Aminikhanghahi Samaneh, Cook Diane J
School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA.
Pervasive Mob Comput. 2019 Feb;53:75-89. doi: 10.1016/j.pmcj.2019.01.004. Epub 2019 Jan 16.
Segmenting behavior-based sensor data and recognizing the activity that the data represents are vital steps in all applications of human activity learning such as health monitoring, security, and intervention. In this paper, we enhance activity recognition by identifying activity borders. To accomplish this goal, we introduce a change point detection-based activity segmentation model which segments behavior-driven sensor data in real time, which in turn increases the performance of activity recognition. We evaluate our proposed method on data collected from 29 smart homes. Results of this analysis indicate that the method not only provides useful information about their activity boundaries and transitions between activities but also increase the average accuracy of recognizing individuals' activities while they are performing their daily routines more than 1%.
对基于行为的传感器数据进行分割并识别数据所代表的活动，是人类活动学习的所有应用（如健康监测、安全和干预）中的关键步骤。在本文中，我们通过识别活动边界来增强活动识别。为实现这一目标，我们引入了一种基于变化点检测的活动分割模型，该模型可实时分割行为驱动的传感器数据，进而提高活动识别的性能。我们在从29个智能家居收集的数据上评估了我们提出的方法。该分析结果表明，该方法不仅提供了有关其活动边界和活动之间转换的有用信息，而且在个体进行日常活动时，将活动识别的平均准确率提高了1%以上。
