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％.     

Solution-Synthesized Multifunctional Janus Nanotree Microswimmer

Synthetic active matters are perfect model systems for non-equilibrium thermodynamics and of great potential for novel biomedical and environmental applications. However, most applications are limited by the complicated and low-yield preparation, while a scalable synthesis for highly functional microswimmers is highly desired. In this paper, an all-solution synthesis method is developed where the gold-loaded titania-silica nanotree can be produced as a multi-functional self-propulsion microswimmer. By applying light, heat, and electric field, the Janus nanotree demonstrated multi-mode self-propulsion, including photochemical self-electrophoresis by UV and visible light radiation, thermophoresis by near-infrared light radiation, and induced-charge electrophoresis under AC electric field. Due to the scalable synthesis, the Janus nanotree is further demonstrated as a high-efficiency, low-cost, active adsorbent for water decontamination, where the toxic mercury ions can be reclaimed with enhanced efficiency.     

Object Detection in RGB-D Images via Anchor Box with Multi-Reduced Region Proposal Network and Multi-Pooling

Journal of Signal Processing Systems - With the latest development of automation technology, object detection technology has received more and more research attention. Automated object detection...     

基于GA_XGBoost模型的大学生科研能力预测问题研究

科学评价大学生科研创新能力对我国科研水平的提高具有重要意义.采用机器学习模型来预测大学生科研能力可以起到良好的效果,提出一种GAXGBoost模型来实现对大学生的科研能力预测.此模型是以Xgboost算法为基础,然后充分利用遗传算法的全局搜索能力自动搜索Xgboost最优超参数,避免了人为经验调参不准确的缺陷,最后采用精英选择策略以此确保每一轮都是最佳的进化结果.通过分析表明,所采用的GAXGBoost模型在大学生科研能力预测的结果中具有很高的精度,将此模型与Logistic Regression、Random Forest、SVM等模型进行对比,GAXGBoost模型的预测精度最高.     

基于图像分割技术的图像数字水印算法研究

针对数字图像水印技术,通过对闭运算得到的图像再进行开运算,使实验得到的图像区域较为完整,采用4×4的正方形结构元素,使得图像区域有更多的白色像素被置为黑色,对图像进行取反操作,能够对图像区域的非连通区域进行填充.希望能够利用精确的图像分割算法,实现对复杂版面的文档图像的有效切割,在一定程度上对图像数字水印的推广起到促进作用.     

Understanding the solubility and crystallization of molybdenum in high-sodium borosilicate glasses: effect of lanthanum oxide

Journal of Radioanalytical and Nuclear Chemistry - The simplified 8-oxide system (SiO2-B2O3-Na2O-Al2O3-CaO-TiO2-MoO3-La2O3) has been prepared under two types of cooling methods, and analyzed with...     

Hitherto-Unexplored Photodynamic Therapy of Ag2S and Enhanced Regulation Based on Polydopamine In Vitro and Vivo

Given their superior penetration depths, photosensitizers with longer absorption wavelengths present broader application prospects in photodynamic therapy (PDT). Herein, Ag₂S quantum dots were discovered, for the first time, to be capable of killing tumor cells through the photodynamic route by near-infrared light irradiation, which means relatively less excitation of the probe compared with traditional photosensitizers absorbing short wavelengths. On modification with polydopamine (PDA), PDA-Ag₂S was obtained, which showed outstanding capacity for inducing reactive oxygen species (increased by 1.69 times). With the addition of PDA, Ag₂S had more opportunities to react with surrounding O₂, which was demonstrated by typical triplet electron spin resonance (ESR) analysis. Furthermore, the PDT effects of Ag₂S and PDA-Ag₂S achieved at longer wavelengths were almost identical to the effects produced at 660 nm, which was proved by studies in vitro. PDA-Ag₂S showed distinctly better therapeutic effects than Ag₂S in experiments in vivo, which further validated the enhanced regulatory effect of PDA. Altogether, a new photosensitizer with longer absorption wavelength was developed by using the hitherto-unexplored photodynamic function of Ag₂S quantum dots, which extended and enhanced the regulatory effect originating from PDA.     

Boron(iii) β-diketonate-based small molecules for functional non-fullerene polymer solar cells and organic resistive memory devices

A class of acceptor–donor–acceptor chromophoric small-molecule non-fullerene acceptors, 1–4, with difluoroboron(iii) β-diketonate (BF₂bdk) as the electron-accepting moiety has been developed. Through the variation of the central donor unit and the modification on the peripheral substituents of the terminal BF₂bdk acceptor unit, their photophysical and electrochemical properties have been systematically studied. Taking advantage of their low-lying lowest unoccupied molecular orbital energy levels (from −3.65 to −3.72 eV) and relatively high electron mobility (7.49 × 10⁻⁴ cm² V⁻¹ s⁻¹), these BF₂bdk-based compounds have been employed as non-fullerene acceptors in organic solar cells with maximum power conversion efficiencies of up to 4.31%. Moreover, bistable resistive memory characteristics with charge-trapping mechanisms have been demonstrated in these BF₂bdk-based compounds. This work not only demonstrates for the first time the use of a boron(iii) β-diketonate unit in constructing non-fullerene acceptors, but also provides more insights into designing organic materials with multi-functional properties.

Boron(iii) β-diketonates have been demonstrated to serve as multi-functional materials in NFA-based OPVs and organic resistive memories.