Systematic review of artificial intelligence with near-infrared in blueberries

Abstract

The fruit quality has a direct impact on how the fruit looks and how tasty the fruit is. The correct use of tools to determine fruit quality is essential to offer the best product for the final consumer. This study has used the preferred reporting items for systematic reviews and meta-analyses (PRISMA) methodology. The study objective was elaborate a systematic literature review (SLR) about research of the application of techniques based on artificial intelligence to analyze indicators obtained by near infrared spectroscopy (NIRS) and chemometrics to determine the quality of fruits, including blueberries. The most frequently addressed indicator is the soluble solids concentration (SSC) which was used in several studies with techniques such as support vector machines (SVM) and convolutional neural networks (CNN). According to the results obtained, it is possible to use these techniques to predict blueberry quality indicators. There was an acceptable performance and high accuracy of these models. However, future research could cover other techniques and help to provide better quality control of products in food industries.