计算智能改进方法及其在金融与环境领域中的应用
|
摘要
本文以计算智能方法为基础,对人工神经网络和进化算法进行了理论改进和应用研究,为金融和大气环境领域提供了一些改进的方法和新的可行途径。具体内容包括(:1)在Kohonen提出的SOM (Self-Organizing Map)神经网络的基础上,通过对获胜节点的拓广以及改进邻域函数、连接权函数等方法,提出了具有多获胜节点SOM2W (SOM with 2 winners), SOM3W (SOM with 3 winners), SOM4W(SOM with 4 winners)和SOM5W (SOM with 5 winners)的网络模型。通过对上市公司进行聚类模拟的实验结果表明,具有双获胜节点的SOM2W聚类能力最强,具有收敛速度快、计算量小、计算复杂性低等优点,并且该网络在分析股票的数量较多时,其优越性更为明显。(2)鉴于时间收益因素和惩罚收益因素所具有的优点,为了进一步提高Elman网络的预测性能,将惩罚收益因素和时间收益因素引入到Elman网络的目标函数中,提出带有惩罚和时间收益因素的Elman神经网络模型,即ENNDPF (Elman Neural Network with Direction Profit Factor), ENNTPF (Elman Neural Network with Time Profit Factor),和ENNDTPF (Elman Neural Network with Direction and Time Profit Factor)神经网络,并将其用于股市投资领域。实验结果表明,ENNDTPF网络的预测性能优于Elman网络,且优于ENNDPF和ENNTPF网络,可以实现大幅度提高收益的目的。(3)为了使新股的价格真正体现上市公司的真实价值,利用SOM2W模型对反映上市公司综合能力的财务指标进行聚类模拟,进行规律挖掘和知识发现,确定新股上市公司的性质和所属类别,然后利用RBF神经网络模拟股市“黑箱”系统对新股进行合理定价,得到了令人满意的结果。(4)采用具有全局优化功能的粒子群优化算法(Particle Swarm Optimization, PSO)对S型生长曲线指数公式中的参数进行优化,得到了对各种大气污染物均适用的大气污染损害率计算公式和指数公式,以及基于PSO大气质量综合污染损害率评价模型和指数评价模型,并将其用于对长春市的大气质量进行评价,所得到的评价结果与实际评价结果基本吻合。(5)在OIF Elman神经网络的基础上,提出了改进的OIF Elman网络。根据长春市环境监测中心站提供的数据,利用改进OIF Elman模型对长春市的大气质量进行预测,并根据预测结果对大气质量进行评价。实验结果表明,该模型具有良好的泛化能力、信息处理能力和很好的非线性逼近能力,所得结果与实际结果基本一致。该模型在大气污染预测领域具有一定的应用前景。
Computation intelligent is based on the idea of bionics and the knowledge of biology intelligence to simulate and realize human being intelligence by using numeric calculation. It is a new crossover subject based on mathematics, physics, biology, psychics, neurology, computer science and intelligence technology, which is also studying focus in the world. Its theory and application study has made greatly progress and produce enormous economic profits and society benefit, which has been applied widely in many fields such as industry, agriculture, national defence, engineering, traffic, finance, communication etc. Especially in the fields of finance and environment, many economists, mathematicians, meteorologists and some reachers of computer are focusing on the study of computational intelligent methods. They use computational intelligent methods to solve some problems in the fields of finance and environment and some satisfactory results are also obtained.
Some theoretical study and applications study based on the approaches of computation intelligence are made in the paper. The major contents could be summarized as follows:
(1) In order to enhance the dynamic competition and clustering capability of self-organizing map (SOM) neural network and improve the precision of solutions, multi-winners SOM models are proposed by extending numbers of winners based on an unsupervised SOM neural network and improving the neighbor function and weight function in the network. In addition, a tabu-mapping method is proposed to avoid that the same output node is mapped by more than one input. The clustering analysis for the stock is used to examine the effectiveness of the proposed models. The financial indexes reflecting the whole performance level of companies are used in the simulated experiments. Simulation results show that the clustering effect of the SOM with 2 winners (SOM2W) is the best compared with those from the standard SOM and other proposed multi-winner SOMs. The proposed model could provide a feasible approach for analyzing and selecting stock, which has potential applications in the financial field.
(2) Considering that the main purpose of investors is to obtain more profits, it seems that the profit should be paid more attention rather than forecasting precision when the stock indexes’prediction is performed. By experimenting, it could be found that the profits of stock exchange dealt according to the prediction results are not always accordant with the forecasting precision but accordant with the correctness of the fluctuation trend forecasting. While by further observing, it was found that if the fluctuation trend of stock indexes is predicted correctly by the calculating model, the profits are always high; and vice versa. Therefore considering this point, we propose improved Elman neural networks by introducing direction profit factor and time profit factor into Elman model, which are called ENNDPF, ENNTPF, ENNDTPF network. Experimental simulation results show that the proposed models are feasible and effective in the field of stock investment. They could improve evidently the forecasting precision and achieve the aim for obtaining more income compared with Elman model. Therefore it could be a novel effective approach applied to the financial field.
(3) At present, investors’investment ideas get to science and reason during they are investing. So reference gist has important value and reality significance. Considering the factors, in order to obtain a new feasible, scientific, reasonable stock price approach, we applied SOM2W model to simulate clustering through a large number data in this paper. So the property and category of new stock companies can be confirmed. In order to make the price of new stock can express the value of stock companies in deed, the financial indexes reflecting the compositive performance of companies are used as data sample in the simulated experiments. Radial basis function (RBF) neural network is used to confirm the new stock price by simulating the black box of stock market reasonable. Experimental simulation results and numeric results show that the proposed SOM2W-RBF network can provide a new reference tool for making new stock price.
(4) The air environment is closely linked with human health and life, whereas the atmospheric quality has been deteriorating with the quickening rhythm of economic growth and industrialized progress. The problems regarding the atmospheric pollution have attracted more and more attention. In order to control and evaluate the grade of the atmospheric pollution, in this paper, particle swarm optimization (PSO) algorithm is used to optimize the parameters in the universal formula for calculating harm rate of atmospheric pollution, therefore the calculating harm rate formula and index formula of atmospheric pollution suited for the cases of multi-pollutants can both be obtained. In addition, the comprehensive models based on the particle swarm optimization algorithm that have optimization advantage are also proposed in this paper, which include the model of calculating the harm rate of pollution and the harm index of pollution for the assessment of atmospheric quality with multi-pollutants. The models are applied to assess the atmospheric pollution of a city in the Northeast of China. Experimental results show the advantages of the proposed models, such as pellucid principle and physical explication, predigested formula and low computation complexity.
(5) In order to forecast timely and correctly atmospheric change, avoid the serious pollution events and improve people’s living quality, the atmospheric quality forecasting has become an important research subject. Considering the factors, in this paper, in order to obtain more accurate forecasting precision, three improved OIF Elman neural networks are proposed by introducing the direction and/or time profit factors into the output-input feedback (OIF) Elman neural network. Simulations show that the proposed models are pretty well, which could improve the forecasting precision evidently. The accurate assessment results could be obtained by using the improved models. Experimental results show that the proposed OIF Elman neural networks are feasible and effective in the fields of forecasting and assessment of the atmospheric quality, which has great potential in the field of atmospheric environment.
