oalib

OALib Journal期刊

ISSN: 2333-9721

费用:99美元

投稿

时间不限

2019 ( 44 )

2018 ( 450 )

2017 ( 515 )

2016 ( 667 )

自定义范围…

匹配条件: “吴仍康” ,找到相关结果约89964条。
列表显示的所有文章,均可免费获取
第1页/共89964条
每页显示
基于机器学习方法的上证综合指数的预测分析
Forecast Analysis of Shanghai Composite Index Based on Machine Learning Method
 [PDF]


Hans Journal of Data Mining (HJDM) , 2016, DOI: 10.12677/HJDM.2016.61001
Abstract:
上证综合指数是广大投资者关注的重要指数。上证综合指数不仅反映了我国股票市场的基本状况,同时对我国经济走向也具有重要的导向作用。对上证综合指数的预测分析以及趋势研判对稳定市场、引导投资者具有重大意义。而股票市场数据是典型的非线性系统,传统统计学预测方法在处理时预测精度较低。本文综合运用R软件并结合目前机器学习领域最新的六种方法——决策树、boosting、bagging、随机森林、支持向量机、神经网络分别对训练集进行训练,得到相应模型。并建立相应的十折交叉验证集计算出每种方法的预测均方误差进行对比。筛选出效果较好的模型,并对预测数据与真实数据进行数据可视化对比。对结果分析可知,随机森林、支持向量机两种机器学习方法拟合效果较好,且精度高。
The Shanghai composite index is an important index that general investors pay close attention to. Shanghai composite index, which not only reflects the basic situation of the stock market in our country, but also takes an important guiding role to our economy. Prediction of Shanghai composite index and trend analysis plays an important role to stabilize market and guide investors. And stock market data are a typical nonlinear system; traditional statistical forecasting methods predict a low accuracy. In this paper, we use R software comprehensively and combine with the latest six kinds of methods in machine learning field, decision tree, boosting, bagging, random forests, support vector machine (SVM), neural network to train the training set, respectively, get the corresponding model. And set up the corresponding ten-fold cross validation to calculate the prediction mean square error of each method for comparison. Select the model with better effect, and make a visualized comparison between prediction data and real data. Analysis shows that the results of random forests, SVM are more fitting, and have high precision.
基于岭回归的证券指数的预测分析—以上证综合指数为例
Forecast Analysis of Securities Index Based on Ridge Regression—In Case of Shanghai Composite Index
 [PDF]


Business and Globalization (BGlo) , 2016, DOI: 10.12677/BGlo.2016.42007
Abstract:
证券市场的是衡量一个国家总体经济发展水平的重要指标。而证券指数是对各个证券市场总体水平的反映,是广大投资者关注的重要指数。它不仅反映了证券市场的基本状况,同时对经济走向也具有重要的导向作用。对证券指数的预测分析以及趋势研判对稳定市场、引导投资者具有重大意义。然而,在建立相应统计预测模型时自变量之间常常出现严重的多重共线。本文通过对模型进行改进,综合运用岭回归解决了自变量间多重共线性的问题。并且以我国上证综合指数的真实数据为例,将改进后岭回归模型的预测值与真实值进行对比,拟合结果较好。
Security market is an important indicator to measure a country’s overall level of economic devel-opment. The securities index is a reflection of the overall level of the securities market, and it is an important index of the majority of investors concerned. It not only reflects the basic situation of the securities market, but also plays an important role in guiding the economic trend. Prediction of securities index and trend analysis plays an important role to stabilize market and guide investors. However, serious multi-collinearity between variables often appears in the establishment of the corresponding statistical prediction model. In this paper, the model is improved, and the problem of multi-collinearity between independent variables is solved by using ridge regression. And taking the real data of Shanghai Composite Index as an example, the predicted value of the improved ridge regression model is compared with the true value, and the fitting result is better.
基于机器学习方法的无线信道特征的识别与区域划分
Identification and Region Division of Wireless Channel Characteristics Based on Machine Learning Method
 [PDF]


