Abstract
This paper describes about a sorting bin of Recyclable Municipal Solid Waste. This bin is described as intelligent due to automatic source separation method has been implemented in this bin. A method called Convolutional Neural Network (CNN) has been implemented in waste sorting process. CNN is one kind of deep learning process. CNN is very fast, efficient and reliable method for object classification. For this reason, this method is implemented for waste sorting. There are many algorithms have already been developed for object detection. Among these algorithms the Inception-ResNet V2 is used. Inception-ResNet V2 is simply the combination of the Inception and the Residual Network structure. This model is trained by images of PET and LDPE about 300 of each sample. PET bottles and chips packet has been considered as sample. Training has been done by Google Collaboratory platform. Accuracy of detection is measured on the basis of 100 observations and accuracy is 84 CSS for manual feeding of image and decision making. This technique may increase recyclable MSW (PET LDPE) collection rate, reduce environment pollution, can help recycling plants economically.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
