Internet of things (IoT) results in massive amount of streaming data, often referred to as “big data”, which brings new opportunities to monitor agricultural and food processes. Besides sensors, big data from social media is also becoming important for the food industry. In this review we present an overview of IoT, big data, and artificial intelligence (AI) and their disruptive role in shaping the future of agri-food systems. Following an introduction to the fields of IoT, big data, and AI, we discuss the role of IoT and big data analysis in agriculture (including greenhouse monitoring, intelligent farm machines, and drone-based crop imaging), supplychain modernization, social media (for open innovation and sentiment analysis) in food industry, food quality assessment (using spectral methods and sensor fusion), and finally, food safety (using gene sequencing and blockchain based digital traceability). A special emphasis is laid on the commercial status of applications and translational research outcomes.

Ripeness classification is one of the most challenging tasks in the postharvest management of mulberry fruit. The risks of microbial contamination and human error in manual sorting are significant; it may result in quality degradation and wasting of processed products. Due to advanced developments in computer vision and machine learning, automated sorting became possible. This study presents the results of developing and testing a computer vision-based application using convolutional neural networks (CNNs) for the classification of mulberry fruit ripening stages. To reduce the training cost and improve the accuracy of classification, transfer learning was used to fine-tune the CNN models. The CNN models in the test include DenseNet, Inception-v3, ResNet-18, ResNet-50, and AlexNet. Transfer learning was used to fine-tune the models and improve the accuracy of classification. The AlexNet and ResNet-18 networks exhibited the best performance with 98.32% and 98.65% overall accuracy for classifying the ripeness of white and black mulberries, respectively. Moreover, the performance of the models did not change when the data sets of both genotypes were mixed. The ResNet-18 was able to classify both genotype and ripeness from 600 fruit images in 2.36 min with an overall accuracy of 98.03%, which was superior to other architectures. It indicates that the model could be used for precise classification of the ripening stages of mulberries and other horticultural products, as a part of an automated sorting system.

Previous experiments have demonstrated positive effect of Acadian® extract of Ascophyllum nodosum on plant stress-resistance, however the mode of action is not fully understood. The aim of this study was to understand the physiological effect of Acadian® seaweed extract on the plant response to drought stress. Leaf temperature and leaf angle were measured as early-stage indicators of plant stress with thermal imaging “in situ” over a 5-day stress-recovery trial. The early stress-response of control became visible on the third day as a rapid wilting of leaves, accompanied with the asymptotic increase of leaf temperature on 4–5 °C to the thermal equilibrium with ambient air temperature. At the same time Acadian® treated plants still maintained turgor, accompanied with the linear increase in leaf temperature, which indicated better control of stomatal closure. Re-watering on the fifth day showed better survival of treated plants compared to control. This study demonstrated the ability of Acadian® seaweed extract to improve resistance of soybean plants to water stress.

Interest in the development and adoption of nonthermal technologies is burgeoning within the food and bioprocess industry, the associated research community, and among the consumers. This is evident from not only the success of some innovative nonthermal technologies at industrial scale, but also from the increasing number of publications dealing with these topics, a growing demand for foods processed by nonthermal technologies and use of natural ingredients. A notable feature of the nonthermal technologies such as cold plasma, electrohydrodynamic processing, pulsed electric fields, and ultrasound is the involvement of external fields, either electric or sound. Therefore, it merits to study the fundamentals of these technologies and the associated phenomenon with a unified approach. In this review, we revisit the fundamental physical and chemical phenomena governing the selected technologies, highlight similarities, and contrasts, describe few successful applications, and finally, identify the gaps in research.

Nutrient damage and high energy consumption are the challenges of convective drying to achieve food security and economic stability. Wild berries have high nutritional value, but they are difficult to dry because of the waxed skin tissue. Such a cellular structure is highly resistant to mass transfer, which increases drying time and nutrient degradation. Although chemical pretreatments can facilitate a mass transfer, they reduce the amounts of soluble nutrients. As an alternative, we propose an innovative strategy with cold plasma pretreatment followed by ultrasound-assisted convective drying. Cold plasma pretreatment enabled reducing drying temperature from 60–90 °C to 50 °C, which improved the nutritional quality of the dried goldenberries. The application of ultrasound energy significantly reduced drying time. Compared to the untreated convective dried samples, the vitamin C retention, antioxidant activity, and total phenolic content increased by up to 175.07%, 84.32%, and 52.31%, respectively. This drying approach can significantly contribute to food security by improving product quality, nutritional value, shelf stability, and reducing greenhouse gas emissions.

Although very important for analysis of drying processes, physics-based models are limited in terms of their prediction ability and in most cases are unsuitable for real-time process control and optimization of industrial drying. In this paper, we provide an overview of the machine learning (ML) techniques and the state-of-the-art ML applications in drying of food and biomaterials. The applications include but not limited to data-driven models, nonlinear control and multi-objective optimization. The advantages of integration of ML with machine vision for real-time observation of product quality and fine-tuning control strategies are briefly discussed. Future research should focus on the integration of ML software tools with sensors to measure process and product variables. In addition, the drying research community should contribute towards building of open-source datasets, which is extremely important to leverage the power of ML algorithms. Integration of sensors, process analysis and software engineering will enable the development of “intelligent” drying systems.