Journal of Antennas (JA) , 2016, DOI: 10.12677/JA.2016.51001
Abstract: 本文运用机器学习方法,对无线信道的特征建立了相应的决策树分类模型。并且对所建立的决策树模型运用真实信道数据进行了测试检验,发现分类效果较好。因此,该机器学习模型对无线信道特征的识别具有较高的准确性。进而可以运用该模型对无线信道数据进行有效的区域划分,并且该模型还具备了一定的统计学意义。
In this paper, using the machine learning method establishes the corresponding decision tree classification model for the characteristics of wireless channel. Using the real channel data tests the decision tree model and finds the classification results are better. Therefore, this machine learning method recognition model has high accuracy for wireless channel characteristics. Then we can use the model to divide the wireless channel data into region effectively, and the model also has statistical significance.
基于统计分析的国民体质综合指数研究及相关建议
Based on the Statistical Analysis of the National Constitution Index Research and Related Recommendations
 [PDF]

罗婷,
Advances in Physical Sciences (APS) , 2016, DOI: 10.12677/APS.2016.43010
Abstract:
国民体质是一个国家综合国力和国家竞争力的重要组成部分,是我国全面建设小康社会和建设体育强国的保障。国民体质的强弱,关系到国家和民族的兴衰存亡。我国采取了一系列增强国民体质的策略:完善相关的法律法规、建立国民体质监测系统、力促全面健身并提供健身场所、加强体育产业的硬件设施等。本文以统计局发布《2014年国民体质监测公报》中的“国民体质综合指数”数据为研究对象,运用统计方法来分析各省市的体质情况并给出各省市的相关建议。本文研究意义在于,运用统计方法来分析国民体质综合指数,反映出各省市的体质情况并提出相关建议。
The national physical fitness is an important part of the overall national strength and national competitiveness, and it is the guarantee of our country to build a moderately prosperous society as well as a sports power. The strength and weakness of the national physical fitness have a sig-nificant influence on the rise and fall of the state and the nation. China has adopted a series of strategies to enhance the national physical fitness: the improvement of relevant laws and regula-tions, the establishment of national physique monitoring system, the promotion of nationwide fitness with providing fitness venues and the enhancement of the hardware facilities in sports industry. This paper has studied “2014 National Physique Monitoring Bulletin” issued by the Bureau of Statistics and focused on the “national physical fitness index”, which helps in analyzing the people’s physical conditions from different provinces and cities by statistical methods, and providing recommendations respectively. The meaning of this paper is to reflect the civil physical fitness conditions of each province and city and provide relevant recommendations by analyzing the national physical fitness index in the statistical approach.
t分布及其应用的探讨
Discussion on t-Distribution and Its Application
 [PDF]

申小征,
Statistics and Applications (SA) , 2015, DOI: 10.12677/SA.2015.44036
Abstract: t分布是统计学中的一类重要分布,它在区间估计和假设检验中有很重要的应用,具体包括单样本的区间估计、独立两样本的区间估计、单样本的均值检验、两样本均值差的t检验。文中详细介绍了t分布定义性质及其在产品寿命、渔业、农业等实际生活中的应用,并借助统计软件SPSS实现单样本t检验和两样本t检验。
The t-distribution is an important distribution in statistics, it has very important application in the interval estimation and hypothesis test, including t-test in the interval estimation of single samples, two samples of independent interval estimation, one sample of the mean test, two sample mean difference. The paper introduces the nature of t-distribution and its application in real life, such as product life, fishery, agriculture, and also achieves a single sample and two sample t-test in the test of hypothesis with the help of the statistical software SPSS.
基于MATLAB软件的无线信道“指纹”特征建模
The Wireless Channel “Fingerprint” Feature Modeling Based on MATLAB Software
 [PDF]

, 敬林, 申小征
Journal of Antennas (JA) , 2015, DOI: 10.12677/JA.2015.44004
Abstract: 本文针对移动通信中的无线信道特征进行综合分析,通过运用Matlab软件求解出离散线性时变系统以及滤波器的相关参数作为无线信道最主要的特征。同时,提取了多径时延扩展、Doppler扩展以及角度扩展等重要特征指标。因此,本文从离散线性时变系统的信道特征、时间、频率、空间四个维度分别提取了无线信道的信道系数、多径时延扩展(相干带宽)、Doppler扩展(相干时间)以及角度扩展(相干距离)四个特征指标,较为完整地刻画出了无线信道的“指纹”特征并具有实际的物理意义。
According to the wireless channel characteristics of the mobile communication, this paper took it into comprehensive analysis, using the MATLAB software to solve the channel parameters of the discrete linear system and filter parameters as the main feature for wireless channel. Then the multipath time delay spreading, angle spreading and Doppler spreading as the important charac-teristic indexes were extracted. Therefore, this article extracted the channel coefficients of the wireless channel, multipath time delay spreading (coherence bandwidth), Doppler spreading (coherent time) and angle spreading (coherence distance) from four dimensions of channel, time, frequency, and space of discrete linear time variable systems. These four indicators can depict the “fingerprint” feature of the wireless channel completely and show the actual physical significance.
厦门市售甲鱼蛋携带病原菌情况初步调查
Primary Investigation of Pathogenic Bacteria from Sold Terrapin Eggs in Xiamen
 [PDF]

