行政事业海量题库管理系统设计

提出了行政事业单位海量题库管理系统,给出了系统总体架构设计思路,论述了各主要功能模块的实现。着重讨论了题目重复度判别、题目难度系数调整等关键算法的实现,给出了系统部署、配置与应用实例。     

一种mIBS方案的分析与改进

魏松杰等人提出一种基于安全仲裁SEM（security mediator）的mIBS（identity based signature）方案,利用SEM节点实现用户身份实时撤销。mIBS方案中,SEM持有部分用户私钥,与签名者共同完成签名。对mIBS方案进行了安全性分析,发现该方案存在严重安全缺陷,并给出一个具体的攻击实例。在攻击实例中,签名者通过与SEM的一次正常签名交互,窃取SEM持有的部分私钥,进而绕开SEM单独实施签名,使得SEM失效。提出一种改进的mIBS方案（记为mIBSG）,对SEM持有的部分私钥增加了随机性保护。进一步,建立了mIBS方案安全模型mEUF-CMIA（existential unforgeability under adaptive chosen message and identity attacks）,重点讨论了其敌手模型。除传统IBS敌手外,mEUF-CMIA模型定义第二种类型敌手模拟一个恶意但合法的签名者,通过访问随机预言机,在没有SEM参与的情况下独立产生签名。在mEUF-CMIA模型下,mIBSG方案的不可伪造性被归约为求解循环群上的CDH问题。对比分析表明,mIBSG方案以较小的计算代价实现了可证明安全性。mIBSG方案可用于构建基于IBC的跨域认证系统。     

基于ADASYN-SFS-RF的欺诈检测模型泛化性能提升及可解释性研究

针对行业欺诈行为形式多样、操作隐蔽,且数据分布极端不平衡等问题,研究采用ADASYN（adaptive synthetic sampling approach for imbalanced learning）算法将分类决策边界向困难的实例进行自适应移动实现数据扩增,以解决不平衡数据造成的过拟合问题。采用基于随机森林的序列向前搜索策略算法筛选出最优特征子集对欺诈进行检测,降低ADASYN算法添加噪声数据对分类边界确定的影响,构建欺诈检测模型,并使用LIME对模型检测结果作出局部解释,提高模型的使用价值。实验表明,该模型可以较好地克服传统欺诈检测模型对多数类样本误分类的缺陷,有助于提高行业对交易欺诈行为识别的效率。同时,通过LIME对模型检测出的随机样本进行有效解析,便于决策者对算法模型的检测结果作出实证分析,起到明显的预警及决策参考价值。     

环境荷载联合作用下海上风电结构动力响应分析

为研究海上风电结构在复杂的海洋环境中承受环境荷载(风、波、冰、流)的联合作用时,结构产生的剧烈的动力响应问题。文章以三脚架基础海上风电结构为研究对象,采用ANSYS有限元软件建立其整体模型并进行荷载(风、波、流和风、冰、流)联合作用下的静力校核,通过对环境荷载联合作用下的三脚架基础海上风电结构进行瞬态分析,掌握其动力响应的特性及规律。结果表明:三脚架基础结构的一、二阶自振频率均为0.285Hz,在所选风机允许的频率范围内,可以保证整体结构不会与风机转动发生共振;风荷载在风、波、流荷载联合作用下主导控制结构响应的稳态波动,冰荷载在风、冰、流荷载联合作用下主导控制结构的稳态振动过程;塔筒顶端呈现的位移和加速度响应均远大于三脚架基础顶端;环境荷载联合作用下结构动力响应是环境荷载单独作用下动力响应叠加的结果。     

洪水预报智能模型在中国半干旱半湿润区的应用对比

为探究不同洪水预报智能模型在我国半干旱半湿润区的应用效果,选用决策树、多层感知器、随机森林和支持向量机4种模型在陕西省3个典型流域进行逐时洪水预报;选择相关系数、纳什效率系数、均方根误差、平均绝对误差和相对误差等评价指标,比较不同预见期下4种模型在半干旱半湿润典型流域洪水预报的适用性。结果表明:在短预见期预报中,4种模型在半湿润区典型流域均可获得较高的预报结果,在半干旱典型流域模拟精度相对偏低,仅支持向量机模型满足预报要求;随着预见期延长,不同模型性能变化差异大,支持向量机模型整体稳定,在小流域实时洪水预报中具有明显优势;随机森林模型与决策树模型精度随预见期延长而缓慢下降,前者适应性更好;多层感知器模型精度随预见期延长而骤减,模型稳定性较差。     

Selection of optimized features for fusion of palm print and finger knuckle‐based person authentication

