IoT in Agriculture and Environmental Sustainability

Abstract

This exploration investigates the collaborations between Internet of Things (IoT) advancements and horticulture, zeroing in on the groundbreaking effect of decision Trees (DT), Random Forest (RF), Support Vector Machines (SVM), and K-Means Grouping (KMC). Persuaded by the basic to address worldwide populace development and cultivate feasible horticultural practices, the review surveys these calculations with regards to accuracy cultivating. Utilizing a different dataset from IoT sensors, the exploration utilizes thorough examinations and relative measurements, including exactness, accuracy, review, F1 score, and relapse measurements, to assess the presentation of every calculation. With an accuracy of 92%, the results show that Random Forest outperforms other algorithms, effectively reducing the overfitting in Decision Trees. Support Vector Machines exhibit vigorous grouping abilities, accomplishing an exactness of 88%. K-Means Clustering features utility in field division, adding to the accuracy of agribusiness procedures with a precision of 84%. Decision Trees, regardless of incidental overfitting, keep an excellent exactness of 85%. Regression metrics uncover that Random Forest accomplishes a MSE of 7.2 and an R-squared worth of 0.82, stressing its adequacy in advancing asset use. These discoveries give pivotal bits of knowledge to professionals and policymakers, featuring the assorted qualities and uses of every calculation in improving farming proficiency. The exploration makes way for the reconciliation of IoT-driven advances into accuracy agribusiness, offsetting efficiency with ecological supportability.