Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Mao, Axiu, Zhu, Meilu, Shen, Lei, Wang, Xiaoshuai, Norton, Tomas, Liu, Kai
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2604.00517
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910093062176768
author Mao, Axiu
Zhu, Meilu
Shen, Lei
Wang, Xiaoshuai
Norton, Tomas
Liu, Kai
author_facet Mao, Axiu
Zhu, Meilu
Shen, Lei
Wang, Xiaoshuai
Norton, Tomas
Liu, Kai
contents With the rapid advancements in deep learning techniques, wearable sensor-aided animal activity recognition (AAR) has demonstrated promising performance, thereby improving livestock management efficiency as well as animal health and welfare monitoring. However, existing research often prioritizes overall performance, overlooking the fact that classification accuracies for specific animal behavioral categories may remain unsatisfactory. This issue typically stems from suboptimal sampling rates or class imbalance problems. To address these challenges and achieve high classification accuracy across all individual behaviors in farm animals, we propose a novel Individual-Behavior-Aware Network (IBA-Net). This network enhances the recognition of each specific behavior by simultaneously customizing features and calibrating the classifier. Specifically, considering that different behaviors require varying sampling rates to achieve optimal performance, we design a Mixture-of-Experts (MoE)-based Feature Customization (MFC) module. This module adaptively fuses data from multiple sampling rates, capturing customized features tailored to various animal behaviors. Additionally, to mitigate classifier bias toward majority classes caused by class imbalance, we develop a Neural Collapse-driven Classifier Calibration (NC3) module. This module introduces a fixed equiangular tight frame (ETF) classifier during the classification stage, maximizing the angles between pair-wise classifier vectors and thereby improving the classification performance for minority classes. To validate the effectiveness of IBA-Net, we conducted experiments on three public datasets covering goat, cattle, and horse activity recognition. The results demonstrate that our method consistently outperforms existing approaches across all datasets.
format Preprint
id arxiv_https___arxiv_org_abs_2604_00517
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Toward Optimal Sampling Rate Selection and Unbiased Classification for Precise Animal Activity Recognition
Mao, Axiu
Zhu, Meilu
Shen, Lei
Wang, Xiaoshuai
Norton, Tomas
Liu, Kai
Computer Vision and Pattern Recognition
Artificial Intelligence
With the rapid advancements in deep learning techniques, wearable sensor-aided animal activity recognition (AAR) has demonstrated promising performance, thereby improving livestock management efficiency as well as animal health and welfare monitoring. However, existing research often prioritizes overall performance, overlooking the fact that classification accuracies for specific animal behavioral categories may remain unsatisfactory. This issue typically stems from suboptimal sampling rates or class imbalance problems. To address these challenges and achieve high classification accuracy across all individual behaviors in farm animals, we propose a novel Individual-Behavior-Aware Network (IBA-Net). This network enhances the recognition of each specific behavior by simultaneously customizing features and calibrating the classifier. Specifically, considering that different behaviors require varying sampling rates to achieve optimal performance, we design a Mixture-of-Experts (MoE)-based Feature Customization (MFC) module. This module adaptively fuses data from multiple sampling rates, capturing customized features tailored to various animal behaviors. Additionally, to mitigate classifier bias toward majority classes caused by class imbalance, we develop a Neural Collapse-driven Classifier Calibration (NC3) module. This module introduces a fixed equiangular tight frame (ETF) classifier during the classification stage, maximizing the angles between pair-wise classifier vectors and thereby improving the classification performance for minority classes. To validate the effectiveness of IBA-Net, we conducted experiments on three public datasets covering goat, cattle, and horse activity recognition. The results demonstrate that our method consistently outperforms existing approaches across all datasets.
title Toward Optimal Sampling Rate Selection and Unbiased Classification for Precise Animal Activity Recognition
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2604.00517