Ear Tags Research Articles

Motion blur aware multiscale adaptive cascade framework for ear tag dropout detection in reserve breeding pigs

Timely and accurate detection of ear tag dropout is crucial for standardized precision breeding, health monitoring, and breeding evaluation. Reserve breeding pigs exhibit high activity levels and frequent interactions, leading to a higher prevalence of ear tag dropout. However, detection is challenging due to motion blur, small tag size, and significant target scale variations. To address this, we propose a motion blur-aware multi-scale framework, Adapt-Cascade. First, a Weight-Adaptive Attention Module (WAAM) enhances the extraction of motion blur features. Second, Density-Aware Dilated Convolution (DA-DC) dynamically adjusts the convolutional receptive field to improve small ear tag detection. Third, a Feature-Guided Multi-Scale Region Proposal strategy (FGMS-RP) strengthens multi-scale target detection. Integrated into the Cascade Mask R-CNN framework with Focal Loss, Adapt-Cascade achieves 93.46% accuracy at 19.2 frames per second in detecting ear tag dropout in reserve breeding pigs. This model provides a high-accuracy solution for intelligent pig farm management.

A Novel Missense Variant in Ultrarare SLC35A1-CDG Alters Cellular Glycosylation, Lipid, and Energy Metabolism Without Affecting CDG Serum Markers

SLC35A1-CDG is a very rare type of congenital disorders of glycosylation (CDG) with only five cases known to date. Here, we review the literature and present new data from a sixth patient carrying the uncharacterized variant c.133A>G; p.Thr45Ala in the SLC35A1 gene. In addition to known clinical symptoms of SLC35A1-CDG, the patient presents with failure to thrive, short stature, café-au-lait spot, and preauricular ear tag. Even though examination of CDG markers transferrin (Tf), alpha-1-antitrypsin (A1AT), and apolipoprotein CIII (ApoCIII) revealed no abnormalities in serum, the patient's fibroblasts showed significant alterations of protein expression or glycosylation of ICAM1, GP130, and TGN46 as well as differences in staining signals of lectins MAL-I, RCAI, and SNA and deviations in LC-MS analysis of total cellular N-glycans. Transfection of CRISPR/Cas9 generated SLC35A1 HEK293 knockout cells with either wild-type SLC35A1 or the c.133A>G variant restored the cellular CMP-Neu5Ac to wild-type levels, making a direct effect of p.Thr45Ala on the function of the transporter unlikely. Instead, our results imply that the residual transporter activity of 65% is caused by a decreased stability of the mutated SLC35A1 protein. Since O-GlcNAcylation was affected as well, energy and lipid homeostasis were analyzed and found to be significantly altered. Notably, proliferation and glycosylation of the SLC35A1-deficient patient fibroblasts were enhanced by supplementation of the cell culture medium with 10 mM GlcNAc.

Multistage pig identification using a sequential ear tag detection pipeline

Reliable animal identification in livestock husbandry is essential for various applications, including behavioral monitoring, welfare assessment, and the analysis of social structures. Although recent advancements in deep learning models have improved animal identification using biometric markers, their applicability remains limited for species without distinctive traits like pigs. Consequently, synthetic features such as ear tags have become widely adopted. However, challenges such as poor lighting conditions and the complexity of ear tag coding continue to restrict the effectiveness of Computer Vision and Deep Learning techniques. In this study, we introduce a robust, lighting-invariant method for individual pig identification that leverages commercially available ear tags within a sequential detection pipeline. Our approach employs four object detection models in succession to detect pigs, localize ear tags, perform rotation correction via pin detection, and recognize digits, ultimately generating a reliable ID proposal. In a first evaluation stage, we assessed the performance of each model independently, achieving a mAP0.95 value of 0.970, 0.979, 0.974 and 0.979 for the pig detection, ear tag detection, pin detection and ID classification model, respectively. In addition, our method was further evaluated in two different camera environments to assess its performance in both familiar and unfamiliar conditions. The results demonstrate that the proposed approach achieves a very high precision of 0.996 in a familiar top-down camera scenario and maintained a strong generalization performance in an unfamiliar, close-up setup with a precision of 0.913 and a recall of 0.903. Furthermore, by publicly proposing three custom datasets for ear tag, pin, and digit detection, we aim to support reproducibility and further research in automated animal identification for precision livestock farming. The findings of this study demonstrate the effectiveness of ID-based animal identification and the proposed method could be integrated within advanced multi-object tracking systems to enable continuous animal observation and for monitoring specific target areas, thereby significantly enhancing overall livestock management systems.

