共查询到20条相似文献，搜索用时 348 毫秒
1.
2.
经济系统是一个极端复杂的系统,系统内部影响因素众多且各个因素之间有着比较复杂的关系,是具有高度不确定的非线性系统。针对中国煤炭企业经济预测的问题,由于实际情况错综复杂,各种预测模型的精确度都不是很理想,所以难以在实际中应用。为了解决这一问题,以中国煤炭企业1999—2008年时间段的净资产收益率为样本,分析了几种影响因素,依据BP神经网络模型的理论和方法,从而建立净资产收益率的经济预测的模型。实例分析表明采用BP神经网络模型较好地得到了预测点的预测结果,更适用于经济预测。 相似文献
3.
随着神经网络在数据分析、预测及生产控制中的应用,神经网络的优化学习成为研究的一个重要课题.通过探讨BP神经网络模型的建立过程,针对BP神经网络的模型优化问题进行了详细研究.并通过对银行客户分类的仿真实验证明,优化模型能够有效地提高BP神经网络的收敛速度及预测精度. 相似文献
4.
文章基于2022年“关于高考改革的调查”获取的33470份对高考有深切体会的大学生样本，按70%、15%、15%的比例随机将样本分为训练组、验证组和测试组，并用训练组构建了一个泛化性能较好、预测精度较高的BP神经网络模型，结果模型通过了验证组和测试组的检验。研究发现：在三种选科模式下，影响学生选科的基本因素具有较强的一致性。其中，首要是个人因素，其次是家庭因素，最后是学校因素和社会因素。在重要性排名中，前三的具体因素都是性别、学生成绩和就业形势；家庭因素与学生选科自由度呈正相关，但作用有限；选科自由度与学校因素的重要性呈负相关；社会因素对学生选科的影响值得进一步关注。基于此，文章从高考改革的前期筹备、实施进程和后续跟进三个维度提出了相应的对策建议。 相似文献
5.
公路客运量和货运量预测是一个复杂的非线性问题,由于影响因素较多,难以用普通的数学方法建模,而建立BP神经网络可以表达这些非线性问题。根据公路客运量货运量历史数据及其相关影响因素数据建立了BP神经网络预测模型。利用实际数据确定网络输入与输出样本,对BP神经网络预测系统进行训练和预测。通过对网络输出预测结果与实际数据的分析,验证了BP神经网络预测系统的精确性和方便性,提高了公路客运货运预测的精确性。 相似文献
6.
鉴于BP神经网络、RBF神经网络在城市供水量预测精度上的不足,利用粒子群算法优化两者相关参数,实现更高预测精度,并通过建立BP神经网络、RBF神经网络、PSO-BP神经网络、PSO-RBF神经网络分别对城市供水量数据进行仿真预测。最终测试样本统计结果显示：RBF神经网络比BP神经网络平均相对误差（MRE）低约1%,在拟合度（R2）上高约0.014;PSO-BP神经网络比BP神经网络在MRE上降低约1.25%,在R2上提高约0.05;PSO-RBF神经网络比RBF神经网络在MRE上降低约0.3%,在R2上提高约0.072。由此说明RBF神经网络比BP神经网络在城市供水量预测方面更有优势,并且利用粒子群算法优化神经网络模型参数可有效提升神经网络预测精度。 相似文献
7.
刘朋辉 《江西电力职业技术学院学报》2023,(2):10-12
当前现有预测方法对智能电网短期时间内的电力负荷预测存在预测精度低、预测精度受气象条件变化影响等问题,现引入BP神经网络研究智能电网短期电力负荷预测方法：获取智能电网历史运行数据,对数据进行预处理,对样本进行归一化处理;利用BP神经网络构建电力负荷预测模型;建立模型训练网络拓扑结构,训练模型预测性能;完成电网短期电力负荷预测,并在考虑气象因素的情况下对预测进行补偿,得到预测结果。实验证明：新的预测方法在实际应用中预测精度更高,且预测精度不会受到气象条件的影响。 相似文献
8.
唐晓城 《河南职业技术师范学院学报(职业教育版)》2018,(1)
针对大气污染的预测预报问题,在BP神经网络的基础上设计了一个新模型.把BP神经网络的逐次迭代的学习过程,改为批处理计算所有样本的系统误差,再统一修改权值,提高了执行效率.通过6项大气污染指标的预测值和实测值的比较,证明新模型的预测准确率较高,误差率较低. 相似文献
9.
人工神经网络在中长期电力负荷预测中的应用 总被引：3，自引：0，他引：3
设计了一个由输入层、隐含层和输出层组成的三层BP网络模型,利用神经网络高度非线性建模能力,进行电力系统的中长期负荷预测.选取影响电力负荷的一些经济因素作为神经网络的输入变量,并对分别采用单个因素和多个因素的组合作为输入量对预测精度的影响进行了探讨.在多因素组合时对输入量进行了归一化处理.仿真结果证明,使用人工神经网络方法进行中长期电力负荷预测是可行和有效的. 相似文献
10.
