Feature Selection Using Grey Wolf Optimization with Random Differential Grouping

Big data are regarded as a tremendous technology for processing a huge variety of data in a short time and with a large storage capacity.The user’s access over the internet creates massive data processing over the internet.Big data require an intelligent feature selection model by addressing huge varieties of data.Traditional feature selection techniques are only applicable to simple data mining.Intelligent techniques are needed in big data processing and machine learning for an efficient classification.Major feature selection algorithms read the input features as they are.Then,the features are preprocessed and classified.Here,an algorithm does not consider the relatedness.During feature selection,all features are misread as outputs.Accordingly,a less optimal solution is achieved.In our proposed research,we focus on the feature selection by using supervised learning techniques called grey wolf optimization(GWO)with decomposed random differential grouping(DrnDG-GWO).First,decomposition of features into subsets based on relatedness in variables is performed.Random differential grouping is performed using a fitness value of two variables.Now,every subset is regarded as a population in GWO techniques.The combination of supervised machine learning with swarm intelligence techniques produces best feature optimization results in this research.Once the features are optimized,we classify using advanced kNN process for accurate data classification.The result of DrnDGGWO is compared with those of the standard GWO and GWO with PSO for feature selection to compare the efficiency of the proposed algorithm.The accuracy and time complexity of the proposed algorithm are 98%and 5 s,which are better than the existing techniques.

Some Methods to Maximize Extraction of Scientific Knowledge from Parallel Group Randomized Trials

The amount of scientific knowledge from randomized parallel group trials have been improved by the CONSORT Guideline, but important intelligence with important clinical implications remains to be extracted. This may though be obtained if the conventional statistical significance testing is supplied by 1) Addition of an unbiased and reproducible quantification of the magnitude or size of the clinical significance/importance of a difference in treatment outcome;2) Addition of a quantification of the credulity of statements on any possible effect size and finally;3) Addition of a quantification of the risk of committing an error when the null hypothesis is either accepted or rejected. These matters are crucial to proper conversion of trial results into good usage in every-day clinical practice and may produce immediate therapeutic consequence in quite opposite direction to the usual ones. In our drug eluting stent trial “SORT OUT II”, the implementation of our suggestions would have led to immediate cessation of use of the paclitaxel-eluting stent, which the usual Consort like reporting did not lead to. Consequently harm to subsequent patients treated by this stent might have been avoided. Our suggestions are also useful in cancer treatment trials and in fact generally so in most randomized trial. Therefore increased scientific knowledge with immediate and potentially altered clinical consequence may be the result if hypothesis testing is made complete and the corresponding adjustments are added to the CONSORT Guideline—first of all— for the potential benefit of future patients.

Group Exercise versus Personal Training for Prostate Cancer Patients: A Pilot Randomized Trial

Background: Previous studies have demonstrated psychosocial and physical benefit from exercise for older men treated with androgen deprivation therapy (ADT) for prostate cancer (PCa). To date, different intervention delivery methods have not been assessed. This study compared the effect of group-based exercise (GBE) to personal training (PT) in men undergoing ADT for PCa. Methods: 13 participants (mean age = 68.2, SD = 7.2) were randomly assigned to GBE or PT for 8 weeks. Participants exercised for 60 minutes three times per week at a moderate-vigorous intensity. Results: 10 participants completed the intervention. At post-intervention, the PT group improved: fatigue, systolic BP, waist circumference, body fat percentage, and maximal leg strength;participants in the GBE group improved leg strength. At 8 weeks, maximal upper body strength in the PT group was greater than the GBE group. There were no adverse events associated with moderate-high intensity training in this population of older men. Conclusion: PT may be more efficacious than GBE in improving several physical fitness outcomes and fatigue in men with PCa who are androgen deprived. Due to the small sample size and attrition, these results require cautious interpretation and confirmation from adequately powered trials.

