  • 10. Rahman, C.R., Arko, P.S., Ali, M.E., Iqbal Khan, M.A., Apon, S.H., Nowrin, F., Wasif, A., 2020. Identification and Recognition of Rice Diseases and Pests using Convolutional Neural Networks. Biosystems Engineering, 194, 112-120.
  • 11. Lu, Y., Yi, S., Zeng, N., Liu, Y., Zhang, Y., 2017. Identification of Rice Diseases using Deep Convolutional Neural Networks. Neurocomputing, 267, 378-384.
  • 12. Ökten, İ., Yüzgeç, U., 2022. Evrişimli Sinir Ağı ile Çeltik Bitkisi Hastalığının Tespiti. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 11(1), 203-217.
  • 13. Kılıç, Ş., Doğan, Y. 2023. Deep Learning Based Gender Identification using Ear Images. Traitement du Signal, 40(4).
  • 14. Dogan, Y., 2023. A New Global Pooling Method for Deep Neural Networks: Global Average of Top-K Max-Pooling. Traitement du Signal, 40(2).
  • 15. Dogan, Y., Atas, M., Özdemir, C., 2014. A New Approach for Plotting Raster Based Image Files. In 2014 22nd Signal Processing and Communications Applications Conference (SIU), 1027-1030. IEEE.
  • 16. Özdemi̇r, C., Ataş, M., Özer, A.B., 2013. Classification of Turkish Spam E-Mails with Artificial Immune System. In 2013 21st Signal Processing and Communications Applications Conference (SIU), 1-4. IEEE.
  • 17. Kılıç, Ş., Kaya, Y., Askerbeyli, İ., 2021. A New Approach for Human Recognition Through Wearable Sensor Signals. Arabian Journal for Science and Engineering, 46, 4175-4189.
  • 18. Petchiammal, A., Briskline Kiruba, S., Murugan, D., Pandarasamy, Arjunan., 2022. Paddy Doctor: A Visual Image Dataset for Automated Paddy Disease Classification and Benchmarking. IEEE Dataport.
  • 19. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z., 2016. Rethinking the Inception Architecture for Computer Vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818-2826.
  • 20. He, K., Zhang, X., Ren, S., Sun, J., 2016. Identity Mappings in Deep Residual Networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part IV 14, 630-645. Springer International Publishing.
  • 21. Chollet, F., 2017. Xception: Deep Learning with Depthwise Separable Convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1251-1258.
  • 22. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C., 2018. Mobilenetv2: Inverted Residuals and Linear Bottlenecks. In Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition, 4510-4520.
  • 23. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q., 2017. Densely Connected Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4700-4708).

Early Diagnosis of Paddy Leaf Diseases using Deep Learning Models and Data Preprocessing Techniques

Yıl 2023, , 807 - 817, 18.10.2023
https://doi.org/10.21605/cukurovaumfd.1377763

Öz

In recent years, deep learning-based computer-aided systems have gained significant importance in the agriculture sector and have played an effective role in various application areas. These systems have not only contributed to the early diagnosis of diseases but have also provided crucial support to agricultural professionals. In this context, this study aims to investigate the effectiveness of deep learning methods in the early diagnosis of rice leaf diseases. For this research, the Paddy Doctor dataset, comprising a total of 4160 images from 13 different rice diseases, was utilized. Five different transfer learning models were meticulously evaluated on the dataset. The results clearly indicate that the Xception model achieved the highest performance with an accuracy rate of 93.37%. Additionally, this study aimed to enrich the dataset and improve diagnostic accuracy by optimizing data preprocessing and augmentation techniques. The performance of the successful model in diagnosing rice leaf diseases was thoroughly assessed. Through this evaluation, disease categories in which the model excelled and those in which it struggled or had the lowest accuracy rates were identified. These findings underscore the potential of transfer learning models in the early diagnosis of rice diseases, facilitating the development of effective automated diagnostic systems in the agriculture sector. Furthermore, this research, with a focus on promoting healthier and sustainable agricultural practices, may contribute to future strategies.

