A Machine Learning Based Framework for Intelligent High Density Garbage Area Classification

Abstract

With increase in pollution level, the need of proper management of garbage is also increasing rapidly. In current scenario enormous amount of garbage/waste generated every day, which require proper dumping of waste and recycling of it. The improper disposal of waste leads to numerous health related disease. Although agencies try hard to collect waste from all areas, still they lack in it. One major reason behind this is the inaccurate tracking of areas with garbage. Agencies are using traditional methodologies for assessment and tracking of areas which need to be upgraded by using current technologies. In this paper we propose a machine learning based framework to classify the areas which are free from garbage and areas with having high density garbage. In our approach we have used four different algorithms and achieved the accuracy of 98.6% with kNN and Naive Bayes, 85.4% with Decision Tree and 98.4% with Random Forest.