Computation intelligent is based on the idea of bionics and the knowledge of biology intelligence to simulate and realize human being intelligence by using numeric calculation. It is a new crossover subject based on mathematics, physics, biology, psychics, neurology, computer science and intelligence technology, which is also studying focus in the world. Its theory and application study has made greatly progress and produce enormous economic profits and society benefit, which has been applied widely in many fields such as industry, agriculture, national defence, engineering, traffic, finance, communication etc. Especially in the fields of finance and environment, many economists, mathematicians, meteorologists and some reachers of computer are focusing on the study of computational intelligent methods. They use computational intelligent methods to solve some problems in the fields of finance and environment and some satisfactory results are also obtained.
Some theoretical study and applications study based on the approaches of computation intelligence are made in the paper. The major contents could be summarized as follows:
(1) In order to enhance the dynamic competition and clustering capability of self-organizing map (SOM) neural network and improve the precision of solutions, multi-winners SOM models are proposed by extending numbers of winners based on an unsupervised SOM neural network and improving the neighbor function and weight function in the network. In addition, a tabu-mapping method is proposed to avoid that the same output node is mapped by more than one input. The clustering analysis for the stock is used to examine the effectiveness of the proposed models. The financial indexes reflecting the whole performance level of companies are used in the simulated experiments. Simulation results show that the clustering effect of the SOM with 2 winners (SOM2W) is the best compared with those from the standard SOM and other proposed multi-winner SOMs. The proposed model could provide a feasible approach for analyzing and selecting stock, which has potential applications in the financial field.
(2) Considering that the main purpose of investors is to obtain more profits, it seems that the profit should be paid more attention rather than forecasting precision when the stock indexes’prediction is performed. By experimenting, it could be found that the profits of stock exchange dealt according to the prediction results are not always accordant with the forecasting precision but accordant with the correctness of the fluctuation trend forecasting. While by further observing, it was found that if the fluctuation trend of stock indexes is predicted correctly by the calculating model, the profits are always high; and vice versa. Therefore considering this point, we propose improved Elman neural networks by introducing direction profit factor and time profit factor into Elman model, which are called ENNDPF, ENNTPF, ENNDTPF network. Experimental simulation results show that the proposed models are feasible and effective in the field of stock investment. They could improve evidently the forecasting precision and achieve the aim for obtaining more income compared with Elman model. Therefore it could be a novel effective approach applied to the financial field.
(3) At present, investors’investment ideas get to science and reason during they are investing. So reference gist has important value and reality significance. Considering the factors, in order to obtain a new feasible, scientific, reasonable stock price approach, we applied SOM2W model to simulate clustering through a large number data in this paper. So the property and category of new stock companies can be confirmed. In order to make the price of new stock can express the value of stock companies in deed, the financial indexes reflecting the compositive performance of companies are used as data sample in the simulated experiments. Radial basis function (RBF) neural network is used to confirm the new stock price by simulating the black box of stock market reasonable. Experimental simulation results and numeric results show that the proposed SOM2W-RBF network can provide a new reference tool for making new stock price.
(4) The air environment is closely linked with human health and life, whereas the atmospheric quality has been deteriorating with the quickening rhythm of economic growth and industrialized progress. The problems regarding the atmospheric pollution have attracted more and more attention. In order to control and evaluate the grade of the atmospheric pollution, in this paper, particle swarm optimization (PSO) algorithm is used to optimize the parameters in the universal formula for calculating harm rate of atmospheric pollution, therefore the calculating harm rate formula and index formula of atmospheric pollution suited for the cases of multi-pollutants can both be obtained. In addition, the comprehensive models based on the particle swarm optimization algorithm that have optimization advantage are also proposed in this paper, which include the model of calculating the harm rate of pollution and the harm index of pollution for the assessment of atmospheric quality with multi-pollutants. The models are applied to assess the atmospheric pollution of a city in the Northeast of China. Experimental results show the advantages of the proposed models, such as pellucid principle and physical explication, predigested formula and low computation complexity.
(5) In order to forecast timely and correctly atmospheric change, avoid the serious pollution events and improve people’s living quality, the atmospheric quality forecasting has become an important research subject. Considering the factors, in this paper, in order to obtain more accurate forecasting precision, three improved OIF Elman neural networks are proposed by introducing the direction and/or time profit factors into the output-input feedback (OIF) Elman neural network. Simulations show that the proposed models are pretty well, which could improve the forecasting precision evidently. The accurate assessment results could be obtained by using the improved models. Experimental results show that the proposed OIF Elman neural networks are feasible and effective in the fields of forecasting and assessment of the atmospheric quality, which has great potential in the field of atmospheric environment.
引文
[1]王万森编著. 人工智能原理及其应用. 电子工业出版社,2007.
[2]邓秀勤. 聚类分析在股票市场板块分析中的应用. 数理统计与管理,1999,18(5):1- 4.
[3]Hu YC, et al. Measuring retail company performance using credit scoring techniques. European Journal of Operational Research, 2007, 183 (3): 1595-1606.
[4]Isasi P, et al. Applied computational intelligence for finance and economics. Computational Intelligence, 2007, 23 (2): 111-116.
[5]Hayward S, et al. Genetically optimized artificial neural network for financial time series data mining. Lecture Notes Computer Science, 2006, 4247: 703-717.
[6]Bodyanskiy Y, et al. Neural network approach to forecasting of quasiperiodic financial time seriesL. European Journal of Operational Research, 2006, 175 (3): 1357-1366.
[7]Wang XZ. Characteristic-based clustering for time series data. Data Mining and Knowledge Discovery, 2006, 13 (3): 335-364.
[8]OConnor N. A neural network approach to predicting stock exchange movements using external factors. Knowledge-Based System, 2006, 19 (5): 371-378.
[9]Kodogiannis VL. A Forecasting financial time series using neural network and fuzzy system-based techniques. Neural Computing & Applications, 2002, 11 (2): 90-102.
[10]Dutot AL, et al. A 24-h forecast of ozone peaks and exceedance levels using neural classifiers and weather predictions. Environmental Modelling & Software, 2007, 22 (9): 1261-1269.
[11]Brunelli U, Piazza V, Pignato L. A neural network model for three-hours-ahead prediction of ozone concentration in the urban area of Palermo. Air Pollution, 2006, 133-142.
[12]Farago I, Georgiev KH. Advances in Air Pollution Modeling for Environmental Security, 2005.
[13]Martin JD, Morton YT, Zhou QH. Neural network development for the forecasting of upper atmosphere parameter distributions. Space Weather Advances in Space Research, 2005, 36 (12): 2480-2485.
[14]Rothney MP, Neumann MB. An artificial neural network model of energy expenditure using nonintegrated acceleration signals. Journal of Application Physiology, 2007, 103 (4): 1419-27.
[15] Zeng J, Guo HF, Hu YM. Artificial neural network model for identifying taxi gross emitter from remote sensing data of vehicle emission. Joural of Environment Science, 2007, 19 (4): 427-31.
