Maria P. Nikolopoulou

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.

Precision livestock farming (PLF), by integrating multimodal sensor data, provides opportunities to enhance welfare monitoring and management in small ruminants. This study evaluated whether environmental, physiological, and behavioral measurements—including the temperature–humidity index (THI), carbon dioxide (CO₂) and ammonia (NH₃) concentrations measured at the barn level, body condition score (BCS), rectal and ocular temperatures, GPS-derived locomotion metrics, accelerometry data, and fixed animal traits—can serve as key predictors of welfare and productivity in dairy sheep. Data were collected from 90 ewes: all animals underwent the same repeated welfare assessments, while 30 of them were additionally equipped with GPS–accelerometer sensor collars; environmental conditions were continuously recorded for the entire flock, generating 773 complete multimodal records. All predictive models were developed using data from all 90 ewes; collar-derived behavioral variables were included only for individuals equipped with GPS–accelerometer collars. Nine regression methods (linear regression (LR), partial least square regression (PLSR), elastic net (EN), mixed-effects models, random forest (RF), extreme gradient boosting (XGBoost), support vector regression (SVR), neural networks (multilayer perceptron, MLP), and an ensemble of RF–XGBoost–EN were evaluated using a combination of nested cross-validation (CV) and leave-one-animal-out CV (LOAOCV) to ensure robustness and generalization at the individual animal level. Nonlinear models—particularly RF, XGBoost, SVR, and the ensemble—consistently delivered superior performance across traits. For behavioral (e.g., daily distance movement) and thermal indicators (e.g., medial canthus temperature), the highest predictive capacity (R² ≈ 0.60–0.70) was achieved, while moderate predictive capacity (R² ≈ 0.40–0.50 and ≈0.35–0.45), respectively, was observed for respiratory rate and milk yield, reflecting their multifactorial nature. Feature importance analyses underscored the relevance of THI, CO₂, NH₃, concentrations, and BCS across results. Overall, these findings demonstrate that multimodal sensor fusion can effectively support the prediction of welfare and productivity indicators in intensively reared dairy sheep and emphasize the need for larger and more diverse datasets to further enhance model generalizability and model transferability.

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.