Sains Malaysiana 53(2)(2024): 447-459

http://doi.org/10.17576/jsm-2024-5302-17

Optimizing Degradable Plastic Density Prediction: A Coarse-to-Fine Deep Neural Network Approach

(Mengoptimumkan Ramalan Ketumpatan Plastik Terdegradasi: Pendekatan Rangkaian Neuron Dalam Carian Kasar-ke- Halus)

SYAMSIAH ABU BAKAR^1,2,*, SAIFUL IZZUAN HUSSAIN² & ZIROUR MOURAD³

¹Department of Mathematics, Universiti Kuala Lumpur Malaysia France Institute, 43650 Bandar Baru Bangi, Selangor, Malaysia

²School of Mathematical Sciences, Faculty of Science and Technology, Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia 

³France Collaboration Programme, Universiti Kuala Lumpur Malaysia France Institute, 43650 Bandar Baru Bangi, Selangor, Malaysia

Received: 7 July 2023/Accepted: 15 January 2024

Abstract

Density is an important property for the production of high-quality degradable plastics. Density is useful to determine the type of plastic material and to detect physical changes in the plastic material. In this paper, a novel technique for predicting the density of degradable plastics using Deep Neural Networks (DNN) is presented. The aim was to reduce the dimension of the inputs in order to establish a strong relationship between the inputs using principal component analysis (PCA). The results show that the combination of polyethylene, oil palm biomass, starch and palm oil has a greater impact on predicting the density of degradable plastics. Subsequently, the number of hidden neurons is determined by a coarse-to-fine search to develop the network topology of the DNN model for predicting the density of degradable plastics. The developed DNN model consists of 4 input neurons, 62 neurons in the first hidden layer, 31 neurons in the second hidden layer and one output neuron. The developed DNN model showed high accuracy with the lowest values for RMSE, MAE and MSE, indicating that the use of a DNN model is a suitable method for predicting the density of degradable plastics. Furthermore, this study has the potential to make rapid and accurate predictions about the physical properties of degradable plastics in the context of polymers.

Keywords: Deep Neural Networks; degradable plastics; density

Abstrak

Ketumpatan adalah sifat penting untuk pengeluaran plastik terurai berkualiti tinggi. Ketumpatan berguna untuk menentukan jenis bahan plastik dan untuk mengesan perubahan fizikal dalam bahan plastik. Dalam kajian ini, teknik baharu untuk meramalkan ketumpatan plastik terurai menggunakan Rangkaian Neuron Dalam (DNN) dibentangkan. Matlamatnya adalah untuk mengurangkan dimensi input bagi mewujudkan hubungan yang kukuh antara input menggunakan analisis komponen utama (PCA). Keputusan menunjukkan bahawa gabungan polietilena, biojisim kelapa sawit, kanji dan minyak sawit mempunyai kesan yang lebih besar dalam meramalkan ketumpatan plastik terurai. Seterusnya, bilangan neuron tersembunyi ditentukan oleh carian kasar ke halus untuk membangunkan topologi rangkaian model DNN untuk meramalkan ketumpatan plastik terdegradasi. Model DNN yang dibangunkan terdiri daripada 4 neuron input, 62 neuron dalam lapisan tersembunyi pertama, 31 neuron dalam lapisan tersembunyi kedua dan satu neuron output. Model DNN yang dibangunkan menunjukkan ketepatan yang tinggi dengan nilai terendah untuk RMSE, MAE dan MSE, menunjukkan bahawa penggunaan model DNN adalah kaedah yang sesuai untuk meramalkan ketumpatan plastik terdegradasi. Selain itu, kajian ini berpotensi untuk membuat ramalan yang cepat dan tepat tentang sifat fizikal plastik terdegradasi dalam konteks polimer.

Kata kunci: Ketumpatan; plastik terdegradasi; Rangkaian Neuron Dalam

REFERENCES

Azman, B.M., Hussain, S.I., Azmi, N.A., Athir, M.Z., Ghani, A. & Norlen, N.I.D. 2022. Prediction of distant recurrence in breast cancer using a deep neural network. Revista Internacional de Métodos Numéricos para Cálculo y Diseño en Ingeniería 38(1). https://www.scipedia.com/public/Azman_et_al_2021a

Bakar, S.A., Hussain, S.I., Zirour, M. & Noor, M.F.M. 2023. Principal component analysis and deep neural networks in modeling the melt flow index of degradable plastics. International Journal of Advances in Engineering Sciences and Applied Mathematics https://doi.org/10.1007/s12572-023-00352-5

Doukim, C.A., Dargham, J.A. & Chekima, A. 2010. Finding the number of hidden neurons for an MLP neural network using coarse to fine search technique. 10th International Conference on Information Science, Signal Processing and Their Applications (ISSPA 2010). pp. 606-609.

Doukim, C.A., Dargham, J.A., Chekima, A. & Omatu, S. 2011. Combining neural networks for skin detection. arXiv:1101.0384.

Dugvekar, M. & Dixit, S. 2021. High density polyethylene composites reinforced by jute fibers and rice stalk dust: A mechanical study. Materials Today: Proceedings 47: 5966-5969.

Etim, A.O. 2022. Experimental and computational exploration of advanced biodiesel fuels and hybridisation process evaluation of feedstocks and their chemical combinations. PhD Thesis. Durban University of Technology (Unpublished). 

