Although trap-neuter-return (TNR) is a popular method for managing free-roaming domestic cat populations, a common criticism is that sterilization fails to mitigate the public health risks posed by free-roaming cats. One of these risks is the environmental contamination of <i>Toxoplasma gondii</i>, a parasite that can be spread in the feces of actively infected felids (both domestic and wild). In healthy humans, toxoplasmosis tends to be mild or asymptomatic; however, the disease can have severe consequences (e.g., for pregnant women) and even be fatal in immunocompromised individuals. Previous research has examined the extent to which free-roaming domestic cats might contaminate sites frequented by young children (e.g., schools and parks). However, the model used included several assumptions that are not reflective of sterilized cats in an urban setting (e.g., smaller home range). By properly accounting for several key factors (e.g., reproductive status, home range), our modeling revealed considerably lower rates of potential incursions by sterilized free-roaming cats than those reported previously. More importantly, our results show that sterilization contributes to a considerable reduction in the risk of environmental contamination; TNR therefore appears to be a valuable harm reduction strategy in mitigating the risks of <i>T. gondii</i> infection.
J. Suppi, P. Salgado-López, E. Llauradó-Calero
et al.
Early weaning in piglets commonly leads to a postweaning (PW) fasting period, compromising intestinal integrity and triggering inflammation, overall affecting welfare and growth. Despite the well-documented consequences of fasting, no feasible and non-invasive method exists to monitor feeding patterns in postweaned piglets. Therefore, this study aimed to evaluate the use of faecal inflammatory biomarkers—calprotectin (fCal), lipocalin-2 (LCN-2), myeloperoxidase (MPO), and adenosine deaminase (ADA)—to detect whether an animal is eating or not by correlating fasting with its presence in faeces. The trial involved 623 weaned piglets (21 days) which were weighed at days 0, 3 and 10 PW. A blue-coloured creep-feed was provided before and after weaning to qualitatively trace feed consumption via rectal swabs. Piglets were assessed for feeding status at weaning and on day 3 PW. Additionally, 120 animals were selected to monitor feed status daily over the first 4 days PW. Animals were classified into three categories: creep-feed eaters (CFE), began feed intake preweaning and maintained it PW; PW eaters (PWE), started consuming feed PW; and non-eaters (NE), which did not consume any feed. Out of the 120 piglets, faecal samples were obtained from 77 piglets: CFE (n = 19 sampled from days 0–3), PWE (n = 7 on day 1, n = 14 on day 2, n = 33 on day 3), and NE (n = 30 on day 0, n = 28 on day 1, n = 27 on day 2, n = 25 on day 3). Among all piglets, 4.5% were classified as CFE, 69.5% as PWE, and 26% as NE. On average, CFE gained 44 g/day more than PWE, and 100 g/day more than NE in the first 10 days of PW (P < 0.001). The biomarkers fCal, LCN-2, and MPO differed by eater category (P ≤ 0.014), while ADA increased over time (P = 0.001) without differences between categories. Calprotectin and LCN-2 were higher in NE than CFE, correlating with reduced growth (r ≤ −0.29, P ≤ 0.044). Conversely, MPO was higher in CFE than NE (P < 0.001), with no growth association. Calprotectin showed strong discriminatory power between CFE and NE, with an area under the curve of 0.86, sensitivity of 86%, and specificity of 69%. Calprotectin and LCN-2 increased with fasting and correlated negatively with growth, highlighting their utility as biomarkers of low feed intake−related inflammation, with fCal being the most sensitive. Myeloperoxidase and ADA showed no feeding-related associations.
Paweł Niemiec, Jowita Samanta Niczyporuk, Wojciech Kozdruń
et al.
(1) Background: The Asian bush mosquito <i>Aedes japonicus</i> is an invasive species in Europe, including Poland. Given its laboratory-confirmed competence for West Nile virus (WNV) transmission and its detection as a WNV vector in field-collected mosquitoes, this study investigated whether Polish <i>Aedes japonicus</i> harbor WNV and aimed to update knowledge on its distribution in Poland. (2) Methods: In September 2024, 137 adult <i>Aedes japonicus</i> were collected from three suburban sites in Poland (Kielce, Mikołów, Kraków). Specimens were screened for WNV using RT-PCR and rRT-PCR. Additionally, unpublished records of <i>Aedes japonicus</i> were compiled to update the species’ distribution. (3) Results: No WNV genetic material was detected in field-collected mosquitoes in Poland. By 2025, <i>Aedes japonicus</i> had been recorded in half of Polish voivodeships, with most observations in Małopolskie, Śląskie, and Łódzkie. The largest adult populations occurred in Kielce. Ecological traits in Poland matched European and US data, including larval development in artificial containers, preference for suburban and forested habitats, and peak adult activity in late summer. (4) Conclusions: Although WNV was not detected, the rapid spread of <i>Aedes japonicus</i> in Poland underlines the need for continued monitoring of its distribution, population dynamics, and potential role in WNV transmission.
