Smart Waste Management Systems by Using Automated Machine Learning Techniques

https://doi.org/10.55529/jaimlnn.24.16.25

Authors

  • Anuradha Reddy Assistant Professor Malla Re ddy Institute Of Technology and Science
  • Dr. Viswanathan Professor , Punjab Department of Computer Science and Engineering Secun derabad 500100
  • Vikram Gude Assistant Professor Malla Re ddy Institute Of Technology and Science
  • Mamatha K Assistant Professor Malla Re ddy Institute Of Technology and Science
  • D. Nageswara Rao Assistant Professor Chitkara University Institute of Engineering &Technology,

Abstract

This investigating demonstrates how a Smart Waste Manag ement system may use automated machine learning to handle a global question. This investigation focuses on detecting i.e., binary classification which is the removal of a recycling container using detector accumulation. A wide variety of data driven soluti ons for dealing with the difficulty are examined in a realistic context where most natural events are not actual emptying. Among the tactics investigated are the existing manually generated framework and its alteration as well as typical machine learning algorithms. Machine learning improves the assortment quality and reminiscence of the existing enchiridion constructed model from 86.8% and 47.9% to 99.1% and 98.2%, respectively, when utilizing the advanced performing resolution. This method utilizes a Ran dom Forest classifier to categorize a set of attributes based on the quantity of filling at assorted period of time intervals. Ultimately, when similitude to the present enchiridion constructed baseline framework the foremost performing solution amend the quality of prognostication for recycling container evacuation period of time.

Published

2022-06-20

How to Cite

Anuradha Reddy, Dr. Viswanathan, Vikram Gude, Mamatha K, & D. Nageswara Rao. (2022). Smart Waste Management Systems by Using Automated Machine Learning Techniques. Journal of Artificial Intelligence,Machine Learning and Neural Network , 2(04), 16–25. https://doi.org/10.55529/jaimlnn.24.16.25