Real-Time Data from IoT Devices and Their Influence on Decision Making

随着物联网(IoT)的广泛扩展和普及，收集我们的个人数据并监控我们的一举一动的设备现在正在产生海量的信息。目前的预测显示，到2020年，物联网互联设备将达到260亿到750亿台，到2022年，物联网智能家居市场的规模预计将达到1217.3亿美元，预计到2019年，高达69%的北美人将至少购买一台家用或可穿戴的物联网设备。然而，这些技术产生的所有数据仍然孤立在制造商的云服务中，需要处理专有算法，为用户提供有意义和可操作的知识的努力有限。由于数据和信息过载的用处有限，用户正在停止使用物联网和可穿戴技术。*在本研究计划中，我们旨在通过以下方式推进物联网和可穿戴技术领域的人因工程知识：(1)探索不同类型的用户(新手/专家、年轻人/老年人、用户/超级用户)如何处理和整合这些数据，对互联技术的信任的影响，这些数据如何影响决策(DM)，以及信息过载的影响；(2)创建数据集成框架和数据可视化以生成这些数据的有意义的使用；以及(3)创建完全集成到智能家居中的封装和新的无处不在的传感器，以减少数据收集的障碍。*将使用混合方法来探索不同类型的用户如何管理信息过载，并将来自物联网设备的数据集成到可操作的知识中。现场观察与访谈相结合，将为不同类型的用户如何处理其家庭环境中的超载提供洞察力，为新技术的设计提供重要的背景信息。实验室对照研究将被用来展示数据对数据挖掘和对技术的信任的影响。数据集成框架、可视化和新封装将使用成熟的人因工程方法生成和测试，复制经验丰富的用户使用的认知过程，为日常用户提供相同级别的可操作信息。*本研究计划将为物联网技术用户、研究人员和创新者提供：(1)关于物联网和可穿戴数据对DM的影响、对该技术的信任和信息过载的高级知识；以及(2)处理信息过载的资源(数据集成框架、数据可视化和改进的传感器)，以提供可操作和有用的信息，提高对情况的感知，并改善对该技术的信任。该研究计划中产生的知识将造福于物联网和可穿戴传感器技术的日常使用、军事、紧急服务、交通和医疗应用。

With the wide expansion and uptake of Internet of Things (IoT), devices collecting our personal data and monitoring our every single move are now generating huge amounts of information. Current forecasts indicate between 26 and 75 billion IoT connected devices by 2020, with the IoT smart home market estimated to be at US$ 121.73 billion by 2022, and as much as 69% of North Americans expected to buy at least one in-home or wearable IoT device by 2019. However, all the data generated by these technologies are still siloed within manufacturers' cloud services and require proprietary algorithms to be processed, with limited effort towards providing users with meaningful and actionable knowledge. Users are discontinuing the use of IoT and wearable technology due to limited usefulness of the data and information overload. ***In this research program, we aim to advance knowledge of Human Factors Engineering in the area of IoT and wearable technology by: (1) exploring how different types of users (novice/experts, young/elderly, users/super users) have been processing and integrating this data, the impact of trust in the connected technology, how this data influences decision making (DM), and the effects of information overload; (2) creating data integration frameworks and data visualizations to generate meaningful use for this data, and (3) creating encapsulations and new ubiquitous sensors fully integrated into a smart homes to reduce barriers towards data collection.***A mixed-methods approach will be used to explore how different types of users manage the information overload and integrate the data from IoT devices into actionable knowledge. In-situ observations combined with interviews will provide insights on how different types of users handle the overload in their home settings, providing important contextual information for the design of new technology. In-lab controlled studies will be used to demonstrate the impact of data on DM and trust in the technology. Data integration frameworks, visualizations, and new encapsulations will be generated and tested using well established Human Factors Engineering methodologies, replicating cognitive processes used by experienced users to provide everyday users with the same level of actionable information. ***This research program will provide IoT technology users, researchers, and innovators with: (1) advanced knowledge of the impact of IoT and wearable data on DM, trust in the technology, and information overload; and (2) resources to deal with information overload (data integration frameworks, data visualizations, and improved sensors) to provide actionable and useful information, increase situation awareness, and improve trust in the technology. The knowledge generated in this research program will benefit everyday use, military, emergency services, transportation, and healthcare applications of IoT and wearable sensory technology.