A Deep Learning Approach for Recognizing Activity of Daily Living (ADL) for Senior Care: Exploiting Interaction Dependency and Temporal Patterns
A Deep Learning Approach for Recognizing Activity of Daily Living (ADL) for Senior Care: Exploiting Interaction Dependency and Temporal Patterns
复制标题
DOI：
10.25300/misq/2021/15574
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Hongyi Zhu;Sagar Samtani;Randall A. Brown;Hsinchun Chen
中科院分区：
文献类型：
--
作者：
Hongyi Zhu;Sagar Samtani;Randall A. Brown;Hsinchun Chen
确保独居老年人的健康和安全是一个日益受到社会关注的问题。日常生活活动（ADL）方法是监测疾病进展以及这些个体自我照顾能力的常用手段。然而，现有的基于传感器的ADL监测系统主要依赖可穿戴运动传感器，获取的信息不足以进行准确的ADL识别，并且无法从不同粒度全面理解ADL。当前的医疗保健信息系统（IS）和移动分析研究侧重于研究系统、设备和所提供的服务，需要一种端到端的解决方案，以便基于移动传感器数据全面识别ADL。本研究采用设计科学范式，并运用先进的深度学习算法，开发了一种新颖的分层、多阶段ADL识别框架，以对不同粒度的ADL进行建模。我们为卷积神经网络提出了一种新颖的二维交互核，以利用人与物体运动传感器之间的交互。我们在两个包含不同粒度ADL的真实运动传感器数据集（Opportunity和INTER）上，根据最先进的基准（例如支持向量机、DeepConvLSTM、隐马尔可夫模型以及基于主题建模的ADLR）严格评估了每个提出的模块和整个框架。结果和一个案例研究表明，我们的框架能够更准确地识别不同层次的ADL。我们讨论了利益相关者如何能从我们提出的框架中进一步获益。除了展示实际用途外，我们还讨论了对信息系统知识库的贡献，以便用于未来基于设计科学的网络安全、医疗保健和移动分析应用。
Ensuring the health and safety of senior citizens who live alone is a growing societal concern. The Activity of Daily Living (ADL) approach is a common means to monitor disease progression and the ability of these individuals to care for themselves. However, the prevailing sensor-based ADL monitoring systems primarily rely on wearable motion sensors, capture insufficient information for accurate ADL recognition, and do not provide a comprehensive understanding of ADLs at different granularities. Current healthcare IS and mobile analytics research focuses on studying the system, device, and provided services, and is in need of an end-to-end solution to comprehensively recognize ADLs based on mobile sensor data. This study adopts the design science paradigm and employs advanced deep learning algorithms to develop a novel hierarchical, multiphase ADL recognition framework to model ADLs at different granularities. We propose a novel 2D interaction kernel for convolutional neural networks to leverage interactions between human and object motion sensors. We rigorously evaluate each proposed module and the entire framework against state-of-the-art benchmarks (e.g., support vector machines, DeepConvLSTM, hidden Markov models, and topic-modeling-based ADLR) on two real-life motion sensor datasets that consist of ADLs at varying granularities: Opportunity and INTER. Results and a case study demonstrate that our framework can recognize ADLs at different levels more accurately. We discuss how stakeholders can further benefit from our proposed framework. Beyond demonstrating practical utility, we discuss contributions to the IS knowledge base for future design science-based cybersecurity, healthcare, and mobile analytics applications.