Haipeng Yu

Impact of trait measurement error on quantitative genetic analysis of computer vision derived traits

This study investigates the impact of trait measurement error on quantitative genetic analysis of pig body weight, finding no genetic influence on the error and equivalent heritability between scale-based and image-based measurements.

End-to-end genomic prediction: direct prediction of images and text from genome-wide molecular markers

This paper introduces end-to-end genomic prediction to directly predict images and text from genetic markers, showing comparable accuracy to traditional numeric phenotype-based methods.

Impact of cross-validation designs on cattle behavior prediction using machine learning and deep learning models with tri-axial accelerometer data

Leave-cow-out validation lowered cattle behavior classification accuracy to 0.72 to 0.82, versus 0.9 to 0.96 under random hold-out splits that can place one animal's records in both sets.

AnimalMotionViz: an interactive software tool for tracking and visualizing animal motion patterns using computer vision

AnimalMotionViz tracks and visualizes dairy cattle movement patterns using computer vision to generate motion heatmaps and analyze space utilization.

Validation of the linear regression method to evaluate population accuracy and bias of predictions for non-linear models

This paper validates the linear regression method for assessing population bias and accuracy of predictions, showing it works for non-linear models when data are appropriately partitioned.

GCA: An R package for genetic connectedness analysis using pedigree and genomic data

The paper introduces the GCA R package for genetic connectedness analysis using pedigree and genomic data, providing tools to calculate connectedness statistics and assess data comparability.

Modeling multiple phenotypes in wheat using data-driven genomic exploratory factor analysis and Bayesian network learning

This study uses data-driven exploratory factor analysis and Bayesian networks to identify latent phenotypes and their genetic relationships in wheat, revealing how traits like yield and disease resistance are interrelated.

Deciphering cattle temperament measures derived from a four-platform standing scale using genetic factor analytic modeling

This study uses genetic factor analytic modeling to explore the genetic relationships among cattle temperament measures, validating an objective movement-based method as an alternative to subjective scoring.

Examining the relationships between phenotypic plasticity and local environments with genomic structural equation models

The paper introduces a genomic structural equation model to examine relationships between phenotypic plasticity and local environments using Bayesian networks and mixed-effects SEM.

Genomic Bayesian confirmatory factor analysis and Bayesian network to characterize a wide spectrum of rice phenotypes

This paper uses Bayesian confirmatory factor analysis and Bayesian networks to analyze rice phenotypes and identify genetic correlations among traits.

Genomic Relatedness Strengthens Genetic Connectedness Across Management Units

This study evaluates how genomic information improves genetic connectedness across management units compared to pedigree-based methods using simulation and real data from mice and cattle.