基于深度神经网络和联邦学习的网络入侵检测

在高速网络环境中,对复杂多样的网络入侵进行快速准确的检测成为目前亟待解决的问题。联邦学习作为一种新兴技术,在缩短入侵检测时间与提高数据安全性上取得了很好的效果,同时深度神经网络（DNN）在处理海量数据时具有较好的并行计算能力。结合联邦学习框架并将基于自动编码器优化的DNN作为通用模型,建立一种网络入侵检测模型DFC-NID。对初始数据进行符号数据预处理与归一化处理,使用自动编码器技术对DNN实现特征降维,以得到DNN通用模型模块。利用联邦学习特性使得多个参与方使用通用模型参与训练,训练完成后将参数上传至中心服务器并不断迭代更新通用模型,通过Softmax分类器得到最终的分类预测结果。实验结果表明,DFC-NID模型在NSL-KDD与KDDCup99数据集上的准确率平均达到94.1%,与决策树、随机森林等常用入侵检测模型相比,准确率平均提升3.1%,在攻击类DoS与Probe上,DFC-NID的准确率分别达到99.8%与98.7%。此外,相较不使用联邦学习的NO-FC模型,DFC-NID减少了83.9%的训练时间。     

Exploring a Stable and Dense 3D Lead Chloride Hybrid with Emission of Self-Trapped Excitons toward X-Ray Scintillation

The exceptional photophysical properties of 3D organic–inorganic lead halide hybrids (OILHs) endow their significant potential for usage in optoelectronics, which has sparked intense research on novel 3D OILHs and associated applications. However, constructing new 3D OILHs based on large organic cations suffers from tough challenges due to the limitation of the Goldschmidt tolerance factor rule, let alone further explorations of their practical applications. Herein, a brand-new 3D lead chloride hybrid, (1MPZ)Pb₄Cl₁₀·H₂O ( 1 , 1MPZ = 1-methylpiperazine) is reported, featuring a dense 3D lead chloride framework made of the corner-, edge-, and face-shared lead chloride polyhedra. 1 presents a broadband white light emission with a large Stokes shift and a nanosecond photoluminescence lifetime, which originates from radiative recombination of self-trapped excitons (STEs) induced by the highly distorted structure. Such a reabsorption-free and fast-decayed STEs emission coupling with the dense 3D architecture further enables 1 with effective X-ray scintillation with good sensitivity. Impressively, 1 also shows superior environmental and radiation stability. This study provides a new 3D OILH with appealing luminescence, not only expanding the 3D OILH family but also inspiring the exploitation of their optoelectronic applications.     

Control allocation technology based on fault diagnosis for the unmanned aerial vehicle system subject to physical constraints and fault reconfiguration mismatch

The problem of the system robustness subject to physical constraints and mismatched fault reconstruction is discussed in this paper. In order to facilitate the design, a four-rotor unmanned aerial vehicle (UAV) system model was selected for research. First, the control allocation model of the nonlinear UAV system with disturbances is shown in the paper. Secondly, a weighted pseudo-inverse method based on adaptive weights is proposed, which reduces the impact of physical constraints on the system. After that, a dynamic weight control allocation method based on the fault efficiency matrix is designed. The weight matrix can dynamically adjust the control distribution law according to the fault estimation value provided by the observer. Then, a dynamic adaptive control allocation method for faults and physical constraints is carried out by combining adaptive weights and dynamic weights. Finally, a simulation example is presented to further illustrate the effectiveness of the algorithm proposed in this paper.     

Excluded volume effects in on‐ and off‐lattice reaction–diffusion models

Mathematical models are important tools to study the excluded volume effects on reaction–diffusion systems, which are known to play an important role inside living cells. Detailed microscopic simulations with off‐lattice Brownian dynamics become computationally expensive in crowded environments. In this study, the authors therefore investigate to which extent on‐lattice approximations, the so‐called cellular automata models, can be used to simulate reactions and diffusion in the presence of crowding molecules. They show that the diffusion is most severely slowed down in the off‐lattice model, since randomly distributed obstacles effectively exclude more volume than those ordered on an artificial grid. Crowded reaction rates can be both increased and decreased by the grid structure and it proves important to model the molecules with realistic sizes when excluded volume is taken into account. The grid artefacts increase with increasing crowder density and they conclude that the computationally more efficient on‐lattice simulations are accurate approximations only for low crowder densities.Inspec keywords: reaction‐diffusion systems, cellular biophysics, biodiffusion, Brownian motion, cellular automata, molecular biophysics, molecular configurationsOther keywords: crowder density, grid artefacts, grid structure, crowded reaction rates, artificial grid, randomly distributed obstacles, crowding molecules, cellular automata models, on‐lattice approximations, crowded environments, off‐lattice Brownian dynamics, detailed microscopic simulations, living cells, mathematical models, off‐lattice reaction‐diffusion models, on‐lattice reaction‐diffusion models, excluded volume effects     

