Application of deep learning object classifier to improve e-waste collection planning. (15th May 2020)

• Record Type: Journal Article
• Authors: Nowakowski, Piotr; Pamuła, Teresa
• Is Part Of: Waste management. Volume 109(2020)
• Page Start: 1
• Page End: 9
• Publication Date: 2020-05-15
• Subjects: E-waste -- Waste electrical and electronic equipment -- Deep learning object classifier -- E-waste detector -- Convolutional neural network -- Waste collection planning; Hazardous wastes -- Periodicals; Refuse and refuse disposal -- Periodicals; 363.728
• DOI: 10.1016/j.wasman.2020.04.041
• Languages: English
• ISSNs: 0956-053X

Abstract

Highlights: Novel identification method of e-waste from photos. Application of convolutional neural networks for the identification of waste equipment. High recognition and classification accuracy of the selected e-waste categories ranged from 90 to 97%. Ease in requesting e-waste collection by taking and uploading e-waste pictures. Supporting e-waste collection planning. Abstract: This study investigates an image recognition system for the identification and classification of waste electrical and electronic equipment from photos. Its main purpose is to facilitate information exchange regarding the waste to be collected from individuals or from waste collection points, thereby exploiting the wide acceptance and use of smartphones. To improve waste collection planning, individuals would photograph the waste item and upload the image to the waste collection company server, where it would be recognized and classified automatically. The proposed system can be operated on a server or through a mobile app. A novel method of classification and identification using neural networks is proposed for image analysis: a deep learning convolutional neural network (CNN) was applied to classify the type of e-waste, and a faster region-based convolutional neural network (R-CNN) was used to detect the category and size of the waste equipment in the images. The recognition and classification accuracy of the selected e-waste categories ranged from 90 to 97%. After the size and category of the waste is automatically recognized and classified from the uploaded images, e-waste collection companies can prepare a collection plan by assigning a sufficient number of vehicles and payload capacity for a specific e-waste project.