Perbandingan Performance Algoritma KNN dan Liner Regresi Dalam Percepatan Masa Tanam Sawi Berdasarkan Suhu air dan Nutrisi

Comparison of the Performance of the KNN and Liner Regression Algorithms in Accelerating Mustard Planting Period Based on Water Temperature and Nutrients

Abstract

Hydroponics is a technological advancement in agriculture that allows planting without using soil and relying on water and nutrients for plant growth. This method is effective in overcoming problems in the agricultural sector such as drought and pests which can inhibit the growth of vegetable plants.This study investigates the use of K-Nearest Neighbors (KNN) and Linear Regression algorithms to predict the growth time of mustard greens based on water temperature and nutrient levels. The dataset used includes these variables measured during the growth period. Experimental steps included dividing the data into training and testing sets, feature standardization, model training, and evaluation using metrics such as Mean Squared Error (MSE): KNN model (3.69625) had lower MSE compared to Linear Regression (4.33562), Root Mean Squared Error (RMSE): KNN (1.92156) had lower RMSE compared to Linear Regression (2.08121), R^2 Score: KNN (0.96567) had a slightly higher R^2 Score compared to Linear Regression (0.95932).

 

Keywords:K-Nearest Neighbors, KNN, Linear Regression, growing time, mustard greens, prediction, model evaluation