FUME: Fused Unified Multi-Gas Emission Network for Livestock Rumen Acidosis Detection

2026-01-13

AI Summary

This study addresses the limitations of conventional ruminal acidosis diagnosis, which relies on invasive pH measurements and lacks scalability for continuous monitoring. To overcome this, the authors propose a novel deep learning approach based on infrared optical gas imaging (OGI) of dual gases—carbon dioxide (CO₂) and methane (CH₄). They construct the first pixel-level annotated dual-gas OGI dataset and design a lightweight dual-stream network featuring a shared-weight encoder, modality-specific self-attention, and channel attention-based fusion. The model simultaneously achieves gas plume segmentation and classification of dairy cow rumen health status into healthy, transitional, or acidotic states. With only 1.28 million parameters and 1.97 G MACs, it attains a mean Intersection-over-Union (mIoU) of 80.99% and a classification accuracy of 98.82%, reducing computational cost by an order of magnitude while outperforming existing methods.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Ruminal acidosis is a prevalent metabolic disorder in dairy cattle causing significant economic losses and animal welfare concerns. Current diagnostic methods rely on invasive pH measurement, limiting scalability for continuous monitoring. We present FUME (Fused Unified Multi-gas Emission Network), the first deep learning approach for rumen acidosis detection from dual-gas optical imaging under in vitro conditions. Our method leverages complementary carbon dioxide (CO2) and methane (CH4) emission patterns captured by infrared cameras to classify rumen health into Healthy, Transitional, and Acidotic states. FUME employs a lightweight dual-stream architecture with weight-shared encoders, modality-specific self-attention, and channel attention fusion, jointly optimizing gas plume segmentation and classification of dairy cattle health. We introduce the first dual-gas OGI dataset comprising 8,967 annotated frames across six pH levels with pixel-level segmentation masks. Experiments demonstrate that FUME achieves 80.99% mIoU and 98.82% classification accuracy while using only 1.28M parameters and 1.97G MACs--outperforming state-of-the-art methods in segmentation quality with 10x lower computational cost. Ablation studies reveal that CO2 provides the primary discriminative signal and dual-task learning is essential for optimal performance. Our work establishes the feasibility of gas emission-based livestock health monitoring, paving the way for practical, in vitro acidosis detection systems. Codes are available at https://github.com/taminulislam/fume.

Problem

• ruminal acidosis
• livestock health monitoring
• non-invasive diagnosis
• gas emission
• dairy cattle

Innovation

• dual-gas optical imaging
• lightweight dual-stream architecture
• joint segmentation and classification
• rumen acidosis detection
• infrared gas emission