The Journal of the Korea institute of electronic communication sciences (한국전자통신학회논문지)

Korea Institute of Electronic Communication Science (한국전자통신학회)
권호 표지
DOI QR코드

DOI QR Code

Avocado Classification and Shipping Prediction System based on Transfer Learning Model for Rational Pricing

합리적 가격결정을 위한 전이학습모델기반 아보카도 분류 및 출하 예측 시스템

  • 유성운 (동서대학교 소프트웨어학과) ;
  • 박승민 (동서대학교 소프트웨어학과)
  • Received : 2022.02.16
  • Accepted : 2023.04.17
  • Published : 2023.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Avocado, a superfood selected by Time magazine and one of the late ripening fruits, is one of the foods with a big difference between local prices and domestic distribution prices. If this sorting process of avocados is automated, it will be possible to lower prices by reducing labor costs in various fields. In this paper, we aim to create an optimal classification model by creating an avocado dataset through crawling and using a number of deep learning-based transfer learning models. Experiments were conducted by directly substituting a deep learning-based transfer learning model from a dataset separated from the produced dataset and fine-tuning the hyperparameters of the model. When an avocado image is input, the model classifies the ripeness of the avocado with an accuracy of over 99%, and proposes a dataset and algorithm that can reduce manpower and increase accuracy in avocado production and distribution households.

타임지가 선정한 슈퍼푸드이며, 후숙 과일 중 하나인 아보카도는 현지가격과 국내 유통 가격이 크게 차이가 나는 식품 중 하나이다. 이러한 아보카도의 분류과정을 자동화한다면 다양한 분야에서 인건비를 줄여 가격을 낮출 수 있을 것이다. 본 논문에서는 아보카도의 데이터셋을 크롤링을 통하여 제작하고, 딥러닝 기반 전이학습모델을 다수 사용하여, 최적의 분류모델을 만드는 것을 목표로 한다. 실험은 제작한 데이터셋에서 분리한 데이터셋에서 딥러닝 기반 전이학습모델에 직접 대입하고, 해당 모델의 하이퍼 파라미터를 Fine-tuning하며 진행하였다. 제작된 모델은 아보카도의 이미지를 입력하였을 때, 해당 아보카도의 익은 정도를 99% 이상의 정확도로 분류하였으며, 아보카도 생산 및 유통가정의 인력감소 및 정확성을 높일 수 있는 데이터셋 및 알고리즘을 제안한다.

Keywords

Acknowledgement

본 논문은 2022년도 동서대학교 "Dongseo Cluster Project"지원에 의하여 이루어진 것임.(DSU-2022002)

References

  1. H. Lee and I. Kim, "Empirical Analysis of Consumers Purchase Satisfaction and Repurchase Intention on Imported Mangoes and Avocados," Korea Association for International Commerce and Information, vol. 23, no. 4, Dec. 2021, pp. 269-292. https://doi.org/10.15798/kaici.2021.23.4.269
  2. H. Chong, N. Lee, and H. Cho, "Development of Image Defect Detection Model Using Machine Learning," Journal of the Korea Institute of Information and Communication Engineering, vol. 15, no. 3, June 2020, pp. 513-520.
  3. K. He, R. Girshick, and P. Dollar, "Rethinking ImageNet Pre-training Facebook AI Research (FAIR)," 2019 IEEE/CVF International Conference on Computer Vision (ICCV), Seoul, South Korea. 2019 pp. 4917-4926.
  4. O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A. C Berg, and L. Fei-Fei, International Journal of Computer Vision, vol. 115, no. 3, 2015, pp. 211-252. https://doi.org/10.1007/s11263-015-0816-y
  5. K. Simonyan and A. Zisserman, "Very Deep Convolutional Networks for Large-Scale Image Recognition," Oxford University Technical Report, Apr. 2015.
  6. K. He, Xi. Zhang, S. Ren, and J. Sun, "Deep ResidualLearning for Image Recognition," 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, United States, 2016 pp. 770-778.
  7. G. Huang, Z. Liu, L. Maaten, and K. Weinbberger, "Densely Connected Convolutional Networks," 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, United States, 2017, pp. 2261-2269.
  8. J. Jo, "Effectiveness of Normalization Pre-Processing of Big Data to the Machine Learning Performance," Journal of the Korea Institute of Information and Communication Engineering, vol. 14, no. 3, June 2019, pp. 547-552.
  9. J. Kim and H. Oh, "The methods to improve the performance of predictive model using machine learning for the quality properties of products," Journa of the Korea Institute of Information and Communication Engineering, vol. 25, no. 6, June 2021, pp. 749-756.
  10. H. Lee, "Optimization of the Number of Filter in CNN Noise Attenuator," J. of the Korea Institute of Electronic Communication Sciences, vol. 16, no. 4, Aug. 2021, pp. 625-632.
  11. I. Kandel and M. Castelli, "The effect of batch size on the generalizability of the convolutional neural networks on a histopathology dataset," ICT Express, vol. 6, issue 4, Dec. 2020, pp. 312-315. https://doi.org/10.1016/j.icte.2020.04.010