组织蛋白酶与骨密度的因果关系:双向孟德尔随机化分析

背景:既往研究表明,中老年人体内组织蛋白酶K水平可通过影响骨密度来干预骨质疏松的发生和发展,但组织蛋白酶家族与其他人群骨密度之间是否存在因果关系仍未知。目的:探讨组织蛋白酶与骨密度的因果关系。方法:从IEU Open GWAS数据库提取与8种组织蛋白酶相关的遗传位点作为工具变量,以5个年龄段人群的骨密度作为结局。通过双向孟德尔随机化分析,评估组织蛋白酶与骨密度的因果关系。使用Cochran’s Q检验评估遗传工具变量的异质性,使用MR-Egger截距检验评估多效性,使用留一法评估作为工具变量的单核苷酸多态性对暴露和结局因果关系影响的敏感性。结果与结论:①正向孟德尔随机化的逆方差加权法结果显示,组织蛋白酶H与>45岁且≤60岁人群的骨密度呈负相关[OR(95%CI)=0.965(0.94-0.99),P=0.04],组织蛋白酶Z与>30岁且≤45岁人群的骨密度呈负相关[OR(95%CI)=1.06(1.00-1.11),P=0.03];②敏感性分析结果显示因果关系稳定,MR-Egger截距分析未检测到潜在的水平多效性;③反向孟德尔随机化结果显示,骨密度对组织蛋白酶无显著反向作用;④上述结果证实,组织蛋白酶对部分年龄段人群骨密度会造成影响,可能会增加骨质疏松症的发病风险,应给予更多关注。

Observations of Freak Waves in Random Wave Field in 2D Experimental Wave Flume

Long time series of wave field are experimentally simulated by JONSWAP spectra with random phases in a 2D wave flume. Statistic properties of wave surface, such as significant wave height, skewness and kurtosis, are analyzed, and the freak wave occurrence probability and its relations with Benjamin-Feir index （BFI） are also investigated. The results show that the skewness and the kurtosis are significantly dependent on the wave steepness, and the kurtosis increases along the flume when BFI is large. The freak waves are observed in random wave groups. They occur more frequently than expected, especially for the wave groups with large BFI.

An Adaptive Grouping Scheme in Ultra-Dense IEEE 802.11ax Network Using Buffer State Report Based Two-Stage Mechanism

IEEE 802.11ax,which is an emerging WLAN standard,aims at providing highly efficient communication in ultra-dense wireless networks.However,due to a large number of stations(STAs)in the ultra-dense device deployment scenarios,the potentially high packet collision rate significantly decreases the communication efficiency of WLAN.In this paper,we propose an adaptive STA grouping scheme to overcome this dense network challenge in IEEE 802.11ax by using Buffer State Report(BSR)based Two-stage Mechanism(BTM).In order to achieve the optimal efficiency of BSR delivery,we analyze the functional relationship between STA number in group and Resource Unit(RU)efficiency.Based on this analysis results,an adaptive STA grouping algorithm with variable group size is proposed to achieve efficient grouping in BTM.The numerical results demonstrate that the proposed adaptive BTM grouping algorithm significantly improves the BSR delivery efficiency and the throughput of overall system and each STA in the ultra-dense wireless network.

Secure Passwords Using Combinatorial Group Theory

Password security is a crucial component of modern internet security. In this paper, we present a provably secure method for password verification using combinatorial group theory. This method relies on the group randomizer system, a subset of the MAGNUS computer algebra system and corrects most of the present problems with challenge response systems, the most common types of password verification. Theoretical security of the considered method depends on several results in asymptotic group theory. We mention further that this method has applications for many other password situations including container security.

