SmartAgro-Spectral: Teknik Pengukuran Kandungan Nitrit Pada Sarang Burung Walet Berbasis Spektral Menggunakan Metode Regresi Linier

Abstract

Indonesia is the largest exporter of edible bird’s nest (EBN) to China, involving many EBN farmers from various regions in Indonesia. Therefore, a portable device is needed to rapidly and accurately measure the required quality of SBW to avoid rejection by Chinese buyers, which could result in significant losses. Consequently, for this purpose, an electronic instrument has been developed. smartAgro-Spectral is a microcontroller-based electronic instrument that measures nitrite content in edible bird’s nest (EBN) using linear regression method in machine learning calculations. This instrument can measure nitrite content based on the intensity of colors produced by EBN products. The coloring process is carried out by mixing EBW powder with Sulphanilamide solution and N-(1-naphthyl) Ethylenediamine Dihydrochloride (NED) solution. The concentration of EBN solution is normalized to values between 0.2 ppm and 0.7 ppm. The measurement process is carried out by emitting 18 waves of the light spectrum. The intensity of the 18 wavelengths of the measured light spectrum was selected based on the strong correlation between the intensity of the light spectrum and the value of nitrite content in the EBN product. The measurement results show that the intensity of the light spectrum that has a strong linear correlation is at wavelengths of 460 nm, 485 nm, 510 nm, 535 nm, and 610 nm. So, smartAgro-Spectral electronic instruments can be realized based on the intensity relationship of each wavelength through multiple linear regression analysis, and are able to linearly measure nitrite content in EBW products with a precision level of 99.85% and an accuracy rate of 99.85%.