Gimenez‐Nadal, J.I., Molina, J.A. & Velilla, J. 2019. Modelling commuting time in the US: Bootstrapping techniques to avoid overfitting. Papers in Regional Science 98(4): 1667-1684.

Huang, G-B. 2003. Learning capability and storage capacity of two-hidden-layer feedforward networks. IEEE Transactions on Neural Networks 14(2): 274-281.

Jahedsaravani, A., Marhaban, M.H. & Massinaei, M. 2016. Application of statistical and intelligent techniques for modeling of metallurgical performance of a batch flotation process. Chemical Engineering Communications 203(2): 151-160.

Jahedsaravani, A., Marhaban, M. & Massinaei, M. 2014. Prediction of the metallurgical performances of a batch flotation system by image analysis and neural networks. Minerals Engineering 69: 137-145.

Khaki, S. & Wang, L. 2019. Crop yield prediction using deep neural networks. Frontiers in Plant Science 10: 621. https://doi.org/10.3389/fpls.2019.00621

Khan, S.M., Malik, S.A., Gull, N., Saleemi, S., Islam, A. & Butt, M.T.Z. 2019. Fabrication and modelling of the macro-mechanical properties of cross-ply laminated fibre-reinforced polymer composites using artificial neural network. Advanced Composite Materials 28(4): 409-423.

Leong, Y.K., Chang, C-K., Arumugasamy, S.K., Lan, J.C-W., Loh, H-S., Muhammad, D. & Show, P.L. 2018. Statistical design of experimental and bootstrap neural network modelling approach for thermoseparating aqueous two-phase extraction of polyhydroxyalkanoates. Polymers 10(2): 132.

Liang, H., Zhang, S., Sun, J., He, X., Huang, W., Zhuang, K. & Li, Z. 2019. Darts+: Improved differentiable architecture search with early stopping. arXiv:1909.06035.

Mairpady, A., Mourad, A-H.I. & Mozumder, M.S. 2021. Statistical and machine learning-driven optimization of mechanical properties in designing durable hdpe nanobiocomposites. Polymers 13(18): 3100.

Mohammadi, F., Bina, B., Karimi, H., Rahimi, S. & Yavari, Z. 2020. Modeling and sensitivity analysis of the alkylphenols removal via moving bed biofilm reactor using artificial neural networks: Comparison of levenberg marquardt and particle swarm optimization training algorithms. Biochemical Engineering Journal 161: 107685.

Muraina, I.O. 2022. Ideal dataset splitting ratios in machine learning algorithms: General concerns for data scientists and data analysts. 7th International Mardin Artuklu Scientific Research Conference, Mardin, Turkey.  pp. 496-504.

Narine, L.L., Popescu, S.C. & Malambo, L. 2019. Synergy of ICESat-2 and landsat for mapping forest above ground biomass with deep learning. Remote Sensing 11(12): 1503.

Nguyen, Q.H., Ly, H-B., Ho, L.S., Al-Ansari, N., Le, H.V., Tran, V.Q., Prakash, I. & Pham, B.T. 2021. Influence of data splitting on performance of machine learning models in prediction of shear strength of soil. Mathematical Problems in Engineering 2021: 4832864.

Popoola, S.I., Jefia, A., Atayero, A.A., Kingsley, O., Faruk, N., Oseni, O.F. & Abolade, R.O. 2019. Determination of neural network parameters for path loss prediction in very high frequency wireless channel. IEEE Access 7: 150462-150483.

Raja, V., Santhamoorthy, M., Alagumalai, K., Haldhar, R., Raorane, C.J., Raj, V. & Kim, S-C. 2022. Novel approach in biodegradation of synthetic thermoplastic polymers: An overview. Polymers 14(20): 4271.

Rosli, N.A., Wan Ishak, W.H. & Ahmad, I. 2021. Eco-friendly high-density polyethylene/amorphous cellulose composites: Environmental and functional value. Journal of Cleaner Production 290: 125886.

Salunke, A. 2022. Bio-degradable plastic from corn starch & cassava starch. International Research Journal of Modernization in Engineering Technology and Science 4: 959-964.

Shahin, M.A., Maier, H.R. & Jaksa, M.B. 2000. Evolutionary Data Division Methods for Developing Artificial Neural Network Models in Geotechnical Engineering. Report number R171, Dept. Civil & Env. Engrg., University of Adelaide.

Shin-Ike, K. 2010. A two phase method for determining the number of neurons in the hidden layer of a 3-layer neural network. Proceedings of SICE Annual Conference 2010.  pp. 238-242.

Swamidass, P.M. 2000. Forecasting mean percentage error in mean percentage error (MPE). Encyclopedia of Production and Manufacturing Management. Boston: Springer US. pp. 462-463.

Zaman, H. & Beg, M.D.H. 2021. Effect of filler starches on mechanical, thermal and degradation properties of low-density polyethylene composites. Progress in Applied Science and Technology 11(2): 26-36.

Zaman, H. & Khan, R.A. 2021. Improving the physico-mechanical and degradable properties of thermoplastic polymer with modified starch blend composites for food packaging applications. Progress in Applied Science and Technology 11(3): 1-8.

*Corresponding author; email: syamsiah@unikl.edu.my