Implementation of an open-source customizable minimization program for allocation of patients to parallel groups in clinical trials

Current minimization programs do not permit full control over different aspects of minimization algorithm such as distance or probability measures and may not allow for unequal allocation ratios. This article describes the implementation of “MinimPy” an open-source minimization program in Python programming language, which provides full customizetion of minimization features. MinimPy supports naive and biased coin minimization together with various new and classic distance measures. Data syncing is provided to facilitate minimization of multicenter trial over the network. MinimPy can easily be modified to fit special needs of clinical trials and in particular change it to a pure web application, though it currently supports network syncing of data in multi-center trials using network repositories.

扩大中等收入群体路径探析——基于随机森林模型画像

本文将扩大中等收入群体对象细分为“提低、入中、稳中”三个层级,运用随机森林模型对不同收入群体的特征进行画像,基于特征指标重要度排序确定影响各收入群体的主要因素,进而设计差异化扩中路径。研究发现,年龄、工资性收入、经营性收入和转移性收入在偏低收入群体与潜在中等收入群体之间呈现较大的分布差异,是“提低”环节需要重点关注的特征;食品支出、居住支出、交通通讯支出、教育文化娱乐支出和其他支出对推动潜在中等收入群体越级、实现低收入者“入中”有显著影响;受教育程度、社会参与和家庭规模与新增中等收入群体脆弱性程度紧密相关,是巩固扩中成果必须考虑的因素;医疗保健支出、衣着支出、社会公平、社会信任、职业类型、家庭劳动力占比和生活困难则在低收入群体向中等收入行列迈进的全过程均有重要作用。应该建立科学的政策扶持机制,分类制定差异化政策,打造以保障劳动报酬和转移收入为基石、以激活经营和财产收入与社会参与为支撑、以优化教育水平与家庭劳动结构为牵引、以提升消费层次与生活质量为导向的多层次、立体化扩中平台。

A RING SIGNATURE SCHEME OVER BRAID GROUPS

Quantum algorithms bring great challenges to classical public key cryptosystems, which makes cryptosystems based on non-commutative algebraic systems hop topic. The braid groups, which are non-commutative, have attracted much attention as a new platform for constructing quantum attack-resistant cryptosystems. A ring signature scheme is proposed based on the difficulty of the root extraction problem over braid groups, which can resist existential forgery against the adaptively cho-sen-message attack under the random oracle model.

基于分群游走机制的灰狼优化算法的FPRM逻辑电路面积优化

针对基于XNOR/OR的固定极性Reed-Muller电路(FPRM)逻辑电路面积优化方法搜索最优解速度较慢,易陷入局部最优等问题,提出一种新的FPRM逻辑电路面积优化方法,利用基于分群游走机制的灰狼优化算法(GDGWO)搜索电路面积最小的FPRM电路.GDGWO在初始化种群后,采取“轮盘赌”选择算法选出合适的新群体头狼,以提高种群多样性;执行种群分裂机制,防止因原始种群陷入局部最优而降低算法的鲁棒性;在分群搜索开发过程中引入改进后的随机游走策略,使灰狼种群能够更快地包围猎物,提高算法的收敛速度.基于北卡罗来纳微电子中心Benchmark测试电路的实验结果表明,GDGWO与粒子群算法相比,电路面积优化率提升57.42%;与黑猩猩算法相比,提升41.94%;与原始灰狼优化算法相比,提升43.68%.

基于随机有限集滤波器的可分辨群目标跟踪技术研究综述

群目标跟踪在救灾搜救、海陆防御和战场作战等领域展现出广阔的应用前景。与传统多目标跟踪不同,群目标跟踪不仅涉及对多个个体目标的跟踪,还涉及对一个群体目标的跟踪。在群体中各个子目标需要同步运动以避免碰撞,同时群体中的子目标数量和群结构还将随着时间推移而改变。根据子目标数量和传感器分辨率的不同,群目标跟踪问题包含可分辨、不可分辨、部分可分辨以及部分不可分辨群目标跟踪等多个类别。其中,可分辨群目标跟踪问题需要同时对群体结构、群内子目标交互和数目进行估计。现有研究主要关注基于传统数据关联和随机有限集滤波器的可分辨群目标跟踪方法,其中,基于随机有限集滤波器的方法通过将多个目标状态联合建模成随机有限集,缓解了数据关联问题,从而可更好地适应跟踪场景。为更好地展示群目标跟踪方法的研究进展,综述了近年来基于随机有限集滤波器的可分辨群目标跟踪的若干代表性方法,包括基于多目标多伯努利滤波器、基于标签随机有限集滤波器和基于泊松多伯努利混合滤波器的群目标跟踪方法。这些方法在处理可分辨群目标跟踪问题时展示出了显著的优势。最后,探讨了存在的问题和未来的发展方向。

