Cognitive solutions to surveillance in security (CSSS)

安全监控认知解决方案 (CSSS)

• 批准号: 436704-2012
• 负责人: Tremblay, Sébastien
• 金额: $ 9.22万
• 依托单位: Université Laval
• 依托单位国家: 加拿大
• 项目类别: Collaborative Research and Development Grants
• 财政年份: 2015
• 资助国家: 加拿大
• 起止时间: 2015-01-01 至 2016-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=574352
• 关键词: Cognitive; solutions; surveillance; security; CSSS

Surveillance in public security and cyber-defence is essential to protecting the country's critical infrastructure and public places against the threat of terrorism, civil unrest, criminal activity, and cyber-attacks. Reliance on human operators to monitor multiple screens and sources of information in real-time has and will lead to undetected incidents, thus increasing the threat to local and national security. Despite advances in surveillance equipment, operators are still faced with many cognitive challenges (e.g., information overload, multitasking, background sound distraction, interruptions, and fatigue) which place stresses on the operator's cognitive system and reduce efficiency. Hence, the development of user-centered adaptive, intelligent systems becomes critical to ensure optimal surveillance work. In this project we adopt an interdisciplinary approach by combining system engineering with cognitive neuroscience to ensure a thorough, empirically-based characterisation of the problem space and then test innovative solutions to improve security and cyber-defence surveillance work. Using well-established cognitive paradigms we seek to establish weak functional points and thus identify areas that need support. To do so, we will create controlled experiments using multi-screen surveillance immersive environments of dynamically evolving crowd scenes or cyber-intrusions alerts, which provide an optimal compromise between external realism and empirical control. The initial empirical work will help develop a set of criteria that will provide sensitive diagnostic metrics with which to assess the ability of different systems to support performance, which in turn will be used to develop and test prototypes of decision support systems and innovative training procedures.

公共安全和网络防御监控对于保护国家的关键基础设施和公共场所免受恐怖主义、内乱、犯罪活动和网络攻击的威胁至关重要。依赖人工操作员实时监控多个屏幕和信息来源已经并将导致未被发现的事件，从而增加了对地方和国家安全的威胁。尽管监控设备取得了进步，但操作员仍然面临着许多认知挑战（例如，信息过载、多任务处理、背景声音干扰、中断和疲劳），这些挑战给操作员的认知系统带来了压力，降低了效率。因此，开发以用户为中心的自适应智能系统对于确保最佳监控工作至关重要。在这个项目中，我们采用跨学科的方法，将系统工程与认知神经科学相结合，以确保对问题空间进行彻底的、基于经验的表征，然后测试创新的解决方案，以改善安全和网络防御监视工作。使用公认的认知范式，我们试图建立薄弱的功能点，从而确定需要支持的领域。为此，我们将使用动态发展的人群场景或网络入侵警报的多屏幕监视沉浸式环境创建对照实验，这在外部现实主义和经验控制之间提供了最佳折衷。最初的实证工作将有助于制定一套标准，这些标准将提供敏感的诊断指标，用以评估不同系统支持绩效的能力，而这些指标又将用于开发和测试决策支持系统和创新培训程序的原型。