The rapid growth of the human population, the increase in consumer needs regarding food authenticity, and the sub-par synchronization between agricultural and food industry production necessitate the development of reliable track and tracing solutions for food commodities. The present research proposes a simple and affordable digital system that could be implemented in most production processes to improve transparency and productivity. The system combines non-destructive, rapid quality assessment methods, such as near infrared spectroscopy (NIRS) and computer/machine vision (CV/MV), with track and tracing functionalities revolving around the Internet of Things (IoT) and radio frequency identification (RFID). Meanwhile, authenticity is provided by a self-developed blockchain-based solution that validates all data and documentation “from farm to fork”. The system is introduced by taking certified Hungarian sweet potato production as a model scenario. Each element of the proposed system is discussed in detail individually and as a part of an integrated system, capable of automatizing most production flows while maintaining complete transparency and compliance with authority requirements. The results include the data and trust model of the system with sequence diagrams simulating the interactions between participants. The study lays the groundwork for future research and industrial applications combining digital tools to improve the productivity and authenticity of the agri-food industry, potentially increasing the level of trust between participants, most importantly for the consumers.

Non-destructive testing (NDT) for eggshell faults is highly important for the egg industry, as cracked eggs account for around 3% of total production. The most commonly used method at present, candling, is labor intensive, while computer vision systems are expensive and complicated. In this paper, we present a simple, yet efficient, novel method for eggshell crack detection by acoustic spectroscopy. Altogether, 693 sound recordings were evaluated by different classification methods. The results show a cross-validated 2.1% total classification error, with only 0.87% false positive rate, which is the crucial metric for fresh eggs. Adapting the developed method to an industrial setting may lead to a reliable, fast and cost-effective detection method.

Coffee is both a vastly consumed beverage and a chemically complex matrix. For a long time, an arduous chemical analysis was necessary to resolve coffee authentication issues. Despite their demonstrated efficacy, such techniques tend to rely on reference methods or resort to elaborate extraction steps. Near infrared spectroscopy (NIRS) and the aquaphotomics approach, on the other hand, reportedly offer a rapid, reliable, and holistic compositional overview of varying analytes but with little focus on low concentration mixtures of Robusta-to-Arabica coffee. Our study aimed for a comparative assessment of ground coffee adulteration using NIRS and liquid coffee adulteration using the aquaphotomics approach. The aim was to demonstrate the potential of monitoring ground and liquid coffee quality as they are commercially the most available coffee forms. Chemometrics spectra analysis proved capable of distinguishing between the studied samples and efficiently estimating the added Robusta concentrations. An accuracy of 100% was obtained for the varietal discrimination of pure Arabica and Robusta, both in ground and liquid form. Robusta-to-Arabica ratio was predicted with R²CV values of 0.99 and 0.9 in ground and liquid form respectively. Aquagrams results accentuated the peculiarities of the two coffee varieties and their respective blends by designating different water conformations depending on the coffee variety and assigning a particular water absorption spectral pattern (WASP) depending on the blending ratio. Marked spectral features attributed to high hydrogen bonded water characterized Arabica-rich coffee, while those with the higher Robusta content showed an abundance of free water structures. Collectively, the obtained results ascertain the adequacy of NIRS and aquaphotomics as promising alternative tools for the authentication of liquid coffee that can correlate the water-related fingerprint to the Robusta-to-Arabica ratio.

Ultrasonic testing is an emerging non-destructive testing technology with high repeatability and precision. Milk is a very complex liquid and the change of its viscosity is a highly relevant property throughout conversion into other dairy products. In the following paper, we propose a novel method for the monitoring of viscosity during enzymatic milk clotting by ultrasonic spectroscopy. An ultrasonic transducer–receiver couple with a 250 kHz nominal frequency was submerged in the samples and an enveloped sweep (“chirp”) signal was applied in a through-transmission mode. Simultaneously, the change in viscosity was measured with a rotational viscometer at a constant shearing speed. The data were analyzed with an algorithm developed by the authors for spectral ultrasonic testing. Estimations yielded a high adjusted R² (0.963–0.998) and low cross-validated estimation error (RPD: 4.38–14.22), suggesting that the method is suitable for industrial use given the right instrumentation.

The rapid increase in the global population is driving up the demand for high-quality biological proteins and contributing to rising plastic production and plastic waste. Research indicates that certain larvae may break down plastic, which is resistant to biodegradation, due to bacteria and enzymes in their gut. This study aims to identify a measurement method suitable for industrial use to detect plastic consumption by larvae, which were fed three distinct diets: a mixture of flour and carrot (control), white Styrofoam (wPs), and grey Styrofoam (gPS) enriched with activated carbon. In addition to Styrofoam (polystyrene (PS)), the second two groups were given a mix of flour and carrots. The measurements were conducted using near-infrared spectroscopy, and the data were analysed using Matlab2019a software. A variety of classification algorithms were employed to separate the three groups following pretreatment of the spectra. The linear support vector machine (SVM) model demonstrated an 88% accuracy rate in separating the three groups. Larvae fed on polystyrene-free feed were accurately identified, while larvae fed on two types of polystyrene were less well differentiated. The classification methods were also tested for two groups: larvae fed with polystyrene-containing and polystyrene-free feed. The results indicate that the linear SVM was 92% efficient. At the same time, the quadratic SVM and cubic SVM demonstrated 100% efficiency. The results show that the appropriate model can be employed to differentiate between larvae that consume polystyrene and those that consume plastic-free diets. The underlying mechanism responsible for this separation, whether it be undegraded microplastics in the larval gut or other substances accumulated from polystyrene, requires further investigation.