Toward Optimal Sampling Rate Selection and Unbiased Classification for Precise Animal Activity Recognition
arXiv:2604.00517v1 Announce Type: new Abstract: 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 eac
View PDF
Abstract: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.
Comments: 26 pages, 14 figures
Subjects:
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
Cite as: arXiv:2604.00517 [cs.CV]
(or arXiv:2604.00517v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2604.00517
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Meilu Zhu [view email] [v1] Wed, 1 Apr 2026 06:02:58 UTC (1,397 KB)
Sign in to highlight and annotate this article
Conversation starters
Daily AI Digest
Get the top 5 AI stories delivered to your inbox every morning.
More about
announcefeaturestock
Brain-inspired chip could make some AI tasks up to 2,000 times more energy efficient
A new type of computer chip that uses the physics of materials to process information could make some artificial intelligence (AI) systems far more energy efficient, researchers have found. Loughborough University physicists have developed a device that can process data that changes over time directly in hardware, rather than relying on software running on conventional computers.
Knowledge Map
Connected Articles — Knowledge Graph
This article is connected to other articles through shared AI topics and tags.
More in Releases
Google Home’s latest update makes Gemini better at understanding your commands
Google is launching another update to its Home app, which is supposed to make controlling your smart home with its Gemini AI assistant "more natural and reliable," according to this week's release notes. With the update, you can describe the type of lighting you want, such as "the color of the ocean," and Gemini will [ ]
Dan Pratl believes the credibility economy is coming and it will redefine value in the age of AI
A growing sense of unease is shaping how professionals engage with artificial intelligence, particularly as its capabilities expand across information creation and execution. Dan Pratl, founder of Quadron, believes this anxiety reflects a deeper structural issue that extends beyond automation and into how value itself is recognized. “We’ve reached a point at which the maturation [ ] This story continues at The Next Web
Discussion
Sign in to join the discussion
No comments yet — be the first to share your thoughts!