Feasibility Study for an Optical Sensing System for Hardy kiwi (Actinidia arguta) Sugar Content Estimation

Abstract

In this study, we tried to find out the most appropriate pre-processing method and to verifythe feasibility of developing a low-price sensing system for predicting the hardy kiwis sugarcontent based on VNIRS and subsequent spectral analysis. A total of 495 hardy kiwi sampleswere collected from three farms in Muju, Jeollabukdo, South Korea. The samples were scannedwith a spectrophotometer in the range of 730-2300 nm with 1 nm spectral sampling interval. The measured data were arbitrarily separated into calibration and validation data for sugar contentprediction. Partial least squares (PLS) regression was performed using various combinations ofpre-processing methods. When the latent variable (LV) was 8 with the pre-processing combinationof standard normal variate (SNV) and orthogonal signal correction (OSC), the highest R2 valuesof calibration and validation were 0.78 and 0.84, respectively. The possibility of predicting thesugar content of hardy kiwi was also examined at spectral sampling intervals of 6 and 10 nmin the narrower spectral range from 730 nm to 1200 nm for a low-price optical sensing system. The prediction performance had promising results with R2 values of 0.84 and 0.80 for 6 and10 nm, respectively. Future studies will aim to develop a low-price optical sensing system witha combination of optical components such as photodiodes, light-emitting diodes (LEDs) and/orlamps, and to locate a more reliable prediction model by including meteorological data, soildata, and different varieties of hardy kiwi plants.