EAGER: Smart and Connected Communities: Engineering Networked Devices for Multiteam Learning and Performance

该研究项目将通过创新的社会技术系统的重新设计，将跨学科的专业知识应用于多团队行为和学习研究，以潜在地改变智能，互联社区中多团队系统的研究。多团队系统存在于医疗保健、军事、灾难响应、应急响应环境等许多领域，可以包括人员、设备、信息的转移以及跨团队交互的协调。一个这样的例子是紧急响应团队将患者运送并移交给医院急诊科创伤团队，然而，多团队行为跟踪系统以及为智能，互联社区设计和开发它们的过程也适用于其他基于团队的环境。跨多个团队的学习和协调，以准备应对紧急情况或危机，对于防止错误和保护公民健康和安全至关重要。这项研究建立在概念验证的基础上，基于移动的行为感知系统在真实的世界条件下进行测试，通过建立和建模有意义的协议，将多个团队的学习，行为和表现联系起来，以改善基于传感器的测量，实时数据分析和智能连接社区及其公民的福祉。这项研究将为多团队行为，过渡点和参与者的学习提供前所未有的洞察力。建模和测量有意义的基于团队的互动和活动的过程将被解决，以确定衡量多团队绩效的重要指标。研究人员将研究和利用移动的行为传感技术，并利用社会技术分析连接到实时可视化技术，以帮助多团队学习。这项研究将学习科学，行为科学，工程，数据分析和人为因素的跨学科观点联系起来，以迭代地完善和测试一个系统，该系统有可能为多团队培训环境转换反馈和可操作的洞察力。

This research project will apply interdisciplinary expertise to multiteam behavioral and learning research through the re-engineering of an innovative sociotechnical system to potentially transform research on multiteam systems in smart, connected communities. Multiteam systems are found in healthcare, military, disaster response, emergency response contexts,and many others, and can include the transfer of people, equipment, information, and coordination of cross-team interaction. One such example is the emergency response team transporting and handing over a patient to a hospital emergency department trauma team, however, multiteam behavioral tracking systems and the process of designing and developing them for smart, connected communities are applicable to other team-based contexts. Learning and coordination across multiple teams to prepare for an emergency or crisis response is crucial to prevent mistakes and to protect citizen health and safety. This research builds upon a proof of concept, mobile-based behavioral sensing system tested in real world conditions to connect learning, behavior and performance among multiple teams in a high fidelity simulation through establishing and modeling meaningful protocols toward improved sensor-based measurement, real-time data analysis and actionable insights for smart connected communities and the well-being of their citizens. This research will provide an unprecedented level of insight into multiteam behavior, transition points, and learning by participants. Processes to model and measure meaningful team-based interaction and activity will be addressed to identify metrics that matter in gauging multi-team performance. The researchers will study and leverage mobile behavioral sensing techniques and utilize sociotechnical analysis connected to real-time visualization techniques to aid multi-team learning. This research will link interdisciplinary perspectives in the learning sciences, behavioral sciences, engineering, data analytics and human factors to iteratively refine and test a system with potential to transform feedback and actionable insight for multiteam training contexts.