基于BP神经网络和小波降噪的沪深300股指期货价格预测

本文在小波去噪的基础上构建了BP神经网络模型,选取了具有代表性的沪深300股指期货来进行价格预测,并对去噪前后的预测结果进行了对比,发现小波去噪后的BP神经网络模型对股指期货价格的预测效果更佳,为短期投资者们提供了一定的决策依据。     

BP神经网络结合小波处理在城市扩张预测中的应用——以长沙市区为例

研究目的预测城市扩张规模,从而为合理调控城市建设用地扩张提供决策依据.研究方法通过Granger检验提取城市扩张的驱动因子,利用BP神经网络结合小波处理对建成区扩张趋势进行预测.研究结果未来几年长沙市新增建设用地数量将呈递增趋势,以年均约27 km2的速度扩张.研究结论与GM(1,1)模型及回归模型预测方法相比,BP 神经网络结合小波处理的预测精度最高.其预测结果可为城市制定相关的政策提供科学依据.     

基于遗传算法改进的BP神经网络房价预测——以重庆市为例

商品房的价格受多方面因素的影响,传统的预测方法并不十分有效。为了探索新的房价预测理论模型,利用重庆市的数据,验证了遗传算法改进的BP神经网络房价预测的有效性,从而可以对房地产供求双方及监管机构提供一定的参考。     

BP神经网络在耕地减少预测中的应用研究

由于耕地资源的有限性,因此有必要掌握陕西省的耕地面积减少趋势.利用前向多层神经网络的反向传播算法,即BP算法.采用MATLAB软件建立用于预测的BP神经网络,将已知陕西省的耕地资源年减少量通过BP神经网络进行训练,建立陕西年耕地面积减少的时间序列的预测模型.此BP神经网络在对陕西的耕地资源年减少量进行预测时精度较高,可靠性较好.表明BP神经网络用于耕地减少的预报具有一定的可行性.     

基于BP神经网络的我国农产品市场风险预警研究

本文从影响农产品供给与需求的因素,以及自然、经济、政策与国际环境等影响农产品价格的因素等方面出发构建了我国农产品市场风险预警的指标体系,并以大豆为例,利用BP神经网络对大豆市场风险预警进行了实证分析,网络训练和验证结果表明BP神经网络很好地拟和、预测出了我国大豆市场风险水平,说明基于BP人工神经网络的农产品市场风险预警模型是切实可行的。     

鲈鱼人工育苗难题告破

<正> 最近,来自中国科学院,农业部和国家海洋局等单位的12位专家教授经过鉴定后一致认为:山东省威海市环翠区羊亭水产公司开发的中国鲈鱼全人工育苗技术无论在基础研究.还是在应用技术方面均处于世界领先水平,超过在该领域起步较早的日本和韩国。至此,困扰世界水产养殖界的鲈鱼人工育苗难题告破。 我国海水养殖业经历了海带、对虾和扇贝三次浪潮以后,即将迎来第四次浪潮——鱼类养殖。鲈鱼因其肉味鲜美、生长快、适应     

BP神经网络矿产资源评价程序模块设计及其应用研究——以东天山铜镍硫化物矿床为例

在深入研究BP神经网络算法的基础上,开发BP神经网络矿产资源评价功能模块并以东天山地区铜镍硫化物矿床为例开展成矿远景区预测工作。使用MRAS软件中的特征分析功能基于相同样本数据开展预测评价,并对两种模型产生的结果进行对比分析和交叉验证。证明BP神经网络程序的正确性,同时总结BP神经网络矿产资源评价应用的关键技术要点。     

区域耕地数量变化预测方法的对比研究

研究目的:对区域耕地数量变化预测方法进行对比分析,科学合理确定区域耕地数量。研究方法:通过Pearson相关分析法筛选影响耕地变化的关键因子,利用改进的BP神经网络算法、灰色模型和多元线性回归模型法对费县耕地数量变化进行预测。研究结果:改进的BP神经网络算法相对传统的灰色模型和多元线性回归模型等预测方法具备较高的预测精度。研究结论:改进的BP神经网络算法是进行耕地数量变化预测的较好方法,具有实际指导意义,其预测结果可以为当地相关部门合理地确定耕地保有量、推进耕地保护提供科学依据。     

