Journal of Internet Computing and Services (인터넷정보학회논문지)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지
DOI QR코드

DOI QR Code

Study on the method for interoperability of AI model to improve usability of artificial intelligence models in agricultural field

농업분야 인공지능 모델의 활용성 향상을 위한 AI 모델의 상호호환성 관리 방안 연구

  • Jung-Ho Um (DataON Development Team, Korea Institute of Science and Technolongy Information) ;
  • Juseop Kim (Department of Library and Information Science, Jeonbuk National University) ;
  • Hwan Suk Cheong (Rural Development Administration)
  • Received : 2024.06.04
  • Accepted : 2024.09.02
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

With the development of artificial intelligence technology, various studies are being actively conducted to apply it to agriculture. In South Korea, AI training datasets are being produced for research on artificial intelligence technology. In various fields, including the agricultural and livestock sectors, datasets are posted through the site AI HUB. However, since AI models can be developed in multiple artificial intelligence learning frameworks, more things can interfere with the AI model as framework compatibility is considered in terms of serving the AI model. For system design, we derive requirements and propose the overall structure of the system. In addition, we show examples of the feasibility of implementing each component. To verify the feasibility of the proposed method, we trained a total of four eggplant disease classification models through transfer learning. We built a model with the best accuracy of 99% and converted it to ONNX, confirming that there was no difference in performance compared to the existing model. In future research, we plan to apply the model-sharing method verified in this paper to a data platform.

인공지능 기술이 발전하면서 이를 농업에 적용하기 위한 다양한 연구가 활발히 진행되고 있다. 국내에서는 인공지능 기술 연구를 위한 AI 훈련 데이터 세트가 구축되고 있다. 농·축산업 등 다양한 분야의 데이터 셋은 AI 허브 사이트를 통해 게시되고 있다. 하지만 AI 모델의 경우 다양한 인공지능 학습 프레임워크에서 개발될 수 있기 때문에, AI 모델을 제공하는 측면에서 프레임워크 간 상호호환성이 고려되면 더 많은 이용자가 AI 모델을 활용할 수 있다. 본 논문에서는 이를 위해, 시스템에 필요한 요구사항을 도출하고 각 컴포넌트 간 상호호환성을 위해 개방형 뉴럴 네트워크 표현 형식인 ONNX를 활용하였다. 또한 제안하는 방안의 타당성에 대한 입증을 위해 가지 질병 분류 모델을 전이학습을 통해 총 4가지 모델에 대해 학습을 진행했으며, 최고 99%의 정확도를 가지는 모델을 구축하고 이를 ONNX로 변환하여 기존 모델과 성능에 차이가 없음을 확인하였다. 향후 연구로 본 논문에서 검증한 모델 공유 방법을 데이터 플랫폼에 적용할 수 있는 방안을 연구할 예정이다.

Keywords

Acknowledgement

본 논문은 농촌진흥청 연구사업(과제번호: RS-2022-RD010352(PJ0170742022))의 지원에 의해 이루어진 것임.

