Carlson Logan, Navalta Dalton, Nicolescu Monica, Nicolescu Mircea, Woodward Gail
Department of Computer Science and Engineering, University of Nevada Reno, Reno, NV, United States.
NASA Jet Propulsion Laboratory, Pasadena, CA, United StAtes.
Front Artif Intell. 2021 Oct 7;4:702153. doi: 10.3389/frai.2021.702153. eCollection 2021.
The need for increased maritime security has prompted research focus on intent recognition solutions for the naval domain. We consider the problem of and propose our solution using multinomial hidden Markov models (HMMs). Our contribution stems from (instead of static values) for parameters relevant to the task, which enables the early classification of hostile behaviors, well before the behavior has been finalized. We discuss our implementation of a one-versus-all intent classifier using multinomial HMMs and present the performance of our system for three types of hostile behaviors (ram, herd, block) and a benign behavior.
对增强海上安全的需求促使研究聚焦于海军领域的意图识别解决方案。我们考虑了该问题，并使用多项式隐马尔可夫模型（HMM）提出了我们的解决方案。我们的贡献源于为与任务相关的参数使用了（而非静态值），这使得能够在敌对行为最终确定之前很早就对其进行分类。我们讨论了使用多项式HMM的一对多意图分类器的实现，并展示了我们的系统针对三种敌对行为（冲撞、驱赶、阻挡）和一种良性行为的性能。