Design and Performance Analysis of a Miniaturized Low-Profile Antenna for Cattle Health Monitoring Tags

Abstract This paper presents the design and evaluation of a miniaturized low-profile antenna intended for integration into cattle health monitoring tags. The antenna, with dimensions of 5x5x0.8 mm3 and weighing only 10 grams, is optimized to fit seamlessly into standard cattle ear tags without causing discomfort. The study investigates the impact of the antenna’s placement within the cow’s ear tag and its interaction with the surrounding environment, assessing its performance under real-world conditions. Specific Absorption Rate (SAR) simulations are conducted to evaluate the antenna’s compliance with FCC safety standards, ensuring minimal electromagnetic exposure. The results demonstrate that the proposed antenna design maintains robust communication performance while adhering to regulatory safety guidelines, making it an ideal solution for livestock health monitoring systems.

Research and application progress of electronic ear tags as infrastructure for precision livestock industry: a review

With the rapid development of modern livestock farming, animal electronic ear tags (AEET), as animal identification and tracking tools based on radio frequency identification technology, are playing an increasingly important role in precision livestock management. This review summarizes the latest technological advancements in AEET, including material innovations, design improvements, and manufacturing process enhancements, and explores their wide-ranging applications in production management, food traceability, breeding optimization, behavior recognition, and disease monitoring. Additionally, the article highlights the main challenges faced by AEET, such as durability in harsh environments, data security, and cost-effectiveness. Furthermore, it looks ahead to future development trends, including the integration of Internet of Things and blockchain technologies to further enhance the precision and sustainability of livestock farming. By reviewing the current status and future directions of AEET, this review provides references for researchers and practitioners aiming to improve the efficiency and sustainability of modern livestock industry.

41 Effect of space allocation on feeding behavior in grow-finish pigs

Abstract The objective of this study was to evaluate the feeding behavior of grow-finish pigs in pens with two different floor space allowances. A total of 159 commercial crossbred barrows (n = 90; 25.87 ± 7.43 kg) and gilts (n = 69; 28.74 ± 4.08 kg) were housed in single gender pens and fed a common diet for approximately 14 weeks. At the start of the trial pigs were randomly assigned to pens providing one of two space allocations: 3.05m2/pig or 2.29m2/pig with 3 replicate pens per treatment. At allotment each pig was tagged in the ear with a unique colored ear tag for individual identification. Feed was delivered in standard 3-hole box feeders and water was delivered via nipple waterers. Pigs had ad libitum access to feed and water throughout the trial. Final body weight averaged 119.15 ± 31.54 kg (barrows) and 122.84 ± 12.55 kg (gilts). Video monitoring of trial pens was accomplished with cameras mounted to the barn ceiling and 12 h recordings were taken during week 1 (first week on trial following a 7 d acclimation period) and week 14 (last week before marketing at 97 d) to evaluate feeding behavior and activity at both the beginning and end of the grow-finish period. Behaviors of interest included activity (walking, standing, moving, drinking), the number of times each pig entered the feeder, total time spent eating and eating type (nibbler vs. gorger). Data were analyzed as a completely randomized design using the MIXED procedure in SAS. In week 1, increased floor space tended to increase the number of times pigs entered the feeder (P = 0.07) and significantly increased (P = 0.008) the total time spent eating by ~14%. However, these trends were not present at week 14. Floor space allocation did not influence eating type or alter activity level (P > 0.05) in either week 1 or week 14. No significant differences in feeding behavior resulted from an interaction between space allocation and gender. In week 1, gender did not influence the number of times pigs entered the feeder. However, barrows spent more time eating than gilts (84 vs. 63 min) (P < 0.0001). At week 14 these differences were not present (P > 0.05). As space allocation in swine production becomes increasingly scrutinized it will be important to evaluate behavior changes in the context of performance. In this study, increasing floor space impacted grow-finish pig feeding behavior early in the finishing period, but those behaviors were not observed at the end of finishing. Future research in this direction will attempt to identify at which point in production those behaviors change.

