基于1D CNN与XGBoost的恶意代码纹理检测

恶意代码数量已经呈现爆炸式增长,对于恶意代码的检测防护显得尤为重要.近几年,基于深度学习的恶意代码检测方法开始出现,基于此,提出一种新的检测方法,将恶意代码二进制文件转化为十进制数组,并利用一维卷积神经网络(1 Dimention Convolutional Neural Networks,1D CNN)对数组进行分类和识别.针对代码家族之间数量不平衡的现象,该算法选择在分类预测上表现良好的XGBoost,并对Vision Research Lab中的25个不同恶意软件家族的9458个恶意软件样本进行了实验.实验结果表明,所提的方法分类预测精度达到了97％.     

The effect of alkali metal oxide on the properties of borosilicate fireproof glass: Structure,thermal properties,viscosity, chemical stability

The purpose of the current work was to research the effect of alkali metal oxide on the structure, thermal properties, viscosity and chemical stability in the glass system (R₂O–CaO–B₂O₃–SiO₂) systematically. Because the glass would emulsify when Li₂O was added to the glass batch, this article did not discuss Li₂O. The results showed that when the amount of Na₂O was less than 4 mol.%, there was a higher interconnectivity of borate and silicate sub-networks in glass, as more mixed Si–O–B bonds were present in glass. The glass samples exhibited excellent thermal properties and chemical stabilities. As the amount of Na₂O exceeded 4 mol.%, the interconnectivity of borate and silicate sub-networks was weakened. The thermal properties and chemical stabilities of the glass samples were reduced. The connectivity of the silicate sub-network was weakened slightly as the Na/K ratio varied, and the coefficient of thermal expansion (CTE) of the glass samples gradually increased, and the resistance to thermal shock (RTS) value gradually decreased. Moreover, the viscosity of the glass samples decreased with the ratio of Na/Si and Na/K increased.     

Enhanced electrochemical performance of LiNi0.8Co0.1Mn0.1O2 via titanium and boron co-doping

Titanium and boron are simultaneously introduced into LiNi_0.8Co_0.1Mn_0.1O₂ to improve the structural stability and electrochemical performance of the material. X-ray diffraction studies reveal that Ti⁴⁺ ion replaces Li⁺ ion and reduces the cation mixing; B³⁺ ion enters the tetrahedron of the transition metal layers and enlarges the distance of the [LiO₆] layers. The co-doped sample has spherical secondary particles with elongated and enlarged primary particles, in which Ti and B elements distribute uniformly. Electrochemical studies reveal the co-doped sample has improved rate performance (183.1 mAh·g^-1 at 1 C and 155.5 mAh·g^-1 at 10 C) and cycle stability (capacity retention of 94.7% after 100 cycles at 1 C). EIS and CV disclose that Ti and B co-doping reduces charge transfer impedance and suppresses phase change of LiNi_0.8Co_0.1Mn_0.1O_2.     

基于图神经网络的网络性能智能预测

传统网络性能预测技术存在网络状态获取不够全面及网络性能评估准确性欠佳等问题，利用图神经网络学习推理网络关系数据的特点，结合捕获的网络全局信息，提出了一种基于图神经网络的网络性能智能预测方法。通过网络系统抽象及网络性能建模，将复杂的网络信息转化为形式化的图数据进行描述，利用图空域卷积处理图网络节点的消息传递过程，实现网络信息之间的关系推理，研究了实现网络性能预测的图神经网络模型，提出了一种能处理流量矩阵、网络拓扑、路由策略、节点配置的图神经网络体系结构，最后通过实验论证了模型能更好地实现包括时延、抖动和丢包率的网络性能的准确预测。     

Fabrication of Cu/graphite film/Cu sandwich composites with ultrahigh thermal conductivity for thermal management applications

Effective thermal management of electronic integrated devices with high powder density has become a serious issue, which requires materials with high thermal conductivity (TC). In order to solve the problem of weak bonding between graphite and Cu, a novel Cu/graphite film/Cu sandwich composite (Cu/GF/Cu composite) with ultrahigh TC was fabricated by electro-deposition. The micro-riveting structure was introduced to enhance the bonding strength between graphite film and deposited Cu layers by preparing a rectangular array of micro-holes on the graphite film before electro-deposition. TC and mechanical properties of the composites with different graphite volume fractions and current densities were investigated. The results showed that the TC enhancement generated by the micro-riveting structure for Cu/GF/Cu composites at low graphite content was more effective than that at high graphite content, and the strong texture orientation of deposited Cu resulted in high TC. Under the optimizing preparing condition, the highest in-plane TC reached 824.3 W·m⁻¹·K⁻¹, while the ultimate tensile strength of this composite was about four times higher than that of the graphite film.     

Insights into low-carbon hydrogen production methods: Green,blue and aqua hydrogen

The primary aim of this study is to provide insights into different low-carbon hydrogen production methods. Low-carbon hydrogen includes green hydrogen (hydrogen from renewable electricity), blue hydrogen (hydrogen from fossil fuels with CO₂ emissions reduced by the use of Carbon Capture Use and Storage) and aqua hydrogen (hydrogen from fossil fuels via the new technology). Green hydrogen is an expensive strategy compared to fossil-based hydrogen. Blue hydrogen has some attractive features, but the CCUS technology is high cost and blue hydrogen is not inherently carbon free. Therefore, engineering scientists have been focusing on developing other low-cost and low-carbon hydrogen technology. A new economical technology to extract hydrogen from oil sands (natural bitumen) and oil fields with very low cost and without carbon emissions has been developed and commercialized in Western Canada. Aqua hydrogen is a term we have coined for production of hydrogen from this new hydrogen production technology. Aqua is a color halfway between green and blue and thus represents a form of hydrogen production that does not emit CO₂, like green hydrogen, yet is produced from fossil fuel energy, like blue hydrogen. Unlike CCUS, blue hydrogen, which is clearly compensatory with respect to carbon emissions as it captures, uses and stores produced CO₂, the new production method is transformative in that it does not emit CO₂ in the first place. In order to promote the development of the low-carbon hydrogen economy, the current challenges, future directions and policy recommendations of low-carbon hydrogen production methods including green hydrogen, blue hydrogen, and aqua hydrogen are investigated in the paper.