Do fish respond to the presence of underwater vehicles, potentially biasing our estimates about them? If so, are there strategies to measure and mitigate this response? This work provides a theoretical and practical framework towards bias-free estimation of animal behavior from underwater vehicle observations. We also provide preliminary results from the field in coral reef environments to address these questions.
Characterizing interactions between brain areas is a fundamental goal of systems neuroscience. While such analyses are possible when areas are recorded simultaneously, it is rare to observe all combinations of areas of interest within a single animal or recording session. How can we leverage multi-animal datasets to better understand multi-area interactions? Building on recent progress in large-scale, multi-animal models, we introduce NeuroPaint, a masked autoencoding approach for inferring the dynamics of unrecorded brain areas. By training across animals with overlapping subsets of recorded areas, NeuroPaint learns to reconstruct activity in missing areas based on shared structure across individuals. We train and evaluate our approach on synthetic data and two multi-animal, multi-area Neuropixels datasets. Our results demonstrate that models trained across animals with partial observations can successfully in-paint the dynamics of unrecorded areas, enabling multi-area analyses that transcend the limitations of any single experiment.
Dante Francisco Wasmuht, Otto Brookes, Maximillian Schall
et al.
Automated video analysis is critical for wildlife conservation. A foundational task in this domain is multi-animal tracking (MAT), which underpins applications such as individual re-identification and behavior recognition. However, existing datasets are limited in scale, constrained to a few species, or lack sufficient temporal and geographical diversity - leaving no suitable benchmark for training general-purpose MAT models applicable across wild animal populations. To address this, we introduce SA-FARI, the largest open-source MAT dataset for wild animals. It comprises 11,609 camera trap videos collected over approximately 10 years (2014-2024) from 741 locations across 4 continents, spanning 99 species categories. Each video is exhaustively annotated culminating in ~46 hours of densely annotated footage containing 16,224 masklet identities and 942,702 individual bounding boxes, segmentation masks, and species labels. Alongside the task-specific annotations, we publish anonymized camera trap locations for each video. Finally, we present comprehensive benchmarks on SA-FARI using state-of-the-art vision-language models for detection and tracking, including SAM 3, evaluated with both species-specific and generic animal prompts. We also compare against vision-only methods developed specifically for wildlife analysis. SA-FARI is the first large-scale dataset to combine high species diversity, multi-region coverage, and high-quality spatio-temporal annotations, offering a new foundation for advancing generalizable multianimal tracking in the wild. The dataset is available at https://www.conservationxlabs.com/sa-fari.
Alex S. C. Maia, John B. Hall, Hugo F. M. Milan
et al.
Advances in technology are transforming sustainable cattle farming practices, with electronic feeding systems generating big longitudinal datasets on individual animal feed intake, offering the possibility for autonomous precision livestock systems. However, the literature still lacks a methodology that fully leverages these longitudinal big data to accurately predict feed intake accounting for environmental conditions. To fill this gap, we developed an AI-based framework to accurately predict feed intake of individual animals and pen-level aggregation. Data from 19 experiments (>16.5M samples; 2013-2024) conducted at Nancy M. Cummings Research Extension & Education Center (Carmen, ID) feedlot facility and environmental data from AgriMet Network weather stations were used to develop two novel environmental indices: InComfort-Index, based solely on meteorological variables, showed good predictive capability for thermal comfort but had limited ability to predict feed intake; EASI-Index, a hybrid index integrating environmental variables with feed intake behavior, performed well in predicting feed intake but was less effective for thermal comfort. Together with the environmental indices, machine learning models were trained and the best-performing machine learning model (XGBoost) accuracy was RMSE of 1.38 kg/day for animal-level and only 0.14 kg/(day-animal) at pen-level. This approach provides a robust AI-based framework for predicting feed intake in individual animals and pens, with potential applications in precision management of feedlot cattle, through feed waste reduction, resource optimization, and climate-adaptive livestock management.