[16]Jeyanthi J, Saseetharan MK, Priya VS. Modelling of secondary clarifier using regression analysis and artificial neural networks. Journal of Environmental Science & Engineering, 2006, 48 (1): 1-8.
[17]Chang DW. Comments on Absolute exponential stability of a class of neural networks with unbounded delay. Neural Networks, 2007, 20 (6): 759-60.
[18] Norman KA, Newman EL. A neural network model of retrieval-induced forgetting. Psychol Rev, 2007, 114 (4): 887-953.
[19]Tzagkarakis G, Taroudakis MI, Tsakalides P. A statistical geoacoustic inversion scheme based on a modified radial basis functions neural network. J Acoust Soc Am, 2007, 122 (4): 1959-68.
[20]Zarei K. Simultaneous spectrophotometric determination of phosphate and silicate by using principal component artificial neural network. Annali Data Input of Chimica, 2007, 97 (8): 723-731.
[21]Incerti G. Analysis of bioclimatic time series and their neural network-based classification to characterise drought risk patterns in South Italy. International Journal of Biometeorology, 2007, 51 (4): 253-263.
[22]Pizzi R. Learning in human neural networks on microelectrode arrays. Biosystems, 2007, 88 (1-2): 1-15.
[23]Elena G, Velzen V, Eimer J. Dissociating effector and movement direction selection during the preparation of manual reaching movements: Evidence from lateralized ERP components. Clinical Neurophysiology, 2007, 118 (9): 2031-2049.
[24]Wang Z, Li XC, Zhu WX. Prediction of drug bioavailability by genetic algorithm and artificial neural network. Yao Xue Xue Bao, 2006, 41 (12): 1180-3.
[25]Lowe M. The capacity of q-state Potts neural networks with parallel retrieval dynamics. Statistics & Probability Letters, 2007, 77 (14): 1505-1514. [26] Rivera J. Self-calibration and optimal response in intelligent sensors design based on artificial neural networks. Sensors, 2007, 7 (8): 1509-1529.
[27]Baker KM. A neural network approach to using synoptic forecasts in a statewide potato late blight expert system. Phytopathology, 2007, 97(7):S7-S7.
[28]Ma XL, Jiao LC. An effective learning algorithm of Synergetic Neural Network. Lceture Notes Computer Science, 2004, 3173: 258-263.
[15]Li MY, Cai ZX, Shi YX, et al. A hybrid immune evolutionary computation based on immunity and clonal selection for concurrent mapping and localization. Lceture Notes Computer Science, 2005, 3612: 1308-1311.
[29]Wang ZQ, Zhang DX. Immunity-based genetic algorithm for classification rule discovery. Lceture Notes Computer Science, 2005, 3611: 727-734.
[30]Chen Y, Huang XY. An optimization method based on Chaotic Immune Evolutionary Algorithm. Lceture Notes Computer Science, 2005, 3611: 890-894.
[31]Wu JM, Zuo HF, Chen, Y. An estimation method for direct maintenance cost of aircraft components based on particle swarm optimization with immunity algorithm. Journal of Cetral South University of Technology, 2005, 12: 95-101.
[32]韩力群,人工神经网络教程. 北京邮电大学出版社,2006.
[33]马少平,朱小燕. 人工智能. 清华大学出版社,2004.
[34]王培勋. 非线形回归的弹性分析在股票投资与行情预测中的应用. 系统工程理论与实践,2000,(8):100-104.
[35]李曦. 基于年报选择股票的二级模糊综合评判法,南昌大学(工科版),2001,23(4):99-102.
[36]陈兴,孟卫东,严太华. 基于 T-S 模型的模糊神经网络在股市预测中的应用[J],统工程理论与实践,2001,(2):66-72.
[37]姚洪兴,盛昭瀚,陈洪香. 股市预测中的小波神经网络方法. 系统工程理论与实践,2002,(6):33-38.
[38]张秀艳,徐立本. 基于神经网络集成系统的股市预测模型. 统工程理论与实践,2003,(9):67-70.
[39]冯学军,赵琴. 径向基神经网络在股市预测中的应用. 安庆师范学院学报(自然科学版),2005,11(1):29-31.
[40]邹阿金,罗移祥. Legender 神经网络建模及股票预测. 计算机仿真,2005,22(11):241-246.
[41]王波,张凤玲. 神经网络与时间序列模型在股票预测中的比较. 武汉理工大学学报(信息与管理工程版),2005,27(6):69-73.
[42]殷光伟,郑丕谔. 小波变换和混沌理论在股市预测中的应用. 西北农林科技大学学报(社会科学版),2005,5(1):42-47.
[43]Li ZX, Wu W, Gao W. Prediction of Stock Market by BP Neural Networks with Technical Indexes as Input. Journal of Mathematical Research & Exposition, 2003, 23(1): 83-97.
[44]史忠植. 知识发现. 北京:清华大学出版社,2002.
[45] Ji CY. Land use classification of remotely sensed data using Kohonen self-organizing feature map neural networks. Photogrammetric Engineering & Remotes Sensing, 2000, 66:1451-1460.
[46] Mu CS, Hsiao TC. A New Model of Self-Organizing Neural Network and Its Application in Data Projection. IEEE Transactions on Neural Networks, 2001, 12:153-162.
[47] Rahul S, Vladimir C, Nikolaos P. Self-Organizing Maps for the Skeletonization of Sparse Shapes. IEEE Transactions on Neural Networks, 2000, 11: 241-250.
[48]Yin HJ, MAllinson, N. Self Organizing Mixture Networks for Probability Density Estimation. IEEE Transactions on Neural Networks, 2001, 12: 405-416.
[49] Aoki T, Aoyagi T. Self-organizing maps with asymmetric neighborhood function. Neural Computation, 2007, 19 (9): 2515-2535.
[50] Rustum R, Adeloye AJ. Replacing outliers and missing values from activated sludge data using kohonen self-organizing map. Journal of Environmental Engineering, 2007, 133 (9): 909-916.
[51] Chen YY, Young KY. An SOM-based algorithm for optimization with dynamic weight updating. International Journal of Neural Systems, 2007, 17 (3): 171-181.
[52] Horio K, Yamakawa T. Handwritten character recognition based on relative position of local features extracted by self-organizing maps. International Journal of Innoveative Computing Information and Control, 2007, 3 (4): 789-798.
[53] Ohtsuka A, Tanii H, Kamiura N, et al. Self-organizing map based data detection of hematopoietic tumors. IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences, 2007, (6): 1170-1179.
[54] Zhuang HL, Chiu MS. An extended self-organizing map network for modeling and control of pulse jet fabric filters. Journal of Air & Waste Management Association, 2001, 51 (7): 1035-1042.
[55] Su MC, Liu IC. Application of the self-organizing feature map algorithm in facial image morphing. Neural Processing Letters, 2001, 14 (1): 35-47.
[56] Lopez RE, Munoz PJ, Gomez RA. A principal components analysisself-organizing map. Neural Networks, 2004, 17 (2): 261-270.
