arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2402.09264cs.LGcs.HC
收藏

UR2M:微控制器上的不确定性与资源感知事件检测

UR2M: Uncertainty and Resource-Aware Event Detection on Microcontrollers

University of Cambridge(剑桥大学);Singapore Management University(新加坡管理大学);Cardiff University(卡迪夫大学);Nokia Bell Labs(诺基亚贝尔实验室);University of Colorado Boulder(科罗拉多大学博尔德分校)

Hong Jia, Young D. Kwon, Dong Ma, Nhat Pham, Lorena Qendro, Tam Vu, Cecilia Mascolo

AI总结:

UR2M提出了一种面向微控制器的不确定性与资源感知事件检测框架,通过证据理论、级联早期退出和部署优化,实现了更快的推理、节能和内存节省,并提升了不确定性量化性能。

摘要:

传统机器学习技术在训练和测试阶段数据分布发生变化时,容易产生不准确的预测。这种脆弱性可能导致严重后果,尤其是在移动医疗等应用中。不确定性估计有可能通过评估模型输出的可靠性来缓解这一问题。然而,现有的不确定性估计技术通常需要大量的计算资源和内存,使其在微控制器(MCU)上难以实现。这一局限性阻碍了许多重要的设备端可穿戴事件检测(WED)应用(如心脏病发作检测)的可行性。\n在本文中,我们提出了UR2M,一种用于MCU的新型不确定性与资源感知事件检测框架。具体来说,我们(i)基于证据理论开发了一种不确定性感知的WED,用于准确的事件检测和可靠的不确定性估计;(ii)引入了一个级联机器学习框架,通过在不同事件模型之间共享较浅的模型层,实现早期退出的高效模型推理;(iii)优化了模型和MCU库的部署以提高系统效率。我们进行了大量实验,并使用三个可穿戴数据集将UR2M与传统不确定性基线进行了比较。我们的结果表明,UR2M在两种流行的MCU上实现了高达864%的推理速度提升、857%的不确定性估计节能、55%的内存节省,以及22%的不确定性量化性能改进。\nUR2M可以部署在广泛的MCU上,显著扩展了实时和可靠的WED应用。

英文摘要:

Traditional machine learning techniques are prone to generating inaccurate predictions when confronted with shifts in the distribution of data between the training and testing phases. This vulnerability can lead to severe consequences, especially in applications such as mobile healthcare. Uncertainty estimation has the potential to mitigate this issue by assessing the reliability of a model's output. However, existing uncertainty estimation techniques often require substantial computational resources and memory, making them impractical for implementation on microcontrollers (MCUs). This limitation hinders the feasibility of many important on-device wearable event detection (WED) applications, such as heart attack detection. In this paper, we present UR2M, a novel Uncertainty and Resource-aware event detection framework for MCUs. Specifically, we (i) develop an uncertainty-aware WED based on evidential theory for accurate event detection and reliable uncertainty estimation; (ii) introduce a cascade ML framework to achieve efficient model inference via early exits, by sharing shallower model layers among different event models; (iii) optimize the deployment of the model and MCU library for system efficiency. We conducted extensive experiments and compared UR2M to traditional uncertainty baselines using three wearable datasets. Our results demonstrate that UR2M achieves up to 864% faster inference speed, 857% energy-saving for uncertainty estimation, 55% memory saving on two popular MCUs, and a 22% improvement in uncertainty quantification performance. UR2M can be deployed on a wide range of MCUs, significantly expanding real-time and reliable WED applications.

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。

↑