References

  1. J. Zha, "Artificial Intelligence in Agriculture," Journal of Physics: Conference Series, Vol. 1693, 012058, 2020. https://doi.org/10.1088/1742-6596/1693/1/012058
  2. E. Elbasi, N. Mostafa, Z. AlArnaout, A. I. Zreikat, E. Cina, G. Varghese, A. Shdefat, A. E. Topcu, W. Abdelbaki, S.Mathew, and C. Zaki, "Artificial Intelligence Technology in the Agricultural Sector: A Systematic Literature Review," IEEE Access, Vol. 11, pp.171-202, 2023. https://doi.org/10.1109/ACCESS.2022.3232485
  3. V. Meshram, K. Patil, V.Meshram, D. Hanchate, and S. D. Ramkteke, "Machine learning in agriculture domain: A state-of-art survey," Artificial Intelligence in the Life Sciences, Vol. 1, 2021. https://doi.org/10.1016/j.ailsci.2021.100010.
  4. https://github. com/onnx/onnx, 2023.11.27.
  5. J. Um, M. Hwang and Youngho Shin, "A Study on Development of Artificial Intelligence Big Data Storing and Sharing System in Agricultural Science," Korea Contents Association General Conference Proceedings, pp.175-176, 2022.
  6. J. Um, Mi. Hwang, Y. Shin, J. Kim, S. Kim, Y. Jo, and H. S. Cheong, "Design and Implementation of Platform for Managing Artificial Intelligent Training DataSet in Agriculture and LiveStock," 2023 KSII FALL Conference, Vol. 24, No 2, pp.351-352, 2023.
  7. https://www.rdaidata.kr/, 2023.11.27.
  8. M. Morales-Hernandez, M. B. Sharif, A. Kalyanapu, S. K. Ghafoor, T. T. Dullo, S. Gangrade, S. Kao, M.R. Norman, and K. J. Evans, "TRITON: A Multi-GPU open source 2D hydrodynamic flood model," Environmental Modelling & Software, Vol. 141, 2021. https://doi.org/10.1016/j.envsoft.2021.105034
  9. https://github.com/awslabs/multi-model-server, 2023.11.27.
  10. K. He, X. Zhang, S. Ren and J. Sun, "Deep residual learning for image recognition," IEEE Conference on Computer Vision and Pattern Recognition, pp.770-778, 2016. https://openaccess.thecvf.com/content_cvpr_2016/html/He_Deep_Residual_Learning_CVPR_2016_paper.html
  11. K. Simonyan and A. Zisserman, "Very deep convolutional networks for large-scale image recognition," CoRR abs/1409.1556, http://arxiv.org/abs/1409.1556, 2014.
  12. G. Huang, Z. Liu, L. Van Der Maaten and K. Q. Weinberger, "Densely connected convolutional networks," IEEE conference on computer vision and pattern recognition, pp.4700-4708, 2017.
  13. F. Chollet, "Xception: Deep learning with depthwise separable convolutions," IEEE conference on computer vision and pattern recognition, pp.1251-1258, 2017. https://openaccess.thecvf.com/content_cvpr_2017/html/Chollet_Xception_Deep_Learning_CVPR_2017_paper.html
  14. K. He, G. Gkioxari, P. Dollar, and R. Girshick, " Mask r-cnn," IEEE international conference on computer vision, pp.2961-2969, 2017. https://openaccess.thecvf.com/content_iccv_2017/html/He_Mask_R-CNN_ICCV_2017_paper.html
  15. J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," IEEE Conference on Computer Vision and Pattern Recognition, pp.779-788, 2016. https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Redmon_You_Only_Look_CVPR_2016_paper.html
  16. S. Vosoughi, P. Vijayaraghavan and D. Roy " Tweet2Vec: learning Tweet embeddings using character-level CNN-LSTM encoder-decoder," The 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp.1041-1044, 2016. https://doi.org/10.1145/2911451.2914762
  17. S. Qiao, L. C. Chen and A. Yuille, "Detectors: Detecting objects with recursive feature pyramid and switchable atrous convolution," IEEE/CVF conference on computer vision and pattern recognition, pp.10213-10224, 2021. https://openaccess.thecvf.com/content/CVPR2021/html/Qiao_DetectoRS_Detecting_Objects_With_Recursive_Feature _Pyramid_and_Switchable_Atrous_CVPR_2021_paper.html
  18. H. Duan, Y. Zhao, K. Chen, D. Lin and B. Dai, "Revisiting skeleton-based action recognition," IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp.2969-2978, 2022. https://openaccess.thecvf.com/content/CVPR2022/html/Duan_Revisiting_Skeleton-Based_Action_Recognition_CVPR_2022_paper.html
  19. C. Yu, B. Xiao, C. Gao, L. Yuan, L. Zhang, N. Sang, and J. Wang, "Lite-hrnet: A lightweight high-resolution network," IEEE/CVF conference on computer vision and pattern recognition, pp.10440-10450, 2021.
  20. A. Karpathy, , G. Toderici, , S. Shetty, T. Leung, R. Sukthankar and L. Fei-Fei, "Largescale video classification with convolutional neural networks," IEEE Conference on Computer Vision and Pattern Recognition, pp.1725-1732, 2014. https://www.cv-foundation.org/openaccess/content_cvpr_ 2014/html/Karpathy_Large-scale_Video_Classification_2014_CVPR_paper.html
  21. X. Li and X. Wu, "Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition," IEEE International Conference on Acoustics, Speech and Signal Processing, pp.4520-4524, 2015. https://doi.org/10.1109/ICASSP.2015.7178826
  22. https://github.com/ultralytics/yolov5, 2023.11.27.
  23. Bochkovskiy, Alexey, Chien-Yao Wang, and Hong-Yuan Mark Liao, "Yolov4: Optimal speed and accuracy of object detection," arXiv preprint arXiv:2004.10934, 2020. https://doi.org/10.48550/arXiv.2004.10934
  24. P. Adarsh, P. Rathi and M. Kumar, "YOLO v3-Tiny: Object Detection and Recognition using one stage improved model," 6th International Conference on Advanced Computing and Communication Systems (ICACCS), Coimbatore, India, pp.687-694, 2020. https://doi.org/10.1109/ICACCS48705.2020.9074315
  25. https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=115&topMenu=100&aihubDataSe=data&dataSetSn=153, 2023.11.27.
  26. C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens and Z. Wojna, "Rethinking the Inception Architecture for Computer Vision," IEEE conference on computer vision and pattern recognition, pp. 2818-2826, 2016. https://www.cv-foundation.org/openaccess/content_cvpr_ 2016/html/Szegedy_Rethinking_the_Inception_CVPR_2 016_paper.html
  27. https://https://dataon.kisti.re.kr/canvas/intro.do,2024.08.09.