115 Effects of stocker steer performance and behavior while consuming essential oil or ionophore minerals

Abstract The feeding of antibiotics; monensin or lasalocid, has been proven to increase production of grazing cattle. Recently, interest in improving animal health and production has taken priority while also decreasing possible antibiotic resistance. An alternative, essential oils, has been shown to have antimicrobial properties that could increase performance without the use of antibiotics. This study evaluated an alternative to antibiotics for growth performance in grazing stocker steers. Steers (n = 281; 291 ± 5 kg) were assigned to one of two mineral treatments and grazed tallgrass native range. Treatments consisted of the positive control of ionophore (ION; lasalocid at 1,633 g/ton) and essential oil (EO; garlic oil at 1.4 kg/ton and essential oil blend at 2.7 kg/ton) in free-choice mineral. Steers were weighed individually at the beginning (May) and end (August) of the grazing period (92 d). Steers were randomly allocated to pasture (n = 4 pastures/treatment) based on predetermined sort order through chute. At initial processing, steers (n = 29; 3-4 per pasture, equal to 10% of total steers per pasture) were fitted with commercial GPS and activity tracking ear tags to monitor biological and behavioral data. Pasture biomass production and mineral intake were recorded weekly. Steer gains, mineral intake, and pasture biomass and behavioral data were analyzed using PROC GLIMMIX in SAS 9.4 with pasture as experimental unit with steer as subsample. Mineral intake and pasture biomass were analyzed using PROC GLIMMIX in SAS 9.4 with pasture as experimental unit. There was no difference in total gains (P = 0.92; 93 kg for ION vs. 92 kg for EO; SEM = 3.9) nor average daily gain (P = 0.92; 0.98 kg/d for ION vs. 0.97 kg/d for EO; SEM = 0.04) between the two minerals fed to the steers. Mineral intake was the same for both treatments (P = 0.58) and was slightly higher than formulated intake (148 g•steer-1•d-1 as compared to113 g•steer-1•d-1). Available forage was not different between treatment pastures (P = 0.67). There was no difference in average daily steps taken (P = 0.24) nor time spent walking (P = 0.41); time spent ruminating (P = 0.85); time spent resting (P = 0.25); or time spent grazing (P = 0.94). Heart rate (beats per minute) tended (P = 0.07) to be lower in ION supplemented steers than those supplemented with EO. Overall, there was no difference between feeding ionophore or essential oils in mineral in regard to cattle gain during summer double stock grazing on tallgrass native range. The results of this study could provide operations that implement natural marketing systems an option to reduce cost of gain for a more profitable feeding system on the same level as conventional production systems.

