Suppr超能文献

用于医疗保健中个性化温度控制的智能热致变色加热电子织物。

Intelligent Thermochromic Heating E-Textile for Personalized Temperature Control in Healthcare.

作者信息

Lee Ching, Tan Jeanne, Tan Jun Jong, Tang Hiu Ting, Yu Wing Shan, Lam Ngan Yi Kitty

机构信息

School of Fashion and Textiles, The Hong Kong Polytechnic University, Hung Hom, Hong Kong Special Administrative Region.

Laboratory for Artificial Intelligence in Design, Hong Kong Science Park, New Territories, Hong Kong Special Administrative Region.

出版信息

ACS Appl Mater Interfaces. 2025 Jan 22;17(3):5515-5526. doi: 10.1021/acsami.4c19174. Epub 2025 Jan 8.

Abstract

Heating electronic textiles (e-textiles) are widely used for thermal comfort and energy conservation, but prolonged heating raises concerns about heat-related illnesses, especially in the elderly. Despite advancements, achieving universal user satisfaction remains difficult due to diverse thermal needs. This paper introduces an intelligent thermochromic heating e-textile with an artificial intelligence (AI)-based temperature control system for optimized personal comfort and color indicators for elderly caregivers. The fabric integrates conductive yarn, temperature-induced discoloration yarn (TIDY), and polymeric optical fiber (POF) to visualize temperature changes, ensuring efficiency and comfort. Equipped with microcontrollers, ambient sensors, and Bluetooth connectivity, the system offers comprehensive intelligent heating solutions. An AI model, trained on data from 50 wearability test subjects, determines optimal heating temperatures (40-50 °C) with 5.083 mean squared error (MSE), showing a high correlation between predicted and actual comfort levels. This concept enhances thermal comfort and mitigates overheating risks, promising for wearable healthcare applications.

摘要

加热电子织物(电子纺织品)被广泛用于提供热舒适性和节能,但长时间加热引发了对与热相关疾病的担忧,尤其是在老年人中。尽管取得了进展,但由于不同的热需求,实现普遍的用户满意度仍然很困难。本文介绍了一种智能热致变色加热电子织物,它具有基于人工智能(AI)的温度控制系统,用于优化个人舒适度,并为老年护理人员提供颜色指示。该织物集成了导电纱、温度致变色纱(TIDY)和聚合物光纤(POF)以可视化温度变化,确保效率和舒适度。该系统配备了微控制器、环境传感器和蓝牙连接,提供全面的智能加热解决方案。一个基于50名可穿戴测试对象的数据训练的AI模型,以5.083的均方误差(MSE)确定最佳加热温度(40-50°C),显示出预测舒适度与实际舒适度之间的高度相关性。这一概念提高了热舒适性并降低了过热风险,有望用于可穿戴医疗保健应用。

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验