arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1811.08006cs.HCcs.LG
收藏

基于细微放大和深度学习的节能无创热舒适感知

Non-invasive thermal comfort perception based on subtleness magnification and deep learning for energy efficiency

Nanjing University of Posts and Telecommunications(南京邮电大学);Xi’an University of Architecture and Technology(西安建筑科技大学);Umeå University(于默奥大学);Royal Institute of Technology (KTH)(瑞典皇家理工学院(KTH));Swiss Federal Institute of Technology (ETH)(瑞士联邦理工学院(ETH))

Xiaogang Cheng, Bin Yang, Anders Hedman, Thomas Olofsson, Haibo Li, Luc Van Gool

摘要:

人体热舒适测量是建筑节能的重要反馈指标。为了实现舒适、节能的建筑环境,设计了一种基于细微放大和深度学习(NIDL)的非侵入式测量方法。该方法依赖于皮肤特征数据,细微的运动和纹理变化,以及用于构建皮肤特征与皮肤温度之间关系的315层深层神经网络。进行了生理实验,以收集特征数据(144万)和算法验证。基于部分个性化饱和温度模型(NIPST)的非侵入式测量算法用于算法性能比较。结果表明,NIDL的平均误差和中位误差分别为0.4834摄氏度和0.3464摄氏度,相当于精度分别提高了16.28%和4.28%。

英文摘要:

Human thermal comfort measurement plays a critical role in giving feedback signals for building energy efficiency. A non-invasive measuring method based on subtleness magnification and deep learning (NIDL) was designed to achieve a comfortable, energy efficient built environment. The method relies on skin feature data, e.g., subtle motion and texture variation, and a 315-layer deep neural network for constructing the relationship between skin features and skin temperature. A physiological experiment was conducted for collecting feature data (1.44 million) and algorithm validation. The non-invasive measurement algorithm based on a partly-personalized saturation temperature model (NIPST) was used for algorithm performance comparisons. The results show that the mean error and median error of the NIDL are 0.4834 Celsius and 0.3464 Celsius which is equivalent to accuracy improvements of 16.28% and 4.28%, respectively.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