PSV-7 Managing Serecia lespedeza in native pastures by concentrated grazing

Abstract Throughout Kansas, invasive grass species are taking over native prairie and grasslands, thus reducing the quantity and quality of native grasses for ruminants to graze. Ultimately, complete eradication is unlikely for some invasive species, but working to manage population expansion is important to ecosystems. Sericea lespedeza encompasses approximately 2.2 million ha of the United States grazing land and continues to encroach on quality grazeland. The objective of this study was to identify if spraying a molasses mixture at four different levels would decrease the infestation of a noxious weed, Sericea lespedeza, in tallgrass native range pastures grazed during the summer. Steers (n=281; 291 ± 5 kg) were randomly assigned to one of 8 tallgrass native range pastures to graze between May and August based on a predetermined sort order through chute. Within each pasture, four locations were identified to have heavy S. lespedeza infestation and were randomly assigned to one of four treatments. Treatments were applied weekly at equal rates of 468 L/ha and consisted of 4 treatments: control (CON: water only); 12.5% (v/v) molasses concentrated spray (12.5M); 25% (v/v) molasses concentrated spray (25M); and 50% (v/v) molasses concentrated spray (50M). Plant counts of S. lespedeza were conducted on permanent transects within spray quadrants and occurred on 0, 30, 60, and 90 d of cattle grazing pastures. Steers (n = 29; 3-4 per pasture, equal to 10% of total steers per pasture) were fitted with GPS and activity tracking ear tags and monitored for location to determine proportion of time spent in sprayed areas and within the immediate vicinity of sprayed area. Sericea lespedeza count data was analyzed using PROC GLIMMIX in SAS 9.4 with pasture as experimental unit. Animal grazing data was analyzed using PROC GLIMMIX in SAS 9.4 with animal within pasture as experimental unit. Sericea lespedeza numbers were lower at the end of grazing in the subplots that were sprayed with molasses as compared to CON (P = 0.003). There was a quadratic effect (P = 0.01) where 12M had a more pronounced effect on S. lespedeza than CON and 50M. Spraying infested areas did not stop the growth of S. lespedeza as there were more plants in August as compared to May (P < 0.01). There was no difference in time spent grazing in the sprayed areas (P = 0.31); however, the steers spent more time grazing in the areas closest to 12.5M as compared to 50M with 25M being intermediate (P = 0.01). Overall, in this first year of data collection, it appeared that spraying with 12.5% molasses (v/v) will entice cattle to spend more time in an area with undesirable plant populations, ultimately resulting in a less pronounced growth of plants.

Pig survival, average daily gain, and individual antimicrobial treatments from birth to slaughter in Finland.

Birth weight appears to be a key indicator for survival and average daily gain (ADG) in piglets. However, parameters associated with piglet antimicrobial treatment are less explored. We assessed the factors influencing piglet survival, ADG, and first individual antimicrobial treatment. Data were collected on sex, weight, litter details, and medication throughout the lifespan of 3991 ear tagged pigs in Finland. Discrete-time survival models were performed for piglet survival and individual antimicrobial treatment as well as a linear regression model for piglet ADG from birth to slaughter. Medium (1 - 1.49 kg) and lightweight (< 1.0 kg) piglets at day 4 had 2.26 and 4.04 times higher odds of dying (in terms of odds for discrete hazards), respectively, than heavyweight (≥ 1.5 kg) piglets. Barrows and antimicrobial-treated suckling piglets had 1.81 and 1.67 times, respectively, higher odds of dying than females and unmedicated piglets. The mean average daily gain from birth to slaughter was 714 g (SD 70.2 g). Pigs born to sows grew 29.2 g/day more than pigs born to gilts, and barrows grew 13.3 g/day better than females, but these results should be interpreted with caution because a considerable number of ear tags lost during the study could have led to selection bias of the pigs with a measured ADG. Altogether 756 piglets received at least one individual parenteral antimicrobial treatment. Antimicrobial-treated pigs were to a considerable extent medicated before weaning mainly for diarrhea and leg problems during two treatment peaks: before day 8 and around weaning. Lightweight piglets at day 4 had 2.35 and piglets born to gilts 1.56 times higher odds of becoming medicated with antimicrobials than heavyweight piglets and piglets born to sows, respectively. Half of the study piglets receiving antimicrobials were treated again later. In summary, our results show that lightweight piglets at day 4 had poorer survival, and they received more antimicrobial treatments than their heavier littermates. Further, gilt offspring were medicated more frequently. This emphasizes the need to direct extra attention to litters born to gilts.

Novel Gels for Post-Piercing Care: Evaluating the Efficacy of Pranoprofen Formulations in Reducing Inflammation.