玉娟, 孔繁德, 徐淑菲,
Advances in Microbiology (AMB) , 2014, DOI: 10.12677/AMB.2014.32005
Abstract:

目的:了解厦门市售甲鱼蛋携带病原菌情况。方法:按照病原菌的检测标准进行分离培养,获得纯培养物后,用基质辅助激光解析电离飞行时间质谱(MALDI-TOF-MS)结合相应的诊断血清及PCR方法进行鉴定。结果:自7批厦门市售甲鱼蛋中分离到了16个属26种共76株细菌,甲鱼蛋带菌率为100%,多重带菌情况严重。结论:该次甲鱼蛋的检验结果表明,甲鱼蛋所携带病原菌种类广,大部分为多重带菌,部分携带致病菌或条件致病菌。因此必须做好甲鱼蛋的检疫工作,以确保人们身体健康和养殖业的健康持续发展。
Objective: To explore the situation of pathogens of Xiamenlocal terrapin eggs. Methods: The pathogens were isolated with standard methods. The pure cultures isolated from terrapin eggs were further specified by MALDI-TOF-MS, serological test and PCR methods. Results: 100% of 7 batches of Xiamen local terrapin eggs were contaminated with pathogenic bacteria according to MALDI- TOF-MS. 76 strains of isolated pathogenic bacteria fell into 16 genera and 26 species. All of the terrapin eggs carried five or more pathogenic bacteria. Conclusion: The results suggest that high- contamination rate, broad genera, coexistence of multiple species and isolation of pathogenic bacterium are very common phenomena. It’s very necessary to enforce surveillance of pathogenic bacteria in terrapin eggs.

电网规划智能辅助决策系统的设计与实现
周鲲鹏,,颜炯,重庆,,林海英,刘秀坤
电力系统自动化 , 2013, DOI: 10.7500/AEPS201202158
Abstract: 为有效应对电网规划面临的数据量大、决策复杂、技术手段匮乏的局面,文中设计并实现了一种基于平台化设计、具有可视化及高级决策支持功能的电网规划智能辅助决策系统。该系统与地理信息系统(GIS)密切融合,内嵌一体化数据库,具有适应性评估、投资优先级决策、差异化规划及电网仿真软件数据接口等功能。在辅助决策过程中,通过电网调度模拟实现电源电网协调评估,仿照静态安全分析的原理确定项目投资优先级,利用图论算法识别电网骨干网架,借助新开发的仿真软件数据接口从规划方案提取数据进行拓扑重构及模型数据初始化。系统的设计与开发立足于工程实践,软件成果在湖北电网的初步应用验证了文中的设计思路和实现方法。
戏曲文化的空间扩散及其文化区演变——以国家非物质文化遗产淮剧为例
,
地理研究 , 2009, DOI: 10.11821/yj2009050027
Abstract: 基于文化地理学理论,运用传统定性与定量互补的研究方法,以淮剧为例进行了分析。首先,淮剧的传播和发展大致分为四个阶段,第一、二阶段以扩展扩散为主,第三阶段以迁移扩散为主,第四阶段主要体现出传染扩散的效应;淮剧扩散的空间结构表现为由文化源地沿着多条交通线扩散,并逐渐形成了苏北和上海的双中心结构。其次,基于现有的研究提出了淮剧空间扩散模型,揭示了灾变事件导致的大规模移民是扩散的主要因素。第三,以县、区为基本空间单元,将淮剧文化区划分为核心区、外围区和过渡区,总结出淮剧文化区存在着南、北两大文化亚区和北亚区内又分化出东、中、西三片子文化亚区的空间分异特征。最后,通过选取典型年份下专业淮剧团的数量变化来考察淮剧文化区的演变轨迹,发现核心文化区十分稳定地集中在盐城和淮安两市,外围区和过渡区呈现先扩张后收缩的空间趋势。
后 序

华南师范大学学报(自然科学版) , 2014,
Abstract:
第1页/共89964条
每页显示


Home
Copyright © 2008-2017 Open Access Library. All rights reserved.