Prediction of retail sales of footwear using feedforward and recurrent neural networks

Fluctuation of sales over time is one of the major problems faced by most of the industries. To alleviate this problem management tries to base their plans on forecast of sales pattern, which are mostly adhoc and rarely provides solid foundation for the plans. This study makes an attempt to solve this problem by taking a neural network approach, at the process of sales of footwear, and arriving at an optimum neural network model. The algorithms used for developing such model through neural network are both feedforward and recurrent Elman network. The data used in this work are the weekly sales of footwear and the information about the seasonality of sales process. While solving the problem, the focus is on forecasting of weekly retail sales as per the requirement of management. This work would reduce the uncertainty existing in the short-term/middle term planning of sales and distribution logistics of footwear over different time horizons across the entire supply chain of footwear business.     

基于RBF神经网络的污水处理软测量算法研究

分析了软测量技术在污水处理问题上的可行性，建立了径向基（RBF）神经网络软测量模型，对污水处理过程中的各种污染物质进行监控和预测。结果表明：应用软测量技术能较好的克服污水处理过程中由随机干扰、强非线性、大时变、严重滞后等因素带来的一系列问题，具有广阔的应用前景。     

基于不变特征的标志识别技术研究

标志识别是近距离空间交会对接中的一项重要的关键技术.在空间交会对接过程中,太阳和月球等各种天体以及飞行器上零部件的辐射与反射都会影响CCD的成像,形成大量杂散光干扰.为此,本文首先设计了具有不变特征的标志系统,然后根据标志系统固有的不变特征,详细设计了左右像点匹配、远场像平面不变特征识别、近场像平面预测识别以及像空间模型匹配全等识别等一套完整算法,可以保证彻底消除杂散光的干扰,正确可靠地完成各个标志灯像点的辨识.模拟图像仿真实验和真实图像仿真实验结果验证了算法的正确性和可靠性.     

基于动态Markov的热风炉操作预测

针对马尔可夫预测传统的状态划分采用人为确定方法,由预测者的经验决定预测对象的初始状态,状态界限的划分定性分析因素极大的问题。提出根据预测对象数据自身的相似度,采用动态聚类方法对预测对象进行初始状态划分,确定初始状态概率和状态转移概率矩阵,进行马尔可夫预测的方法。该改进的方法在某厂的热风炉操作预测中进行了应用,预测结果表明该方法可以有效指导热风炉操作。     

GIS Approach of Delineation and Risk Assessment of Areas Affected by Arsenic Pollution in Drinking Water

The objective of this study is to analyze health effects of arsenic pollution of drinking water using a geographical information system (GIS). The paper reports the regional impact of arsenic contamination in six administrative blocks of the central part of the Murshidabad district, West Bengal, India. In this area about 1,248,580 people are exposed to arsenic pollution out of whom 388,316 people are exposed to arsenic concentrations above 0.05?mg/L, the WHO maximum permissible level of arsenic in drinking water. The study estimates that 65% of the total area of the six blocks has arsenic concentrations below 0.05?mg/L, 26.12% of the area has arsenic concentrations above 0.05?mg/L, and for the rest of the area no arsenic distribution data available. The total number of expected death cases has been estimated considering the percent of risk involved in a concentration range and corresponding total population using such water for drinking purpose. The analysis forecasts that 11,890 people may risk death due to arsenic pollution in the whole life span. The maximum number of death cases is expected in Domkal and Beldanga 1 blocks and the minimum number of death cases is expected in Block Bhagabangola 2. This study also reports a comparison between the theoretical expectation of death cases and actual reported arsenicosis cases for the Domkal block. The areas of theoretical expectation and the areas of actually reported cases match fairly well except in a few cases. The present study helps planning and implementing of priority-based arsenic mitigation options.     

基于Agent的水产品价格预测支持系统

综述了基于Agent程序的开发方法，提出采用面向领域工程的Agent方法进行系统设计，从水产品价格预测定义出发，构建了水产品价格预测的领域本体模型，并将系统设计成为由10类不同功能Agent组成的多Agent系统。     

包含自发自用电量情况的负荷预测

本文针对一种含有自发电的特殊情况来进行负荷预测，对时间序列法在负荷预测的建模中应用，提出了一种ARMAX的模型，结合预测模型，将自发电作为一个大扰动来考虑。通过验证，得到了较好的结果。     

利用神经网络PRPE算法进行短期负荷预报

本文根据神经网络的并行递推预估误差训练理论,建立了一种负荷预报的新算法——PRPE预报算法。该算法属利用多层前传网进行负荷预报的范畴,由于该算法有效的权重训练方式,使其收敛速度大大高于传统的BP算法。尽管该算法的训练过程比较复杂,但对于时段负荷预报这类单输出系统,总体训练时间较BP算法成倍减少,且预报精度较高。可用于在线短期负荷预报。     

优选平滑系数的指数平滑法电量预测系统

本介绍了一个用指数平滑法开发的电量预测系统。系统中平滑系数的选择采用了新近提出的０．６１８优选法，系统具有预测精度高，运行速度快和使用方便的特点。     

Quantifiable data mining using ratio rules

Association Rule Mining algorithms operate on a data matrix (e.g., customers products) to derive association rules [AIS93b, SA96]. We propose a new paradigm, namely, Ratio Rules, which are quantifiable in that we can measure the “goodness” of a set of discovered rules. We also propose the “guessing error” as a measure of the “goodness”, that is, the root-mean-square error of the reconstructed values of the cells of the given matrix, when we pretend that they are unknown. Another contribution is a novel method to guess missing/hidden values from the Ratio Rules that our method derives. For example, if somebody bought $10 of milk and $3 of bread, our rules can “guess” the amount spent on butter. Thus, unlike association rules, Ratio Rules can perform a variety of important tasks such as forecasting, answering “what-if” scenarios, detecting outliers, and visualizing the data. Moreover, we show that we can compute Ratio Rules in a single pass over the data set with small memory requirements (a few small matrices), in contrast to association rule mining methods which require multiple passes and/or large memory. Experiments on several real data sets (e.g., basketball and baseball statistics, biological data) demonstrate that the proposed method: (a) leads to rules that make sense; (b) can find large itemsets in binary matrices, even in the presence of noise; and (c) consistently achieves a “guessing error” of up to 5 times less than using straightforward column averages. Received: March 15, 1999 / Accepted: November 1, 1999