Mild to moderate pain for a few hours to several days post-piercing is normal, and the pain is usually accompanied by swelling, redness, and warmth due to the inflammatory response. Cool compresses and over-the-counter analgesics (e.g., NSAIDs) can ease mild discomfort. However, oral NSAIDs may have systemic side effects; for this reason, we propose a topical anti-inflammatory approach. Four pranoprofen-loaded gels were created using different gelling agents: Sepigel® 305 (PF-Gel-Sep), Carbopol® 940 (PF-Gel-Car), Pluronic® F-68 (PF-Gel-Plu), and Lutrol® F-127 (PF-Gel-Lut). The gels were assessed for pH, morphology, FT-IR spectroscopy, rheological properties, spreadability, swelling and degradation, drug release kinetics, skin permeation (cow and human skin), irritation potential (HET-CAM assay), and impact on skin barrier function (TEWL and SCH). The gels exhibited varied rheological properties with PF-Gel-Car showing high viscosity and PF-Gel-Plu very low viscosity. All gels had similar spreadability with PF-Gel-Lut showing the highest. PF-Gel-Car showed the highest amounts of PF released, whereas PF-Gel-Plu led to the highest amount of pranoprofen retained in human and bovine skin. The HET-CAM assay indicated that none of the PF-Gels were irritating. Additionally, PF-Gel-Car and PF-Gel-Plu showed no cytotoxic effects on HaCaT cells. In vivo testing on mice showed that PF-Gel-Car prevented inflammation, while the rest of the gels were able to revert it in 25 min. Skin tolerance tests revealed the gels did not affect TEWL, and some gels improved SCH. The study successfully formulated and characterized four PF-loaded topical gels with potential to be used as an alternative for treating inflammation from piercings and ear tags.

Assessment of Flurbiprofen Suspension and Composite Gel Pre- and Post Skin Perforation: Effectiveness in Managing Inflammatory Responses in Ear Tags and Periocular Piercings.

(1) Background: Controlled skin perforations, such as ear tags, piercings, and microdermal implants, induce inflammation and stress in individuals undergoing these procedures. This localized trauma requires care to optimize healing, reduce inflammation, and prevent infections. (2) Methods: Two formulations were developed: an FB-suspension and an FB-gel. Their in vivo efficacy was evaluated, along with drug retention in porcine and human skin after 30 min of administration, chemical stability at different temperatures, cytotoxicity, histological changes induced via transdermal application, and irritative potential, assessed using the HET-CAM assay. (3) Results: Both formulations reduced inflammation when applied 30 min before perforation compared to the positive control. The FB-suspension demonstrated no cytotoxicity and exhibited greater efficacy than the free flurbiprofen solution, highlighting the advantages of using nanoparticle-mediated drug delivery. Moreover, the FB-gel maintained chemical stability for up to 3 months across a temperature range of 4 to 40 °C. Histologically, no significant changes in skin composition were observed. (4) Conclusions: The FB-suspension is viable for both pre- and post-perforation application, as it is a sterile formulation. In contrast, the FB-gel is a convenient and easy application, making it a practical alternative for use in both clinical and veterinary settings.

A Perspective on Ear Malformations: A Case Series

Ear deformities, both congenital and acquired, can significantly impact aesthetics, hearing function and psychological well-being. The present case series presents a diverse range of auricular anomalies, discussing their clinical presentation, underlying causes and management strategies. Congenital deformities include microtia, characterised by underdeveloped external ear structures that may be associated with conductive hearing loss, as well as prominent ears, which can lead to self-esteem issues. Additionally, ear tags, which are small benign appendages of skin and cartilage and cupped ear deformity, where the helix and antihelix are malformed, are highlighted, emphasising the role of early intervention in improving cosmetic and functional outcomes. Acquired ear deformities arise due to trauma, chronic inflammation, or improper healing. This series discusses cases of ear keloids, which form due to excessive scar tissue following ear piercings or surgeries, requiring multimodal treatment that includes corticosteroid injections, surgical excision and pressure therapy. Cauliflower ear, which results from repeated trauma leading to haematoma formation and fibrosis, is examined in the context of preventive measures and surgical correction. Burn-related ear deformities, which lead to severe tissue loss and contracture formation, present reconstructive challenges that necessitate skin grafts or cartilage framework reconstruction. Early diagnosis and timely management, facilitated by a multidisciplinary approach involving plastic surgeons, dermatologists and otolaryngologists, are crucial for optimising patient outcomes. The present case series underscores the importance of addressing both functional impairments and aesthetic concerns to enhance the overall quality of life for patients.

