Predicting intensive care unit bed occupancy for integrated operating room scheduling via neural networks

In a master surgery scheduling (MSS) problem, a hospital's operating room (OR) capacity is assigned to different medical specialties. This task is critical since the risk of assigning too much or too little OR time to a specialty is associated with overtime or deficit hours of the staff, deferral or delay of surgeries, and unsatisfied—or even endangered—patients. Most MSS approaches in the literature focus only on the OR while neglecting the impact on downstream units or reflect a simplified version of the real‐world situation. We present the first prediction model for the integrated OR scheduling problem based on machine learning. Our three‐step approach focuses on the intensive care unit (ICU) and reflects elective and urgent patients, inpatients and outpatients, and all possible paths through the hospital. We provide an empirical evaluation of our method with surgery data for Universitätsklinikum Augsburg, a German tertiary care hospital with 1700 beds. We show that our model outperforms a state‐of‐the‐art model by 43% in number of predicted beds. Our model can be used as supporting tool for hospital managers or incorporated in an optimization model. Eventually, we provide guidance to support hospital managers in scheduling surgeries more efficiently.     

基于改进核极限学习机和集成学习理论的目标机动轨迹预测

为了提高目标轨迹预测的精度以及预测模型的泛化能力,提出基于改进蝙蝠算法优化的核极限学习机(Kernel Extreme Learning Machine,KELM)和集成学习理论目标机动轨迹预测模型。构建KELM模型,并采用改进的蝙蝠算法对KELM的参数进行优化;以优化后的KELM神经网络为弱预测器,结合集成学习算法生成强预测器,通过训练不断优化强预测的结构和参数,得到一种基于集成学习理论的目标机动轨迹预测模型;基于不同规模的样本,将所得预测模型与逆传播神经网络、支持向量机和极限学习机等模型进行对比分析。仿真结果表明:所提目标机动轨迹预测模型具有较好的预测精度和泛化能力。     

柴油机间歇性排气噪声自适应有源前馈控制的DSP仿真

分析了柴油机排气噪声的特征,利用自适应有源前馈系统对噪声进行控制;对间歇性噪声的控制进行了建模分析;对柴油机的排气噪声进行了有源消声的初步设计;参考柴油机实际工况,利用高速信号处理芯片TMS320F2812进行了编程及调试;通过实测数据和DSP仿真实验验证了所采用方法的有效性。     

学员英语学习动机激发之管见

学习动机是直接推动学生进行学习的一种内在动力。学习者的动机和态度作为非智力因素对于英语学习起着相当大的作用,在对军校学员英语学习动机深入了解的基础上,提出了激发学员英语学习动机的具体对策。     

照射箔条在机载电子对抗中的功率分析

深入分析了箔条干扰和雷达有源干扰技术结合使用的原理和功率改善效果,针对机载目标的电磁辐射和箔条云的二次辐射进行了仿真计算,给出采用有源干扰技术前后箔条干扰的功率效果对比,表明二者结合后箔条干扰效果有极大改善,对该方式的使用进行了分析,并提出了建议。     

基于活动轮廓的机器人视觉伺服控制

提出了基于活动轮廓的视觉伺服控制方法。将活动轮廓和光流模型相结合用于运动物体图像的实时跟踪 ,以抽取物体图像的边缘信息 ,并以此信息控制摄像机的运动 ,达到机器人定位、跟踪等目的。该方法跟踪精度高 ,鲁棒性好 ,且满足实时跟踪的要求。实验结果表明了该方法的正确性和有效性。     

活性填料在聚碳硅烷先驱体转化陶瓷中的应用

比较了铝 (Al)、铬 (Cr)、二氢化钛 (TiH2 )和锆 (Zr)等活性填料在聚碳硅烷 (PCS)先驱体转化陶瓷中的应用。研究表明 ,在先驱体中加入活性填料能有效降低陶瓷素坯的气孔率 ,可与PCS气态裂解产物、游离碳和 (或 )N2 气氛反应生成新的化合物 ,提高PCS的陶瓷产率。活性填料的种类与含量对陶瓷烧成体的线收缩有较大的影响 ,Al、Cr能抑制烧成体的线收缩 ,其含量越高 ,线收缩越小。但是TiH2和Zr并不能抑制陶瓷烧成体的线收缩 ,其含量越高 ,线收缩越大。此外 ,活性填料的种类及含量对陶瓷烧成体的三点弯曲强度也有较大的影响。Al、Zr的含量越高 ,材料的强度也越大。但Cr和TiH2 的加入却使材料强度下降。认为Al是较好的活性填料。用X -衍射法 (XRD)分析了烧成产物的物相组成 ,扫描电子显微镜 (SEM)观察了陶瓷烧成体的断口形貌。     

磁浮飞轮试验模型的研究

磁浮飞轮是采用磁轴承支承的卫星姿态控制执行机构。本文在综述磁轴承特点的基础上,介绍了本磁轴承飞轮试验模型的工作原理,推导了其动力学模型。给出了磁轴承设计中的关键参数：轴向不平衡刚度、径向恢复刚度、旋转刚度的计算方法。最后对磁轴承的被动悬浮特性进行了分析,对其主动悬浮控制系统进行了设计,给出了实验结果。本文中所涉及的问题对其它依靠磁力支承装置的设计有参考价值。     

一种改进的BP算法

ＢＰ算法是目前应用极为广泛的神经网络算法,但它也存在一些不足。文中提出了采用共轭梯度法及黄金分割相结合的改进ＢＰ算法（ＭＢＰ）,自适应调整学习率,提高了运算速度,减少了迭代次数。最后将标准ＢＰ算法和ＭＢＰ算法进行了比较,仿其结果表明：ＭＢＰ算法的学习次数和收敛速度得到极大改善。     

Russia’s strategy for influence through public diplomacy and active measures: the Swedish case

Russia, as many contemporary states, takes public diplomacy seriously. Since the inception of its English language TV network Russia Today in 2005 (now ‘RT’), the Russian government has broadened its operations to include Sputnik news websites in several languages and social media activities. Moscow, however, has also been accused of engaging in covert influence activities – behaviour historically referred to as ‘active measures’ in the Soviet KGB lexicon on political warfare. In this paper, we provide empirical evidence on how Russia since 2014 has moved towards a preference for active measures towards Sweden, a small country in a geopolitically important European region. We analyse the blurring of boundaries between public diplomacy and active measures; document phenomena such as forgeries, disinformation, military threats and agents of influence and define Russian foreign policy strategy. In summary, we conclude that the overarching goal of Russian policy towards Sweden and the wider Baltic Sea is to preserve the geostrategic status quo, which is identified with a security order minimising NATO presence in the region.