[57]Liao G, Liu S, Shi T, et al. Gearbox condition monitoring using self-organizing feature maps. Proceedings of the Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Science, 2004, 218 (1): 119-129.
[58] Guha R, Serra JR, Jurs PC. Using a Kohonen self-organizing map to generate representative training, cross validation and prediction sets for QSAR modelling. Abstracts of Parper of the American Chemical Society 226: U448-U448 159-COMP Part 1, 2003.
[59]Knopf GK, Sangole A. Interpolating scattered data using 2D self-organizing feature maps. Graphical Models, 2004, 66 (1): 50-69.
[60]Chen YP. A hybrid framework using SOM and fuzzy theory for textual classification in data mining. Lecture Notes in Artificial Intelligence, 2003, 2873: 153-167.
[61]Mahony S, Hendrix D, Golden A, et al. Transcription factor binding site identification using the self-organizing map. Bioinformatics, 2005, 21 (9): 1807-1814.
[62]Hoffmann M. Numerical control of kohonen neural network for scattered data approximation. Numerical Algorithms, 2005, 39 (1-3): 175-186.
[63]Matsuda Y, Yamaguchi K. An efficient MDS-based topographic mapping algorithm. Neurocomputing, 2005, 64: 285-299.
[64]Dragomir A, Mavroudi S, Bezerianos A. SOM-based class discovery exploring the ICA-reduced features of microarray expression profiles Comparative and Functional Genomics, 2004, 5 (8): 596-616.
[65] Budinich, M. A self-organizing neural network for the traveling salesmanproblem that is competitive with simulated annealing. Neural Computer, 1996, 8: 416-424.
[66]Leung, KS, Jin, HD, Xu, ZB. An expanding self-organizing neural network for the traveling salesman problem. Neurocomputing, 2004, 62: 267-292.
[67] Aras N, Oommen, BJ, Altinel, IK. The Kohonen network incorporating explicit statistics and its application to the traveling salesman problem. Neural Networks, 1999, (12): 1273-1284.
[68] Teuvo K. The Self-organizing map. Neurocomputing, 1998, 21:1-6.
[69]韩力群编著. 人工神经网络教程. 北京邮电大学出版社,2006.
[70]林昌,康泰兆. 基于自组织特征映射的矢量量化方法. 南京理工 大学学报,1999,23(5):393-396.
[71]王春立,陈益强. 基于 SOFM/HMM 模型的非特定人手语识别系 统. 计算机学报,2002,25(1):16-21.
[72]赵菁,彭慧敏,张家亮,谢维廉. 基于自组织特征映射神经网络的短期负荷预测. 贵州工业大学学报(自然科学版),2003,32(2):57-62.
[73]建岭,王磊,杨建华,高峰. 基于自组织特征映射网络的气体识别方法研究. 测控技术,2000,19(3):6-8.
[74]Frederico, CV, Adriao DD, Jose AC. An Efficient Approach of the SOM Algorithm to the Traveling Salesman Problem. Proceedings of the VII Brazilian Symposium on Neural Networks, 2002.
[75] Lu ZM, Sun SH. Vector Quantization Based on Self-Organizing Feature Map Neural Network. Journal of Image and Graphics, 2000, 5: 846-850.
[76] Abdolhamid M, Samerkae S, Takao E. A self-organizing neural network approach for multiple traveling salesman and vehicle routing problems.International Transactions in Operational Research, 1999, 591-606.
[77]韩江舟,葛世伦,盛永祥. 1999 年度沪深两市中期上是高科技公司股票聚类分析,华东船舶工业学院学报(自然科学版),2001,15(2):86-91.
[78]Hornik K, Wtinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks, 1989, 2: 359-366.
[79]Hornik K, Stinchcombe M, White H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks, 1990, 3: 551-560.
[80]林杰,郭耀煌. 用神经网络方法预测股票短期走势. 西南交通大学学报,1998,33(3):299-304.
[81]王上飞,周佩玲等. 径向基神经网络在股市预测中的应用. 预测,1998,(6):44-46
[82]郑丕谔,马艳华. 基于 RBF 网络的股市建模与预测. 天津大学学报,2000,33(4): 483-486.
[83]赵宏,邹雯等. 证券市场预测的神经网络方法. 系统工程理论与实践,1997(6):127-131.
[84]何芳,陈收. 基于扩展 Kalman 滤波的神经网络学习算法在股票预测中的应用. 系统工程,2003,21(6):75-79.
[85]孙丹, 张秀艳. 基于人工神经网络的股市预测模型. 吉林大学学报(信息科学版),2002,20(4):68-70.
[86]吴微,陈维强. 用于股市预测的 BP 算法的一些改进. 大连理工大学学报,2001,41(5):518-522.
[87]王培勋. 非线性回归的弹性分析在股票投资与行情预测中的应用, 系统工程理论与实践. 2000, (8): 100-104.
[88]周广旭. 一种新的时间序列分析算法及其在股票预测中的应用. 计算机应用,2005,25(9):2179-2184.
[89]殷光伟,郑丕谔. 应用小波理论进行股市预测,系统工程理论方法应用. 2004,13(6):543-547.
[90]李正学. 神经网络理论及其在股市短期预测中的应用. 吉林大学博士学位论文,2001.
[91]Kwon YK, Moon BR. A hybrid neurogenetic approach for stock forecasting. IEEE Transactions on Neural Networks, 2007, 18 (3): 851-864.
[92]Cheng P, Quek C, Mah ML. Predicting the impact of anticipatory action on US stock market - An event study using a neural fuzzy model. Computational Intelligence, 2007, 23 (2): 117-141.
[93]Liu F, N GS, Quek C. RLDDE: A novel reinforcement learning-based dimension and delay estimator for neural networks in time series prediction. Neurocomputing, 2007, 70 (7-9): 1331-1341.
[94]Thawornwong S, Enke D. The adaptive selection of financial and economic variables for use with artificial neural networks. Neurocomputing, 2004, 56: 205-232.
[95]Brabazon A. Financial time series modelling using neural networks: An assessment of the utility of a stacking methodology. Lecture Notes in Artificial Intelligence, 2002, 2464: 137-143.
[96]Chen YH, Abraham A, Yang J, et al. Hybrid methods for stock index modeling. Lecture Notes in Artificial Intelligence, 2005, 3614: 1067-1070.
[97] Kim HJ, Shin KS, Park K. Time delay neural networks and genetic algorithms for detecting temporal patterns in stock markets. LectureNotes in Computer Science, 2005, 3610: 1247-1255.
[98]Redko VG, Mosalov OP, Prokhorov DV. A model of evolution and learning. Neural Networks, 2005, 18 (5-6): 738-745.
[99] Watada J. Structural learning of neural networks for forecasting stock prices. Lecture Notes in Artificial Intelligence, 2006, 4253: 972-979.
[100]Chen HC, Magdon IM. Neural network for option pricing using multinomial tree. Lecture Notes in Computer Science, 2006, 4234: 360-369.
[101] Roh TH. Forecasting the volatility of stock price index. Lecture Notes in Artificial Intelligence, 2006, 4093: 424-435.