DEGREE:一种基于Delaunay三角的任意群目标外形识别方法

集群目标相比单一甚至多目标表现出复杂时变集群特性,其外形估计与评价颇具挑战性。针对任意形状的集群目标外形估计与评价难题,本文提出了一种基于数据驱动的多传感器集群目标群形状建模与识别方法,以及一种群目标外形拟合度评判指标。所提算法由三个部分组成:首先,采用信息洪泛(Flooding)方法实现强连接的多传感器对视场中目标信息的采集与传播;其次,采用密度峰值聚类实现观测数据的聚类;最后,采用改进Delaunay三角网络算法实现群目标外形的拟合。所提群外形拟合度指标可用于对群目标外形估计准确度定量评价。通过与超曲面、随机矩阵等经典方法进行比较,证实了所提出算法的有效性和可靠性。

基于群结构集成势均衡多目标多伯努利滤波器的群目标跟踪算法

群目标跟踪已被广泛应用于作战对抗、自动驾驶、低空防御等各个军民领域。群目标是指由多个单目标组成,并以相同的速度或方向进行移动的一组或多组目标集群。鉴于随机有限集(Random Finite Set,RFS)滤波器在处理多目标数据关联方面的优势,现有的群目标跟踪算法大多基于RFS滤波器。然而,这些滤波器在对群目标进行跟踪时大多忽略了各目标之间的关联、依赖关系等问题,为此,提出了一种基于群结构集成的势均衡多目标多伯努利(Cardinality Balanced Multi-target Multi-Bernoulli,CBMeMBer)滤波器的群目标跟踪算法。具体而言,首先通过邻接矩阵对目标群结构进行估计,即将群目标看作无向图,利用各目标之间的距离来估计群目标的邻接矩阵,进而将群目标划分为多个子群。并根据各子群中目标的运动状态,将其划分为群中心和群成员两种类别,分别建立了运动方程。而后在预测步骤中,利用估计的群结构来对目标状态进行预测。特别地,在滤波器的高斯混合实现步骤中,多个高斯分量被用来拟合相对应的各伯努利分量,但过多高斯分量的存在会降低对群目标状态估计的准确性,从而降低群结构估计的准确性,因此,在状态提取阶段,本文所提算法对高斯分量进行修剪,即对更新步骤后的每个伯努利分量中所包含的高斯分量进行筛选,只保留一个权重最大的高斯分量。最后,仿真结果表明,本文所提算法实现了对群目标的稳定跟踪,且跟踪性能优于传统的CBMeMBer滤波器。

Theoretical Quantization of Exact Wave Turbulence in Exponential Oscillons and Pulsons

