By contrasting Random Forest with Convolutional Neural Networks, a novel location intelligence-based smart waste management system is developed.

Abstract

Aim: The aim of the research work is to classify an end user's Smart Waste Management system using random forest and conventional neural networks. Materials and Methods: The categorizingis performed by adopting a sample size of n = 10 in random forest and sample size n=10 in conventional neural networks was iterated 20 times for efficient and accurate analysis on labeled images with G power in 80% and threshold 0.05%, CI 95% mean and standard deviation. Results and Discussion: The analysis of the results shows that the random forest has a high accuracy 91.96% comparison with the conventional neural networks algorithm (81.87). There is a statistically significant difference between the study groups with p<0.05. Conclusion: Prediction in classifying an end user's waste management system shows that the random forest appears to generate 91.96% better accuracy than the waste system conventional neural networks algorithm.