基于决策树技术的日前市场清算电价预测

以澳大利亚昆士兰州电力市场为背景,采用决策树技术,建立了提前日的电力市场清算电价预测模型。详细介绍了决策树技术的原理及其在电价预测中的实现方法,考虑了非电价因素对电价预测的影响。实际结果表明该方法具有良好的预测效果和直观性。     

中国新闻纸需求量灰色预测

针对我国新闻纸需求量大且具有不确定性的特点,运用具有适用性广,预测准确率高等优点的灰色系统理论预测了我国新闻纸需求量,建立了需求量模型并对该模型的精度进行了检验。预测结果表明,该模型用于预测我国新闻纸需求量具有一定的可行性和有效性。     

地质超前预报和动态施工在隧洞施工中的应用

通过在直峰架洞施工过程中，地质超首预报与隧洞动态施工的结合，将国际岩体质量分级到生产实践中，针对不同级别的岩级，应用相应的施工方案，以达到为隧洞篱工总结经验的目的。     

A Study on the Model of Forecasting System about the Actual Telephone Occupation in the Lead Development

ＡＳｔｕｄｙｏｎｔｈｅＭｏｄｅｌｏｆＦｏｒｅｃａｓｔｉｎｇＳｙｓｔｅｍａｂｏｕｔｔｈｅＡｃｔｕａｌＴｅｌｅｐｈｏｎｅＯｃｃｕｐａｔｉｏｎｉｎｔｈｅＬｅａｄＤｅｖｅｌｏｐｍｅｎｔ￥ＸｉｅＳｈｉｃｈａｎｇ；ａｎｄＸｉｅＸｕｅｍｅｉ（Ｄｅｐａｒｔｍｅｎｔｏ...     

Comparisons of Urban Travel Forecasts Prepared with the Sequential Procedure and a Combined Model

Detailed analyses and comparisons of urban travel forecasts prepared by applying the state-of-practice sequential procedure and the solution of a combined network equilibrium model are presented. The sequential procedure for solving the trip distribution, mode choice and assignment problems with feedback is the current practice in most transportation planning agencies, although its important limitations are well known. The solution of a combined model, in contrast, results from a single mathematical formulation, which ensures a well-converged and consistent result. Using a real network, several methods for solving the sequential procedure with feedback are compared to the solution of the combined model ESTRAUS. The results of these methods are shown to have various levels of instability. The paper concludes with a call for a new paradigm of travel forecasting practice based on an internally consistent model formulation that can be solved to a level of precision suitable for comparing alternative scenarios.     

Identification environment and robust forecasting for nonlinear time series

In this paper, the methods of time series for nonlinearity are briefly surveyed, with particular attention paid to a new test design based on a neural network specification. The proposed integrated expert system contains two main components: an identification environment and a robust forecasting design. The identification environment can be viewed as a integrated dynamic design in which cognitive capabilities arise as a direct consequence of their self-organizational properties. The integrated framework used for discussing the similarities and differences in the nonlinear time series behavior is presented. Moreover, its performance in prediction proves to be superior than the former work. For the investigation of robust forecasting, we perform a simulation study to demonstrate the applicability and the forecasting performance.     

一种改进的灰度预测模型

灰色预测模型通常是GM模型,但预测精度有时不令人满意。在对模型GM做了进一步研究的基础上,提出了一个预测精度较高的新灰色预测模型,并从理论上证明了这种模型可以有效提高建模数据序列的光滑度。最后把此方法应用于东部某镇GDP的建模中,试验结果表明该方法是可行且有效的,所建模型的精度优于传统GM（1,1）模型的精度。     

主动推送模式下的情报需求预测模型

针对主动推送模式下的情报需求预测问题,提出了基于案例推理的解决方案。设计了进行情报需求预测案例分析的工作流程,建立了案例属性描述模型;应用最近邻法进行案例的相似度评价,并通过信息增益的计算确定每个属性的权值,获得相似案例(集);提出了方案调整和推理策略。     

基于全信息新陈代谢的GM（1，1）电力预测

传统的灰色预测模型所需的样本容量较少,仅4个数据就可以建立灰色预测模型。虽然传统的灰预测建模较为简单,但是忽略了对预测较为确利的新信息,容易产生预测模型老化的现象,预测精度不高。全信息新陈代谢的GM（1,1）灰色预测模型更为合理、科学,全信息建模避免了局部信息建模的局限性,每预测一个结果去除原始数列的最老数据的新陈代谢处理保证了预测数列的实效性,并用Matlab实现改进GM（1,1）模型的编程计算,应用于双流县电力需求量的预测,预测精度好。     

旱情预报技术进展与展望

受全球气候变化影响和人类活动的加剧,干旱灾害发生频次增加且强度增大,严重威胁着我国的粮食安全和水安全。准确及时的旱情预报,对于制定科学有效的干旱应对策略、减少灾害造成的损失具有重大意义。从基于数理统计模型的预报技术和基于物理机制模型的预报技术两方面入手,梳理回顾了国内外研究进展,揭示了当前预报技术所存在的问题,并提出针对性的解决方案。未来研究应注重提高干旱监测数据的质量、突破核心关键技术、构建全国旱情预报业务化系统,为抗旱减灾事业提供强有力的科技支撑。