Use of radio frequency identification technology to enhance the traceability of bull semen does not affect sperm motility or nonreturn rates.

Use of radio frequency identification technology to enhance the traceability of bull semen does not affect sperm motility or nonreturn rates.

Wearable biosensors: an aid for cattle well-being

Purpose The purpose of this study was to gather data regarding cattle wearable wireless sensor systems (WWSS) and to provide a thorough literature analysis on the reliability of these systems’ physiological parameter predictions. The WWSS was divided into types that were vaginally mounted, tail-mounted, rumen bolus, leg tags, halters, neck collars and ear tags. Design/methodology/approach Data was gathered via an online Google search followed by a careful manual curation of the data. Several WWSSs were on the market, and most sensors had an accelerometer. The literature assessing the performance of the WWSS was gathered using a Scopus keyword search. Findings The WWSS is essential for providing physiological and behavioral data to every individual. This study analyzed the broadest range of sensor system types currently on the market and summarized comprehensive data about them. With a few exceptions (drinking time and walking time), most produce great performance regarding cattle’s behavioral and physiological characteristics (e.g. eating, ruminating, laying and standing). Originality/value To monitor the state of cattle health in real time and without delay, it is necessary to combine all available sensors and develop an effective online monitoring system. To detect various infectious diseases in cattle, this review paper explores the range of wearable technologies for cattle, nano biosensors and advanced molecular biology diagnostic techniques. It also compares and contrasts these technologies based on their benefits and drawbacks in cattle health management. To offer insight into the best strategy to be used from now on for improved cattle welfare, this study takes into account all current advancements regarding the field of biosensors and their applications for cattle health.

Two years of precision livestock management: harnessing ear tag device behavioral data for pregnancy detection in free-range dairy cattle on silage/hay-mix ration

IntroductionThe aim of this study was to evaluate the transformative potential of precision livestock farming (PLF) in dairy production, nutrition, and reproductive efficiency by implementing proactive management strategies that utilize real-time data.MethodsData were gathered from a commercial dairy farm, employing a 3D accelerometer system attached to ear-tags to monitor activity and rumination behavior. Additionally, information on animal-related events such as oestrus, artificial insemination, clinical diseases, and treatments was recorded.ResultsIt was observed that there were differences in rumination between positive and negative cows in the days following artificial insemination (AI). Specifically, from day 0 to day 16, negative cows exhibited a higher rumination time compared to positive cows, with this contrast being particularly significant on days 9 and 10. Over the duration of the study, cows that tested negative produced, on average, 0.78 kg more milk per day.DiscussionThis suggests that animals with higher milk production were less likely to be pregnant, potentially due to increased nutrient allocation to the mammary gland, resulting in a more pronounced negative energy balance and consequently lower conception rates. Furthermore, the accelerometer utilized in this study was capable of distinguishing differences in daily lying time between pregnant and non-pregnant animals on the days of oestrus return. This finding highlights the potential for developing a system alert to identify “probable pregnant” and “probable non-pregnant” animals.

Utilizing Physiological Metrics and Change Point Analysis for Real-Time Livestock Health Monitoring

Objective: This study introduces a smart ear tag system for real-time monitoring of cattle health, integrating physiological metrics such as body temperature, heart rate, and oxygen saturation (SpO2) with Change Point Analysis (CPA) to detect state changes. Materials and Methods: The system was tested over a 7-day period on 10 cattle, monitoring health metrics continuously. CPA was applied to identify synchronized changes in the monitored parameters. The system's performance was evaluated based on its ability to detect potential health status changes while maintaining reliability and specificity. Results: The system successfully identified synchronized state changes in one animal, flagging a potential health issue, while showing no significant changes in the other nine animals. This indicates the system’s capability to differentiate between normal variability and significant health-related changes. Conclusion: The proposed smart ear tag system demonstrates significant potential for Precision Livestock Farming. By integrating multiple physiological metrics and advanced analysis, it offers a reliable framework for improving animal welfare and enabling early disease detection.

