Ethogram-Based Characterization for Identifying Inactivity not related to NREM Sleep in Horses Using Artificial Intelligence and Quantifying Movement with Inertial Measurement Unit

• Grant number: 25/09102-8
• Support Opportunities: Scholarships abroad - Research Internship - Doctorate
• Start date: October 27, 2025
• End date: June 27, 2026
• Field of knowledge: Agronomical Sciences - Veterinary Medicine - Animal Clinics and Surgery
• Principal Investigator: Raquel Yvonne Arantes Baccarin
• Grantee: Ângela Perrone Barbosa
• Supervisor: Emanuela Dalla Costa
• Host Institution: Faculdade de Medicina Veterinária e Zootecnia (FMVZ). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Institution abroad: Università degli Studi di Milano, Italy
• Associated to the scholarship: 24/20303-2 - Rest Patterns Assessment in Horses Using Electroencephalogram (EEG) and Characterization of an Ethogram to Identify Non-NREM Sleep-Related Inactivity While Standing, BP.DR

Abstract

The project focuses on improving equine welfare by developing and refining an ethogramto differentiate inactivity behaviors from standing NREM sleep. It aims to address behavioralchanges due to confinement, boredom, or unstimulating environments, as these can lead tofrustration, stereotypic behaviors, and reduced welfare.This research seeks to optimize welfare monitoring through innovative approaches thatcombine artificial inteligence (AI), video analysis, and IMU data. By refining tools and methodologies, the projectaims to address significant gaps in understanding equine inactivity and sleep deprivation,ultimately enhancing their welfare in diverse environments.By training artificial intelligence (AI) using 1,500 hours of video footage, the detection ofequine behaviors will be enhanced, allowing for precise identification and inclusion of newbehaviors in the ethogram. In addition to AI, inertial measurement units (IMUs) will be tested astools to monitor equine movements non-invasively. These devices will provide insights intorecumbency patterns and total movement, complementing video analysis. During the study,equines subjected to REM sleep deprivation will be observed and their behaviors compared withthose in control conditions. Data gathered will help refine the ethogram by adding new behaviorsand improving its accuracy in identifying inactivity states and sleep deprivation.The project also investigates sleep in hospitalized equines. Using video footage andIMUs, the ethograms efficiency in real-world scenarios will be validated. Collaboration withProf. Emanuela Dalla Costa, a leading expert in equine behavior, ensures access to advancedtechniques and expertise.