AI 기술 기반의 단계적 예측 실험계획법 개발
Development of Stepwise Forecasting Experimental Design Methods Based on AI Technologies
2
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
Purpose: The objective of this paper is to develop forecasting experiment procedures increasing the efficiency and effectiveness of experiments by combining DoE (Design of Experiments) and AI (Artificial Intelligence) algorithms to reduce unnecessary cost and period in phase of animal experiments in the field of new drug development. Methods: A methodology utilizing AI algorithms like k-NN and XGBoost for interpolating outliers and missing values of DoE results and for predicting results at remaining experimental points of FD (Factorial Design) based on FFD (Fractional Factorial Design) results is proposed in a stepwise experimental design methods. Results: In this case study, a proposed methodology utilizing AI algorithms for predicting results at remaining experimental points show performance of XGBoost is better than k-NN and the predicting results are significant. Especially, when predicting results at remaining experimental points of FD (Factorial Design) based on FFD (Fractional Factorial Design) results, predicting results are sensitive from whether or not data of center points. This proposed methodology can reduce the cost and period for retesting by utilizing an appropriate AI algorithm in a stepwise experimental design methods. Conclusion: Combining DoE based on traditional statistical methods with AI algorithms for predicting experimental results is shown that a stepwise experimental design methods can become more efficient and effective.
Abstract
Purpose: The objective of this paper is to develop forecasting experiment procedures increasing the efficiency and effectiveness of experiments by combining DoE (Design of Experiments) and AI (Artificial Intelligence) algorithms to reduce unnecessary cost and period in phase of animal experiments in the field of new drug development. Methods: A methodology utilizing AI algorithms like k-NN and XGBoost for interpolating outliers and missing values of DoE results and for predicting results at remaining experimental points of FD (Factorial Design) based on FFD (Fractional Factorial Design) results is proposed in a stepwise experimental design methods. Results: In this case study, a proposed methodology utilizing AI algorithms for predicting results at remaining experimental points show performance of XGBoost is better than k-NN and the predicting results are significant. Especially, when predicting results at remaining experimental points of FD (Factorial Design) based on FFD (Fractional Factorial Design) results, predicting results are sensitive from whether or not data of center points. This proposed methodology can reduce the cost and period for retesting by utilizing an appropriate AI algorithm in a stepwise experimental design methods. Conclusion: Combining DoE based on traditional statistical methods with AI algorithms for predicting experimental results is shown that a stepwise experimental design methods can become more efficient and effective.
참고문헌 (28)
- Chang, H. H., "Neuro-genetic approach to optimize parameter design of dynamic multiresponse experiments", Applied Soft Computing, 11(1), pp.436~442 (2011)
- Cheon, M., "A Study on the traffic flow prediction through Catboost algorithm", Journal of the Korea Academia-Industrial cooperation Society, 22(3), pp.58~64 (2021)
- Dasarathy, B. V, "Nearest neighbor (NN) norms: NN pattern classification techniques", IEEE Computer Society Tutorial (1991)
- G. Hessler, "Artificial Intelligence in Drug Design", Molecules, 23(10), pp.2520~ (2018)
- Han, Y., "Study on the Parameter Optimization of the Heat Treatment Process Using the Design of Experiment(DoE)", Korean Journal of Computational Design and Engineering, 26(4), pp.273~284 (2021)
- "Pharmaceutical Development Q8 (R2)", International conference of harmonisation (2009)
- J. Freiesleben, "Machine learning and Design of Experiments : Alternative approaches or complementary methodologies for quality improvement?", Qual Reliab Engng Int, 36, pp.1837~1848 (2020)
- J. Vamathevan, "Applications of machine learning in drug discovery and development", Nature Review of Drug Discovery, 18(6), pp.463~477 (2019)
- J. Vamathevan, "Applications of machine learning in drug discovery and development", Nature Review of Drug Discovery, 18(6), pp.463~477 (2019)
- Jung, M., "Present Status and Future of AI-based Drug Discovery", Journal of the Korea Institute of Information and Communication Engineering, 25(12), pp.1797~1808 (2021)
- Jung, Y., "Methodology for Variable Optimization in Injection Molding Process", J Korean Soc Qual Manag, 52(1), pp.43~56 (2024)
- K. Mak, "Artificial intelligence in drug development : present status and future prospects", Drug Discovery Today, 24(3), pp.773~780 (2019)
- Kim, H, "The Prediction of PM2. 5 in Seoul through XGBoost ensemble", Journal of the Korean Data Analysis Society, 22(4), pp.1661~1671 (2020)
- Kim, K., "A Study on Optimization of Classification Performance through Fourier Transform and Image Augmentation", J Korean Soc Qual Manag, 51(1), pp.119~129 (2023)
- Kim, S, "The analysis of current performance and perception on QbD(Quality by Design) of pharmaceutical companies in south Korea", MS, pp.2016
- L. Patel, "Machine Learning Methods in Drug Discovery", Molecules, 25, pp.5277~ (2020)
- Lee, H., "Optimal Parameter Design for a Cryogenic Submerged Arc Welding(SAW)Process by Utilizing Stepwise Experimental Design and Multi-dimensional Design Space Analysis", J Korean Soc Qual Manag, 48(1), pp.1~18 (2020)
- Lee, S., "A Case Study on Quality Improvement of Electric Vehicle Hairpin Winding Motor Using Deep Learning AI Solution", J Korean Soc Qual Manag, 5(2), pp.283~296 (2023)
- Lou, H., "The application of machine learning algorithms in understanding the effect of core", shell technique on improving powder compactability, 2019, pp.555, 368~379
- M. Ragoza, "Protein–ligand scoring with convolutional neural etworks", Journal of Chemical Information and Modeling, 57, pp.942~957 (2017)
- R. C. Mohs, "Drug discovery and development : role of basic biological research", Alzheimer’s & Dementia, 3(4), pp.651~657 (2017)
- S. Woo, "Drug Discovery Enhanced by Artificial Intelligence", Biomedical Journal of Scientific & Technical Research, 12(1) (2018)
- T. Chen, "XGBoost: A Scalable Tree Boosting System, Association for Computing Machinery", KDD’16, pp.13~17 (2016)
- T. H. Le, "Structured neural network models to improve robust design solutions", Computers &Industrial Engineering, 156, pp.107231~ (2021)
- T. H. Le, "Determination of the Optimal Neural Network Transfer Function for Response Surface Methodology and Robust Design", Appl. Sci, 11, pp.6768~ (2021)
- T. H. Le, "Robust Process Parameter Design Methodology: A New Estimation Approach by Using Feed-Forward Neural Network Structures and Machine Learning Algorithms", Appl. Sci, 12, pp.2904~ (2022)
- Viana FA, "An algorithm for fast optimal Latin hypercube design of experiments", Int J Numer Methods Eng, 82(2), pp.135~156 (2010)
- Won, C, "Reflections on the importance of variables in k-NN", MS, pp.2018