用热成像自动识别呼吸模式，准确率达98.8%。
BreathAI: Transfer Learning-Based Thermal Imaging for Automated Breathing Pattern Recognition
- 基于自适应迁移学习与多阈值分割，提取呼吸特征
- 在热成像数据上实现98.8%的识别准确率
- 适合睡眠呼吸暂停等呼吸疾病智能监测
本研究提出一种自适应迁移学习与阈值结合的深度学习模型（ATL-TDLM），用于基于热成像的自动呼吸模式识别。不同于依赖声音数据的传统方法，该模型通过分层深度特征提取与自适应多阈值（AMT）提升特征分割效果。通过知识蒸馏微调（KD-FT）优化知识迁移，并引入对比表示学习（CRL）增强吸气（INH）与呼气（EXH）阶段的类间可分性。ATL-TDLM框架在测试中达到98.8%的准确率，显著优于现有模型，同时保持计算高效。该方法在呼吸系统疾病检测（如睡眠呼吸暂停、哮喘监测）中具有应用潜力。
原文摘要 · Abstract (English)
This study presents an Adaptive Transfer Learning and Thresholding-based Deep Learning Model (ATL-TDLM) for automated breathing pattern recognition using thermal imaging. Unlike conventional methods that rely on sound-based respiratory data, our approach leverages hierarchical deep feature extraction and adaptive multi-thresholding (AMT) to enhance feature segmentation. The model integrates knowledge distillation-based fine-tuning (KD-FT) to optimize learning transfer and contrastive representation learning (CRL) to improve inter-class separability between inhalation (INH) and exhalation (EXH) phases. The ATL-TDLM framework achieves an accuracy of 98.8%, significantly outperforming state-of-the-art models while ensuring computational efficiency. This approach has potential applications in respiratory disorder detection, including sleep apnea and asthma monitoring.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。