Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

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

Comparative analysis of monocular depth generation and camera depth for non-invasive rabbit live weight estimation

  • Méndez-Reyes, Daniel Alexander|||0000-0001-6414-305X
  • Cano, Carmen
  • Martínez, Alberto
  • Ruiz, Carlos
  • Aguilar, Enrique
  • Cubero, Sergio
  • Villagra, Arantxa
[EN] In contemporary commercial rabbit farming, accurate live weight assessment is essential for efficient production management. Traditional manual weighing is labour-intensive, stressful for animals, and impractical for frequent monitoring. This study evaluates computer vision approaches for non-invasive liveweight prediction by comparing RGB, real depth, and AI-generated depth images as input modalities. A dataset of synchronized RGB and depth images was collected from 1113 weaned and near-slaughter rabbits (1.2-7.7 kg) under controlled conditions. Image segmentation was performed using YOLOv11 without fine-tuning, demonstrating its feasibility for rabbit detection. Morphological pre-processing was applied to assess its impact, while tabular features from RGB were used to train traditional models (Extra Trees, Gradient Boosting). Deep learning models Effi-cientNetV2, MobileNetV4, and a dual-stream fusion model were trained on RGB, camera depth, and generated depth inputs. Results show that generated depth maps match or exceed the performance of RGB, with Effi-cientNetV2 achieving the highest accuracy using MG_4 (Marigold monocular depth model with 4 denoise steps)-an AI-generated depth map synthesized from RGB images (R2 = 0.945, RMSE = 368.36 g). In our experiments, morphological pre-processing degraded performance across all tested models and input types, suggesting that such operations may remove features information that are informative for model prediction. The fusion model achieved competitive results (R2 = 0.941, RMSE = 379.935 g), but gains were marginal compared to unimodal inputs. Notably, Extra Trees achieved R2 = 0.945, RMSE = 366.241 g without pre-processing, rivalling deep learning models. MobileNetV4 offered the best efficiency-accuracy trade-off (31.18 MB, 1.79 GFLOPS), making it suitable for edge deployment. These findings highlight AI-generated depth as a scalable, cost-effective alternative to hardware depth sensors in precision rabbit farming., This work was supported by GVA-IVIA and was co-funded by the EU through the Operational Programme ERDF of the Comunitat Valenciana 2021-2027 [grant number 52201 L, AgroAlimVal].
RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Publicación Artículo científico (JournalArticle)

Impact of including two types of destoned olive cakes in pigs diets on fecal bacterial composition and study of the relationship between fecal microbiota, feed efficiency, gut fermentation, and gaseous emissions

  • Belloumi, Dhekra
  • García-Rebollar, Paloma
  • Francino, M. Pilar
  • Reyes-Prieto, Mariana
  • Piquer-Molina, Laia
  • González-Garrido, Jorge
  • Bermejo-Del Castillo, Almudena
  • Cano-Aguilar, Carmen
  • Cerisuelo, Alba
  • Calvet, S.|||0000-0001-6639-9892
  • Jiménez Belenguer, Ana Isabel|||0000-0002-3329-7221
[EN] The microbial population in the pig¿s gastrointestinal tract can be influenced by incorporating fibrous by-products into the diets. This study investigated the impact of including two types of dried olive cake (OC) in pigs¿ diets on fecal bacterial composition. The correlation between fecal microbiota and growth performance, nutrient digestibility, gut fermentation pattern and slurry gas emissions was also evaluated. Thirty male Pietrain x (Landrace x Large white) pigs (47.9¿±¿4.21¿kg) were assigned to three groups: a control group (C), a group fed a diet with 20% partially defatted OC (20PDOC), and a group fed a diet with 20% cyclone OC (20COC) for 21¿days. Fecal samples collected before and after providing the experimental diets were analyzed for the V3-V4 region of the 16S rRNA gene. Pigs were weighed, and feed intake was recorded throughout the study. Potential ammonia and methane emissions from slurry were measured. No significant differences in alpha diversity indexes were found. The taxonomic analysis revealed that Firmicutes and Bacteroidota phyla were dominant at the phylum level across all groups. Differential abundance analysis using ALDEx showed significant differences among groups for various bacteria at the phylum, genus, and species levels at the end of the experiment. Pigs from 20PDOC and 20COC groups exhibited increased abundances of health-promoting bacteria, such as Plactomycetota at the phylum level and Allisonella and an unidentified genus from the Eggerthellaceae family at the genus level. These changes influenced short-chain fatty acids¿ (SCFA) concentration in slurries, leading to greater acetic, butyric, caproic and heptanoic acids in OC-fed groups, especially 20COC pigs. A volatility analysis revealed significant positive correlations (p¿<¿0.05) between Uncultured_Bacteroidales and Unculured_Selenomonadaceae and energy digestibility. Monoglobus and Desulfovibrio showed a positive significant (p¿<¿0.05) correlation with total SCFA, indicating a high impact on gut fermentation. However, growth performance parameters and potential gas emission displayed no significant correlations with a specific bacterial genus. In conclusion, our results suggest that OC inclusion into pig diets could positively modulate and contribute to the gut microbiota¿s favorable composition and functionality. Also, nutrient digestibility and gut fermentation patterns can be associated with specific microbial populations., The author(s) declare that financial support was received for the research, authorship, and/or publication of this article. This work was funded by the Spanish Ministry of Science and Innovation (Project RTI-2018-095246-B-C22) and the project IVIA-GVA (52201L) from Instituto Valenciano de Investigaciones Agrarias (this project is co-financed by the European Union through the ERFF Program 2021 2027 Comunitat Valenciana). DB is a recipient of the Santiago Grisolía PhD scholarship (GRISOLIAP/2020/023).