DOI QR코드

DOI QR Code

Design of Classifier for Sorting of Black Plastics by Type Using Intelligent Algorithm

지능형 알고리즘을 이용한 재질별 검정색 플라스틱 분류기 설계

  • Park, Sang Beom (Department of Electrical Engineering, The University of Suwon) ;
  • Roh, Seok Beom (Department of Electrical Engineering, The University of Suwon) ;
  • Oh, Sung Kwun (Department of Electrical Engineering, The University of Suwon) ;
  • Park, Eun Kyu (Waste Recycling Institute, The University of Suwon) ;
  • Choi, Woo Zin (Waste Recycling Institute, The University of Suwon)
  • 박상범 (수원대학교 전기공학과) ;
  • 노석범 (수원대학교 전기공학과) ;
  • 오성권 (수원대학교 전기공학과) ;
  • 박은규 (수원대학교 폐기물자원화기술연구소) ;
  • 최우진 (수원대학교 폐기물자원화기술연구소)
  • Received : 2017.01.19
  • Accepted : 2017.03.20
  • Published : 2017.04.30

Abstract

In this study, the design methodology of Radial Basis Function Neural Networks is developed with the aid of Laser Induced Breakdown Spectroscopy and also applied to the practical plastics sorting system. To identify black plastics such as ABS, PP, and PS, RBFNNs classifier as a kind of intelligent algorithms is designed. The dimensionality of the obtained input variables are reduced by using PCA and divided into several groups by using K-means clustering which is a kind of clustering techniques. The entire data is split into training data and test data according to the ratio of 4:1. The 5-fold cross validation method is used to evaluate the performance as well as reliability of the proposed classifier. In case of input variables and clusters equal to 5 respectively, the classification performance of the proposed classifier is obtained as 96.78%. Also, the proposed classifier showed superiority in the viewpoint of classification performance where compared to other classifiers.

본 연구에서는 레이저유도붕괴분광(Laser Induced Breakdown Spectroscopy, LIBS)을 이용하여 방사형 기저함수 신경회로망(Radial Basis Function Neural Networks, RBFNNs) 분류기 설계방법론을 개발하고 실제 폐소형가전제품의 플라스틱 분류 시스템에 적용하였다. ABS, PP, PS와 같은 검정색 플라스틱을 구별하기 위해, 지능형 알고리즘 중 하나인 방사형 기저함수 신경회로망 분류기를 설계하였다. 획득한 입력변수는 주성분 분석법(Principal Component Analysis, PCA)을 이용하여 축소시켰으며, 군집화기법 중 하나인 K-means 클러스터링 방법을 이용해 여러 그룹으로 분할하였다. 전체 데이터는 학습 데이터와 테스트 데이터를 4:1의 비율로 나누었으며, 제안된 분류기의 성능 및 신뢰도를 평가하기 위하여 5-FCV(5-Fold Cross Validation) 기법을 사용하였다. 입력변수와 클러스터의 개수가 각각 5개인 경우, 제안된 분류기의 분류 성능은 96.78%로 나타났다. 또한, 제안된 분류기는 다른 분류기들과 비교하였을 경우 분류 성능의 관점에서 우수성을 보여주었다.

Keywords

References

  1. Park, E. K. et al., 2016 : Environmental Impact Assessment on Dismantling . Crushing . Sorting Process for Recycling of Used Small Household Appliances, J. of Korean Inst. of Resources Recycling, 25(2), pp. 17-24. https://doi.org/10.7844/kirr.2016.25.2.17
  2. Albert Bifet. et al., 2015 : Efficient online evaluation of big data stream classifiers, In proc 21st ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 59-68.
  3. Kingo Azuma and Takashi Kimura, 2016 : Plasma parameters of titanium-based metallic plasma generated by compact-type high-powerpulsed sputtering penning discharge, IEEE Transactions on Plasma Science, 44(12), pp. 3201-3206. https://doi.org/10.1109/TPS.2016.2615310
  4. Choi, W. Y. and Oh, S. K., 2014 : Design of meteorological radar pattern classifier using clustering-based RBFNNs : Comparative studies and analysis, Journal of KIIS, 24(5), pp. 536-541.
  5. Kim, S. H. and Oh, S. K., 2016 : RBFNNs-based recognition system of vehicle license plate using distortion correction and local binarization, The Transactions of KIEE, 65(9), pp. 1531-1540.
  6. Oh, S. K. and Park, H. S., 2000 : Multi-FNN identification by means of HCM clustering and its optimization using genetic algorithms, Journal of KIIS, 10(5), pp. 487-496.
  7. Kim, W. D. et. al., 2010 : Structural design of FCM-based fuzzy inference system : A comparative study of WLSE and LSE, The Transactions of KIEE, 59(5), pp. 981-989.
  8. Chung, H. S. et al., 1994 : Status of discarded home electric appliances treatment, J. of Korean Inst. of Resources Recycling, 3(2), pp. 24-27.

Cited by

  1. LIBS를 이용한 흑색 플라스틱의 자동선별 시스템 개발 vol.26, pp.6, 2017, https://doi.org/10.7844/kirr.2017.26.6.73