Existing optical flow datasets focus primarily on real-world simulation or synthetic human motion, but few are tailored to Celluloid(cel) anime character motion: a domain with unique visual and motion characteristics. To bridge this gap and facilitate research in optical flow estimation and downstream tasks such as anime video generation and line drawing colorization, we introduce LinkTo-Anime, the first high-quality dataset specifically designed for cel anime character motion generated with 3D model rendering. LinkTo-Anime provides rich annotations including forward and backward optical flow, occlusion masks, and Mixamo Skeleton. The dataset comprises 395 video sequences, totally 24,230 training frames, 720 validation frames, and 4,320 test frames. Furthermore, a comprehensive benchmark is constructed with various optical flow estimation methods to analyze the shortcomings and limitations across multiple datasets.
If you had an AI Whale-to-English translator, how could you validate whether or not it is working? Does one need to interact with the animals or rely on grounded observations such as temperature? We provide theoretical and proof-of-concept experimental evidence suggesting that interaction and even observations may not be necessary for sufficiently complex languages. One may be able to evaluate translators solely by their English outputs, offering potential advantages in terms of safety, ethics, and cost. This is an instance of machine translation quality evaluation (MTQE) without any reference translations available. A key challenge is identifying ``hallucinations,'' false translations which may appear fluent and plausible. We propose using segment-by-segment translation together with the classic NLP shuffle test to evaluate translators. The idea is to translate animal communication, turn by turn, and evaluate how often the resulting translations make more sense in order than permuted. Proof-of-concept experiments on data-scarce human languages and constructed languages demonstrate the potential utility of this evaluation methodology. These human-language experiments serve solely to validate our reference-free metric under data scarcity. It is found to correlate highly with a standard evaluation based on reference translations, which are available in our experiments. We also perform a theoretical analysis suggesting that interaction may not be necessary nor efficient in the early stages of learning to translate.
Aleksandr Algasov, Ekaterina Nepovinnykh, Fedor Zolotarev
et al.
Existing individual re-identification methods often struggle with the deformable nature of animal fur or skin patterns which undergo geometric distortions due to body movement and posture changes. In this paper, we propose a geometry-aware texture mapping approach that unwarps pelage patterns, the unique markings found on an animal's skin or fur, into a canonical UV space, enabling more robust feature matching. Our method uses surface normal estimation to guide the unwrapping process while preserving the geometric consistency between the 3D surface and the 2D texture space. We focus on two challenging species: Saimaa ringed seals (Pusa hispida saimensis) and leopards (Panthera pardus). Both species have distinctive yet highly deformable fur patterns. By integrating our pattern-preserving UV mapping with existing re-identification techniques, we demonstrate improved accuracy across diverse poses and viewing angles. Our framework does not require ground truth UV annotations and can be trained in a self-supervised manner. Experiments on seal and leopard datasets show up to a 5.4% improvement in re-identification accuracy.
Sodium butyrate (NaB) can regulate lipid metabolism and inhibit hepatic steatosis. This study aimed to investigate whether NaB can alleviate fructose-induced hepatic steatosis via remodeling the gut microbiota and evaluate the anti-fatty liver mechanisms. The results showed that NaB and NaB-remodeled gut microbiota significantly alleviated fructose-induced hepatic steatosis and increased plasma uric acid and fructose levels. Furthermore, both NaB and NaB-remodeled gut microbiota increased the abundance of Lactobacillus and altered the levels of plasma amino acids (upregulating gamma-amino butyric acid (GABA) and downregulating L-glutamic acid and L-arginine) in fructose-exposed mice. The correlation analysis showed that GABA levels positively correlated with Lactobacillus abundance, and increased GABA levels might promote the reduction of the hepatic triglyceride content. Further studies confirmed that GABA significantly reduced lipid deposition in mouse hepatocytes induced via fructose pretreatment in vitro. These findings suggested that NaB could ameliorate fructose-induced hepatic steatosis by regulating gut microbiota.
Tabitha Hookey, Brianne Morrow, Georgiana R. T. Woods
et al.
The health of adult dogs and cats is affected positively or negatively by their development in utero and throughout postnatal growth. Preventive veterinary care is particularly important when animals are physiologically immature and sensitive to modifiable environmental factors. Veterinary nurses/technicians are often at the forefront of promoting healthy development, reinforcing the work of veterinarians and using their knowledge, experience, and passion to lead initiatives with breeders and pet guardians. This opinion article considers the role of qualified veterinary nurses/technicians in the care of puppies and kittens throughout their developmental life stages—gestation, the suckling period, growth post-weaning to puberty or neutering, and late growth to adulthood. Much of their influence is through the education of pet carers; they provide trustworthy information relevant to the individual pet and focused on the practicalities of best husbandry practices. These include practical advice on recognizing dystocia, neonatal care, weaning, introduction to the new home, the prevention and management of infectious diseases, socialization with conspecifics and humans, habituation to potential environmental stresses, nutrition, oral hygiene, and grooming. The veterinary nurse’s goal is not only to see young pets develop into healthy, well-adjusted adults but also to see pet guardians developing sustainable human–animal bonds.
