Rapid Detection of Fraudulent Rice Using Low-Cost Digital Sensing Devices and Machine Learning

Abstract

Rice fraud is one of the common threats to the rice industry. Conventional methods to detect rice adulteration are costly, time-consuming, and tedious. This study proposes the quantitative prediction of rice adulteration levels measured through the packaging using a handheld near-infrared (NIR) spectrometer and electronic nose (e-nose) sensors measuring directly on samples and paired with machine learning (ML) algorithms. For these purposes, the samples were prepared by mixing rice at different ratios from 0% to 100% with a 10% increment based on the rice's weight, consisting of (i) rice from different origins, (ii) premium with regular rice, (iii) aromatic with non-aromatic, and (iv) organic with non-organic rice. Multivariate data analysis was used to explore the sample distribution and its relationship with the e-nose sensors for parameter engineering before ML modeling. Artificial neural network (ANN) algorithms were used to predict the adulteration levels of the rice samples using the e-nose sensors and NIR absorbances readings as inputs. Results showed that both sensing devices could detect rice adulteration at different mixing ratios with high correlation coefficients through direct (e-nose; R = 0.94-0.98) and non-invasive measurement through the packaging (NIR; R = 0.95-0.98). The proposed method uses low-cost, rapid, and portable sensing devices coupled with ML that have shown to be reliable and accurate to increase the efficiency of rice fraud detection through the rice production chain.

Keywords: adulteration; artificial intelligence; electronic nose; food fraud; near-infrared; sensor.

Figure 1

Regression models developed using (a) electronic nose sensors data (Model 1–6) and (b) NIR absorbance values (Model 7–12) as inputs to predict the rice adulteration levels of six adulterated rice samples. The description of the adulterated rice samples is available in Table 1.

Figure 2

Near-infrared curves of raw absorbance values for adultered rice samples with different proportions of adulterants for (a) Adulterated Rice 1, (b) Adulterated Rice 2, (c) Adulterated Rice 3, (d) Adulterated Rice 4, (e) Adulterated Rice 5, and (f) Adulterated Rice 6. The description of rice mixtures and their abbreviations are shown in Table 1. Abbreviation: 0% adulteration (A0), 10% adulteration (A10), 20% adulteration (A20), 30% adulteration (A30), 40% adulteration (A40), 50% adulteration (A50), 60% adulteration (A60), 70% adulteration (A70), 80% adulteration (A80), 90% adulteration (A90), and 100% adulteration (A100).

Figure 3

Results from principal components analysis showing a biplot of rice samples with different levels of adulteration and e-nose sensors for (a) Adulterated Rice 1, (b) Adulterated Rice 2, (c) Adulterated Rice 3, (d) Adulterated Rice 4, (e) Adulterated Rice 5, and (f) Adulterated Rice 6. The abbreviations of the rice samples and e-nose sensors are shown in Table 1 and Materials and Methods. PC1: Principle component 1 and PC2: Principal component 2.

Figure 4

The overall correlation of the regression ANN models developed to predict rice adulteration levels using e-nose sensors for (a) Model 1, (b) Model 2, (c) Model 3, (d) Model 4, (e) Model 5, and (f) Model 6. The abbreviations of the rice samples are shown in Table 1.

Figure 5

The overall correlation of the artificial neural network regression models developed to predict rice adulteration levels using NIR absorbance values for (a) Model 7, (b) Model 8, (c) Model 9, (d) Model 10, (e) Model 11, and (f) Model 12. The abbreviations of the rice samples are shown in Table 1.