Multifractal characterization and recognition of animal behavior based on deep wavelet transform

Abstract

The study conduct an in-depth exploration of the multifractal characteristics of dairy cows behavioral data, aiming to reveal their complexity and representation in behavioral patterns. By means of Multifractal Detrended Fluctuation Analysis (MFDFA) in conjunction with deep wavelet transform, we extract multifractal indices that precisely depict the differences and dynamic changes of cows behavior. Further, we delves into the potential correlations between these multifractal features and the physiological states of dairy cattle, particularly focusing on their potential applications in predicting different physiological conditions. And an assessment model is developed based on these fractal indices and utilize advanced machine learning techniques to evaluate their effectiveness and accuracy in predicting the physiological states of dairy cattle. This study not only unveils the multifractal properties of cattle behavior but also demonstrates how these features can be utilized to predict significant physiological states, providing new scientific bases and methods for dairy cattle health management.