Machine Learning Enabled Nanosensor Array for Monitoring Citrus Juice Adulteration

Abstract

Citrus fruit is a global commodity that is decreasing in production, leading to adulteration and fraud of citrus juices. Here, a biomarker-free detection assay was developed using an optical nanosensor array to aid in the food safety of citrus juices. Coupling the machine learning capability of our computational process named algorithmically guided optical nanosensor selector (AGONS) with the fluorescence data collected using our nanosensor array, we studied hundreds of citrus juice adulterations. Over 707 measurements of pure and adulterated citrus juices were collected for prediction. Overall, our approach achieved above 90% accuracy on three data sets in discriminating three pure citrus fruit juices, artificially sweetened tangerine juice with various concentrations of corn syrup, and juice-to-juice dilution of orange juice using apple juice. This machine learning-enabled nanosensor array can be applied toward combating food fraud worldwide in the rising threat to food security.

Machine Learning Techniques for Improving Nanosensors in Agroenvironmental Applications

“…", it was demonstrated that the main problems addressed via the application of nanosensors in conjunction with machine learning are food safety and food classification, the detection of agrochemicals, plant protection and environmental sensing. In general, these applications involve the detection of marker chemicals associated with food decay [190], food adulteration [180] and plant infection [211], as well as the presence of contaminants in food [178] and environmental samples [104]. Table 1 is a summary of the reviewed work classified according to the problem addressed and the type of nanosensor used.…”

“…The use of an algorithmically guided optical nanosensor selector (AGONS) was reported by Smith et al [179,180]; data from optical nanosensor arrays were analysed in order to improve data for biomarker detection [179] and the detection of citrus juices' adulteration [180].…”

Machine-Learning-Enhanced Fluorescent Nanosensor Based on Carbon Quantum Dots for Heavy Metal Detection

“…In order to overcome these challenges, machine learning and deep learning approaches for accurate fluorescent signal analysis of optical nanosensors have started to be developed recently. − Representative methods have been explored such as discrimination of fluorometric images of various target analytes using convolutional neural network (CNN) models and anomaly detection of the fluorescence signals using Isolation Forest (iForest) or one-class support sector machine (SVM), among others. − These attempts were successful in precisely distinguishing the stimulation source of the fluorescence signal of the sensors and effectively calculating the biochemical fingerprints from the multivariate data. Significant improvements for the fluorescent sensor signal processing have been achieved; however, there has been still no technique on discrimination of fluorescence signal changes near the noise fluctuation level .…”