The impact of digital technology in biometrics is much more efficient at interpreting data than humans, which results in completely replacement of manual identification procedures in forensic science. Because the single modality‐based biometric frameworks limit performance in terms of accuracy and anti‐spoofing capabilities due to the presence of low quality data, therefore, information fusion of more than one biometric characteristic in pursuit of high recognition results can be beneficial. In this article, we present a multimodal biometric system based on information fusion of palm print and finger knuckle traits, which are least associated to any criminal investigation as evidence yet. The proposed multimodal biometric system might be useful to identify the suspects in case of physical beating or kidnapping and establish supportive scientific evidences, when no fingerprint or face information is present in photographs. The first step in our work is data preprocessing, in which region of interest of palm and finger knuckle images have been extracted. To minimize nonuniform illumination effects, we first normalize the detected circular palm or finger knuckle and then apply line ordinal pattern (LOP)‐based encoding scheme for texture enrichment. The nondecimated quaternion wavelet provides denser feature representation at multiple scales and orientations when extracted over proposed LOP encoding and increases the discrimination power of line and ridge features. To best of our knowledge, this first attempt is a combination of backtracking search algorithm and 2D²LDA has been employed to select the dominant palm and knuckle features for classification. The classifiers output for two modalities are combined at unsupervised rank level fusion rule through Borda count method, which shows an increase in performance in terms of recognition and verification, that is, 100% (correct recognition rate), 0.26% (equal error rate), 3.52 (discriminative index), and 1,262 m (speed).     

一种鲁棒性的少样本学习方法

少样本学习是目前机器学习研究领域的一个热点,它能在少量的标记样本中学习到较好的分类模型.但是,在噪声的不确定环境中,传统的少样本学习模型泛化能力弱.针对这一问题,提出一种鲁棒性的少样本学习方法RFSL(Robust Few-Shot Learning).首先,使用核密度估计(Kernel Density Estimation,KDE)和图像滤波(Image Filtering)方法在训练集中加入不同的随机噪声,形成多个不同噪声下的训练集,并分别生成支持集和查询集.其次,利用关系网络的关系模块通过训练集端到端地学习多个基分类器.最后,采用投票的方式对各基分类器的最末Sigmoid层非线性分类结果进行融合.实验结果表明,RFSL模型可促进小样本学习快速收敛,同时,与R-Net以及其他主流少样本学习方法相比,RFSL具有更高的分类准确率,更强的鲁棒性.     

多重不确定的密码体制研究

针对现有密码体制中只有密钥不确定的特点,文章提出了多重不确定密码体制的概念,指出了可能实现的一些途径。文章分析了其优势,指出这类密码体制在大大增强安全性的同时,其可能带来的运算量的增加是可以忽略的。     

自适应变步长最大风能捕获算法

风能具有随机性、不稳定性的特点,为了提高风力发电系统中风能的利用效率,在比较各种最大风能捕获算法的基础上,分析了爬山搜索法和叶尖速比法的不足,提出了自适应变步长搜索算法来捕获最大风能.通过改进爬山搜索法的变步长策略,明显加快了搜索速度,通过引入初始估计叶尖速比值,大大缩小了搜索范围.该算法不需要实时检测准确风速,不依赖风力机最佳功率曲线,有效地降低了成本,提高风力发电的效率.文中重点分析了算法的自适应性和变步长策略,仿真结果表明,该算法能够使风力机更快速到达最大功率点,动态响应快,收敛性好.     

Behavioral and electrophysiological activity of (Z,E)-7,9,11-dodecatrienyl formate,a mimic of the major sex pheromone component of carob moth,Ectomyelois ceratoniae

The behavioral and electrophysiological activity of a mimic [(Z,E)7,9,11-dodecatrienyl formate] of the major sex pheromone component [(Z,E) 9,11,13-tetradecatrienal] of carob moth was assessed. Wind-tunnel bioassays demonstrated that the formate was as effective as natural gland extracts, and significantly more effective than the trienal alone or than the trienal blended with two minor pheromone components, in evoking source contact. Dispensers containing the formate were as effective as trienal-containing blend lures in attracting males when placed at the same dosage in traps in date gardens. Single-cell recordings showed that at least two olfactory neurons, differentiated by spike amplitude, are located in the long trichoid hairs on male carob moth antennae. Dose-response relationships indicated that puffs from cartridges loaded with at least 0.1 g of the formate or of the trienal were necessary to elicit spiking by either the small or the large-spiking cell within a sensillum. Cross-adaptation studies demonstrated that both compounds stimulated the same large-spiking cell. The frequencies of spikes evoked from the large cell when stimulated by emissions from 0.1-g, 1-g, or 10-g cartridges of either the formate or the trienal were not significantly different, suggesting that the formate is an effective mimic of the trienal at the antennal receptor cell level.