Application o f Advanced Machine Learning and Artificial Neural Network Methods in Wireless Sensor Networks Based Applications

Abstract

Wireless sensor networks (WSN) have become very interesting areas of study in computer science these days. WSN is a group of sensors that are used in the physical world. It's easy to see how small these sensors are. They can detect physical wonders and help you deal with them. One of the most important reasons for distributing WSN-built-up applications is to make a decision about what to do next, which has been difficult because WSNs have limited processing power, limited storage space, and a lot of quickly changed data. This makes it important to look into new and appropriate data mining methods that can extract learning from a huge amount and a wide range of information that WSNs send out all the time. Machine Learning algorithms like Random Forest Regression and Artificial Neural networks are used in wireless sensor network-based applications like this one. This article also presents a comprehensive comparison of results from the application of Random Forest Regression and Artificial Neural Network algorithms to WSN data. Keywords: Wireless Sensor Networks,