Machine Learning Regression for RF Path Loss Estimation Over Grass Vegetation in IoWSN Monitoring Infrastructure

Abstract

This proposal examines the effect of grass vegetation elevation and density on path loss between sensors deployed in an IoT-enabled wireless sensor network (IoWSN) crop monitoring infrastructures. Observations via real-time measurement campaigns at different node heights and vegetation depths revealed that the sensor deployment made using free-space or tree vegetation based path loss model (PLM) experiences network disconnectivity due to variations in vegetation density in a cropping cycle. An empirical PLM is formulated to identify signal strength at different development phases of paddy and sugarcane medium grass vegetation. For this, the 2.4 GHz RF path loss coefficient (PLC) is estimated using data collected through measurement campaign over combinations of sensor height and vegetation density. Further, the formulated PLC is used to train multiple regression model to develop a generic PLM for all medium grass vegetation. Improvements in coverage and connectivity have been validated through proof of concept.