Parallel sessions
TUESDAY 10/09/2024 – 12:00 – 13:15
SESSION 6 – COWS HEALTH & DISEASE DETECTION 1
Sala Italia
Chairman: Tami Brown-Brandl
Fever detection in calves using wearable physiological data
Daniel Berckmans, KU Leuven, Belgium
Thermal imaging for claw health classification of dairy cattle
Pieter-Jan De Temmerman, Flanders Research Institute, Belgium
Assessing the effects of sensor-based health monitoring procedures in early lactation on animal health, performance, and surveillance traits on a Holstein dairy farm
Michael Iwersen, University of Veterinary Medicine, Austria
Integrated use of data to improve dairy cow’s health and welfare
Giulia Gislon, University of Milan, Italy
Integrating genomics and phenomics data for the early detection of subclinical ketosis in dairy cows
Rafael Ferreira, University of Wisconsin-Madison, United States
SESSION 7 – COWS OESTRUS TO PARTURITION
Sala avorio
Chairman: Ilan Halachmi
Cattle breeding digitalisation: proximity sensors for oestrus detection under grazing conditions
Manuel Jesús García García, University of Cordoba, Spain
Skeleton-based computer vision algorithms for detecting behavior of dairy cows prior to calving
Mathias Gosch, University of Veterinary Medicine Vienna, Austria
Use of deep learning algorithms to evaluate luteal color Doppler ultrasonography as an alternative method of pregnancy diagnosis in cattle
Anderson A. C. Alves, University of Georgia, United States
Development of a calving detection model based on behaviors from an accelerometer collar device in dairy cows
Milos Kosanovic, University of Nis, Serbia
The Cowtech Project: a module for cow oestrus detection in free stall barns by LoRaWAN services
Marco Bonfanti, University of Catania, Italy
SESSION 8 – COMPUTER VISION PIGS BEHAVIOUR
Sala bianca
Chairman: Paolo Trevisi
Tail biting in pigs: event and biter detection via automatic audiovisual analysis
Philipp Heseker, University of Veterinary Medicine Hannover, Germany
Intelligent recognition of live pig aggregation behavior based on convolutional neural network
Chao Liang, China
Noisy-student piglet detection – An approach for the automatic data generation to increase object detection performance
Martin Wutke, University Kiel, Germany
Pig Behaviour Classification using CRNN
Andrea Parmiggiani, KU Leuven, Belgium
Tail Posture as a Predictor of Tail Biting in Pigs: A Camera-Based Monitoring System
Jan-Hendrik Witte, Universität Oldenburg, Germany
SESSION 9 – POULTRY BEHAVIOUR & PRODUCTION
Sala verde
Chairman: Massimiliano Petracci
Application of passive RFID to monitor the feeding behaviour of broiler chickens
Rudi de-Mol, Wageningen Livestock Research, Netherlands
Towards an adaptive expert-in-the-loop algorithm for early detection of problems in laying hen flocks
Lara van Veen, Vencomatic Group, Netherlands
Predicting broiler gait score at flock level using behavioral and performance data
Xiao Yang, China Agriculture University, China
LED Arrays to Reduce Poultry Piling
Daniel Morris, Michigan State University, United States
Mitigating heat stress in broiler houses using energy balance analysis
Se-yeon Lee, Chonnam National University, Republic of Korea
SESSION 10 – PLF IMPLEMENTATION & ACCEPTANCE
Sala rossa
Chairman: Enrica Santolini
Application and Development of Precision Livestock Farming Technologies to Improve Transparency in Pig Husbandry – A Systematic Literature Review Using PRISMA
Anoma Gunarathne, Thünen Institute of Agricultural Technology, Germany
Precision Livestock Farming technologies in the U.S. swine industry: understanding farmer intention to adopt, their actual adoption practices and veterinarian recommendations to adopt
Babatope Akinyemi, Michigan State University, United States
United States public’s attitudinal acceptance of precision livestock farming tech-nologies in the swine industry
Babatope Akinyemi, Michigan State University, United States
Survey results of swine production across the globe
Shiva Paudel, University of Nebraska, United States
Unlocking the Potential of Precision Livestock Farming Data: A Three-Step Approach for Interface Identification using the Example of the German Pig Value Chain
Hauke Precht, Universität Oldenburg, Germany