Deep learning techniques are dominating automated animal activity recognition (AAR) tasks with wearable sensors due to their high performance on large-scale labelled data. However, current deep learning-based AAR models are trained solely on datasets of individual animal species, constraining their applicability in practice and performing poorly when training data are limited. In this study, we propose a one-for-many framework, dubbed Cross-species Knowledge Sharing and Preserving (CKSP), based on sensor data of diverse animal species. Given the coexistence of generic and species-specific behavioural patterns among different species, we design a Shared-Preserved Convolution (SPConv) module. This module assigns an individual low-rank convolutional layer to each species for extracting species-specific features and employs a shared full-rank convolutional layer to learn generic features, enabling the CKSP framework to learn inter-species complementarity and alleviating data limitations via increasing data diversity. Considering the training conflict arising from discrepancies in data distributions among species, we devise a Species-specific Batch Normalization (SBN) module, that involves multiple BN layers to separately fit the distributions of different species. To validate CKSP's effectiveness, experiments are performed on three public datasets from horses, sheep, and cattle, respectively. The results show that our approach remarkably boosts the classification performance compared to the baseline method (one-for-one framework) solely trained on individual-species data, with increments of 6.04%, 2.06%, and 3.66% in accuracy, and 10.33%, 3.67%, and 7.90% in F1-score for the horse, sheep, and cattle datasets, respectively. This proves the promising capabilities of our method in leveraging multi-species data to augment classification performance.
Traditional animation generation methods depend on training generative models with human-labelled data, entailing a sophisticated multi-stage pipeline that demands substantial human effort and incurs high training costs. Due to limited prompting plans, these methods typically produce brief, information-poor, and context-incoherent animations. To overcome these limitations and automate the animation process, we pioneer the introduction of large multimodal models (LMMs) as the core processor to build an autonomous animation-making agent, named Anim-Director. This agent mainly harnesses the advanced understanding and reasoning capabilities of LMMs and generative AI tools to create animated videos from concise narratives or simple instructions. Specifically, it operates in three main stages: Firstly, the Anim-Director generates a coherent storyline from user inputs, followed by a detailed director's script that encompasses settings of character profiles and interior/exterior descriptions, and context-coherent scene descriptions that include appearing characters, interiors or exteriors, and scene events. Secondly, we employ LMMs with the image generation tool to produce visual images of settings and scenes. These images are designed to maintain visual consistency across different scenes using a visual-language prompting method that combines scene descriptions and images of the appearing character and setting. Thirdly, scene images serve as the foundation for producing animated videos, with LMMs generating prompts to guide this process. The whole process is notably autonomous without manual intervention, as the LMMs interact seamlessly with generative tools to generate prompts, evaluate visual quality, and select the best one to optimize the final output.
Bubacarr Jobarteh, Madalina Mincu, Gavojdian Dinu
et al.
Understanding animal vocalizations through multi-source data fusion is crucial for assessing emotional states and enhancing animal welfare in precision livestock farming. This study aims to decode dairy cow contact calls by employing multi-modal data fusion techniques, integrating transcription, semantic analysis, contextual and emotional assessment, and acoustic feature extraction. We utilized the Natural Language Processing model to transcribe audio recordings of cow vocalizations into written form. By fusing multiple acoustic features frequency, duration, and intensity with transcribed textual data, we developed a comprehensive representation of cow vocalizations. Utilizing data fusion within a custom-developed ontology, we categorized vocalizations into high frequency calls associated with distress or arousal, and low frequency calls linked to contentment or calmness. Analyzing the fused multi dimensional data, we identified anxiety related features indicative of emotional distress, including specific frequency measurements and sound spectrum results. Assessing the sentiment and acoustic features of vocalizations from 20 individual cows allowed us to determine differences in calling patterns and emotional states. Employing advanced machine learning algorithms, Random Forest, Support Vector Machine, and Recurrent Neural Networks, we effectively processed and fused multi-source data to classify cow vocalizations. These models were optimized to handle computational demands and data quality challenges inherent in practical farm environments. Our findings demonstrate the effectiveness of multi-source data fusion and intelligent processing techniques in animal welfare monitoring. This study represents a significant advancement in animal welfare assessment, highlighting the role of innovative fusion technologies in understanding and improving the emotional wellbeing of dairy cows.
