Quality and safety monitoring in the dairy industry is required to ensure products meet a high-standard based on legislation and customer requirements. The need for non-destructive, low-cost and user-friendly process analytical technologies, targeted at operators (as the end-users) for routine product inspections is increasing. In recent years, the development and advances in sensing technologies have led to miniaturisation of near infrared (NIR) spectrometers to a new era. The new generation of miniaturised NIR analysers are designed as compact, small and lightweight devices with a low cost, providing a strong capability for on-site or on-farm product measurements. Applying portable and handheld NIR spectrometers in the dairy sector is increasing; however, little information is currently available on these applications and instrument performance. As a result, this review focuses on recent developments of handheld and portable NIR devices and its latest applications in the field of dairy, including chemical composition, on-site quality detection, and safety assurance (i.e., adulteration) in milk, cheese and dairy powders. Comparison of model performance between handheld and bench-top NIR spectrometers is also given. Lastly, challenges of current handheld/portable devices and future trends on implementing these devices in the dairy sector is discussed.

Animal location technologies have evolved considerably in the last 60 years. Nowadays, animal tracking solutions based on global positioning systems (GPS) are commercially available. However, existing devices have several constraints, mostly related to wireless data transmission and financial cost, which make impractical the monitorization of all the animals in a herd. The main objective of this work is to develop a low-cost solution to enable the monitorization of a whole herd. An IoT-based system, which requires some animals of the herd being fitted with GPS collars connected to a Sigfox network and the rest with low-cost Bluetooth tags, has been developed. Its performance has been tested in two commercial farms, raising sheep and beef cattle, through the monitorization of 50 females in each case. Several collar/tag ratios, which define the cost per animal of the solution, have been simulated. Results demonstrate that a low collar/tag ratio enable the monitorization of a whole sheep herd. A larger ratio is needed for beef cows because of their grazing behavior. Nevertheless, the optimal ratio depends on the purpose of location data. Large variability has been observed for the number of hourly and daily messages from collars and tags. The system effectiveness for the monitorization of all the animals in a herd has been certainly proved.

Seven thousand four hundred and twenty-three compound feed samples were used to develop near-infrared (NIR) calibrations for predicting the percentage of each ingredient used in the manufacture of a given compound feedingstuff. Spectra were collected at 2 nm increments using a FOSS NIRSystems 5000 monochromator. The reference data used for each ingredient percentage were those declared in the formula for each feedingstuff. Two chemometric tools for developing NIRS prediction models were compared: the so-called GLOBAL MPLS (modified partial least squares), traditionally used in developing NIRS applications, and the more recently developed calibration strategy known as LOCAL. The LOCAL procedure is designed to select, from a large database, samples with spectra resembling the sample being analyzed. Selected samples are used as calibration sets to develop specific MPLS equations for predicting each unknown sample. For all predicted ingredients, LOCAL calibrations resulted in a significant improvement in both standard error of prediction (SEP) and bias values compared with GLOBAL calibrations. Determination coefficient values ( r ² ) also improved using the LOCAL strategy, exceeding 0.90 for most ingredients. Use of the LOCAL algorithm for calibration thus proved valuable in minimizing the errors in NIRS calibration equations for predicting a parameter as complex as the percentage of each ingredient in compound feedingstuffs.

Near-Infrared (NIR) Spectroscopy was used for the non-destructive assessment of physico-chemical quality parameters in olive oil. At the same time, the influence of the sample presentation mode (spinning versus static cup) was evaluated using two spectrophotometers with similar optical characteristics. A total of 478 olive oil samples were used to develop calibration models, testing various spectral signal pre-treatments. The models obtained by applying MPLS regression to spectroscopic data yielded promising results for olive oil quality measurements, particularly for acidity, the peroxide index and alkyl and ethyl ester content. The results obtained indicate that this non-invasive technology can be used successfully by the olive oil sector to categorize olive oils, to detect potential fraud and to provide consumers with more reliable information. Although both sample presentation modes yielded comparable results, equations constructed with samples scanned using the spinning mode provided greater predictive capacity.

The use of near-infrared reflectance spectroscopy (NIRS) calibrations to predict the ingredient composition in compound feeds (i.e., inclusion percentage of each ingredient) is a complex task, regarding both the nature of the parameters to be predicted, since they are not well-defined chemical entities, and the heterogeneousness of the matrices/formulas in which each ingredient participates. The present paper evaluates the use of nonlinear regression methods, such as artificial neural networks (ANN), for developing NIRS calibrations to predict these parameters. Two of the most representative ingredients in the Spanish compound feed formulations (wheat and sunflower meal) were selected for evaluating ANN possibilities, using a large spectral library comprising a total of 7523 commercial compound feed samples; 7423 were used as training set and 100 as validation set. Three general models of networks were studied: multilayer perceptron with back-propagation training (BP), multilayer perceptron with Levenberg–Maquartd training (LM), and radial basis function nets (RBF); moreover, in accordance with a factorial design, more complex architectures were evaluated gradually, changing the number of hidden layers and hidden neurons, for the determination of the optimal network topology. For both ingredients, the best results were obtained using ANN with BP training, showing prediction error values (SEP) of 2.72% and 0.66% for wheat and sunflower meal, respectively. These SEP values showed a significant improvement (19%–49% for sunflower meal and wheat, respectively) in comparison with those obtained using calibrations developed with linear methods.