arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2311.06968cs.LGcs.AIeess.SPstat.ML
收藏

面向真实传感系统的物理信息数据去噪

Physics-Informed Data Denoising for Real-Life Sensing Systems

University of California, San Diego(加利福尼亚大学圣迭戈分校);Qualcomm(高通公司);Amazon(亚马逊公司)
Xiyuan Zhang, Xiaohan Fu, Diyan Teng, Chengyu Dong, Keerthivasan Vijayakumar, Jiayun Zhang, Ranak Roy Chowdhury, Junsheng Han, Dezhi Hong, Rashmi Kulkarni, Jing… 展开作者

Xiyuan Zhang, Xiaohan Fu, Diyan Teng, Chengyu Dong, Keerthivasan Vijayakumar, Jiayun Zhang, Ranak Roy Chowdhury, Junsheng Han, Dezhi Hong, Rashmi Kulkarni, Jingbo Shang, Rajesh Gupta

AI总结:

本文提出一种物理信息去噪模型,利用传感器测量间的物理关系(如二阶微分方程)在无真实数据下实现去噪,在惯性导航、CO2监测和HVAC控制中达到最先进性能,并支持实时处理。

摘要:

在当今互联世界中,测量真实物理过程的传感器无处不在。这些传感器固有地带有噪声,常常对它们所支持的系统的性能和可靠性产生不利影响。经典的基于滤波的方法对传感测量的时间或频率特性引入了强假设,而基于学习的去噪方法通常依赖于使用真实干净数据来训练去噪模型,这在许多实际应用中往往难以获得或不可行。我们观察到,在许多场景中,不同传感器测量(例如位置和加速度)之间的关系由物理定律(例如二阶微分方程)解析地描述。通过结合这些物理约束,我们可以指导去噪过程,即使在缺乏真实数据的情况下也能改进。鉴于此,我们设计了一种物理信息去噪模型,利用由底层物理规律支配的不同测量之间固有的代数关系。通过消除对真实干净数据的需求,我们的方法为实际应用提供了一种实用的去噪解决方案。我们在多个领域进行了实验,包括惯性导航、CO2监测和HVAC控制,并与现有去噪方法相比取得了最先进的性能。我们的方法可以实时(1秒序列仅需4毫秒)对低成本噪声传感器进行数据去噪,并产生与高精度、高成本替代方案紧密对齐的结果,从而为更准确的基于传感器的系统提供了一种高效、经济的方法。

英文摘要:

Sensors measuring real-life physical processes are ubiquitous in today's interconnected world. These sensors inherently bear noise that often adversely affects performance and reliability of the systems they support. Classic filtering-based approaches introduce strong assumptions on the time or frequency characteristics of sensory measurements, while learning-based denoising approaches typically rely on using ground truth clean data to train a denoising model, which is often challenging or prohibitive to obtain for many real-world applications. We observe that in many scenarios, the relationships between different sensor measurements (e.g., location and acceleration) are analytically described by laws of physics (e.g., second-order differential equation). By incorporating such physics constraints, we can guide the denoising process to improve even in the absence of ground truth data. In light of this, we design a physics-informed denoising model that leverages the inherent algebraic relationships between different measurements governed by the underlying physics. By obviating the need for ground truth clean data, our method offers a practical denoising solution for real-world applications. We conducted experiments in various domains, including inertial navigation, CO2 monitoring, and HVAC control, and achieved state-of-the-art performance compared with existing denoising methods. Our method can denoise data in real time (4ms for a sequence of 1s) for low-cost noisy sensors and produces results that closely align with those from high-precision, high-cost alternatives, leading to an efficient, cost-effective approach for more accurate sensor-based systems.

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。

↑