eCommons

 

Deep Learning in Chicken Motion Detection and a Pilot Study of its Implementation in Chicken Behavior Analysis with a Vitamin D Enriched Diet

dc.contributor.authorLi, Zhengfei
dc.date.accessioned2023-05-26T13:37:15Z
dc.date.available2023-05-26T13:37:15Z
dc.date.issued2022
dc.description.abstractAnimal behavior and animal welfare are both essential components of animal science. Traditional animal behavior experiments rely on manual observation of data collection and data analysis. Although these methods have evolved rapidly with the help of modern data analysis and statistical computing, the foundation still relies on manual collection. In this experiment, all chicken behavioral data were recorded using video and then modeled using the computer program YOLOv7 in Python®( Van Rossum, G., & Drake Jr, F. L. (1995). Python reference manual. Centrum voor Wiskunde en Informatica Amsterdam.). The artificial intelligence can distinguish the different behaviors of the chicks: eating, drinking, exercising, and resting. At the same time, the computer model is tracking the trajectory of each chick, technically instantaneous speed. Combining the behavioral and velocity data, a more accurate analysis of chick behavior can be derived. The pilot study of twelve chickens in two groups shows that the group with a vitamin D-enriched diet spent a higher percentage of their time eating, drinking, and moving around. The computer deep learning algorithm showed promising implantation by recognizing the behavior and calculating the time spent on each pose.
dc.identifier.urihttps://hdl.handle.net/1813/113229
dc.language.isoen
dc.rightsAttribution 4.0 International*
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/*
dc.titleDeep Learning in Chicken Motion Detection and a Pilot Study of its Implementation in Chicken Behavior Analysis with a Vitamin D Enriched Dieten_US
dc.typedissertation or thesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Li_Zhengfei_Project.docx
Size:
1.69 MB
Format:
Microsoft Word