Prediction of Plastic-Type for Sorting System using Fisher Discriminant Analysis
Abstract
Recycling is a more environmentally friendly method of managing and reducing plastic waste that can significantly reduce land degradation, pollution, and greenhouse gas emissions. According to its composition, an essential first step in the recycling process is sorting out plastic waste. However, inadequate sorting of plastic types can result in cross-contamination and increasing industrial operating costs. A low-cost automated plastic sorting system can be developed by using digital image data in the red, green, and blue (RGB) color space as the dataset and predicting the type using learning datasets. The purpose of this paper is to demonstrate how to use Fisher Discriminant Analysis (FDA) to predict the plastic type from a digital image of the RGB model and then evaluate the performance using cross-validation. This work has four main steps: collecting plastic digital image data, forming statistical tests, predicting plastic types, and evaluating prediction performance. FDA is quite effective for predicting the type of plastic. Performance measures the accuracy of 87.11 %, the recall-micro of 91.67 %, the recall-micro of 80.97 %, the specificity-micro of 90.33 %, and the specificity-macro of 90.38 %, respectively. The micro is determined by the number of decisions made for each object. In comparison, the macro is calculated based on the average decision made by each class.
References
Alpaydin, E. (2016). Introduction to Machine Learning Edition 2 nd. Massachusetts: Massachusetts Institute of Technology Press
Aronoff, S. (1985). The minimum accuracy value as an index of classification accuracy. Photogrammetric Engineering and Remote Sensing, 51(1); 99–111
Bari, M. F. and S. A. Fattah (2020). Epileptic seizure detection in EEG signals using normalized IMFs in CEEMDAN do- main and quadratic discriminant classifier. Biomedical Signal Processing and Control, 58; 101833
Carey, G. (1998). Multivariate analysis of variance (MANOVA) II: practical guide to ANOVA and MANOVA for SAS. Re- trieved September, 1; 2009
Chow, C.-f., W.-M. W. So, and T.-Y. Cheung (2016). Re- search and development of a new waste collection bin to facilitate education in plastic recycling. Applied Environmen- tal Education & Communication, 15(1); 45–57
Chumachenko, K., J. Raitoharju, A. Iosifidis, and M. Gabbouj (2021). Speed-up and multi-view extensions to subclass discriminant analysis. Pattern Recognition, 111; 107660
Dinesh, S. and T. Dash (2016). Reliable Evaluation of Neural Network for Multiclass Classification of Real-World Data. Arxiv Press
Gorunescu, F. (2011). Data Mining: Concepts, Models and Tech- niques, Volume 12. Springer Science & Business Media
Hallin, M. and D. Paindaveine (2009). Optimal tests for homo- geneity of covariance, scale, and shape. Journal of Multivariate Analysis, 100(3); 422–444
Hastie, T., R. Tibshirani, and J. Friedman (2009). The Elements of Statistical Learning 2nd Edition. Springer
James, G., D. Witten, T. Hastie, and R. Tibshirani (2013). An Introduction to Statistical Learning. Springer
Khona’ah, B., D. Rosiliani, and I. Yani (2015). Identification and Clasification of Plastic Color Images Based on The RGB Method. Journal of Multidisciplinary Engineering Science and Technology, 6(6); 10170–10174
Lantz, B. (2019). Machine Learning with R: Expert Techniques for Predictive Modeling. Packt Publishing: Birmingham-Mumbai
Pivnenko, K., M. Eriksen, J. Martín-Fernández, E. Eriksson, and T. Astrup (2016). Recycling of plastic waste: Presence of phthalates in plastics from households and industry. Waste
Management, 54; 44–52
Raudys, Š. and D. M. Young (2004). Results in statistical discriminant analysis: A review of the former Soviet Union literature. Journal of Multivariate Analysis, 89(1); 1–35
Ruj, B., V. Pandey, P. Jash, and V. Srivastava (2015). Sorting of plastic waste for effective recycling. International Journal
of Applied Science and Engineering Research, 4(4); 564–571
Shuai, C., Y. Cheng, W. Yang, P. Feng, Y. Yang, C. He, F. Qi, and S. Peng (2020). Magnetically actuated bone scaffold:
Microstructure, cell response and osteogenesis. Composites Part B: Engineering, 192; 107986
Siddique, R., J. Khatib, and I. Kaur (2008). Use of recycled plastic in concrete: A review. Waste Management, 28(10); 1835–1852
Sokolova, M. and G. Lapalme (2009). A systematic analysis of performance measures for classification tasks. Information Processing & Management, 45(4); 427–437
Srigul, W., P. Inrawong, and M. Kupimai (2016). Plastic classi-
fication base on correlation of RGB color. In 2016 13th Inter- national Conference on Electrical Engineering/Electronics, Com- puter, Telecommunications and Information Technology (ECTI- CON). 1; 1–5
Stevens, J. P. (2012). Applied Multivariate Statistics for The Social Sciences. Routledge
Vranckx, I., J. Raymaekers, B. De Ketelaere, P. J. Rousseeuw, and M. Hubert (2021). Real-time discriminant analysis in the presence of label and measurement noise. Chemometrics and Intelligent Laboratory Systems, 208; 104197
Wahl,P.W.andR.A.Kronmal(1977).Discriminantfunctions when covariances are unequal and sample sizes are moderate. Biometrics, 3(3); 479–484
Wang, X., X. Li, R. Ma, Y. Li, W. Wang, H. Huang, C. Xu,
and Y. An (2018). Quadratic discriminant analysis model for assessing the risk of cadmium pollution for paddy fields in a county in China. Environmental Pollution, 236; 366–372
Yani, I., D. Rosiliani, B. Khona’ah, and F. Almahdini (2020). Identification and plastic type and classification of PET, HDPE, and PP using RGB method. In IOP Conference Series: Materials Science and Engineering, 857; 012015
Authors

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.