Fast network intrusion detection system using adaptive binning feature selection

Aiming at the problems of the low detection rate of traditional intrusion detection systems and the long training and detection time of intrusion detection systems based on deep learning,an adaptive binning feature selection algorithm using the information gain is proposed,which is combined with LightGBM to design a fast network intrusion detection system.First,the original data set is preprocessed to standardize the data;then the redundant features and noise in the original data are removed through the adaptive binning feature selection algorithm,and the original high-dimensional data are reduced to the low-dimensional data,thereby improving the accuracy of the system and reducing the training and detection time;finally,LightGBM is used for model training on the training set selected by the characteristics to train an intrusion detection system that can detect attack traffic.Through verification on the NSL-KDD data set,the proposed feature selection algorithm only takes 27.35 seconds in feature selection,which is 96.68% lower than that by the traditional algorithm.The designed intrusion detection system has an accuracy rate of 93.32% on the test set,and its training time is low.Compared with the existing network intrusion detection system,the accuracy rate of the proposed system is higher,and its model training speed is faster.     

Studies on film potentiometric stripping analysis: effects of electrochemical parameters

Film potentiometric stripping analysis (PSA) is a novel method for concentrating the test ion directly on a glassy carbon electrode with subsequent stripping by a chemical oxidant, the redissolution step being followed by a chronopotentiometric sequence. The electrochemical parameters governing both preconcentration and redissolution steps are studied on a rotating disk electrode: experimental results are compared with the theoretical developments recently published. Except for the influence of rde rotation rates on each step and on analytical parameters, experiments and theory are in agreement. Discrepancies concerning the rotation rate effects are studied by potentiostatic coulometry and voltammetry measurements in regard to the preconcentration step: the rotation rate effects are based on the physical behaviour of the rde. Routine analysis is carried out using film PSA, Pb(II) as the test ion and Fe(III) as oxidizing agent, in perchlorate medium.     

基于多决策树的RFID入侵检测模型

为了能够有效对RFID系统的已知攻击和未知攻击进行检测和预警,在分析大量RFID安全协议的基础上,提出了利用构建多决策树的方法对RFID系统的入侵行为进行检测。通过分析,得到所构造出的多决策树能够发现针对RFID系统的攻击之间的关系,并且具有可扩展性和高效性,使之能够适用于各种实际的RFID系统的应用。     

中国汞污染的现状及防治对策

综述了环境汞污染的主要来源及特点,分析了中国现阶段汞污染的现状,提出加强燃煤汞污染的控制、削减工业汞使用量、提高社会公众的参与意识是治理我国汞污染当采取的有效措施。     

T.C.Powcrs模型若干问题的研究

从T.C.Powers水泥石模型出发,提出了描述水泥混凝土材料初始结构的主要参数是初始孔隙率。由此池绎了水泥浆体组成与结构的定量关系,比原模型有更明了的物理意义,研究结果表明,Powers模型在高孔隙率范围内具有适用性,但不适用于低孔隙率硬化水泥浆体,且在低孔隙率条件下不存在28％的固有凝胶孔隙率,水化产物成份和性质是渐变的。     

On the relationship between pore structure and chloride diffusivity from accelerated chloride migration test in cement-based materials

In this study the electrochemical technique is applied to accelerate chloride ion migration in concrete to determine the chloride ions in anode cell, and the pore characteristic of the same mortars in concrete was obtained from the mercury intrusion porosimetry (MIP). The plain ordinary Portland cement and the constant aggregate with eight w/c ratios ranging from 0.3 to 0.65 were used. A good linear relationship between the steady-state migration coefficient and non-steady-state migration coefficient based on the same experimental setup and specimens was obtained. Both of the steady-state migration coefficient and non-steady-state migration coefficient were linearly related to the capillary pore volume and the critical pore diameter.     

协同入侵检测研究现状与展望

协同入侵检测技术(collaborative intrusion detection system, CIDS)能够检测分布式协同攻击,应对大规模网络入侵,拥有传统入侵检测系统所不具备的优势,而如何在提高检测性能的同时实现去中心化是一个重要的研究课题。通过对近年来CIDS研究成果的梳理,阐述了在检测方法、数据聚合、隐私保护和信任管理方面的研究进展和问题,分析了在去中心化方面面临的挑战,探讨了基于区块链技术的CIDS未来发展方向,最后展望了CIDS在云计算、物联网等新兴领域的应用前景。     

塑料原料中有害重金属铅、镉、汞的测定

采用微波消解为前处理手段 ,以磷酸二氢铵为基体改进剂 ,用石墨炉原子吸收法测定塑料原料样品中的铅、镉 ;用流动注射 -氢化物发生 -原子吸收法测定汞。测定铅的检出限为 4 .5× 10 -11g,镉的检出限为 3.7× 10 -12 g ,汞的检出限为 0 .6 4 μg/kg ;测定结果相对标准偏差一般小于 10 % ;铅、镉、汞的回收率在 93%～ 10 3%之间     

食品中微量汞的固相萃取光度法测定研究

研究了氯磺酚偶氮硫代若丹宁(HSCT)与汞的显色反应,在pH3.6的HAc NaAc缓冲介质中,Tri tonX 100存在下,HSCT与汞反应生成2∶1稳定络合物,该络合物可被C18固相萃取小柱定量萃取,小柱上保留的络合物用四氢呋喃洗脱后用分光光度法测定,λmax=550nm,体系ε=9.64×104L/(mol·cm)。汞含量在0～1.0μg/mL内符合比尔定律,方法可用于食品中痕量汞含量的测定。     

移动传感器随机事件捕获

移动传感器在入侵检测的应用研究中,感兴趣区域主要考虑的是特定形状,如圆形或矩形。由于这种限制,很多研究结论通用性差。研究了感兴趣区域是任何形状的一个环;基于移动传感器的速度,移动模式和数量,建立了一个随机模型;分析多个或单个移动传感器沿环检测的性能。在模型中,当所有移动传感器检测时,它们被置以恒定的速度周期性地沿环移动。对于多个移动传感器,它们的速度都相同。入侵事件的模式为每次入侵到达环上一个随机点,抵达后停留一个随机时间长度。根据移动传感器的数量,导出了移动传感器对入侵漏捕概率和首次捕获入侵所需平均时间的一般表达式。最后,评估了移动传感器的检测性能。