Van Thuy Hoang, Sang Thanh Nguyen, Sangmyeong Lee
et al.
Knowledge graph (KG) embedding has been used to benefit the diagnosis of animal diseases by analyzing electronic medical records (EMRs), such as notes and veterinary records. However, learning representations to capture entities and relations with literal information in KGs is challenging as the KGs show heterogeneous properties and various types of literal information. Meanwhile, the existing methods mostly aim to preserve graph structures surrounding target nodes without considering different types of literals, which could also carry significant information. In this paper, we propose a knowledge graph embedding model for the efficient diagnosis of animal diseases, which could learn various types of literal information and graph structure and fuse them into unified representations, namely LiteralKG. Specifically, we construct a knowledge graph that is built from EMRs along with literal information collected from various animal hospitals. We then fuse different types of entities and node feature information into unified vector representations through gate networks. Finally, we propose a self-supervised learning task to learn graph structure in pretext tasks and then towards various downstream tasks. Experimental results on link prediction tasks demonstrate that our model outperforms the baselines that consist of state-of-the-art models. The source code is available at https://github.com/NSLab-CUK/LiteralKG.
There is great interest in ecology to understand how wild animals are affected by anthropogenic disturbances, such as sounds. Behavioural response studies are an important approach to quantify the impact of naval activity on marine mammals. Controlled exposure experiments are undertaken where the behaviour of animals is quantified before, during, and after exposure to a controlled sound source, often using telemetry tags (e.g., accelerometers, or satellite trackers). Statistical modelling is required to formally compare patterns before and after exposure, to quantify deviations from baseline behaviour. We propose varying-coefficient stochastic differential equations (SDEs) as a flexible framework to model such data, with two components: (1) time-varying baseline dynamics, modelled with non-parametric or random effects of time-varying covariates, and (2) a non-parametric response model, which captures deviations from baseline. SDEs are specified in continuous time, which makes it straightforward to analyse data collected at irregular time intervals, a common situation for animal tracking studies. We describe how the model can be embedded into a state-space modelling framework to account for measurement error. We present inferential methods for model fitting, model checking, and uncertainty quantification (including on the response model). We apply this approach to two behavioural response study data sets on beaked whales: a satellite track, and high-resolution depth data. Our results suggest that the whales' horizontal movement and vertical diving behaviour changed after exposure to the sound source, and future work should evaluate the severity and possible consequences of these responses. These two very different examples showcase the versatility of varying-coefficient SDEs to measure changes in behaviour, and we discuss implications of disturbances for the whales' energetic balance.
We develop an end-to-end deep-neural-network-based algorithm for classifying animal behavior using accelerometry data on the embedded system of an artificial intelligence of things (AIoT) device installed in a wearable collar tag. The proposed algorithm jointly performs feature extraction and classification utilizing a set of infinite-impulse-response (IIR) and finite-impulse-response (FIR) filters together with a multilayer perceptron. The utilized IIR and FIR filters can be viewed as specific types of recurrent and convolutional neural network layers, respectively. We evaluate the performance of the proposed algorithm via two real-world datasets collected from total eighteen grazing beef cattle using collar tags. The results show that the proposed algorithm offers good intra- and inter-dataset classification accuracy and outperforms its closest contenders including two state-of-the-art convolutional-neural-network-based time-series classification algorithms, which are significantly more complex. We implement the proposed algorithm on the embedded system of the utilized collar tags' AIoT device to perform in-situ classification of animal behavior. We achieve real-time in-situ behavior inference from accelerometry data without imposing any strain on the available computational, memory, or energy resources of the embedded system.
Michael P. J. Camilleri, Li Zhang, Rasneer S. Bains
et al.
Our objective is to locate and provide a unique identifier for each mouse in a cluttered home-cage environment through time, as a precursor to automated behaviour recognition for biological research. This is a very challenging problem due to (i) the lack of distinguishing visual features for each mouse, and (ii) the close confines of the scene with constant occlusion, making standard visual tracking approaches unusable. However, a coarse estimate of each mouse's location is available from a unique RFID implant, so there is the potential to optimally combine information from (weak) tracking with coarse information on identity. To achieve our objective, we make the following key contributions: (a) the formulation of the object identification problem as an assignment problem (solved using Integer Linear Programming), and (b) a novel probabilistic model of the affinity between tracklets and RFID data. The latter is a crucial part of the model, as it provides a principled probabilistic treatment of object detections given coarse localisation. Our approach achieves 77% accuracy on this animal identification problem, and is able to reject spurious detections when the animals are hidden.