[102] Connor N, Madden MG. A neural network approach to predicting stock exchange movements using external factors. Knowled-Based Systems, 2006, 19 (5): 371-378.
[103] Liang X. Neural network method to predict stock price movement based on stock information entropy. Lecture Notes in Computer Science, 2006, 3973: 442-451.
[104]Huarng K, Yu THK. The application of neural networks to forecast fuzzy time series. PHYSICA A-Statistical Mechanics and Its Applications, 2006, 363 (2): 481-491 MAY.
[105]Yu L, Wang SY, Lai KK. Mining stock market tendency using GA-based support vector machines. Lecture Notes in Computer Science, 2005, 3828: 336-345.
[106]Fong B, Fong ACM, Hong GY, et al. An empirical study of volatility predictions: Stock market analysis using neural networks. Lecture Notes in Computer Science, 2005, 3828: 473-480.
[107]Shi, XH, Liang, YC, Lee, HP, Lin, WZ, Xu X, Lim, SP. Improved Elman networks and applications for controlling ultrasonic motors. Applied Artificial Intelligence, 2004, 18: 603-629.
[108]姜静情,梁艳春,孙延风,吴春国. 引入收益因素的 RBF 神经网络及其应用. 吉林大学学报(信息科学版),2002,20(3):68-72.
[109]Jingtao YAO, Chew LT. Time dependent Directional Profit Model for Financial Time Series Forecasting. International Joint Conference on Neural Networks, 2000, 291-296.
[110]Caldwell RB. Performances Metrics for Neural Network-based Trading System Development. Neurovest Journal, 1995, 3(2): 22-26.
[111]Refenes AN, Brntz, Y, Bunn DW, Burgess, AN, Zapranis AD. Financial Time Series Modeling with Discounted Least Squares Back Propagation. Neural Computing, 1997, 14(2): 123-138.
[112]Yao JT, Tan CL, Time dependent Directional Profit Model for Financial Time Series Forecasting. International Joint Conference on Neural Networks 2000, IEEE Computer Society, 2000, 291-296.
[113]赵振权,陈守东. 股票基本定价与定价模型的选择. 数量经济技术经济研究,2000,(1):52-55.
[114]蔡华. BP 神经网络与股票发行定价. 计算技术与自动化,2003,22(1):34-39.
[115]何斌,谭界忠. 大气环境质量综合评价的污染损失率法.环境保护,1998,(9):21-24.
[116]李祚泳,张欣莉,丁晶. 水质污染损害指数评价的普适公式. 水科学进展,2001,12(2):161-163.
[117]虞统. 空气质量日报中的空气污染指数. 城市管理与科技,2000,2(1):23-26.
[118]张文艺,蔡建安,朱静,渣胜国,朱晓庆. API 法在马鞍山市空气质量评价中的应用. 植物资源与环境学报,2003,12(1):62-63.
[119]Kennedy J, Eberhart R. Particle swarm optimization. Proc IEEE Int Conf on Neural Networks, 1995, 1942-1948.
[120]Eberhart R, Kennedy J. A new optimizer using particle swarm theory. Proc 6th Int Symposium on Micro Machine and Human Science, 1995, 39-43.
[121]李爱国,覃征,鲍复民,贺开平. 粒子群优化算法. 计算机工程与应用,2002,21:1-3.
[122]Angeline PJ. Evolutionary optimization versus particle swarm optimization: philosophy and performance differences. Evolutionary Programming, 1998, 7: 601-610.
[123]Clerc M, Kennedy J. The particle swarm-explosion, stability, and convergence in a multidimensional complex space. IEEE Transactions on Evolutionary Computation, 2002, 6: 58-73.
[124]Ioan CT. The particle swarm optimization algorithm: convergence analysis and parameter selection. Information Processing Letters, 2003, 85: 317–325.
[125]Shigenori N, Takamu G, Toshiki Y, Yoshikazu F. A hybrid particle swarm optimization for distribution state estimation. IEEE Transactions on Power Systems, 2003, 18: 60-68.
[126]Shi Y, Eberhart R. Parameter selection in particle swarm optimization. Proceedings of the Seventh Annual Conference on Evolutionary Programming, 1998, 591-600.
[127]Mikki S, Kishk A. Improved particle swarm optimization technique using hard boundary conditions. Microwave and Optical Technology Letters, 2005, 46 (5): 422-426.
[128]Liu B, Wang L, Jin YH, Tang F, Huang DX. Improved particle swarm optimization combined with chaos. Chaos Solitons Fractals, 2005, 25(5): 1261-1271.
[129]Jian W, Xue YC, Qian JX. An improved particle swarm optimization algorithm with disturbance. IEEE International Conference on Systems, Man and Cybernetics, 2004, 6: 5900-5904.
[130]Shi Y, Eberhart R. A modified particle swarm optimizer. IEEE World Congress on Computational Intelligence, 1998, 69-73.
[131]何斌, 谭界忠. 大气环境质量综合评价的污染损失率法. 环境保护,1998,(9):21-24.
[132]李祚泳,王钰,刘国东. 大气污染损失率评价模型参数的 GA 优化[J].环境科学研究,2001,14(2):7-10.
[133]钱莲文,吴承祯,宏伟,陈睿,宋萍,范海兰. 大气质量评价的污染危害指数法的改进. 福建林学院学报,2003,23(3):249-252.
[134]李祚泳,张欣莉,丁晶. 水质污染损害指数评价的普适公式. 水科学进展,2001,12(2):161-163.
[135]王俭,胡筱敏,郑龙熙,刘振山. BP 模型的改进及其在大气污染预报中的应用. 城市环境与城市生态,2002,15(5):17-19.
[136]Lu WZ, Fan HY, Leung AYT, Wong JCK. Analysis of pollutant level optimization. Environmental Monitoring and Assessment, 2002, 79: 217-223.
[137]Kesarkar AP, Dalvi M, Kaginalkar A. Coupling of the Weather Researchand Forecasting Model with AERMOD for pollutant dispersion modeling. A case study for PM10 dispersion over Pune, India. Atmospheric Environment, 2007, 41 (9): 1976-1988.
[138]Eder B, Kang D, Mathur R. An operational evaluation of the Eta-CMAQ air quality forecast model. Atmospheric Environment, 2006, 40 (26): 4894-4905.
[139]Ozcan HK, Bilgil E, Sahin U, Ucan ON, Bayat C. Modeling of trophospheric ozone concentrations using genetically trained multi-level cellular neural networks. Advances in Atmospheric Sciences, 2007, 24 (5): 907-914.
[140]Li ZY, Wang Y, Liu GD. Optimum estimation of parameters on assessment model of pollution loss rate of atmospheric environmental quality using genetic algorithm. Research of Environmental Sciences, 2001, 14: 7-10.
[141]Qian LW, Wu CZ, Hong W, Chen R, Fan HL. Study on the improvement of index formula of pollution harm for atmosphere quality assessment. Journal of Fujian College of Forestry, 2003, 23: 249-252.
[142]Schlink U, Herbarth O, Richter M. Statistical models to assess the health effects and to forecast ground-level ozone. Environmental Modelling & Software, 2006, 21 (4): 547-558.
