Accurate monitoring of animal behaviors enables improved management in precision livestock farming (PLF), supporting critical applications including health assessment, estrus detection, parturition monitoring, and feed intake estimation. Although both contact and non-contact sensing modalities are utilized, wearable devices with embedded sensors (e.g., accelerometers, pressure sensors) offer unique advantages through continuous data streams that enhance behavioral traceability. Focusing specifically on contact sensing techniques, this review examines sensor characteristics and data acquisition challenges, methodologies for processing behavioral data and implementing identification algorithms, industrial applications enabled by recognition outcomes, and prevailing challenges with emerging research opportunities. Current behavior classification relies predominantly on traditional machine learning or deep learning approaches with high-frequency data acquisition. The fundamental limitation restricting advancement in this field is the difficulty in maintaining high-fidelity recognition performance at reduced acquisition rates, particularly for integrated multi-behavior identification. Considering that the computational demands and limited adaptability to complex field environments remain significant constraints, Tiny Machine Learning (Tiny ML) could present opportunities to guide future research toward practical, scalable behavioral monitoring solutions. In addition, algorithm development for functional applications post behavior recognition may represent a critical future research direction.

Livestock’s live body dimensions are a pivotal indicator of economic output. Manual measurement is labor-intensive and time-consuming, often eliciting stress responses in the livestock. With the advancement of computer technology, the techniques for livestock live body dimension measurement have progressed rapidly, yielding significant research achievements. This paper presents a comprehensive review of the recent advancements in livestock live body dimension measurement, emphasizing the crucial role of computer-vision-based sensors. The discussion covers three main aspects: sensing data acquisition, sensing data processing, and sensing data analysis. The common techniques and measurement procedures in, and the current research status of, live body dimension measurement are introduced, along with a comparative analysis of their respective merits and drawbacks. Livestock data acquisition is the initial phase of live body dimension measurement, where sensors are employed as data collection equipment to obtain information conducive to precise measurements. Subsequently, the acquired data undergo processing, leveraging techniques such as 3D vision technology, computer graphics, image processing, and deep learning to calculate the measurements accurately. Lastly, this paper addresses the existing challenges within the domain of livestock live body dimension measurement in the livestock industry, highlighting the potential contributions of computer-vision-based sensors. Moreover, it predicts the potential development trends in the realm of high-throughput live body dimension measurement techniques for livestock.

Accurate, efficient, and timely monitoring of animal behaviors is of great significance to precision livestock farming (PLF). Behavioral monitoring serves as a valuable tool for daily production management for farmers. It can be utilized for assessing animal health, detecting estrus, monitoring parturition, and even estimating feed intake. Non-contact machine vision and contact sensors (such as accelerometers, pressure sensors and position sensors) embedded in wearable devices represent the forefront of current research in behavior monitoring. Due to the continuity and traceability in the contact sensing of wearable sensors, this study focused on contact sensing techniques and reviewed the characteristics of various sensing methods. It addressed challenges in data sorting, advancements in identification algorithms, potential industrial applications following behavior recognition, and the associated challenges and prospects. Current behavior classification algorithms primarily rely on traditional machine learning or deep learning approaches, which exhibit the limitations such as high-frequency data acquisition, complex processing requirements, and low adaptability to the intricate scenarios encountered by wearable devices. As a new frontier in machine learning that is adaptable to application scenarios with limited computational resources, the potential use of Tiny Machine Learning (Tiny ML) in behavior recognition was also analyzed to provide guidance for subsequent research and applications.

