Pasar al contenido principal

Integration of Big Data and Artificial Intelligence to develop Precision Livestock Farming

JDC2023-050534-I

•
Nombre agencia financiadora Agencia Estatal de Investigación
Acrónimo agencia financiadora AEI
Programa Programa Estatal para Desarrollar, Atraer y Retener Talento
Subprograma Subprograma Estatal de Formación
Convocatoria Juan de la Cierva
Año convocatoria 2023
Plan Estatal 2021-2023 Plan Estatal de Investigación Científica y Técnica y de Innovación
Centro beneficiario UNIVERSITAT POLITÈCNICA DE VALÈNCIA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 3
Encontrada(s) 1 página(s)

RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Evaluation of Multi-Object Detection models for automated goat behavior identification in intensive farming facilities

  • Méndez-Reyes, Daniel Alexander|||0000-0001-6414-305X
  • Fajardo-Viloria, Blanca
  • Gil-Vidal, Eliseo
  • Calvet, S.|||0000-0001-6639-9892
  • Costantino, Andrea|||0000-0003-4298-432X
[EN] Computer vision offers significant potential for the continuous, stress-free, and cost-effective monitoring of animal behavior, yet its application in goat farming remains limited. In this study, a Multi-Object Detection (MOD) model was developed to classify goat behavior into four categories: eating, standing, drinking, and lying. Zenithal videos were recorded under both light and dark conditions on an experimental goat farm, resulting in 10740 labelled annotations used to train, validate, and test 13 models leveraging Transformer- and CNN-based pretrained architectures. YOLO-based models (YOLOv8 and YOLOX) achieved the highest overall performances across both large and lightweight versions, demonstrating high detection capability and potential suitability for hardwareconstrained scenarios. YOLOX-based MOD model is identified as the most suitable for goat behavior detection due to its superior classification accuracy, fast inference speed, and fully open-source license, enabling flexible customization, deployment, and reproducibility. Other models, particularly DAB-DETR and H-DINO, underperformed, especially in detecting drinking behavior, which represents the most challenging class due to its visual similarity with standing, class imbalance, and fisheye distortion effects that affect the frame regions where drinkers are located. Mitigation strategies, including focal loss and distortion correction, improved detection accuracy for this class and reduced performance variability. The developed MOD model can be deployed for continuous group-level monitoring of goats, paving the way for scalable and efficient solutions for advanced behavioral analyses. Future works will focus on integrating tracking algorithms for animal-level insights, as well as on evaluating model generalizability across different farming conditions and goat breeds., This work was supported by the "Ayuda a Primeros Proyectos de Investigacion" program [grant number PAID-06-23] , Vice-rectorate for Research of Universitat Politecnica de Valencia (UPV) . Andrea Costantino was supported by the grant JDC2022-049782-I funded by MICIU/AEI/10.13039/501100011033 and by the European Union NextGenerationEU/PRTR. Daniel Alexander Mendez was supported by R+D+i project TED2021-130759B-C31, funded by MCIN/AEI/10.13039/501100011033/and by the "European Union NextGenerationEU/PRTR" and by the grant JDC2023-050534-I funded by MICIU/AEI/10.13039/501100011033 and for FSE+. Eliseo Gil Vidal was supported by PLF4ALL project (CIAICO/2021/212, Generalitat Valenciana).
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Classification of Goat Vocalization via Lightweight Machine Learning and High-Dimensional Acoustic Features