[143]Farago I, Georgiev K, Havasi. An Advances in Air Pollution Modeling for Environmental Security. Advances in Air Pollution Modeling for Environmental Security, 2005.
[144]San JR, Perez JL, Gonzalez RM. The use of MM5-CMAQ air pollution modelling system for real-time and forecasted air quality impact ofindustrial emissions. Advances in Air Pollution Modeling for Environmental Security, 2005, 327-336.
[145]Lu WZ, Wang WJ. Potential assessment of the “support vector machine” method in forecasting ambient air pollutant trends. Chemosphere, 2005, 59 (5): 693-701.
[146]Pohjola MA, Rantamaki M, Kukkonen J. Meteorological evaluation of a severe air pollution episode in Helsinki on 27-29 December 1995. Boreal Environment Research, 2004, 9(1): 75-87 27.
[147]Rochelle NEJ, Winter C, Barron C, et al. Artificial neural network analysis of factors controling ecosystem metabolism in coastal systems. Ecological Applications, 2007, 17 (5): S185-S196.
[148]Sterjovski Z, Pitrun M, Nolan D, et al. Artificial neural networks for predicting diffusible hydrogen content and cracking susceptibility in rutile flux-cored arc welds. Journal of Materials Processing Technology, 2007, 184 (1-3): 420-427.
[149]Boulanger JP, Martinez F, Segura EC. Projection of future climate change conditions using IPCC simulations, neural networks and Bayesian statistics. Part 2: Precipitation mean state and seasonal cycle in South America. Climate Dynamics, 2007, 28 (2-3): 255-271.
[150]Dall OM, Harrison RM. Chemical characterisation of single airborne particles in Athens (Greece) by ATOFMS. Atomspheric Environment, 2006, 40 (39): 7614-7631.
[151]Barthes L, Mallet C, Brisseau O. A neural network model for the separation of atmospheric effects on attenuation: Application to frequency scaling. Radio Science, 2006, 41 (4): Art. No. RS4012.
[152]Martin JD, Morton YT, Zhou QH. Neural network development for the forecasting of upper atmosphere parameter distributions. Advances in Space Research, 2005, 36 (12): 2480-2485.
[153]Fatemi MH. Prediction of ozone tropospheric degradation rate constant of organic compounds by using artificial neural networks. Analytica Chimica Acta, 2006, 556 (2): 355-363.
[154]Pasini A, Lore M, Ameli F. Neural network modelling for the analysis of forcings/temperatures relationships at different scales in the climate system. Ecological Modelling, 2006, 191 (1): 58-67.
[155]Del FF, Iapaolo MF, Casadio S. Intercomparison between GOME ozone profiles retrieved by neural network inversion schemes and ILAS products. Journal of Atmospheric and Oceanic Technology, 2005, 22 (9): 1433-1440.
[156]Abdul WSA. IER photochemical smog evaluation and forecasting of short-term ozone pollution levels with artificial neural networks. Process Safety and Environmental Protection, 2001, 79 (B2): 117-128.
[157]Niang A, Gross L, Thiria S, et al. Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge. Remote Sensing of Environment, 2003, 86 (2): 257-271.
[158]Krasnopolsky VM, Schiller H. Some neural network applications in environmental sciences. Part I: forward and inverse problems in geophysical remote measurements. Neural Networks, 2003, 16 (3-4): 321-334.
[159]Brunelli U, Piazza V, Pignato L, Sorbello F, Vitabile S. Two-days aheadprediction of daily maximum concentrations of SO2, O-3, PM10, NO2, CO in the urban area of Palermo, Italy. Atmospheric Environment, 2007, 41 (14): 2967-2995.
[160] Del FF, Ortenzi A, Casadio S, et al. Application of neural algorithms for a real-time estimation of ozone profiles from GOME measurements. IEEE Transctions on Geoscience and Remote Sensing, 2002, 40 (10): 2263-2270.
[161]Nasseh S, Mohebbi A, Jeirani Z, Sarrafi A. Predicting pressure drop in venturi scrubbers with artificial neural networks. Journal of Hazardous Materials, 2007, 143 (1-2): 144-149.
[162]Shi XH, Liang YC, Lee HP, Lin WZ, Xu X, Li M. Improved Elman networks and applications for controlling ultrasonic motors. Applied Artificial Intelligence, 2004, 18: 603-629.
[2]邓秀勤. 聚类分析在股票市场板块分析中的应用. 数理统计与管理,1999,18(5):1- 4.
[3]Hu YC, et al. Measuring retail company performance using credit scoring techniques. European Journal of Operational Research, 2007, 183 (3): 1595-1606.
[4]Isasi P, et al. Applied computational intelligence for finance and economics. Computational Intelligence, 2007, 23 (2): 111-116.
[5]Hayward S, et al. Genetically optimized artificial neural network for financial time series data mining. Lecture Notes Computer Science, 2006, 4247: 703-717.
[6]Bodyanskiy Y, et al. Neural network approach to forecasting of quasiperiodic financial time seriesL. European Journal of Operational Research, 2006, 175 (3): 1357-1366.
[7]Wang XZ. Characteristic-based clustering for time series data. Data Mining and Knowledge Discovery, 2006, 13 (3): 335-364.
[8]OConnor N. A neural network approach to predicting stock exchange movements using external factors. Knowledge-Based System, 2006, 19 (5): 371-378.
[9]Kodogiannis VL. A Forecasting financial time series using neural network and fuzzy system-based techniques. Neural Computing & Applications, 2002, 11 (2): 90-102.
[10]Dutot AL, et al. A 24-h forecast of ozone peaks and exceedance levels using neural classifiers and weather predictions. Environmental Modelling & Software, 2007, 22 (9): 1261-1269.
[11]Brunelli U, Piazza V, Pignato L. A neural network model for three-hours-ahead prediction of ozone concentration in the urban area of Palermo. Air Pollution, 2006, 133-142.
[12]Farago I, Georgiev KH. Advances in Air Pollution Modeling for Environmental Security, 2005.
[13]Martin JD, Morton YT, Zhou QH. Neural network development for the forecasting of upper atmosphere parameter distributions. Space Weather Advances in Space Research, 2005, 36 (12): 2480-2485.
[14]Rothney MP, Neumann MB. An artificial neural network model of energy expenditure using nonintegrated acceleration signals. Journal of Application Physiology, 2007, 103 (4): 1419-27.
[15] Zeng J, Guo HF, Hu YM. Artificial neural network model for identifying taxi gross emitter from remote sensing data of vehicle emission. Joural of Environment Science, 2007, 19 (4): 427-31.
[16]Jeyanthi J, Saseetharan MK, Priya VS. Modelling of secondary clarifier using regression analysis and artificial neural networks. Journal of Environmental Science & Engineering, 2006, 48 (1): 1-8.
[17]Chang DW. Comments on Absolute exponential stability of a class of neural networks with unbounded delay. Neural Networks, 2007, 20 (6): 759-60.
[18] Norman KA, Newman EL. A neural network model of retrieval-induced forgetting. Psychol Rev, 2007, 114 (4): 887-953.