In a preceding paper, the theoretical and experimental, deterministic and random, scalar and vector, kinematic structures, the theoretical and experimental, deterministic-deterministic, deterministic-random, random-deterministic, random-random, scalar and vector, dynamic structures have been developed to compute the exact solution for wave turbulence of exponential pulsons and oscillons that is governed by the nonstationary three-dimensional Navier-Stokes equations. The rectangular, diagonal, and triangular summations of matrices of the turbulent kinetic energy and general terms of numerous sums have been used in the current paper to develop theoretical quantization of the kinetic energy of exact wave turbulence. Nested structures of a cumulative energy pulson, a deterministic energy pulson, a deterministic internal energy oscillon, a deterministic-random internal energy oscillon, a random internal energy oscillon, a random energy pulson, a deterministic diagonal energy oscillon, a deterministic external energy oscillon, a deterministic-random external energy oscillon, a random external energy oscillon, and a random diagonal energy oscillon have been established. In turn, the energy pulsons and oscillons include deterministic group pulsons, deterministic internal group oscillons, deterministic-random internal group oscillons, random internal group oscillons, random group pulsons, deterministic diagonal group oscillons, deterministic external group oscillons, deterministic-random external group oscillons, random external group oscillons, and random diagonal group oscillons. Sequentially, the group pulsons and oscillons contain deterministic wave pulsons, deterministic internal wave oscillons, deterministic-random internal wave oscillons, random internal wave oscillons, random wave pulsons, deterministic diagonal wave oscillons, deterministic external wave oscillons, deterministic-random external wave oscillons, random external wave oscillons, random diagonal wave oscillons. Consecutively, the wave pulsons and oscillons are composed of deterministic elementary pulsons, deterministic internal elementary oscillons, deterministic-random internal elementary oscillons, random internal elementary oscillons, random elementary pulsons, deterministic diagonal elementary oscillons, deterministic external elementary oscillons, deterministic-random external elementary oscillons, random-deterministic external elementary oscillons, random external elementary oscillons, and random diagonal elementary oscillons. Symbolic computations of exact expansions have been performed using experimental and theoretical programming in Maple.

刀切法在我国劳动力调查方差估计中的应用

我国劳动力调查抽样设计复杂,采用通常方法进行方差估计比较困难。本文提出使用刀切法。在使用刀切法时需要划分随机组,文中提出三种划分随机组的方法并对它们作了比较。最后,对我国的失业人数与失业率应用刀切法进行方差估计。

带记忆功能的混合蛙跳算法

针对基本混合蛙跳算法收敛速度慢、优化精度低的问题、提出了带记忆功能的混合蛙跳算法。引入自适应学习因子,使算法在迭代初期加速收敛并不断拓展新的搜索区域,在迭代后期能够在全局最优邻域进行精细搜索,从而保持了开发与探索的平衡,并提高了收敛精度;采用随机分组策略平衡各子群的寻优能力,维持了种群的多样性。对6个测试函数进行了优化实验,并与基本混合蛙跳算法和相关文献中的改进算法进行比较,结果表明了该算法具有更好的优化性能。

面向射电日像仪的随机组结构剖析与文件设计

我国新一代厘米—分米波日像仪(Chinese Spectral Radio Heliograph,CSRH)已经进入了试观测调试阶段,设备误差修正、试观测数据的处理成为当前CSRH的重要工作。其中,有效地保存与快速处理试观测数据是数据处理的前提。在调研当前国内外射电干涉观测设备的基础上,深入分析了Aips++、CASA等当前主流射电天方数据处理软件对数据格式的支持情况,分析了射电天文领域的随机组(UVFITS)格式,给出了满足射电日像仪数据的随机组格式。实验表明,所生成的UVFITS文件可以被主流软件正确处理。对CSRH的研制起到了较好的推动作用,也对国内正在开展的其它大型射电观测数据存储有参考价值。

山东电网基于WAMS的低频振荡统计与评估

提出一种基于广域测量系统(WAMS)的方法对日常扰动引起的小幅振荡进行在线识别和统计,从而可以在系统正常运行中,利用实测数据找到系统的固有振荡模式,对其中易激发的危险模式进行节点同调分群、振荡中心识别和贡献因子计算等模态分析并告警,从而补充或纠正了根据数学模型和特定工况进行振荡分析时,由于模型和参数不准确导致的遗漏和误差。以这一功能在山东电力调度中心应用的实例说明了该方法的有效性和推广应用的重要性。