CIM: A Novel Clustering-based Energy-Efficient Data Imputation Method for Human Activity Recognition
CIM: A Novel Clustering-based Energy-Efficient Data Imputation Method for Human Activity Recognition
复制标题
DOI：
10.1145/3609111
复制
发表时间：
2023-10-01
影响因子：
2
通讯作者：
Bhat，Ganapati
中科院分区：
文献类型：
--
作者：
Hussein，Dina;Bhat，Ganapati
人体活动识别（HAR）是许多健康应用的重要组成部分，包括康复、帕金森病、日常活动监测和健身监测。最先进的HAR方法使用身体上的多个传感器来准确识别运行时的活动。这些方法通常假设来自所有传感器的数据可用于运行时活动识别。然而，由于故障、能量限制或传感器之间的通信问题，来自一个或多个传感器的数据可能不可用。数据缺失会导致准确性的显著降低，从而影响对用户的服务质量。处理丢失数据的常用方法是为丢失的每个传感器组合训练分类器或传感器数据恢复算法。然而，这在资源有限的可穿戴设备上导致了显著的内存和能量开销。与之前的方法形成鲜明对比的是，本文提出了一种基于聚类的方法（CIM）来在运行时输入缺失数据。我们首先为HAR中的每个传感器定义了一组可能的集群和代表性数据模式。然后，我们创建并存储跨传感器集群之间的映射。在运行时，当来自传感器的数据丢失时，我们利用存储的映射表来获得丢失传感器的最可能聚类。然后将识别的集群的代表性窗口用作输入来执行活动分类。我们还提供了一种方法，以获得估算感知的活动预测集，以处理数据在使用估算时的不确定性。在三个HAR数据集上的实验表明，当提供单个活动标签时，CIM在不丢失数据的情况下实现了10%的基线精度。使用假设感知分类，准确率差距降至1%以下。对低功耗处理器的测量表明，与最先进的生成方法相比，CIM实现了接近100%的节能。
Human activity recognition (HAR) is an important component in a number of health applications, including rehabilitation, Parkinson’s disease, daily activity monitoring, and fitness monitoring. State-of-the-art HAR approaches use multiple sensors on the body to accurately identify activities at runtime. These approaches typically assume that data from all sensors are available for runtime activity recognition. However, data from one or more sensors may be unavailable due to malfunction, energy constraints, or communication challenges between the sensors. Missing data can lead to significant degradation in the accuracy, thus affecting quality of service to users. A common approach for handling missing data is to train classifiers or sensor data recovery algorithms for each combination of missing sensors. However, this results in significant memory and energy overhead on resource-constrained wearable devices. In strong contrast to prior approaches, this paper presents a clustering-based approach (CIM) to impute missing data at runtime. We first define a set of possible clusters and representative data patterns for each sensor in HAR. Then, we create and store a mapping between clusters across sensors. At runtime, when data from a sensor are missing, we utilize the stored mapping table to obtain most likely cluster for the missing sensor. The representative window for the identified cluster is then used as imputation to perform activity classification. We also provide a method to obtain imputation-aware activity prediction sets to handle uncertainty in data when using imputation. Experiments on three HAR datasets show that CIM achieves accuracy within 10% of a baseline without missing data for one missing sensor when providing single activity labels. The accuracy gap drops to less than 1% with imputation-aware classification. Measurements on a low-power processor show that CIM achieves close to 100% energy savings compared to state-of-the-art generative approaches.