常见鱼类病害的综合防治措施

正对于水产养殖来说,鱼类疾病的防治是决定水产养殖成败的重要因素。而随着生活水平的提高,消费者对水产品的要求也有所提升。如果是经常患病的鱼类,就会严重影响水产品的品质。因此,在水产养殖的整个环节中,都必须做好鱼类常见病害的综合防治措施。     

北京引进黄金鲈鱼苗种

<正> 近日,在北京市农业局的大力支持下,北京市水产技术推广站已从美国引进了黄金鲈鱼苗种。该鱼苗通过空运抵京,并在水产技术推广站的通州水务养殖基地放养。水产工程师将对黄金鲈鱼在生物学、驯化、养殖、繁殖等方面进行     

期权价值对排水管网水价的影响研究

水业巨大的供需矛盾决定了城市水业的市场化方向,受制于污水处理的低产能利用率,排水管网建设成为水务发展的瓶颈。通过引入再投资管网建设工程的期权价值,构建了考虑期权价值的水价模型,得出的修正临界水价低于传统净现值模型得出的水价,形成的理论分析成果为排水管网建设工程的合理水价确定提供理论依据和支持。     

临沂市需水预测信息系统的研究和探讨

借鉴国内外节水管理的成功经验,结合临沂市具体情况,建立了临沂市需水预测模型,并在此基础上把数据库技术和需水预测模型进行系统集成,研究和探讨了临沂市需水预测信息系统的开发,并建立了完整的系统数据库.该系统将为临沂市今后的经济发展模式选择和水利工程建设提供可靠依据.     

Are piglet prices rational hog price forecasts?

In this paper a simple model is developed in which the piglet price serves as a forecast for the hog price 3 months ahead. The model is tested on data from Northern Europe, viz. Norway, Sweden, Denmark and Finland during the period 1982-1992. The empirical results lend strong support to the hypothesis that hog producers hold rational expectations when pricing the piglets. Thus, the weight adjusted piglet price typically represents an unbiased (conditional) forecast with unsystematic errors for the hog price one quarter later.     

基于基准地价评估模型的修正体系编制方法研究

提出了以定级因素作用分和基准地价评估模型相结合的方法计算修正系数,并通过分析定级因素作用分其及计算方法,确定修正系数条件指标。解决了传统的人工编制方法的主观任意性问题,丰富了地价评估理论,完善了城镇土地估价规程中的相关内容,为实现在计算机中以流程化方式编制基准地价修正体系提供了理论依据和实现的可能。     

Demand System Estimation with Upward-Sloping Supply

There are three important implications of this work. First, demand systems estimates that overlook supply response are as subject to simultaneous equations bias as single ad hoc demand equations. Theil shows theoretically that assuming supply curves are perfectly elastic, when in fact they are not will underestimate price responsiveness in demand equations. An empirical example is presented that demonstrates that the price elasticities generally increase when upward-sloping supplies are assumed.
Second, the iterative testing procedure presented may provide direction for model building when the true structure of the system is unknown. For example, the results of the Wu-Hausman test indicate that assuming chicken supply is perfectly elastic in a model of the Japanese livestock industry is justified. The results also indicate that the supplies of Wagyu beef, dairy beef, pork and fish are upward-sloping and therefore should be modeled as endogenous variables in the demand system.
Third, the results emphasize the sensitivity of projections of Japanese beef imports to the assumptions underlying the demand system. If perfectly elastic meat supplies are assumed for an analysis of reducing Japanese beef import liberalization, the results will likely underestimate the impacts on beef imports.
In summary, the supply curves for agricultural products tend to slope upward within the time periods used for traditional policy analysis and demand system estimation, which in turn implies that prices are determined endogenously within the system. Endogenous price determination is contrary to the assumptions that underlie the theoretical foundations and many empirical applications of demand systems. We present a methodology to test for and adjust demand systems for endogeneity. The importance of this adjustment is demonstrated by using an analysis of the liberalization of the Japanese beef market.     

