TITULO: BIG DATA AND DIGITAL TOOLS APPLIED TO LIVESTOCK PRODUCTION

IMPARTIDO POR: Guilherme Rosa y Joao Dorea (Universidad de Wisconsin-Madison)

LENGUA: Impartido en inglés

FECHA: 5 a 9 de Junio de 2023

LUGAR:  Universitat Politècnica de València.

              Escuela Técnica Superior de Ingeniería Agronómica y del Medio Natural

              Edificio 3P - AULA 1.9   Plano de situación

REQUERIMIENTOS: Se requiere traer Laptop

HORARIO:

LUNES 5 y MARTES 6:     9:30 a 13:30  y 14:00 A 17:00

MIERCOLES 7:                 9:30 a 13:30

JUEVES 8 y VIERNES 9:   9:30 a 13:30  y 14:00 A 17:00

MATRICULA:   75 € para los participantes del proyecto TED Farm

                      200 € para el resto de participantes

Para matricularse, acceder a la siguiente dirección y seguir las instrucciones:

https://www.cfp.upv.es/formacion-permanente/curso/big-data-herramientas-digitales-aplicadas-produccion-ganadera_90117.html

PROGRAMA

1. Big Data and Data Science in Livestock
2. Planning Research Studies in Animal Sciences
3. Database Management
4. Multidimensional Regression and Classification
5. Machine Learning Techniques
6. Image Processing and Analysis
7. Infrared Spectroscopy and Hyperspectral Imaging
8. Wearable Sensing Technology
9. Deep Learning
10. Genomics Data
11. Mining Operational Farm data
12. Cloud Computing

 

DESCRIPCION

This graduate-level course is designed for researchers working in all areas of animal sciences, including nutrition and physiology, management, genetics, and reproduction in both industry and academia. The course is particularly suitable for those interested in data analytics and precision management of livestock. Statisticians, computer scientists, and data scientists who want to learn about potential applications in animal science can also benefit from this course.

The course will cover key concepts and techniques related to statistics and machine learning applied to high-dimensional data in livestock, including data from sensors, imaging, genomics, farm-recorded data from management software, and publicly available datasets. The course is structured with four sessions per day, from Monday to Friday (except for Wednesday afternoon, which is free time to foster discussion and networking among participants). The sessions include expository lectures and demos with real data and useful software and algorithms that will be shared with the participants.