Sistem Pengukuran Nitrogen, Fosfor, Kalium Dengan Local Binary Pattern Dan Analisis Regresi

Abstract

Nitrogen, Phosphorus and Potassium (NPK) are macro elements that important for the paddy development. NPK is a parameter that used for calculating fertilizer dosage. Current NPK measurement through laboratory requires a relatively long time, so we design a new system that can speed up the process and provide correct fertilizer dosage recommendations.This paper proposes an android based system using Local Binary Pattern (LBP) and Regression Analysis to measure soil nutrients and provide fertilizer dosage recommendations based on the LPT Bogor's formula. Samples of soil image taken from rice fields in Special Region of Yogyakarta. The measurement is processed by extracting LBP features from the soil image that has through the pre-processing stage. The extraction results were then analyzed using Multiple Linear Regression (MLR). The equation results from MLR is used to calculate NPK.The results show that the proposed system can detect NPK levels in paddy fields in Yogyakarta and provide fertilization dosage with an average detection accuracy of 70.65% (N 94.98%, P 50.84 %, and K 66.14%). The accuracy was obtained from the image taking at an optimal height of 70 cm and optimal angle of 0o to the ground surface. The average processing time is 0.61 seconds.