A hybrid commodity price‐forecasting model applied to the sugar–alcohol sector

Accurate price forecasting for agricultural commodities can have significant decision‐making implications for suppliers, especially those of biofuels, where the agriculture and energy sectors intersect. Environmental pressures and high oil prices affect demand for biofuels and have reignited the discussion about effects on food prices. Suppliers in the sugar–alcohol sector need to decide the ideal proportion of ethanol and sugar to optimise their financial strategy. Prices can be affected by exogenous factors, such as exchange rates and interest rates, as well as non‐observable variables like the convenience yield, which is related to supply shortages. The literature generally uses two approaches: artificial neural networks (ANNs), which are recognised as being in the forefront of exogenous‐variable analysis, and stochastic models such as the Kalman filter, which is able to account for non‐observable variables. This article proposes a hybrid model for forecasting the prices of agricultural commodities that is built upon both approaches and is applied to forecast the price of sugar. The Kalman filter considers the structure of the stochastic process that describes the evolution of prices. Neural networks allow variables that can impact asset prices in an indirect, nonlinear way, what cannot be incorporated easily into traditional econometric models.     

WELFARE IMPLICATIONS OF MORE ACCURATE RATIONAL FORECAST PRICES

Models are constructed to assess the welfare effects for producers, consumers and society of producers using forecast prices based on more accurate estimates of variables causing shifts in the demand for and supply of commodities. The basic model is a stochastic cobweb model in which producers' forecast price is the rational forecast price. The model is extended for many commodities, for partial producer response to more accurate forecast prices, and to include stock holding. In terms of economic surplus, producers and consumers gain from more accurate estimates of demand shift variables, producers gain and consumers lose from more accurate estimates of supply shift variables, and in both cases there is a net society gain.     

基于BP模型的中国水产品出口规模预测研究

由于我国的信息咨询体系发展落后,水产品国际贸易缺乏及时、可靠的预测,导致我国水产品生产存在一定的盲目性,因此信息技术领域已经作为渔业科技十大重点发展领域之一,被列入农业部的工作重点.但是,水产品贸易受许多因素的影响,是一个高度复杂的非线性系统,使用传统的预测方法建立的模型很难对水产品贸易进行较为准确的预测,而利用BP神经网络建立的水产品贸易模型,己利用历史数据对模型进行了训练,最终可得到较为满意的结果.     

Regime Shifts in the Fish Meal/Soybean Meal Price Ratio

Aquaculture growth has led to worries about overfishing and reduction in wild‐caught food fish supply because of increased demand for fish meal. As such, the price ratio between fish meal and soybean meal has received much attention as an indicator of changing market conditions. In recent years, the price ratio between these two commodities has become more volatile. Several authors have suggested that the traditional relationship between fish meal and soybean meal has broken down and that this is evidence of increased demand pressure on fish meal. In this article, we investigate the hypothesis that there are two regimes for the relative price between fish meal and soybean meal. The empirical results support this hypothesis, with the low‐price regime representing the traditional stable relative price. The continued linkages between the fish meal and the soybean meal markets indicate that aquaculture is reducing its dependency on marine proteins in favour of vegetable proteins.     

基于支持向量机算法的乳制品分类识别技术研究

本文针对乳制品分类快速识别技术依旧相对匮乏的现状,获取了样品的拉曼光谱,以此作为表征样品的质量特性数据,输入支持向量机判别模型,构建高效识别技术。结果显示,乳制品拉曼光谱数据采集迅速,含水样品可直接上样测试,单个样品的数据采集时间仅需2.5min,计算机处理时间在10s以内,参数优化条件分别为小波软阈值降噪(db1小波基,分解层数N=3)、归一化处理([-1,1]区间),通过主成分分析提取80个主成分(累计贡献率99%以上),支持向量机算法(径向基核函数,惩罚系数c=32,核函数参数g=0.022097),测试集最佳识别率可达到100%。由此可见,本文所建立的高效识别方法,具有分析速度快、流程便捷等多项优点,能够为乳制品质量安全监管提供技术参考。