首页|Investigators at University of Wisconsin Detail Findings in Machine Learning (Le veraging Computer Vision-based Pose Estimation Technique In Dairy Cows for Objec tive Mobility Analysis and Scoring System)
Investigators at University of Wisconsin Detail Findings in Machine Learning (Le veraging Computer Vision-based Pose Estimation Technique In Dairy Cows for Objec tive Mobility Analysis and Scoring System)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Machine Learn ing have been published. According to news reporting originating from Madison, W isconsin, by NewsRx correspondents, research stated, "This study investigated th e feasibility of utilizing a computer vision-based pose estimation technique for quantitative mobility analysis in dairy cows, specifically focusing on commonly used variables in visual mobility scoring. Additionally, the study determined t he potential of a machine learning classification algorithm to predict mobility scores based on data obtained from the aforementioned pose estimation technique. " Financial support for this research came from Grants-in-Aid for Scientific Resea rch (KAKENHI). Our news editors obtained a quote from the research from the University of Wisco nsin, "A dataset comprising 204 individual cows' video clips was collected, with each video clip recorded from a sideview perspective during walking. The cows were scored using a 4-level mobility scoring system: Score 0 (good mobility: 64 cows), Score 1 (imperfect mobility: 65 cows), Score 2 (impaired mobility: 57 cow s), and Score 3 (severely impaired mobility: 18 cows). The video clips were anal yzed using a software for cattle pose estimation, capable of detecting 25 keypoi nts and generating time-series XY-coordinates of those keypoints. Based on the d ata, a total of 17 mobility variables were calculated, such as head bob, stride length, stride duration, walking speed, back angle, and range of motion in leg j oints. The measurements of these variables closely align with previously reporte d and comparable data derived from precise sensing technologies (e.g., walkway p ressure mapping systems) and labor-intensive techniques (e.g., attaching markers to cows and manually annotating on sequential images). The relationships betwee n these measurements and the mobility scores were also consistent with the findi ngs reported before. To account for the limited number of cows classified as Sco re3, the cows classified as Score 2 and Score 3 were merged into a single class, and a classification model for the 3-level mobility score (Score 0, 1, and 2 + 3) was developed using a random forest algorithm. The model's performance was ev aluated using a repeated holdout data split method. In this process, the dataset was randomly divided into an 80 % training set and a 20 % test set, and this was replicated ten times to ensure a robust assessment of the model's predictive ability. The overall 3-class classification performance of t he model resulted in a weighted kappa coefficient of 0.69 and area under the cur ve of the receiver operating characteristic curve of 0.86."
MadisonWisconsinUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMachine LearningUniversi ty of Wisconsin
NETL
NSTL
