Currency exchange rate prediction and neural network design strategies

This paper describes a non trivial application in forecasting currency exchange rates, and its implementation using a multi-layer perceptron network. We show that with careful network design, the backpropagation learning procedure is an effective way of training neural networks for time series prediction. The choice of squashing function is an important design issue in achieving fast convergence and good generalisation performance. We evaluate the use of symmetric and asymmetric squashing functions in the learning procedure, and show that symmetric functions yield faster convergence and better generalisation performance. We derive analytic results to show the conditions under which symmetric squashing functions yield faster convergence, and to quantify the upper bounds on the convergence improvement. The network is evaluated both for long-term forecasting without feedback (i.e. only the forecast prices are used for the remaining trading days), and for short- term forecasting with hourly feedback. The network learns the training set near perfect, and shows accurate prediction, making at least 22% profit on the last 60 trading days of 1989.This research is partially supported by the European Communities ESPRIT Programme under Project FOES, entitled Front Office Environment Study.     

Towards the Optimal Learning Rate for Backpropagation

A backpropagation learning algorithm for feedforward neural networks withan adaptive learning rate is derived. The algorithm is based uponminimising the instantaneous output error and does not include anysimplifications encountered in the corresponding Least Mean Square (LMS)algorithms for linear adaptive filters. The backpropagation algorithmwith an adaptive learning rate, which is derived based upon the Taylorseries expansion of the instantaneous output error, is shown to exhibitbehaviour similar to that of the Normalised LMS (NLMS) algorithm. Indeed,the derived optimal adaptive learning rate of a neural network trainedby backpropagation degenerates to the learning rate of the NLMS for a linear activation function of a neuron. By continuity, the optimal adaptive learning rate for neural networks imposes additional stabilisationeffects to the traditional backpropagation learning algorithm.     

"Publishing opinions: A note on the usefulness of commentaries": Comment.

Comments on J. J. Christensen-Szalanski and L. R. Beach's (see record 1984-21471-001) conclusion that the attention given to commentaries and replies to articles did not justify the extra space and argues that citation indexes do not measure the major usefulness of these commentaries. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Commentary on "Publishing opinions: A note on the usefulness of commentaries."

Comments on J. J. Christensen-Szalanski and L. R. Beach's (see record 1984-21471-001) conclusion that the attention given to commentaries and replies to articles did not justify the extra space. The author indicates that a 40% increase in space was associated with a 91% increase in citations; data do not argue against the use of commentaries. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

DRYING KINETICS DERIVED FROM DIFFUSION EQUATION WITH FLUX-TYPE BOUNDARY CONDITIONS

A novel approach to drying of both hygroscopic and non-hygroscopic capillary - porous materials is presented. The equations for drying kinetics are obtained, based on the analytical solution of the differential equation of diffusion with a boundary condition in the form of the flux. Theoretical drying curves generated form the model solution compare well with experimental literature data for drying of materials with different sorption properties exemplified by wool bobbins, brick slabs and corn kernels.     

基于大尺寸地层模型的砂岩储层油基钻井液侵入模拟

选用扇形砂岩地层模块作为大尺寸地层模型,以钻井液侵入多功能物理模拟系统为平台,实施了长时间油基钻井液侵入实验,总结了侵入过程中地层模块径向电阻率、油基钻井液滤液滤失流量和侵入深度的变化规律,获得了不同物性条件下的油基钻井液侵入特征;实现了地层条件下的砂岩储层油基钻井液侵入数值模拟。研究结果表明：油基钻井液侵入过程中,地层模块径向电阻率向远离井壁方向依次开始增大,且增大速度随径向深度增大而降低。侵入初期,滤液滤失流量迅速减小,累计滤失量增幅变缓,侵入深度较浅;侵入达到动态平衡后,滤液滤失流量趋于稳定,累计滤失量随侵入时间线性增加,侵入深度增大速度极慢。与高孔渗砂岩储层相比,低孔渗砂岩储层中的滤液滤失流量和累计滤失量更大,侵入更快、更深,径向电阻率率先增大且增大速度更快。     

PBT工程塑料生产中MFR的控制

针对使用BUSS捏合机生产聚对苯二甲酸丁二酯(PBT)过程中出现的熔体流动速率(MFR)与产品配方体系中低分子量PBT树脂用量间的异常关系进行了研究和分析。结果表明，混炼加工PBT时，产品的MFR取决于两个因素的综合作用，一为产品配方中高、低粘度树脂的比例；二为低分子量树脂对主机功率的影响。综合二者影响，PBT的MFR与低分子量PBT用量关系近似为y=0．0471x^2-3．6347x 107．83。     

金属离子影响过氧乙酸分解速度的探讨及对策

本文考察了部分金属离子对过氧乙酸分解速度的影响.结果发现一些金属离子(Cr3 、AL3 、Ni2 、Co2 )引起过氧乙酸快速分解,一些金属离子(Hg2 、Cu26、Zn2 、Pb26、Ag )引起过氧乙酸缓慢分解,还有一些金属离子(Mg2 、K )对过氧乙酸起稳定作用.本文探讨了金属离子对过氧乙酸分解的机理.有针对性地选择一些配位剂(8-羟基喹啉、邻二氮菲、酒石酸盐、草酸钠)作为过氧乙酸稳定剂,这些配位剂与金属离子形成稳定的配合物,从而把金属离子有效地隐蔽起来,增加过氧乙酸的稳定性.     

生物反应器-中空纤维膜处理医院污水

生物反应器-中空纤维膜处理医院污水试验表明,该工艺在技术上可行,处理效率高,操作管理方便。对COD、NH3-N、大肠杆菌的去除率均达90％以上,出水水质良好、稳定。增设粗分离器后,对延长膜清洗周期、提高膜通量效果明显。     

三相气提升循环流化床处理焦化废水

实验室规模的研究表明，用三相气提升内循环流化床反应器（ＡＩＬＲ）处理焦化污水比活性污泥法为优。其处理负荷高，ＣＯＤ的进水负荷为１３ｋｇ／ｄ·ｍ＾３，ＣＯＤ去除的容积负荷可达到７ｋｇ／ｄ·ｍ＾３。ＡＩＬＲ对酚、氰等污染物的耐受力强、去除效果好并具有较低的曝气能耗；其ＣＯＤ去除率为５４．４％￣７６％，酚去除率为９９．５％￣９９．８％，氰去除率为９５％￣９９．２％；曝气能耗是活性污泥法的１／３￣１／４。