An AI-Based Digital Platform for Sustainable Livestock Lifecycle Management

Abstract

Sustainable livestock lifecycle management increasingly depends on reliable phenotype monitoring and decision support built on heterogeneous data streams that often remain fragmented across images, genomic records, and operational metadata. This paper presents an AI-based digital platform centered on the Center for Processing and Visualization of Aggregated Data (CIOD), which provides a secure, analytics-ready environment for data ingestion, integration, storage, and controlled access. CIOD follows a layered architecture comprising secure ingestion and integration, application services, and persistent storage, and exposes functionality through a Web interface, APIs, and machine-access protocols to support reproducible analytics workflows. As an initial platform-level validation of the visual analytics component, we benchmark YOLO-based object detection models (YOLOv5, YOLOv8, and YOLOv11) on a specialized single-class horse image dataset. The evaluated models achieve near-ceiling localization performance under mAP@0.5, while the stricter COCO-style metric mAP@0.5:0.95 provides clearer model separation, with YOLOv11 reaching approximately 0.91. These results support the feasibility of integrating real-time object detection into CIOD as a reusable service; however, the current evaluation is limited to a single-class setting and should be interpreted as an initial proof of concept rather than a definitive assessment of cross-farm or multi-class generalizability. Beyond operational monitoring, the platform can also support veterinary and animal science education by providing curated datasets, transparent AI outputs, and repeatable analytics pipelines for learning digital phenotyping and evidence-based interpretation.

More by Assel Mukasheva

• Performance Evaluation of WPA2 and WPA3 Security Protocols in Private Wi-Fi 6 Environments2026
• HYBRID GAT-AUTOENCODER-BILSTM-ATTENTION ARCHITECTURE FOR MULTI CLASS CYBERATTACK DETECTION IN HETEROGENEOUS IOT NETWORKSВестник Алматинского университета энергетики и связи · 2026
• DISTRIBUTED SYSTEM FOR DATA SHARING AND JOINT PROCESSING BETWEEN RESEARCH CENTERS AND FARMSВестник Алматинского университета энергетики и связи · 2026
• Comparative Study of Regression Models Using Machine Learning to Predict Real Stock PricesInternational Conference on Electronics, Engineering Physics and Earth Science · 2026