[19]Tzagkarakis G, Taroudakis MI, Tsakalides P. A statistical geoacoustic inversion scheme based on a modified radial basis functions neural network. J Acoust Soc Am, 2007, 122 (4): 1959-68.
[20]Zarei K. Simultaneous spectrophotometric determination of phosphate and silicate by using principal component artificial neural network. Annali Data Input of Chimica, 2007, 97 (8): 723-731.
[21]Incerti G. Analysis of bioclimatic time series and their neural network-based classification to characterise drought risk patterns in South Italy. International Journal of Biometeorology, 2007, 51 (4): 253-263.
[22]Pizzi R. Learning in human neural networks on microelectrode arrays. Biosystems, 2007, 88 (1-2): 1-15.
[23]Elena G, Velzen V, Eimer J. Dissociating effector and movement direction selection during the preparation of manual reaching movements: Evidence from lateralized ERP components. Clinical Neurophysiology, 2007, 118 (9): 2031-2049.
[24]Wang Z, Li XC, Zhu WX. Prediction of drug bioavailability by genetic algorithm and artificial neural network. Yao Xue Xue Bao, 2006, 41 (12): 1180-3.
[25]Lowe M. The capacity of q-state Potts neural networks with parallel retrieval dynamics. Statistics & Probability Letters, 2007, 77 (14): 1505-1514. [26] Rivera J. Self-calibration and optimal response in intelligent sensors design based on artificial neural networks. Sensors, 2007, 7 (8): 1509-1529.
[27]Baker KM. A neural network approach to using synoptic forecasts in a statewide potato late blight expert system. Phytopathology, 2007, 97(7):S7-S7.
[28]Ma XL, Jiao LC. An effective learning algorithm of Synergetic Neural Network. Lceture Notes Computer Science, 2004, 3173: 258-263.
[15]Li MY, Cai ZX, Shi YX, et al. A hybrid immune evolutionary computation based on immunity and clonal selection for concurrent mapping and localization. Lceture Notes Computer Science, 2005, 3612: 1308-1311.
[29]Wang ZQ, Zhang DX. Immunity-based genetic algorithm for classification rule discovery. Lceture Notes Computer Science, 2005, 3611: 727-734.
[30]Chen Y, Huang XY. An optimization method based on Chaotic Immune Evolutionary Algorithm. Lceture Notes Computer Science, 2005, 3611: 890-894.
[31]Wu JM, Zuo HF, Chen, Y. An estimation method for direct maintenance cost of aircraft components based on particle swarm optimization with immunity algorithm. Journal of Cetral South University of Technology, 2005, 12: 95-101.
[32]韩力群,人工神经网络教程. 北京邮电大学出版社,2006.
[33]马少平,朱小燕. 人工智能. 清华大学出版社,2004.
[34]王培勋. 非线形回归的弹性分析在股票投资与行情预测中的应用. 系统工程理论与实践,2000,(8):100-104.
[35]李曦. 基于年报选择股票的二级模糊综合评判法,南昌大学(工科版),2001,23(4):99-102.
[36]陈兴,孟卫东,严太华. 基于 T-S 模型的模糊神经网络在股市预测中的应用[J],统工程理论与实践,2001,(2):66-72.
[37]姚洪兴,盛昭瀚,陈洪香. 股市预测中的小波神经网络方法. 系统工程理论与实践,2002,(6):33-38.
[38]张秀艳,徐立本. 基于神经网络集成系统的股市预测模型. 统工程理论与实践,2003,(9):67-70.
[39]冯学军,赵琴. 径向基神经网络在股市预测中的应用. 安庆师范学院学报(自然科学版),2005,11(1):29-31.
[40]邹阿金,罗移祥. Legender 神经网络建模及股票预测. 计算机仿真,2005,22(11):241-246.
[41]王波,张凤玲. 神经网络与时间序列模型在股票预测中的比较. 武汉理工大学学报(信息与管理工程版),2005,27(6):69-73.
[42]殷光伟,郑丕谔. 小波变换和混沌理论在股市预测中的应用. 西北农林科技大学学报(社会科学版),2005,5(1):42-47.
[43]Li ZX, Wu W, Gao W. Prediction of Stock Market by BP Neural Networks with Technical Indexes as Input. Journal of Mathematical Research & Exposition, 2003, 23(1): 83-97.
[44]史忠植. 知识发现. 北京:清华大学出版社,2002.
[45] Ji CY. Land use classification of remotely sensed data using Kohonen self-organizing feature map neural networks. Photogrammetric Engineering & Remotes Sensing, 2000, 66:1451-1460.
[46] Mu CS, Hsiao TC. A New Model of Self-Organizing Neural Network and Its Application in Data Projection. IEEE Transactions on Neural Networks, 2001, 12:153-162.
[47] Rahul S, Vladimir C, Nikolaos P. Self-Organizing Maps for the Skeletonization of Sparse Shapes. IEEE Transactions on Neural Networks, 2000, 11: 241-250.
[48]Yin HJ, MAllinson, N. Self Organizing Mixture Networks for Probability Density Estimation. IEEE Transactions on Neural Networks, 2001, 12: 405-416.
[49] Aoki T, Aoyagi T. Self-organizing maps with asymmetric neighborhood function. Neural Computation, 2007, 19 (9): 2515-2535.
[50] Rustum R, Adeloye AJ. Replacing outliers and missing values from activated sludge data using kohonen self-organizing map. Journal of Environmental Engineering, 2007, 133 (9): 909-916.
[51] Chen YY, Young KY. An SOM-based algorithm for optimization with dynamic weight updating. International Journal of Neural Systems, 2007, 17 (3): 171-181.
[52] Horio K, Yamakawa T. Handwritten character recognition based on relative position of local features extracted by self-organizing maps. International Journal of Innoveative Computing Information and Control, 2007, 3 (4): 789-798.
[53] Ohtsuka A, Tanii H, Kamiura N, et al. Self-organizing map based data detection of hematopoietic tumors. IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences, 2007, (6): 1170-1179.
[54] Zhuang HL, Chiu MS. An extended self-organizing map network for modeling and control of pulse jet fabric filters. Journal of Air & Waste Management Association, 2001, 51 (7): 1035-1042.
[55] Su MC, Liu IC. Application of the self-organizing feature map algorithm in facial image morphing. Neural Processing Letters, 2001, 14 (1): 35-47.
[56] Lopez RE, Munoz PJ, Gomez RA. A principal components analysisself-organizing map. Neural Networks, 2004, 17 (2): 261-270.
[57]Liao G, Liu S, Shi T, et al. Gearbox condition monitoring using self-organizing feature maps. Proceedings of the Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Science, 2004, 218 (1): 119-129.
[58] Guha R, Serra JR, Jurs PC. Using a Kohonen self-organizing map to generate representative training, cross validation and prediction sets for QSAR modelling. Abstracts of Parper of the American Chemical Society 226: U448-U448 159-COMP Part 1, 2003.
[59]Knopf GK, Sangole A. Interpolating scattered data using 2D self-organizing feature maps. Graphical Models, 2004, 66 (1): 50-69.
