Search papers, labs, and topics across Lattice.
This paper introduces the Individual-Behavior-Aware Network (IBA-Net) to improve animal activity recognition (AAR) by addressing suboptimal sampling rates and class imbalance. IBA-Net uses a Mixture-of-Experts (MoE) based Feature Customization (MFC) module to adaptively fuse data from multiple sampling rates, and a Neural Collapse-driven Classifier Calibration (NC3) module to mitigate classifier bias. Experiments on goat, cattle, and horse activity datasets show IBA-Net outperforms existing AAR methods.
Achieve consistently high accuracy across all animal behaviors by adaptively customizing features and calibrating the classifier to overcome suboptimal sampling rates and class imbalance.
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.
