自燃火灾原因分析认定专家系统的设计特点

结合武警学院科研项目"自燃火灾原因分析认定专家系统"(简称FSAIES)的研制工作,介绍FSAIES系统的基本结构,并通过实例详述了适合于系统开发的知识获取和知识表示方法,重点介绍了系统采用的推理机制和学习功能.     

作业名层次化聚类算法预测作业运行时间

预测作业的运行时间有益于提升系统的调度性能,而聚类有助于训练出更好的预测模型。传统的聚类算法很难将相似的作业名聚类,为了将相似的作业更好地聚类,通过分析其组成成分的语义重要性,构建字母-结构-数字的作业名层次化聚类算法。以两台超级计算机的真实数据为例,实验结果发现,应用此算法聚类后的数据训练模型的预测精度相较传统方法有一定的提升,整体预测精度为70%～80%。     

常值海流作用下多自主水下航行器编队控制

研究了常值海流作用下自主水下航行器(Autonomous Underwater Vehicle,AUV)的编队控制问题.控制器设计分为两部分:一部分综合应用Lyapunov方法和Backstepping技术设计了单体AUV路径跟踪动力学控制律,保证了路径跟踪误差在常值海流作用下的全局渐进稳定;另一部分为路径参数一致性协同跟踪控制器,保证在仅有一个或一部分AUV获取虚拟领航AUV路径参数更新速度情形下能对其进行协同跟踪.从理论上证明了整个闭环系统的稳定性.仿真结果表明了所提出方法的有效性.     

基于航路点跟踪的AUV回收控制

针对军事侦察和海洋观测领域中对自主水下航行器(AUV)自主回收能力的需求,研究了AUV自主回收中的航路点跟踪控制问题.在海流干扰作用下,设计航路点规划跟踪路径,然后运用自适应滑模方法设计AUV的动力学控制规律.采用横向跟踪控制算法,使AUV精确地沿着规划的运动路径进入回收器中.仿真结果表明,所设计的控制规律是有效的,AUV能较好地完成航路点的跟踪任务,并最终到达回收器中实现了对接.     

如何提高在线学习者的自我调节能力

与传统课堂教学相比,网络教学环境独有的特点对学习者提出了更高的要求:要求学习者不仅要掌握知识、技能,更要学会学习,管理自己的能力,进行有意义、高效的学习,使其努力指向目标并最终实现目标。本文结合师范生公共必修课《现代教育技术》在线网络课程的教学实践,有效跟踪学习者的学习行为活动,分析学习者的学习状态、学习风格,以及对学习行为的自我调节能力,总结摸索出一些培养并提高学习者自我调节能力的指导性策略,希望能对广大网络学习者有一定的借鉴意义。     

Undergraduate disarmament and nonproliferation education: gaps,opportunities, and new approaches

ABSTRACT

Despite living in a nuclear-weapon state, young Americans are generally ill-informed about weapons of mass destruction (WMD) and their means of control. The result is both widespread apathy toward nonproliferation and disarmament decision making among the general public and a looming personnel crisis within government sectors that enact policy in these domains. Considering that 67 percent of high school graduates in the United States go on to pursue a bachelor’s degree, exposing more undergraduates to nonproliferation and disarmament issues could contribute to addressing both of these challenges. The present study analyzes how these issues are already being taught at select US colleges and universities and explores ways to introduce them to more students that align with current priorities in higher education, such as interdisciplinary learning, digital humanities, and data-science learning. It also proposes concrete steps that the WMD policy community can take to help institutions of higher education integrate these topics more broadly into their curricula. The anticipated result is greater support for education in this important issue area across different stakeholders in academia, as well as increased engagement with these critical issues among a more diverse population of young people.     

面向蛋白质功能预测中有向无环图标记结构的多示例多标记学习

在多示例多标记学习问题中,标记之间往往是相互关联的,其中有向无环图结构是一种常见的层次关联结构,可见于蛋白质的基因本体学生物学功能预测的应用场景中。针对其标记间的有向无环图结构,提出了一种新的多示例多标记学习算法。算法从原始数据的特征空间训练出所有标记共享的低维子空间,通过随机梯度下降方法来降低模型排序损失,并融入标记间有向无环图结构关系对预测标记进行优化。将该算法应用于多个数据集的蛋白质功能预测中,实验结果表明,该算法具有更高的效率及预测性能。     

多约束强化学习最优智能滑翔制导方法

为提升复杂飞行任务下滑翔制导的自主性,提出一种基于最优制导与强化学习的多约束智能滑翔制导策略。引入三维最优制导以满足终端经纬度、高度以及速度倾角约束。提出基于侧向正弦机动的速度控制策略,研究考虑机动飞行的终端速度解析预测方法。针对速度控制中机动幅值无法离线确定的问题,研究基于强化学习的智能调参方法。该方法基于终端速度设计状态空间,以机动幅值设计动作空间,设计综合终端速度误差与滑翔制导任务的回报函数,采用Q-Learning实现机动幅值的智能调整。仿真结果表明,智能滑翔制导方法能够高精度满足终端多种约束,并能有效提升复杂任务下的自主决策能力。     

高性能互连网络中端口阻塞故障预测方法

随着系统规模、芯片功耗和链路速率的提升,高性能互连网络的整体故障率也不断上升,传统运维方式将难以为继,给高性能计算系统整体可靠性和可用性带来了巨大挑战。针对网络端口阻塞这类严重网络故障,提出无监督算法的预测模型。该模型从历史信息中挖掘征兆性规律并形成新的特征向量,应用K-means聚类算法对特征向量进行学习归类。在预测时,结合端口当前状态,利用二次指数平滑算法对未来状态进行预测,将得到的新特征向量使用K-means算法预判是否会发生阻塞故障。利用拓扑结构信息,分别对叶交换机和根交换机构建预测子模型,进而提升预测的精确率。结果表明,该预测模型能保持在召回率为88.2%的前提下,达到65.2%的准确率,可为运维人员提供有效的辅助。     

Visual-simulation region proposal and generative adversarial network based ground military target recognition

Ground military target recognition plays a crucial role in unmanned equipment and grasping the battlefield dynamics for military applications, but is disturbed by low-resolution and noisy-representation. In this paper, a recognition method, involving a novel visual attention mechanism-based Gabor region proposal sub-network (Gabor RPN) and improved refinement generative adversarial sub-network (GAN), is proposed. Novel central–peripheral rivalry 3D color Gabor filters are proposed to simulate retinal structures and taken as feature extraction convolutional kernels in low-level layer to improve the recognition accuracy and framework training efficiency in Gabor RPN. Improved refinement GAN is used to solve the problem of blurry target classification, involving a generator to directly generate large high-resolution images from small blurry ones and a discriminator to distinguish not only real images vs. fake images but also the class of targets. A special recognition dataset for ground military target, named Ground Military Target Dataset (GMTD), is constructed. Experiments performed on the GMTD dataset effectively demonstrate that our method can achieve better energy-saving and recognition results when low-resolution and noisy-representation targets are involved, thus ensuring this algorithm a good engineering application prospect.