On-Board Feature Extraction from Acceleration Data for Activity Recognition
On-Board Feature Extraction from Acceleration Data for Activity Recognition
复制标题
从加速度数据中提取板载特征以进行活动识别
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
I. Craddock
中科院分区：
文献类型：
--
作者：
Atis Elsts;Ryan McConville;Xenofon Fafoutis;N. Twomey;R. Piechocki;Raúl Santos;I. Craddock
现代可穿戴设备配备了越来越强大的微控制器，因此越来越有能力进行计算繁重的操作，例如从传感器数据中提取特征。本文量化了在加速数据上计算特征所需的时间和精力成本，减少了后续的通信负载，以及在分类精度方面对日常活动识别的影响。结果表明，基于现代32位ARM Cortex-M微控制器的平台明显受益于板载时域特征提取。另一方面，从频域特征的计算中获得的效率提高目前在很大程度上仍然是遥不可及的。
Modern wearable devices are equipped with increasingly powerful microcontrollers and therefore are increasingly capable of doing computationally heavy operations, such as feature extraction from sensor data. This paper quantifies the time and energy costs required for on-board computation of features on acceleration data, the reduction achieved in subsequent communication load, and the impact on daily activity recognition in terms of classification accuracy. The results show that platforms based on modern 32-bit ARM Cortex-M microcontrollers significantly benefit from on-board extraction of time-domain features. On the other hand, efficiency gains from computation of frequency domain features at the moment largely remain out of their reach.