Cooperative Multi-Agent Reinforcement Learning with Constraint-Reduced DCOP

Cooperative multi-agent reinforcement learning (MARL) is an important topic in the field of artificial intelligence,in which distributed constraint optimization (DCOP) algorithms have been widely used to coordinate the actions of multiple agents.However,dense communication among agents affects the practicability of DCOP algorithms.In this paper,we propose a novel DCOP algorithm dealing with the previous DCOP algorithms' communication problem by reducing constraints.The contributions of this paper are primarily threefold:① It is proved that removing constraints can effectively reduce the communication burden of DCOP algorithms.② An criterion is provided to identify insignificant constraints whose elimination doesn't have a great impact on the performance of the whole system.③ A constraint-reduced DCOP algorithm is proposed by adopting a variant of spectral clustering algorithm to detect and eliminate the insignificant constraints.Our algorithm reduces the communication burdern of the benchmark DCOP algorithm while keeping its overall performance unaffected.The performance of constraint-reduced DCOP algorithm is evaluated on four configurations of cooperative sensor networks.The effectiveness of communication reduction is also verified by comparisons between the constraint-reduced DCOP and the benchmark DCOP.     

Influence of aging conditions on the mechanical properties and flame retardancy of HIPS composites

In this study, we evaluate the changes in physical properties and flame retardancy of HIPS composites after natural aging tests in Turpan (high sunlight radiation dose and dry) and Qionghai (high temperature and rainy) in China for 21 months. The HIPS composite aged in Turpan revealed a higher chromatic aberration than that in Qionghai due to the higher sunlight radiation dose. After aging tests for 21 months, the mechanical properties and the peak heat release of the HIPS composite aged in Qionghai decreased by more than 50% and increased by 39.7%, respectively, results that were worse than for the HIPS composite in aged Turpan. This was related to the combined effects of light, temperature, rain, and moisture in Qionghai leading to more severe degradation of HIPS composites, which results in breaking of the polymer chains and migration and erosion of the flame retardant. © 2018 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2018 , 135, 46339.     

基于仿生视觉的海面船只检测方法

对地观测系统可以快速检测大面积区域,为世界各沿海国家的船只监测任务带来了极大便利。针对遥感影像中的船只自动化检测问题,利用船只相对于海面呈现明显的视觉显著特性,提出了一种基于船只与海面反差特性的船只检测方法,将对船只的检测定位转变为对场景中显著目标的发现与分割问题。方法以视网膜到初级视觉皮层V1这一视觉通路的生理过程为指导,模拟了其中视觉信号的产生机制以获得场景的显著图。以光学影像为例进行的实验结果显示,在没有目标先验知识的前提下,基于反差特性的方法能有效地将视觉注意力集中于海面船只目标,取得了较好的检测结果。     

基于短地址混淆和谷歌云推送的移动僵尸网络的构建

为了提升对移动僵尸网络的预测能力和防御能力,提出了一种基于短地址混淆(USSes-Flux)和谷歌云(GCM)推送的移动僵尸网络的构建机制。设计了基于中心结构和对等网络(P2P)混合的拓扑结构的移动僵尸网络模型,给出了USSes-Flux算法,从而增强了命令与控制信道的隐秘性和强壮性。给出了该移动僵尸网络的控制模型,分析了不同僵尸节点的状态改变、命令设计和传播算法。实验环境中,研究了短地址的失效率与申请数量之间的关系,并对该移动僵尸网络与不同命令和控制信道的样本进行静态分析、动态分析和电量测试。结果表明:该移动僵尸网络具有较强的隐秘性、强壮性和低消耗。     

Preparation of hybrid silicon materials microcapsulated ammonium polyphosphate and its application in thermoplastic polyurethane