  • Méndez-Reyes, Daniel Alexander|||0000-0001-6414-305X
  • Calvet, S.|||0000-0001-6639-9892
[EN] Simple Summary Nowadays, monitoring the well-being of farm animals continuously and without disturbing them is a major goal. For goats, vocalizations carry important information about their emotions, such as distress from an injury or heat, and more social-related information such as a mother recognizing her kid. While computers can learn to identify these sounds, current methods often require high computer capacity and are difficult to operate directly in barns or fields due to economical and energy constraints. This study developed a lightweight algorithm designed specifically to run on small, low-power devices directly on farms. By analyzing specific acoustic patterns in the sound waves rather than converting them into complex data, the algorithm successfully learned to recognize eight different goat behavioral contexts and states with high accuracy. The system was especially reliable at detecting extreme distress and mother-kid reunions. This development provides farmers with a practical, and real application tool to automatically monitor goat welfare in real-time, helping to identify animal conditions. Continuous monitoring of livestock vocalizations offers a non-invasive tool for welfare assessment, but deploying current deep learning models in resource-constrained farm environments remains challenging due to high computational demands. This study proposes a feature-based machine learning pipeline optimized for edge computing to classify caprine vocalizations. Using the VOCAPRA dataset, which comprises 4147 labeled caprine vocalizations categorized into eight distinct welfare states and contexts, a hybrid feature extraction framework was applied to derive 156 spectral, temporal, and bioacoustic descriptors. Dimensionality reduction and a comprehensive comparative screening of 18 algorithms identified the CatBoost Classifier and a Multilayer Perceptron (MLP) as the optimal models. The CatBoost ensemble achieved a robust accuracy of 85.2%, while the optimized MLP reached 87.2% overall accuracy. An edge deployment benchmark revealed that the MLP was the best candidate with for real-time application, featuring a memory footprint of just 0.639 MB and near-instantaneous inference speeds of under 0.005 milliseconds per sample. Furthermore, feature importance and SHAP analyses revealed that mel-frequency cepstral coefficients heavily drove model decisions, particularly for identifying extreme physical distress and maternal reunion. The proposed methodology achieves competitive classification performance while dramatically reducing pre-processing and computational loads compared to image-based deep learning approaches, demonstrating the viability of lightweight-model, energy-efficient, real-time bioacoustic monitoring for precision livestock farming., This research was funded by the "Ayuda a Primeros Proyectos de Investigacion" program [grant number PAID-06-25], Vice-rectorate for Research of Universitat Politecnica de Valencia (UPV). Daniel Alexander Mendez Reyes was supported by the grant JDC2023-050534-I funded by MICIU/AEI/10.13039/501100011033 and by FSE+.
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Machine learning-based multivariate time-series forecasting for environmental monitoring in pig houses under high stochasticity

  • Méndez-Reyes, Daniel Alexander|||0000-0001-6414-305X
  • Jarque-Durán, Marta
  • Calvet, S.|||0000-0001-6639-9892
[EN] Ammonia gas concentration in intensive swine production pose serious environmental and health challenges, particularly in naturally ventilated systems. This study presents an application-oriented comparative evaluation of eight state-of-the-art forecasting models to predict NH3 concentrations in a commercial pig house. First a factorial design assessed the impact of covariates, resolution time, window lengths, and pre-processing. Results identified data preprocessing as the primary driver of model accuracy, where causal non-centered smoothing significantly outperformed aggressive outlier removal, and the exclusion of non-essential covariates for predictions. Among the architectures, TiDE and D-Linear excelled in short-term forecasting. Targeted optimization of the TiDE model using only past covariates achieved an R2 of 0.895 f 0.005 and a Mean Absolute Error of 0.150 f 0.012 for a 30-minute horizon, representing an improvement in variance explanation over the unoptimized baseline. For longer 60-minute horizons, models relying solely on past covariates showed diminishing returns; the optimized linear model (D-Linear) improved its R2 to 0.507 f 0.005, while the deep TiDE architecture plateaued at an R2 of 0.583 f 0.062. However, integrating future weather covariates proved essential for the Temporal Fusion Transformer (TFT), which utilized these inputs to stabilize multi-horizon forecasts, achieving a highly stable R2 of 0.88 f 0 at 30 min and maintaining a robust R2 of 0.665 f 0.015 at the challenging 60-minute horizon. These findings suggest a hybrid Precision Livestock Farming framework: employing optimized lightweight models like TiDE for immediate, real-time ventilation control, while reserving attention-based architectures enriched with meteorological forecasts for extended operational planning., Daniel Alexander Mendez was supported by the grant JDC2023- 050534-I funded by MICIU/AEI/10.13039/501100011033/ and by FSE+. This publication is part of the R+D+i project PorcNFree CPP2021-008476, funded by MCIN/AEI/10.13039/501100011033/ and by the European Union NextGenerationEU/PRTR .