Kaynakça

  • 1. T.C. Tarım ve Orman Bakanlığı Yayınları, 2007. Çeltik Hastalık ve Zararlıları ile Mücadele, https://www.tarimorman.gov.tr/ GKGM/Belgeler/Uretici_Bilgi_Kosesi/Dokumanlar/celtik.pdf Erişim Tarihi: 16.05.2023, Ankara.
  • 2. Taşlıgil, N., Şahin, G., 2011. Türkiye’de Çeltik (Oryza Sativa L.) Yetiştiriciliği ve Coğrafi Dağılımı. Adıyaman Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 4(6), 182-204.
  • 3. Amritha, H., Jeena, T., Ebin D,R., 2023. Deep Learning System for Paddy Plant Disease Detection and Classification. Environmental Monitoring and Assessment, 195, 1(2023),1–28.
  • 4. Leelavathy, B., Rao Kovvur, R.M., 2020. Prediction of Biotic Stress in Paddy Crop Using Deep Convolutional Neural Networks. In Proceedings of International Conference on Computational Intelligence and Data Engineering. Springer Singapore, 337-346.
  • 5. Shrivastava, V.K., Pradhan, M.K., Minz, S., Thakur, M.P., 2019. Rice Plant Pisease Classification Using Transfer Learning of Deep Convolution Neural Network. International Archives of the Photogrammetry, Remote Sensing & Spatial Information Sciences XLII-3/W6 (July 2019), 631-635.
  • 6. Ramesh, S., Vydeki, D., 2020. Recognition and Classification of Paddy Leaf Diseases Using Optimized Deep Neural Network with Jaya Algorithm. Information Processing in Agriculture, 7(2), 249-260.
  • 7. Bhagawati, R., Bhagawati, K., Singh, A.K.K., Nongthombam, R., Sarmah, R., Bhagawati, G., 2015. Artificial Neural Network Assisted Weather Based Plant Disease Forecasting System. International Journal on Recent and Innovation Trends in Computing and Communication, 3(6), 4168-4173.
  • 8. Lu, R., 2004. Multispectral Imaging for Predicting Firmness and Soluble Solids Content of Apple Fruit. Postharvest Biology and Technology, 31(2), 147-157.
  • 9. Prajapati, H.B., Shah, J.P., Dabhi, V.K., 2017. Detection and Classification of Rice Plant Diseases. Intelligent Decision Technologies, 11(3), 357-373.
  • 10. Rahman, C.R., Arko, P.S., Ali, M.E., Iqbal Khan, M.A., Apon, S.H., Nowrin, F., Wasif, A., 2020. Identification and Recognition of Rice Diseases and Pests using Convolutional Neural Networks. Biosystems Engineering, 194, 112-120.
  • 11. Lu, Y., Yi, S., Zeng, N., Liu, Y., Zhang, Y., 2017. Identification of Rice Diseases using Deep Convolutional Neural Networks. Neurocomputing, 267, 378-384.
  • 12. Ökten, İ., Yüzgeç, U., 2022. Evrişimli Sinir Ağı ile Çeltik Bitkisi Hastalığının Tespiti. Bitlis Eren Üniversitesi Fen Bilimleri Dergisi, 11(1), 203-217.
  • 13. Kılıç, Ş., Doğan, Y. 2023. Deep Learning Based Gender Identification using Ear Images. Traitement du Signal, 40(4).
  • 14. Dogan, Y., 2023. A New Global Pooling Method for Deep Neural Networks: Global Average of Top-K Max-Pooling. Traitement du Signal, 40(2).
  • 15. Dogan, Y., Atas, M., Özdemir, C., 2014. A New Approach for Plotting Raster Based Image Files. In 2014 22nd Signal Processing and Communications Applications Conference (SIU), 1027-1030. IEEE.
  • 16. Özdemi̇r, C., Ataş, M., Özer, A.B., 2013. Classification of Turkish Spam E-Mails with Artificial Immune System. In 2013 21st Signal Processing and Communications Applications Conference (SIU), 1-4. IEEE.
  • 17. Kılıç, Ş., Kaya, Y., Askerbeyli, İ., 2021. A New Approach for Human Recognition Through Wearable Sensor Signals. Arabian Journal for Science and Engineering, 46, 4175-4189.
  • 18. Petchiammal, A., Briskline Kiruba, S., Murugan, D., Pandarasamy, Arjunan., 2022. Paddy Doctor: A Visual Image Dataset for Automated Paddy Disease Classification and Benchmarking. IEEE Dataport.
  • 19. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z., 2016. Rethinking the Inception Architecture for Computer Vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2818-2826.
  • 20. He, K., Zhang, X., Ren, S., Sun, J., 2016. Identity Mappings in Deep Residual Networks. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part IV 14, 630-645. Springer International Publishing.
  • 21. Chollet, F., 2017. Xception: Deep Learning with Depthwise Separable Convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 1251-1258.
  • 22. Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.C., 2018. Mobilenetv2: Inverted Residuals and Linear Bottlenecks. In Proceedings of The IEEE Conference on Computer Vision and Pattern Recognition, 4510-4520.
  • 23. Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q., 2017. Densely Connected Convolutional Networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4700-4708).
Toplam 23 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Bilgisayar Destekli Tasarım, Bilgisayar Yazılımı
Bölüm Makaleler
Yazarlar

Cüneyt Özdemir 0000-0002-9252-5888

Yayımlanma Tarihi 18 Ekim 2023
Yayımlandığı Sayı Yıl 2023

Kaynak Göster

APA Özdemir, C. (2023). Derin Öğrenme Modelleri ve Veri Ön İşleme Yöntemleri ile Çeltik Yaprak Hastalıklarının Erken Teşhisi. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 38(3), 807-817. https://doi.org/10.21605/cukurovaumfd.1377763