IMPROVED DEEP LEARNING MODEL FOR CATTLE IDENTIFICATION USING MUZZLE IMAGES

Using traditional methods such as ear tags, branding, and tattoos for cattle identification requires continuous human involvement and demands significant time and effort. Although radio-frequency identification (RFID) methods are widely used today, they also have certain disadvantages. The RFID devices used must be constantly installed, which can cause discomfort to the animals, and during their movements, the devices may become damaged or lost, leading to further issues.By using biometric features for cattle identification, these disadvantages are eliminated. In this method, animals are identified using their unique biometric features, such as iris patterns, skin textures, muzzle prints, and facial features. This article focuses specifically on identifying cattle based on their muzzle images. In this study, a total of 4923 images of 268 cattle were used. The architectures of eight different models were improved and selected for the training process, and the training was conducted. According to the results, the DonsoNot-121, WidoRosNot-50, and Inception V3 models achieved the highest accuracy rates, with 99.2%, 99.1%, and 99.1%, respectively. These results demonstrate the effectiveness of the proposed architecture.

Performance of machine learning methods for cattle identification and recognition from retinal images

Animal identification is a critical issue in terms of security, traceability, and animal health, especially in large-scale livestock enterprises. Traditional methods (such as ear tags and branding) both negatively affect animal welfare and may lead to security vulnerabilities. This study aims to develop a biometric system based on retinal vascular patterns for the identification and recognition of cattle. This system aims to provide a safer and animal welfare-friendly alternative by using image processing techniques instead of traditional device-based methods. In the study, preprocessing, segmentation, feature extraction, and performance evaluation steps were applied for the biometric identification and recognition process using retinal images taken from both eyes. Techniques such as green channel extraction, contrast-limited adaptive histogram equalization, morphological operations, noise filtering, and threshold determination were used in the preprocessing stage. Fuzzy C-means, K-means, and Level-set methods were applied for segmentation, and feature extraction was performed using SIFT, SURF, BRISK, FAST, and HARRIS methods. At the end of the study, the highest accuracy rate was obtained as 95.6% for identification and 87.9% for recognition. In addition, the obtained dataset was shared publicly, thus creating a reusable resource that researchers from different disciplines can use. It was concluded that this study made a significant contribution to the field of biometric-based animal identification and recognition and offered a practically usable solution in terms of animal welfare and safety.

Hierarchical model with integrated probabilistic strategy for classifying pig behaviors using active electronic ear tags

Hierarchical model with integrated probabilistic strategy for classifying pig behaviors using active electronic ear tags

Classification of behaviour with low-frequency accelerometers in female wild boar.

Accelerometers with low sampling rates (1 Hz) are commercially available as ear tags. While an automated and therefore undisturbed sampling of animal behaviour can be useful not only in behavioural studies but also in ecological or wildlife management studies, the usefulness of such 'a low data collection rate for the prediction of behaviours was the key question addressed here. We classified the behaviour of female wild boar, kept under semi-natural conditions in a large outdoor enclosure, using acceleration data. Predictions were based on a machine learning algorithm, specifically a random forest model in the open software h2o. Remarkably, prediction of many behaviours was possible using ear-tag acceleration sensors that sampled data only at a low frequency. This measurement device was mainly used to minimise the potentially harmful effects caused by the repeated capture of wild animals to exchange batteries. Long battery life will also help to collect long-term accelerometer data and has the potential to explore seasonal and inter-annual trends. Foraging, lateral resting, sternal resting and lactating were identified well, scrubbing, standing and walking not reliably. Balanced accuracy depended on the behaviour type and ranged from 50% (walking) to 97% (lateral resting). Results show that static features of unfiltered acceleration data, as well as of gravitation and orientation filtered data, were used in the prediction of behaviour. The waveform of certain behaviours in the sampled frequency range played no important role. Certain positively identified behaviours, such as food intake and lactation, could be of interest for wildlife managers attempting to control population growth in this pest-species. We provide several R-scripts that allow the analysis of behavioural accelerometer data.