Data integration of humidity sensor and image texture for water content prediction of Gracilaria sp. during sun drying

Abstract Water content on site-measurement of dried seaweed required method with a minimum time sample preparation time, less destructive effect to the sample, and could be validated. This research aimed evaluate potency some features consist image texture, resistance, capacitance data humidity sensor predict water changing Gracilaria sp. during sun-drying. Dried was rehydrated before being used in sun-drying for 4 hours. Gravimetrically-based evaluation, digital taking, measurement resistance value were conducted every 30 minutes interval drying. Images captured collected by webcam conditioned lighting chamber subsequently extraction texture while array contained 2 resistive sensors 1 capacitive respectively applied collect data. Collected create datasets i.e. (1) 54 features; (2) 3 (3) 57 combination dataset 2; (4) 11 Features selected from 3. Correlation coefficient Root Mean Square Error model evaluation utilized Multiple Linear Regression (MLR) Layer Perceptron-based Neural Network (MLPNN). Investigation cross-validation 10 folds test showed that MLPNN best correlation RMSE reached 0.89 9.11 respectively. Data integration substantial prediction sun