Silica‐gel microencapsulated ammonium polyphosphate (SiOAPP), prepared by traditional sol–gel method, is still incompatible with polymer and easily attacked by moisture due to the presence of lots of hydroxyl group, so the traditional sol–gel method was optimized with polydimethyl siloxane (PDMS) to improve the related properties of microcapsules in this study. The results showed that the SiOAPP process and shell shape had changed significantly, and the APP microcapsules with silica/silicone carbon composite shell (SiOCAPP) was successfully prepared. The hydrophobicity of SiOCAPP was much better than that of the SiOAPP, the water contact angle of SiOAPP was 54°, while the water contact angle of SiOCAPP could reach 111°. The property reinforcements of the SiOCAPP in thermoplastic polyurethane (TPU) were studied and compared with the TPU/SiOAPP composites. The time to ignition reduced by 2 s and the maximal peak of heat release rate (pk‐HRR) increased by 4.4%, but the average heat release rate and total heat release, respectively, reduced by 15.5% and 31.4%, which was a great improvement on the flame retardancy of TPU, and the char residue rate, which is related to the condensed flame retardant effect, increased by 10%. Besides, the tensile strength and elongation at break increased by 11.8% and 5.84%, respectively. Generally, the sol–gel method modified by PDMS provided an novel method to improve the comprehensive properties of APP. © 2017 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2018 , 135, 45742.     

铝导线违规连接点过热故障及痕迹分析

通过模拟不同种连接方式,研究铝导线连接点过热故障现象及痕迹特征。测得连接点温度和熔断时间,利用高速摄像机记录熔断过程,并对所得痕迹试样的宏观形貌、金相组织进行观察比较。得出勾接方式连接时,导线断开瞬间产生明显电弧,断开温度低、速度快,熔痕晶粒为细小的胞状晶和柱状晶;缠绕和铰接方式连接时,导线断开瞬间很少产生明显电弧,会有尖状熔痕,绕结、粘接、熔结痕迹,熔痕晶粒为粗大的等轴晶或柱状晶。研究结论为此类电气火灾调查提供依据。     

信息安全技术体系研究

从系统论的观点出发,在对信息安全的目标和信息系统构成分析的基础上,剖析了信息安全技术体系的要素和子系统,并按分层、分域、分级和分时四个维度,给出了信息安全技术的体系结构,探讨了每个维度的具体构成及其与信息安全要素和子系统之间的关系。信息安全技术体系的研究,对认清信息安全技术的本质和规律,以及运用信息安全技术构造信息安全系统具有一定的指导意义。     

Intrusion Detection Approach Using Connectionist Expert System

In order to improve the detection efficiency of rule-based expert systems, an intrusion detection approach using connectionist expert system is proposed. The approach converts the AND/OR nodes into the corresponding neurons, adopts the three-layered feed forward network with full interconnection between layers,translates the feature values into the continuous values belong to the interval [0, 1 ], shows the confidence degree about intrusion detection rules using the weight values of the neural networks and makes uncertain inference with sigmoid function. Compared with the rule-based expert system, the neural network expert system improves the inference efficiency.     

太赫兹光谱技术的应用进展

近年来太赫兹（THz）技术快速发展,在安全检测、航空航天、生命科学、化学等领域应用日趋广泛。由于许多炸药及其相关材料在THz波段具有特征吸收,许多非金属、非极性材料对THz波是透明的,且太赫兹波具有低能性,THz光谱技术在安检中具有巨大的应用潜力。本文介绍了太赫兹波的特性和国内外在太赫兹领域的研究进展,详细介绍了太赫兹波在爆炸物、毒品和包装材料检测中的应用,并讨论了在应用中存在的困难和面临的挑战。     

全二维气相色谱-四级杆质谱联用分析吉林市售汽油组分

用全二维气相色谱-四级杆质谱联用(GC×GC-qMS)对汽油样品进行定性、定量分析,考察了进样方式、程序升温和调制周期3个因素对分离效果的影响.用6种直链烷烃、2种烯烃、2种环烷烃和11种芳香烃组成的混合标准溶液对各族组分的响应值进行校正.结果表明:汽油样品中直链烷烃、支链烷烃、环烷烃、烯烃、烷基苯、茚系和萘系等各族组...