Enhanced segmentation network with deep learning for Biomedical waste classification

T Mythili; A Anbarasi

doi:10.17485/IJST/v14i2.2137

Article

Enhanced segmentation network with deep learning for Biomedical waste classification

VIEWS 2463
PDF 528

Indian Journal of Science and Technology

DOI: 10.17485/IJST/v14i2.2137

Year: 2021, Volume: 14, Issue: 2, Pages: 141-153

Original Article

Enhanced segmentation network with deep learning for Biomedical waste classification

T Mythili^1*, A Anbarasi²

¹Ph.D. Research Scholar, Department of Computer Science, L. R. G. Government Arts College for Women, Tiruppur, Tamilnadu, India
²Assistant Professor, Department of Computer Science, L. R. G. Government Arts College for Women, Tiruppur, Tamilnadu, India

*Corresponding Author
Email: [email protected]

Received Date:26 November 2020, Accepted Date:26 December 2020, Published Date:20 January 2021

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

Abstract

Objective: To maximize the accuracy of classifying the medical wastage, an Enhanced Segmentation Network (EnSegNet) with Deep Neural Network-Trash Classification (EnSegNet-DNN-TC) is proposed in this article. Methods: Initially, a core trainable segmentation network called SegNet framework is proposed which uses the Encoder-Decoder Network (EDN) and a pixel-wise classification layer for image segmentation. The decoder is used to upsample its low-resolution input feature maps via max-pooling. Also, SegNet uses fewer parameters for training. The uncertainty inherent to the EDN is modeled by the Bayesian functions to segment the input images. But, this SegNet can sample a limited amount of pixels in the images. Hence, an EnSegNet is proposed that uses Content-Sensitive Sampling (CSS) to sample more pixels in the data-sparse regions and fewer pixels in data-dense regions. Once the segmentation is completed, the DNN is applied for classifying the wastage using the segmented images. Findings: The experimental results show that the EnSegNet-DNN-TC framework achieves 88% accuracy compared to the DNN-TC for considering 100 images of different categories of biomedical wastes from the trash image dataset.

Keywords: Biomedical wastage classification; deep learning; image segmentation; ResNext; encoder-decoder network

References

Ilyas S, Srivastava RR, Kim H. Disinfection technology and strategies for COVID-19 hospital and bio-medical waste management. Science of The Total Environment. 2020;749. Available from: https://dx.doi.org/10.1016/j.scitotenv.2020.141652
Datta P, Mohi G, Chander J. Biomedical waste management in India: Critical appraisal. Journal of Laboratory Physicians. 2018;10(01):006–014. Available from: https://dx.doi.org/10.4103/jlp.jlp_89_17
Chauhan A, Singh A. A hybrid multi-criteria decision making method approach for selecting a sustainable location of healthcare waste disposal facility. Journal of Cleaner Production. 2016;139:1001–1010. Available from: https://doi.org/10.1016/j.jclepro.2016.08.098
Achuthan A, Madangopal VA. A bio medical waste identification and classification algorithm using MLTRP and RVM. Iranian Journal of Public Health. 2016;45(10):1276.
Bircanoğlu C, Atay M, Beşer F, Genç Ö, Kızrak MA. Recyclenet: Intelligent waste sorting using deep neural networks. IEEE Innovations in Intelligent Systems and Applications. 2018;p. 1–7. Available from: https://doi.org/10.1109/INISTA.2018.8466276
Vo AH, Vo MT, Le T. A novel framework for trash classification using deep transfer learning. IEEE Access. 2019;7:178631–178639.
Kennedy T. Stanford University OscarNet: using transfer learning to classify disposable waste. CS230 Report: Deep Learning.
Chu Y, Huang C, Xie X, Tan B, Kamal S, Xiong X. Multilayer hybrid deep-learning method for waste classification and recycling. Computational Intelligence and Neuroscience. 2018. Available from: https://doi.org/10.1155/2018/5060857
Aral RA, Keskin ŞR, Kaya M, Hacıömeroğlu M. Classification of trashnet dataset based on deep learning models. In: IEEE International Conference on Big Data. (pp. 2058-2062) 2018.
Adedeji O, Wang Z. Intelligent Waste Classification System Using Deep Learning Convolutional Neural Network. Procedia Manufacturing. 2019;35:607–612. Available from: https://dx.doi.org/10.1016/j.promfg.2019.05.086
Sousa J, Rebelo A, Cardoso JS. Automation of waste sorting with deep learning. In: IEEE XV Workshop de Visão Computacional. (pp. 43-48) 2019.
Xue W, Hu X, Wei Z, Mei X, Chen X, Xu Y. A fast and easy method for predicting agricultural waste compost maturity by image-based deep learning. Bioresource Technology. 2019;290. Available from: https://doi.org/10.1016/j.biortech.2019.121761
Mazloumian A, Rosenthal M, Gelke H. Deep learning for classifying food waste. 2020.
Toğaçar M, Ergen B, Cömert Z. Waste classification using AutoEncoder network with integrated feature selection method in convolutional neural network models. Measurement. 2020;153. Available from: https://dx.doi.org/10.1016/j.measurement.2019.107459
Nowakowski P, Pamuła T. Application of deep learning object classifier to improve e-waste collection planning. Waste Management. 2020;109:1–9. Available from: https://dx.doi.org/10.1016/j.wasman.2020.04.041
Wang T, Cai Y, Liang L, Ye D. A Multi-Level Approach to Waste Object Segmentation. Sensors. 2020;20(14):3816. Available from: https://dx.doi.org/10.3390/s20143816
Rezende E, Ruppert G, Carvalho T, Theophilo A, Ramos F, Geus PD. Malicious software classification using VGG16 deep neural network’s bottleneck features. In: Information Technology-New Generations. (pp. 51-59) Springer. 2018.

Copyright

© 2021 Mythili & Anbarasi.This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)