AHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge Devices
AHAR: Adaptive CNN for Energy-Efficient Human Activity Recognition in Low-Power Edge Devices
复制标题
DOI：
10.1109/jiot.2022.3140465
复制
发表时间：
2022-08-01
影响因子：
10.6
通讯作者：
Al Faruque, Mohammad Abdullah
中科院分区：
文献类型：
--
作者：
Rashid, Nafiul;Demirel, Berken Utku;Al Faruque, Mohammad Abdullah
人体活动识别（HAR）是健康监测的关键应用之一，需要持续使用可穿戴设备来跟踪日常活动。本文提出了一种适用于低功耗边缘器件的节能HAR （AHAR）自适应卷积神经网络。与传统的基于分类置信度做出提前退出决策的自适应（早期退出）体系结构不同，AHAR提出了一种新的自适应体系结构，它使用输出块预测器来选择基线体系结构的一部分以在推理阶段使用。实验结果表明，传统的自适应架构存在性能损失，而我们的自适应架构在节能的同时提供了与基准架构相似或更好的性能。我们验证了从两个数据集(1)Opportunity和2)w-HAR对运动活动进行分类的方法。与机遇号数据集的雾/云计算方法相比，我们的基线和自适应架构的F1加权得分分别为91.79%和91.57%。对于w-HAR数据集，我们的基线和自适应架构分别以97.55%和97.64%的权重F1得分优于最先进的作品。在真实硬件上的评估表明，与Opportunity数据集上的工作相比，我们的基线架构具有显著的能效（低422.38倍）和内存效率（低14.29倍）。对于w-HAR数据集，与最先进的工作相比，我们的基准架构需要的能量减少2.04倍，内存减少2.18倍。此外，实验结果表明，我们的自适应架构比我们的基线节能12.32% （Opportunity）和11.14% (w-HAR)，同时提供类似（Opportunity）或更好（w-HAR）的性能，没有显著的内存开销。
Human activity recognition (HAR) is one of the key applications of health monitoring that requires continuous use of wearable devices to track daily activities. This article proposes an adaptive convolutional neural network for energy-efficient HAR (AHAR) suitable for low-power edge devices. Unlike traditional adaptive (early-exit) architecture that makes the early-exit decision based on classification confidence, AHAR proposes a novel adaptive architecture that uses an output block predictor to select a portion of the baseline architecture to use during the inference phase. The experimental results show that traditional adaptive architecture suffer from performance loss whereas our adaptive architecture provides similar or better performance as the baseline one while being energy efficient. We validate our methodology in classifying locomotion activities from two data sets-1) Opportunity and 2) w-HAR. Compared to the fog/cloud computing approaches for the Opportunity data set, our baseline and adaptive architectures show a comparable weighted F1 score of 91.79%, and 91.57%, respectively. For the w-HAR data set, our baseline and adaptive architectures outperform the state-of-the-art works with a weighted F1 score of 97.55%, and 97.64%, respectively. Evaluation on real hardware shows that our baseline architecture is significantly energy efficient ( 422.38x less) and memory-efficient ( 14.29x less) compared to the works on the Opportunity data set. For the w-HAR data set, our baseline architecture requires 2.04x less energy and 2.18x less memory compared to the state-of-the-art work. Moreover, experimental results show that our adaptive architecture is 12.32% (Opportunity) and 11.14% (w-HAR) energy efficient than our baseline while providing similar (Opportunity) or better (w-HAR) performance with no significant memory overhead.