应用灰色系统理论计算了铁路货运量与货运量影响因素的关联度,并对其进行了排序。利用MAT-LAB软件,建立铁路货运量的RBF神经网络预测模型,对我国1992-2008年的铁路货运量进行仿真实验。结果表明基于灰色系统理论的RBF神经网络模型预测平均相对误差为0.44%,常规RBF神经网络模型的平均预测误差为1.47%,因此认为基于灰色系统理论的RBF神经网络的铁路货运量预测方法有效可行。 相似文献
11.
Hui An Chang-shuai Wei Oliver Wang Da-hui Wang Liang-wen Xu Qing Lu Cheng-yin Ye 《Journal of Zhejiang University. Science. B》2018,19(12):935-947
Objective
As one of the most popular designs used in genetic research, family-based design has been well recognized for its advantages, such as robustness against population stratification and admixture. With vast amounts of genetic data collected from family-based studies, there is a great interest in studying the role of genetic markers from the aspect of risk prediction. This study aims to develop a new statistical approach for family-based risk prediction analysis with an improved prediction accuracy compared with existing methods based on family history.Methods
In this study, we propose an ensemble-based likelihood ratio (ELR) approach, Fam-ELR, for family-based genomic risk prediction. Fam-ELR incorporates a clustered receiver operating characteristic (ROC) curve method to consider correlations among family samples, and uses a computationally efficient tree-assembling procedure for variable selection and model building.Results
Through simulations, Fam-ELR shows its robustness in various underlying disease models and pedigree structures, and attains better performance than two existing family-based risk prediction methods. In a real-data application to a family-based genome-wide dataset of conduct disorder, Fam-ELR demonstrates its ability to integrate potential risk predictors and interactions into the model for improved accuracy, especially on a genome-wide level.Conclusions
By comparing existing approaches, such as genetic risk-score approach, Fam-ELR has the capacity of incorporating genetic variants with small or moderate marginal effects and their interactions into an improved risk prediction model. Therefore, it is a robust and useful approach for high-dimensional family-based risk prediction, especially on complex disease with unknown or less known disease etiology.12.
周自斌 《合肥联合大学学报》2013,(3):48-51
针对目前大量的商业活动中对客户诚信度评价方法的欠缺,提出了一种新型的预测模型,即将高斯核函数同SVM算法相结合,在非线性多维特征解空间的环境下,也可做到较为准确的评估．通过实践验证,同以往的预测模型相比较,该算法不论在预测准确性以及泛化能力上都有更为突出的表现． 相似文献
13.
Nilsson PM 《Journal of Zhejiang University. Science. B》2011,12(8):611-623
There is overwhelming evidence that hypertension is an important risk factor for both macrovascular and microvascular complications
in patients with diabetes, but the problem remains to identify appropriate goals for preventive therapies. A number of guidelines
(the European Society of Cardiology (ESC)/European Association for the Study of Diabetes (EASD) 2007, the Joint National Committee
(JNC)-VII 2003, the American Diabetes Association (ADA) 2011) have for example advocated a blood pressure goal of less than
130/80 mmHg, but this suggestion has been challenged by findings in recent trials and meta-analyses (2011). The European Society
of Hypertension (ESH) therefore recommends a systolic blood pressure goal of “well below” 140 mmHg. Based on evidence from
both randomized controlled trials (hypertension optimal treatment (HOT), action in diabetes and vascular disease: preterax
and diamicron MR controlled evaluation (ADVANCE), action to control cardiovascular risk in diabetes (ACCORD)) and observational
studies (ongoing telmisartan alone and in combination with ramipril global endpoint trial (ONTARGET), international verapamil-trandolapril
study (INVEST), treat to new targets (TNT), and the National Diabetes Register (NDR)), it has been shown that the benefit
for stroke reduction remains even at lower achieved blood pressure levels, but the risk of coronary events may be uninfluenced
or even increased at lower systolic blood pressure levels. In a recent meta-analysis, it was therefore concluded that the
new recommended goal should be 130–135 mmHg systolic blood pressure for most patients with type 2 diabetes. Other risk factors
should also be controlled with a more ambitious strategy applied in the younger patients with shorter diabetes duration, but
a more cautious approach in the elderly and frail patients with a number of vascular or non-vascular co-morbidities. In patients
from East Asia, such as China, the stroke risk is relatively higher than the risk of coronary events. This must also be taken
into consideration for individualized goal setting in relation to total risk, for example in patients from stroke-prone families.
In conclusion, the current strategy is to have a more individualized approach to risk factor control in patients with type
2 diabetes, also relevant for blood pressure control. 相似文献
14.
