Context-Aware Operator Functional State Models for Smart Urban Security Applications

随着城市的不断扩张，对智能城市安全的需求也越来越大，以确保公民和公共资产的安全和保护。尽管部署在整个城市的传感器和系统可以促进事件和紧急处理的协调，但技术进步仍然受到操作员认知能力的限制。在智慧城市控制中心，操作员经常面临信息过载、多任务处理、中断和疲劳等认知挑战，所有这些都会延伸认知能力，损害任务效率。此外，现场公共安全官员面临着类似的压力，这可能会增加在往往危及生命的情况下出错的机会。在这两种情况下，对操作员功能状态(OFS)的动态实时监控可以潜在地防止此类错误的发生，通过评估任务所需的心理生理资源的可用性来增强性能。为此，泰利斯加拿大研究和技术公司开发了一种名为传感器中心的网络，它集成了多个传感器，为多维OFS建模提供实时的情境、行为和生理监控。典型的维度包括疲劳、压力、脑力劳动、体力活动和视野狭窄。要将传感器-集线器从实验室过渡到现场，首先必须解决三个关键问题：1)机动性：虽然受控实验室研究要求操作员进行最小限度的移动，以避免污染传感器，但必须考虑真实世界的操作员移动；2)突破性：通过一台设备测量多个医疗设备的能力将减少当前使用的许多传感器(多达7个)，并提高现场可接受性；以及3)在真实使用案例中进行验证。拟议的项目将解决这些问题，并将以申请者在认知科学和生物医学信号处理方面的跨学科专业知识为基础，从而有助于开发具有背景感知能力的创新OFS模式。*

With ever-expanding cities comes an increased need for smart urban security to ensure the safety and protection of citizens and public assets. While sensors and systems deployed across a city can facilitate the co-ordination of incident and emergency handling, technological advances are still limited by the cognitive capacities of the human operator. At smart city control centres, operators are often faced with cognitive challenges such as information overload, multitasking, interruptions, and fatigue, all of which will stretch cognitive capabilities and compromise task efficiency. Furthermore, in-the-field public safety officials are exposed to similar stressors which can increase the chance of error in often life-threatening situations. In both cases, ambulant real-time monitoring of operator functional state (OFS) can potentially prevent the occurrence of such errors, augmenting performance by assessing the availability of psychophysiological resources required by the task. To this end, Thales Research and Technology Canada has developed a nexus called Sensor-Hub, which integrates multiple sensors to provide real-time situational, behavioural and physiological monitoring for multi-dimensional OFS modelling. Typical dimensions include fatigue, stress, mental workload, physical activity, and tunnel vision. To bridge the Sensor-Hub transition from the laboratory to the field, three critical issues must first be addressed: 1) Mobility: While controlled lab research requires operators to make minimal movements to avoid contaminating sensors, real-world operator movements must be taken into account; 2) Obtrusiveness: The capability to measure multiple modalities through a single device will reduce the many sensors currently used (up to 7), and improve in-the-field acceptability; and 3) Validation within a real-world use case. The proposed project will address these issues and will build on the interdisciplinary expertise of the applicants on cognitive science and biomedical signal processing, thus contributing to the development of innovative context-aware OFS models. ****************************