The Journal of the Convergence on Culture Technology (문화기술의 융합)

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

A Study on the AI Model for Prediction of Demand for Cold Chain Distribution of Drugs

의약품 콜드체인 유통 수요 예측을 위한 AI 모델에 관한 연구

  • 김희영 (광운대학교 대학원 실감융합콘텐츠학과) ;
  • 류기환 (광운대학교 스마트융합대학원 ) ;
  • 근재 (광운대학교 대학원 실감융합콘텐츠학과) ;
  • 손현곤 (광운대학교 대학원 실감융합콘텐츠학과)
  • Received : 2023.03.31
  • Accepted : 2023.05.08
  • Published : 2023.05.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, the existing statistical method (ARIMA) and machine learning method (Informer) were developed and compared to predict the distribution volume of pharmaceuticals. It was found that a machine learning-based model is advantageous for daily data prediction, and it is effective to use ARIMA for monthly prediction and switch to Informer as the data increases. The prediction error rate (RMSE) was reduced by 26.6% compared to the previous method, and the prediction accuracy was improved by 13%, resulting in a result of 86.2%. Through this thesis, we find that there is an advantage of obtaining the best results by ensembleing statistical methods and machine learning methods. In addition, machine learning-based AI models can derive the best results through deep learning operations even in irregular situations, and after commercialization, performance is expected to improve as the amount of data increases.

본 논문에서는 의약품 유통량 예측을 위해 기존의 통계 방식(ARIMA)과 머신러닝 방식(Informer)을 개발하고 비교하였다. 일별 데이터의 예측에서는 머신러닝 기반의 모델이 유리하며, 월별 예측에서는 ARIMA를 활용하고 데이터가 증가하면서 Informer로 전환하는 것이 효과적임을 발견하였다. 예측 에러율(RMSE)은 기존 방식 대비 26.6% 낮아졌으며, 예측 정확도도 13% 개선되어 86.2%의 결과를 보였다. 본 논문을 통해 통계적 방법과 머신러닝 방법을 앙상블하여 최상의 결과를 얻을 수 있다는 장점을 발견하였다. 또한 머신러닝 기반의 AI 모델은 불규칙한 상황에서도 딥러닝 연산을 통해 최선의 결과를 도출할 수 있으며, 상용화 이후에는 데이터양이 증가함에 따라 성능이 향상될 것으로 기대된다.

Keywords

References

  1. Rathipriya, R., et al., "Demand forecasting model for time-series pharmaceutical data using shallow and deep neural network model.", Neural Computing and Applications, Vol. 35, No. 2, pp. 1945-1957, 2023. DOI: https://doi.org/10.1007/s00521-022-07889-9
  2. Jin-mo Im, Weol-Youg Kim, Woo-Jin Byoun, Seung-Jung Shin, "Fruit price prediction study using artificial intelligence", The Journal of the Convergence on Culture Technology(JCCT), Vol. 4, No. 2, pp. 197-204, May 2018. DOI: https://doi.org/10.17703/JCCT.2018.4.2.197
  3. Zhu, Xiaodan, et al., "Demand forecasting with supply-chain information and machine learning: Evidence in the pharmaceutical industry.", Production and Operations Management, Vol. 30, No. 9, pp. 3231-3252, March 2021. DOI: https://doi.org/10.1111/poms.13426
  4. Shi, Xingjian, et al., "Convolutional LSTM network: A machine learning approach for precipitation nowcasting.", Advances in neural information processing systems 28, 2015.
  5. Sainath, Tara N., et al., "Convolutional, long short-term memory, fully connected deep neural networks.", 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp.4580-4584, IEEE, 2015. DOI: https://doi.org/10.1109/ICASSP.2015.7178838
  6. Vaswani, Ashish, et al., "Attention is all you need.", Advances in neural information processing systems. 2017.
  7. Zhou, Haoyi, et al., "Informer: Beyond efficient transformer for long sequence time-series forecasting.", Proceedings of the AAAI conference on artificial intelligence, Vol. 35, No. 12, pp. 11106-11115, 2021. DOI: https://doi.org/10.1609/aaai.v35i12.17325
  8. H. Y. Kim, S. M. Jung, W. S. Kim, G. H. Ryu, H. K. Son, "A Study on the Implementation of Restaurant Recommendation System based on Deep Learning-based Consumer Data", The Journal of Convergence of Culture Technology (JCCT), Vol. 7, No. 2, pp. 437-442, 2021. DOI: http://dx.doi.org/10.17703/JCCT.2021.7.2.437
  9. S. H. Song, "Die Probleme des Umlaufs der Infektionskrankheit sowie der Verteilung und des Ausgebots der Entstehungszeit der Krise der Infektionskrankheit-Um die sparliche Zeit des Medikaments-", Law Review (pnulaw), Vol. 61, No. 2, pp. 1-47, 2020. DOI: https://doi.org/10.35275/pnulaw.2020.61.2.001