Milk analysis is critical to determine its intrinsic quality, as well as its nutritional and economic value. Currently, the advancements and utilization of spectroscopy-based techniques combined with machine learning algorithms have made the development of analytical tools and real-time monitoring and prediction systems in the dairy ruminant sector feasible. The objectives of the current review were (i) to describe the most widely applied spectroscopy-based and supervised machine learning methods utilized for the evaluation of milk components, origin, technological properties, adulterants, and drug residues, (ii) to present and compare the performance and adaptability of these methods and their most efficient combinations, providing insights into the strengths, weaknesses, opportunities, and challenges of the most promising ones regarding the capacity to be applied in milk quality monitoring systems both at the point-of-care and beyond, and (iii) to discuss their applicability and future perspectives for the integration of these methods in milk data analysis and decision support systems across the milk value-chain.

Milk analysis is critical to determine its intrinsic quality, as well as its nutritional and economic value. Currently, the advancements and utilization of spectroscopy-based techniques combined with machine learning algorithms have made feasible the development of analytical tools and re-al-time monitoring and prediction systems in the dairy ruminant sector. The objectives of the cur-rent review were i) to describe the most widely applied spectroscopy-based and supervised ma-chine learning methods utilized for the evaluation of milk components, origin, technological properties, adulterants, and drugs residues, ii) to present and compare the performance and adaptability of these methods and their most efficient combinations, providing insights into the strengths, weaknesses, opportunities, and challenges of the most promising ones regarding the capacity to be applied in milk quality monitoring systems both at the point-of-care and beyond, and iii) to discuss their applicability and future perspectives for the integration of these methods in milk data analysis and decision support systems across the milk value-chain.

Water quality monitoring and evaluation are essential across multiple sectors, including public health, environmental protection, agriculture and livestock management, industrial processes, and broader sustainability efforts. Conventional water analysis techniques, although accurate, are often constrained by their labor-intensive nature, extended processing times, and limited applicability for in situ, real-time monitoring. In recent years, spectroscopy-based methods have gained prominence as alternatives for water quality assessment, particularly when combined with chemometric analyses and advanced technological systems. This review provides an overview of the current advancements of spectroscopy-based water monitoring, with a focus on spectroscopy techniques operating within ultraviolet–visible (UV–Vis) and infrared (IR) spectral regions, which are currently applied for the assessment of a broad range of physicochemical and biological parameters relevant to livestock water management, including chemical oxygen demand (COD), dissolved organic carbon (DOC), nitrates, microbial contamination, and heavy metal ions. The findings highlight the growing utility of spectroscopy as a reliable tool in water quality assessment (e.g., COD detection with R² = 0.86 and nitrate detection with R² = 0.95 compared to traditional methods) and underpin the need for continued research into scalable, sensor-integrated solutions tailored for use in livestock farming environments.

The purpose of this study was to examine the use of portable spectroscopy technologies for rapid milk composition and hygiene quality assessment in ovine milk. Two portable analyzers, namely SmartAnalysis (UV/Vis absorbance) and SpectraPod (NIR transmittance), were used to obtain spectral data of raw milk samples. Additionally, reference values of the milk’s compositional, physical, and hygienic traits were measured. Machine learning algorithms were used to explore the correlations between spectral data and milk traits. The initial results indicated a promising potential of utilizing spectral technologies to predict milk quality and hygienic parameters. Regression models presented a moderate predictive accuracy, with R² values between 0.55 and 0.34, respectively, regarding fat (RF-NIR) and protein (LR-UV/Vis). Classification models indicated high accuracy for hygienic parameters, with the highest accuracy and AUC values up to 0.87 and 0.83, respectively, predicting increased levels of total bacterial count (TBC), while somatic cell count (SCC) level was less accurately predicted by the model, with AUC values lower than 0.70. The results demonstrate the applicability potential of UV/Vis and NIR portable devices in milk quality assessment, enabling its rapid evaluation, including milk composition and hygiene parameters at the point of service.

Water quality monitoring and evaluation are essential across multiple sectors, including public health, environmental protection, agriculture and livestock management, industrial processes, and broader sustainability efforts. Conventional water analysis techniques, although accurate, they are often constrained by the labor-intensive nature, extended processing times, and limited applicability for in-situ, real-time monitoring. In recent years, spectroscopy-based methods have gained prominence as alternatives for water quality assessment, particularly when combined with chemometric analyses and advanced technological systems. This review provides an overview of the current advancements of spectroscopy-based water monitoring, with a focus on spectroscopy techniques operating within the Ultraviolet/Visible (UV/Vis) and Infrared (IR) spectral regions, which are currently applied for the assessment of a broad range of physicochemical, and biological parameters relevant to livestock water management, including chemical oxygen demand (COD), dissolved organic carbon (DOC), nitrates, microbial contamination, and heavy metal ions. The findings highlight the growing utility of spectroscopy as a reliable tool in water quality monitoring and underpin for the need for continued research into scalable, sensor-integrated solutions tailored for use in livestock faming environments.

Wearable sensors provide significant potential for continuous animal monitoring. However, the practical implementation of such technologies on livestock farms for animal monitoring raises significant challenges related to power efficiency, robustness, and reliability. In this research paper, we propose the design, implementation, and field testing of a low-energy, low-cost, multi-sensor wearable collar specifically designed for continuous monitoring of ruminants using LoRa. The proposed collar is based on a modular hardware platform that incorporates inertial sensing, temperature sensing, and wireless communication, with special attention to sensor choice, location on the body, casing, and mounting mechanism. Reduced weight, environmental protection, and long-term wearability without affecting animal behavior are the primary focus in the hardware design. Power optimization management strategies, including sleep mode and duty cycling functionality, are implemented to maximize autonomy and battery lifetime and are evaluated under realistic operating scenarios. Field deployment was conducted in a ruminant farm, where the wearable devices operated flawlessly for a long time period. Characteristic sensor data are collected, including accelerometer readings induced by animal movement, variability in received signal strength (RSSI), and animal temperature. The system demonstrates stable operation, satisfactory data completeness and consistency on multi-day basis. The knowledge acquired brings into focus the practical challenges and design issues associated with the use of wearable sensors in livestock and offers insights into designing efficient sensor collars for precision livestock farming.