Long-term exposure to a relatively high concentration of airborne bacteria emitted from intensive livestock houses could potentially threaten the health and welfare of animals and workers. There is a dual effect of air sterilization and promotion of vitamin D synthesis for the specific bands of ultraviolet light. This study investigated the potential use of A-band ultraviolet (UVA) tubes as a clean and safe way of reducing airborne bacteria and improving calf health. The composition and emission characteristics of airborne bacteria were investigated and used to determine the correct operating regime of UVA tubes in calf houses. Intermittent exceedances of indoor airborne bacteria were observed in closed calf houses. The measured emission intensity of airborne bacteria was 1.13 ± 0.09 × 10⁷ CFU h⁻¹ per calf. Proteobacteria were the dominant microbial species in the air inside and outside calf houses. After UVA radiation, the indoor culturable airborne bacteria decreased in all particle size ranges of the Anderson sampler, and it showed the highest reduction rate in the size range of 3.3–4.7 μm. The results of this study would enrich the knowledge of the source characteristics of the airborne bacteria in intensive livestock farming and contribute to the environmental control of cattle in intensive livestock production.

Considering animal welfare, the free-range laying hen farming model is increasingly gaining attention. However, in some countries, large-scale farming still relies on the cage-rearing model, making the focus on the welfare of caged laying hens equally important. To evaluate the health status of caged laying hens, a dataset comprising visible light and thermal infrared images was established for analyses, including morphological, thermographic, comb, and behavioural as-sessments, enabling a comprehensive evaluation of the hens' health, behaviour, and population counts. To address the issue of insufficient data samples in the health detection process for indi-vidual and group hens, a dataset named BClayinghens was constructed containing 61,133 images of visible light and thermal infrared images. The BClayinghens dataset was completed using three types of devices: smartphones, visible light cameras, and infrared thermal cameras. All thermal infrared images correspond to visible light images and have achieved positional alignment through coordinate correction. Additionally, the visible light images were annotated with chicken head labels, obtaining 63,693 chicken head labels, which can be directly used for training deep learning models for chicken head object detection and combined with corresponding thermal infrared data to analyze the temperature of the chicken heads. To enable the constructed deep-learning object detection and recognition models to adapt to different breeding environ-ments, various data enhancement methods such as rotation, shearing, colour enhancement, and noise addition were used for image processing. The BClayinghens dataset is important for ap-plying visible light images and corresponding thermal infrared images in the health detection, behavioural analysis, and counting of caged laying hens under large-scale farming.

Background: Accurate estrus identification in dairy cows is essential for enhancing reproductive efficiency and economic performance. The dispersed nature of estrus data and individual cow differences pose significant challenges for accurate identification. Methods: This study gathered cow estrus data from 812 literature sources using Python 3.9 crawler technology. The data were then preprocessed using CiteSpace 6.4. We constructed a knowledge graph depicting physiological, behavioral, and appearance changes during estrus through entity and relationship extraction. To uncover potential relationships within the graph, we applied and compared two association rule algorithms: FP-Growth and Apriori. We utilized Boolean functions derived from association rule learning to validate the ability of the rules to identify normal estrus. Additionally, we employed an enhanced Iforest-OCSVM anomaly detection model to assess the performance of the association rules in detecting abnormal estrus. Furthermore, we optimized the Incremental FP-Growth Algorithm for Dynamic Knowledge Expansion. Results: Based on the initial knowledge graph with 86 entities and 9 relationships, mining added 17 new strong association relationships marked by ‘with’, enhancing its completeness and providing deeper insights into estrus behaviors and physiological changes. Furthermore, these strong association rules exhibited notable effectiveness in both normal and abnormal estrus detection, validating their robustness in practical applications. The algorithm’s optimization bolstered its scalability, making it more adaptable to future data expansions and complex knowledge integrations. Conclusions: By constructing a knowledge graph that integrates physiological, behavioral, and appearance changes during estrus, we established a comprehensive framework for understanding cow estrus. Association rule mining, particularly with the FP-Growth algorithm, added 17 new strong association relationships to the graph, enriching its content and offering deeper insights into estrus behaviors and physiological changes. The strong association rules derived from FP-Growth demonstrated notable effectiveness in both normal and abnormal estrus detection, validating their robustness and practical utility in enhancing estrus identification accuracy, and providing a robust foundation for future multi-dimensional estrus research.