A Study on Performance Comparison of Machine Learning Algorithm for Scaffold Defect Classification

인공지지체 불량 분류를 위한 기계 학습 알고리즘 성능 비교에 관한 연구

  • Lee, Song-Yeon (Mechatronics Engineering, Graduate School of Korea University of Technology and Education) ;
  • Huh, Yong Jeong (Department of Mechatronics Engineering, Korea University of Technology and Education)
  • 이송연 (한국기술교육대학교대학원 메카트로닉스공학과) ;
  • 허용정 (한국기술교육대학교 메카트로닉스공학부)
  • Received : 2020.09.01
  • Accepted : 2020.09.22
  • Published : 2020.09.30

Abstract

In this paper, we create scaffold defect classification models using machine learning based data. We extract the characteristic from collected scaffold external images using USB camera. SVM, KNN, MLP algorithm of machine learning was using extracted features. Classification models of three type learned using train dataset. We created scaffold defect classification models using test dataset. We quantified the performance of defect classification models. We have confirmed that the SVM accuracy is 95%. So the best performance model is using SVM.

References

  1. Seung-Hyeok Choi, Min-Woo Sa and Jong-Young Kim, "New Fabricatio Method of Bio-Ceramic Scaffolds Based on Mold using a FDM 3D Printer", J. of The Korean Society of Precision Engineering, Vol.18, pp. 957-963, 2018.
  2. Song-Yeon Lee and Yong-Jeong Huh, "A Study on Prediction Model Performance of Scaffold Pore Size Using Machine Learning Regression Method", J. of The Korean Society of Semiconductor & Display Technology, Vol.19, pp. 36-41, 2020.
  3. Song-Yeon Lee and Yong-Jeong Huh, "A Study on Prediction Model of Scaffold Appearance Defect Using Machine Learning", J. of The Korean Society of Semiconductor & Display Technology, Vol.18, pp. 46-50, 2020.
  4. Young-Ho Lee and Seong-Yun Hong, "A Machine Learning Approach to the Prediction of Individual Travel Mode Choices", J of the Koreaa Data and Information Science Society, Vol. 30, pp. 1011-1024, 2019. https://doi.org/10.7465/jkdi.2019.30.5.1011
  5. Song-Yeon Lee and Yong-Jeong Huh, "A Study on Prediction Model of Scaffold Pore Size Using Machine Learning", J. of The Korean Society of Semiconductor & Display Technology, Vol.18, pp. 46-50, 2019.
  6. Yong-Beom Park, Dong-Bin Choi and In-Soo Cho, "Taxation Analysis Using Machine Learning", J. of The Korean Society of Semiconductor & Display Technology, Vol.18, pp. 73-77, 2019.
  7. Yu-Sun Ahn, Hue-Jin Kim, Sang-Kyu Lee and Byung sean Kim, "Prediction of Heating Energy Consumption Using Machine Learning and Parameters in Combined Heat and Power Generation", J of Air-Conditioning and Refrigeration Engineering, Vol. 31, pp. 352-360, 2019. https://doi.org/10.6110/KJACR.2019.31.8.352