Walnut-inspired microsized porous silicon/graphene core–shell composites for high-performance lithium-ion battery anodes

Silicon is considered an exceptionally promising alternative to the most commonly used material, graphite, as an anode for next-generation lithium-ion batteries, as it has high energy density owing to its high theoretical capacity and abundant storage. Here, microsized walnut-like porous silicon/reduced graphene oxide (P-Si/rGO) core–shell composites are successfully prepared via in situ reduction followed by a dealloying process. The composites show specific capacities of more than 2,100 mAh·g^?1 at a current density of 1,000 mA·g^?1, 1,600 mAh·g^?1 at 2,000 mA·g^?1, 1,500 mAh·g^?1 at 3,000 mA·g^?1, 1,200 mAh·g^?1 at 4,000 mA·g^?1, and 950 mAh·g^?1 at 5,000 mA·g^?1, and maintain a value of 1,258 mAh·g^?1 after 300 cycles at a current density of 1,000 mA·g^?1. Their excellent rate performance and cycling stability can be attributed to the unique structural design: 1) The graphene shell dramatically improves the conductivity and stabilizes the solid–electrolyte interface layers; 2) the inner porous structure supplies sufficient space for silicon expansion; 3) the nanostructure of silicon can prevent the pulverization resulting from volume expansion stress. Notably, this in situ reduction method can be applied as a universal formula to coat graphene on almost all types of metals and alloys of various sizes, shapes, and compositions without adding any reagents to afford energy storage materials, graphene-based catalytic materials, graphene-enhanced composites, etc.

Open image in new window

     

硅丙乳液包覆Mg(OH)2核壳结构纳米粒子的制备与表征

为有效提高Mg(OH)_2纳米粒子在硅丙乳液中的相容性与分散稳定性,在油酸修饰Mg(OH)_2纳米粒子的基础上,以甲基丙烯酸甲酯、丙烯酸丁酯、丙烯酸与乙烯基三乙氧基硅烷为共聚单体,通过乳液聚合法制备出具有核壳结构的硅丙乳液包覆Mg(OH)_2复合材料。利用傅里叶变换红外光谱仪(FTIR)、X射线衍射仪(XRD)、透射电子显微镜(TEM)等测试手段对样品结构、形貌进行了表征。通过燃烧实验,研究了硅丙乳液包覆Mg(OH)_2纳米粒子对水性防火涂料阻燃性能的影响。结果表明,油酸通过酯化作用修饰在Mg(OH)_2纳米粒子表面,借助油酸分子中双键结构,丙烯酸类混合单体在纳米Mg(OH)_2表面完成聚合过程,形成以Mg(OH)_2纳米粒子为核、硅丙乳液为壳的复合材料。XRD与热分析表明经硅丙乳液包覆的纳米Mg(OH)_2晶体结构与热稳定性能未受影响。此外,掺杂0.1%(质量分数)的硅丙乳液包覆Mg(OH)_2可使水性防火涂料阻燃时间延长至113 min,较未掺杂水性涂料阻燃时间(91min)提高约23%。     

Crystallization‐Induced Emission Enhancement of a Deep‐Blue Luminescence Material with Tunable Mechano‐ and Thermochromism

Organic luminescent materials with the ability to reversibly switch the luminescence when subjected to external stimuli have attracted considerable interest in recent years. However, the examples of luminescent materials that exhibit multiresponsive properties are rarely reported. In this work, a new stimuli‐responsive dye P1 is designed and synthesized with two identical chromophores of naphthalimide, one at each side of an amidoamine‐based spacer. This amide‐rich molecule offers many possibilities for forming intra‐ and intermolecular hydrogen bond interactions. Particularly, P1 has an intrinsic property of cocrystallizing with methanol. Compared with the pristine P1 sample, the as‐prepared two‐component cocrystalline material displays an exceptive deep‐blue emission, which is extremely rare among naphthalimide‐based molecules in the solid state. Furthermore, the target material exhibits an obvious mechanochromic fluorescent behavior and a large spectral shift under force stimuli. On the other hand, the cocrystalline material shows an unusual “turn off” thermochromic luminescence accompanied by solvent evaporation. Moreover, using external stimuli to reversibly manipulate fluorescent quantum yields is rarely reported to date. The results demonstrate the feasibility of a new design strategy for solid‐state luminescence switching materials: the incorporation of solvents into organic compounds by cocrystallization to obtain a crystalline state luminescence system.