基于物联网的战地装备安全监管问题研究

针对战地环境中军事装备的安全监管问题,分析了战地装备安全监管应用系统的整体结构与功能层次,给出了基于RFID射频识别技术、无线传感器等物联网技术的硬件平台设计方案,以及基于数据采集、分析、融合、传输和可视化技术研发监管控制软件的实现方案。该系统部署应用后可实现对装备实时、连续、精确的分级监管,能够确保装备管理的安全和高效,提高部队指挥决策能力。     

稀疏卷积计算高效数据加载与输出缓存策略

针对现有神经网络加速器在处理稀疏神经网络时存在的数据加载效率低、乘加资源利用率低、输出缓存寻址逻辑复杂等问题,提出了稀疏卷积计算高效数据加载与输出缓存策略。将属于同一输入通道的非零输入特征图像数据和非零权重进行全对全乘累加运算,降低了非零数据配对难度,提高了乘加资源利用率;通过采用输入驻留计算,以及密集型循环加载特征图像数据,大幅减少了数据片外调取次数;优化了输出缓存设计,解决了现有方案中存在的输出缓存地址访问争用、存储拥塞等问题。实验表明,与采用类似架构的细粒度脉动加速器相比,在处理单元面积上减少了21.45%;在数据加载速度方面平均提高了117.71%在平均乘法器利用率方面提高了11.25%,达到89%。     

融合图嵌入的光滑主成分分析网络图像识别算法

主成分分析网络(principal component analysis network, PCANet)是一种简单的深度学习算法,在图像识别领域具有优秀的性能。将图嵌入思想融入PCANet,提出一种新的图像识别算法光滑主成分分析网络(Smooth-PCANet)。为了验证Smooth-PCANet算法的有效性,在人脸、手写体字符以及图片等不同数据集上构建实验,并将Smooth-PCANet与多种基于深度学习的图像识别算法作了对比。实验结果证明,Smooth-PCANet算法比PCANet获得了更高的识别性能,并且更有效地避免了过拟合,在小样本训练时具有显著优势。     

联合生成对抗网络和检测网络的SAR图像目标检测

针对合成孔径雷达图像目标检测中存在的样本获取困难且数量有限问题,提出了联合生成对抗网络和检测网络的学习模型。利用原始训练集对特别设计的超快区域卷积神经网络进行预训练;再通过基于注意力机制的深度学习生成对抗网络生成高质量合成样本,并输入检测网络进行预测;依据预测信息和概率等价类属标签分配策略为新生样本提供注释信息,并以一定占比对原始训练集进行扩充;利用扩充数据集对检测网络进行再训练。多组仿真实验证明,所提框架能够有效提升网络检测效率和性能。     

分布式异构集群中节点优先级调优算法

节点优先级常用于评价异构集群中节点的性能,因此节点优先级评价指标权重的选择非常重要。采用层次分析法(analytic hierarchy process, AHP)建立了节点优先级评价指标体系,计算得到各指标的初始权重,并使用BP神经网络对初始权重进行优化。训练时,BP网络输入为集群运行中采集的节点实时资源数据,输出为节点的优先级。分析网络训练完成后得到的权重矩阵可以获得各优先级评价指标的优化权重。实验表明,基于AHP和BP的节点优先级评价模型可以更加准确地分析节点性能。相比于Spark默认算法和权重未优化的对照算法,使用调优后的节点优先级可以有效提高集群性能。运行不同工作量的相同负载时,集群平均性能分别提高了16.64%和9.76%;处理相同工作量的不同负载时,集群的平均性能分别提高了12.49%和6.54%。     

The SSA-BP-based potential threat prediction for aerial target considering commander emotion

The target's threat prediction is an essential procedure for the situation analysis in an aerial defense system. However, the traditional threat prediction methods mostly ignore the effect of commander's emotion. They only predict a target's present threat from the target's features itself, which leads to their poor ability in a complex situation. To aerial targets, this paper proposes a method for its potential threat prediction considering commander emotion (PTP-CE) that uses the Bi-directional LSTM (BiLSTM) network and the backpropagation neural network (BP) optimized by the sparrow search algorithm (SSA). Furthermore, we use the BiLSTM to predict the target's future state from real-time series data, and then adopt the SSA-BP to combine the target's state with the commander's emotion to establish a threat prediction model. Therefore, the target's potential threat level can be obtained by this threat prediction model from the predicted future state and the recognized emotion. The experimental results show that the PTP-CE is efficient for aerial target's state prediction and threat prediction, regardless of commander's emotional effect.     

One-step synthesis of FeO(OH) nanoparticles by electric explosion of iron wire underwater

In this study,we investigated electric explosion of iron wire in distilled water with different energy input adjusted by charging voltage.The as-prepared samples were characterized by X-ray diffraction (XRD),scanning electron microscopy (SEM),transmission electron microscopy (TEM) and X-ray photoelectron spectroscopy (XPS),showing the presence of iron and multiple iron-based compounds oxides with contents influenced by the experimental conditions.In particular,pure FeO(OH) nanoparticles were obtained using electric explosion of iron wire with energy input of 1125 J at charging voltage of 15 kV.Analysis of discharge current and resistive voltage data indicate that the high energy input induced by strong plasma discharge at high charging voltage is a key factor to form FeO(OH).This study presents a one-step method to synthesize FeO(OH) nanoparticles using electric explosion of iron wire.     

The investigation of NTO/HMX-based plastic-bonded explosives and its safety performance

3-nitro-1,2,4-triazol-5-one (NTO) is the main component of insensitive munitions (IM) formulation because of its outstanding insensitive properties.In this paper,a series of NTO/HMX-based composite explosives were prepared and characterized.The study focuses on the effect of NTO on the performance of the formulations,especially the safety performance.The results revealed that the mechanical sensi-tivity of formulations was associated with NTO content,as well as the thermal conductivity,specific heat capacity and Arrhenius parameters.Then,the high amount of NTO using in formulation was proved to be helpful for NTO/HMX-based formulation to exhibit good thermal safety.Besides,by accelerating rate calorimeter (ARC) and a modified cook-offequipment,the pressure and pressure rise rate were proved as the important indicator for judging the thermal safety performance in confined spaces.Finally,the numerical simulation was used as a credible method for predicting the respond temperature of cook-off experiment.     

Covert radio communications: a viable tactic for international terrorists?

Covert operations by underground groups, such as transnational terrorists, are not new and neither are the methods members of these groups use to communicate in their shadowy world. In this regard, one of the enduring myths is that the main means these covert operatives use to communicate within their cell structure are telephones and emails in their various manifestations. This article critically discusses the possible use of wireless transmissions by transnational terrorists as a reliable form of communications. To critically discuss this proposition, a force field analysis was used to assess the theory that radio is a viable option. Implications of this study's findings are considered in terms of the ramifications they have for defence and security policy.     

从线性供应到网络化保障——英军陆地作战后勤保障转型构想及措施

随着联合作战条件下后勤保障复杂性的日益增加,以及历次战争中后勤保障暴露出诸多不足,为赢取陆地作战的胜利,着眼于不同的陆地作战类型和作战区域,英军提出后勤保障从线性供应转型为网络化保障构想,并提出一系列具体措施,完成陆地作战后勤保障网络的构建,实现转型。