在混合式教学模式基本流程、在线开放课程学习质量评价逻辑的基础上,构建了基于数据驱动的在线开放课程学习质量评价体系。评价体系从课前学情预测、课中迭代监测、课后反馈提升等维度,对影响学习质量的14个因素进行了深入挖掘分析。最后将本评价体系应用在"C语言程序设计"课程中,研究结果表明:投入度高的学习者其学习参与度越高,学习成绩越好;学习能力强的学习者其创新能力并不一定强;在线开放课程中实施混合式教学对学习者顺利完成学习目标具有重要保障作用。 相似文献
15.
Liu Yanwen Zhao Chunyang 《东南大学学报》2008,(Z1)
To establish a financial early-warning model with high accuracy of discrimination and achieve the aim of long-term prediction, principal component analysis (PCA), Fisher discriminant, together with grey forecasting models are used at the same time. 110 A-share companies listed on the Shanghai and Shenzhen stock exchange are selected as research samples. And 10 extractive factors with 89.746% of all the original information are determined by applying PCA, which obtains the goal of dimension reduction without information loss. Based on the index system, the early-warning model is constructed according to the Fisher rules. And then the GM(1,1) is adopted to predict financial ratios in 2004, according to 40 testing samples from 2000 to 2003. Finally, two different methods, a self-validated and a forecasting-validated, are used to test the validity of the financial crisis warning model. The empirical results show that the model has better predictability and feasibility, and GM(1,1) contributes to the ability to make long-term predictions. 相似文献
16.
提出一种基于长短期神经网络的深度学习预测模型,依托现场数据对土仓压力进行预测。结果表明,在5个可控因素的基础上,增加与土仓压力具有相关关系的不可控因素作为输入,评价指标平均绝对误差、均方误差分别降低了0.901%、0.021%,校正后的决定系数提高了16%,为土仓压力的精准预测和设定提供了借鉴。 相似文献
17.
对于银行、P2P等金融机构而言,如何在扩大业务规模的同时,有效控制并合理防范信用风险尤为重要。基于LightGBM算法,根据借款申请人提供的相关个人信息,建立分类预测模型,对借款人是否会逾期、是否该发放贷款进行预测研究。实验结果表明,相较于普通决策树算法,LightGBM预测精度提升了40.8%,且具有较好的鲁棒性,可满足信用评估要求。基于LightGBM的信用评估模型不仅拥有更快的训练速度和更高的训练效率,同时还占用更少的内存,具有支持数据并行处理能力。利用该模型可对用户信用风险进行较为准确的预测,对贷款机构风险管理有重要参考价值。 相似文献
18.
在对安徽省民营上市公司治理风险现状分析的基础上,选取了36家安徽民营上市公司作为研究样本,从公司治理的股权结构、董事会、监事会、经理层等方面建立了公司治理风险评价指标体系和评价模型,并进行了实证研究,得出目前安徽省民营上市公司虽然存在不少公司治理风险,但大部分企业发展平稳,公司治理风险基本能得到控制,并结合安徽民营上市公司治理的特点和运营现状,提出了风险防范的措施。 相似文献
19.
张素玲 《洛阳师范学院学报》2000,19(2):142-144
JNC Ⅵ的最新观点强调 :高血压不仅仅是血压升高 ,而且是全身多脏器病变 ;提出高血压患者危险度的分期和分期法 ,并以此决定治疗方法 ;高血压的危害不仅取决于血压的高低 ,还与是否存在其他危险因素密切相关 ;治疗应更注重个体化 ;任何年龄降压均有益 .HOT研究显示 :收缩压降至 1 8.5kPa (1 39mmHg) ,舒张压降至 1 1 .1kPa(83mmHg)为最佳降压水平 .我国高血压流行具有三高三低的特点 ,患者在治疗上存在着三个误区 .普及高血压的防治知识 ,提高高血压的治疗水平和患者的顺从性 ,是我国高血压防治的当务之急 相似文献
20.
As indicated by research on the long-term effects of adverse childhood experiences (ACEs), maltreatment has far-reaching consequences for affected children. Effective prevention measures have been elusive, partly due to difficulty in identifying vulnerable children before they are harmed. This study employs Risk Terrain Modeling (RTM), an analysis of the cumulative effect of environmental factors thought to be conducive for child maltreatment, to create a highly accurate prediction model for future substantiated child maltreatment cases in the City of Fort Worth, Texas. The model is superior to commonly used hotspot predictions and more beneficial in aiding prevention efforts in a number of ways: 1) it identifies the highest risk areas for future instances of child maltreatment with improved precision and accuracy; 2) it aids the prioritization of risk-mitigating efforts by informing about the relative importance of the most significant contributing risk factors; 3) since predictions are modeled as a function of easily obtainable data, practitioners do not have to undergo the difficult process of obtaining official child maltreatment data to apply it; 4) the inclusion of a multitude of environmental risk factors creates a more robust model with higher predictive validity; and, 5) the model does not rely on a retrospective examination of past instances of child maltreatment, but adapts predictions to changing environmental conditions. The present study introduces and examines the predictive power of this new tool to aid prevention efforts seeking to improve the safety, health, and wellbeing of vulnerable children. 相似文献