[60]Chen YP. A hybrid framework using SOM and fuzzy theory for textual classification in data mining. Lecture Notes in Artificial Intelligence, 2003, 2873: 153-167.
[61]Mahony S, Hendrix D, Golden A, et al. Transcription factor binding site identification using the self-organizing map. Bioinformatics, 2005, 21 (9): 1807-1814.
[62]Hoffmann M. Numerical control of kohonen neural network for scattered data approximation. Numerical Algorithms, 2005, 39 (1-3): 175-186.
[63]Matsuda Y, Yamaguchi K. An efficient MDS-based topographic mapping algorithm. Neurocomputing, 2005, 64: 285-299.
[64]Dragomir A, Mavroudi S, Bezerianos A. SOM-based class discovery exploring the ICA-reduced features of microarray expression profiles Comparative and Functional Genomics, 2004, 5 (8): 596-616.
[65] Budinich, M. A self-organizing neural network for the traveling salesmanproblem that is competitive with simulated annealing. Neural Computer, 1996, 8: 416-424.
[66]Leung, KS, Jin, HD, Xu, ZB. An expanding self-organizing neural network for the traveling salesman problem. Neurocomputing, 2004, 62: 267-292.
[67] Aras N, Oommen, BJ, Altinel, IK. The Kohonen network incorporating explicit statistics and its application to the traveling salesman problem. Neural Networks, 1999, (12): 1273-1284.
[68] Teuvo K. The Self-organizing map. Neurocomputing, 1998, 21:1-6.
[69]韩力群编著. 人工神经网络教程. 北京邮电大学出版社,2006.
[70]林昌,康泰兆. 基于自组织特征映射的矢量量化方法. 南京理工 大学学报,1999,23(5):393-396.
[71]王春立,陈益强. 基于 SOFM/HMM 模型的非特定人手语识别系 统. 计算机学报,2002,25(1):16-21.
[72]赵菁,彭慧敏,张家亮,谢维廉. 基于自组织特征映射神经网络的短期负荷预测. 贵州工业大学学报(自然科学版),2003,32(2):57-62.
[73]建岭,王磊,杨建华,高峰. 基于自组织特征映射网络的气体识别方法研究. 测控技术,2000,19(3):6-8.
[74]Frederico, CV, Adriao DD, Jose AC. An Efficient Approach of the SOM Algorithm to the Traveling Salesman Problem. Proceedings of the VII Brazilian Symposium on Neural Networks, 2002.
[75] Lu ZM, Sun SH. Vector Quantization Based on Self-Organizing Feature Map Neural Network. Journal of Image and Graphics, 2000, 5: 846-850.
[76] Abdolhamid M, Samerkae S, Takao E. A self-organizing neural network approach for multiple traveling salesman and vehicle routing problems.International Transactions in Operational Research, 1999, 591-606.
[77]韩江舟,葛世伦,盛永祥. 1999 年度沪深两市中期上是高科技公司股票聚类分析,华东船舶工业学院学报(自然科学版),2001,15(2):86-91.
[78]Hornik K, Wtinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Networks, 1989, 2: 359-366.
[79]Hornik K, Stinchcombe M, White H. Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Networks, 1990, 3: 551-560.
[80]林杰,郭耀煌. 用神经网络方法预测股票短期走势. 西南交通大学学报,1998,33(3):299-304.
[81]王上飞,周佩玲等. 径向基神经网络在股市预测中的应用. 预测,1998,(6):44-46
[82]郑丕谔,马艳华. 基于 RBF 网络的股市建模与预测. 天津大学学报,2000,33(4): 483-486.
[83]赵宏,邹雯等. 证券市场预测的神经网络方法. 系统工程理论与实践,1997(6):127-131.
[84]何芳,陈收. 基于扩展 Kalman 滤波的神经网络学习算法在股票预测中的应用. 系统工程,2003,21(6):75-79.
[85]孙丹, 张秀艳. 基于人工神经网络的股市预测模型. 吉林大学学报(信息科学版),2002,20(4):68-70.
[86]吴微,陈维强. 用于股市预测的 BP 算法的一些改进. 大连理工大学学报,2001,41(5):518-522.
[87]王培勋. 非线性回归的弹性分析在股票投资与行情预测中的应用, 系统工程理论与实践. 2000, (8): 100-104.
[88]周广旭. 一种新的时间序列分析算法及其在股票预测中的应用. 计算机应用,2005,25(9):2179-2184.
[89]殷光伟,郑丕谔. 应用小波理论进行股市预测,系统工程理论方法应用. 2004,13(6):543-547.
[90]李正学. 神经网络理论及其在股市短期预测中的应用. 吉林大学博士学位论文,2001.
[91]Kwon YK, Moon BR. A hybrid neurogenetic approach for stock forecasting. IEEE Transactions on Neural Networks, 2007, 18 (3): 851-864.
[92]Cheng P, Quek C, Mah ML. Predicting the impact of anticipatory action on US stock market - An event study using a neural fuzzy model. Computational Intelligence, 2007, 23 (2): 117-141.
[93]Liu F, N GS, Quek C. RLDDE: A novel reinforcement learning-based dimension and delay estimator for neural networks in time series prediction. Neurocomputing, 2007, 70 (7-9): 1331-1341.
[94]Thawornwong S, Enke D. The adaptive selection of financial and economic variables for use with artificial neural networks. Neurocomputing, 2004, 56: 205-232.
[95]Brabazon A. Financial time series modelling using neural networks: An assessment of the utility of a stacking methodology. Lecture Notes in Artificial Intelligence, 2002, 2464: 137-143.
[96]Chen YH, Abraham A, Yang J, et al. Hybrid methods for stock index modeling. Lecture Notes in Artificial Intelligence, 2005, 3614: 1067-1070.
[97] Kim HJ, Shin KS, Park K. Time delay neural networks and genetic algorithms for detecting temporal patterns in stock markets. LectureNotes in Computer Science, 2005, 3610: 1247-1255.
[98]Redko VG, Mosalov OP, Prokhorov DV. A model of evolution and learning. Neural Networks, 2005, 18 (5-6): 738-745.
[99] Watada J. Structural learning of neural networks for forecasting stock prices. Lecture Notes in Artificial Intelligence, 2006, 4253: 972-979.
[100]Chen HC, Magdon IM. Neural network for option pricing using multinomial tree. Lecture Notes in Computer Science, 2006, 4234: 360-369.
[101] Roh TH. Forecasting the volatility of stock price index. Lecture Notes in Artificial Intelligence, 2006, 4093: 424-435.
[102] Connor N, Madden MG. A neural network approach to predicting stock exchange movements using external factors. Knowled-Based Systems, 2006, 19 (5): 371-378.
[103] Liang X. Neural network method to predict stock price movement based on stock information entropy. Lecture Notes in Computer Science, 2006, 3973: 442-451.
[104]Huarng K, Yu THK. The application of neural networks to forecast fuzzy time series. PHYSICA A-Statistical Mechanics and Its Applications, 2006, 363 (2): 481-491 MAY.
[105]Yu L, Wang SY, Lai KK. Mining stock market tendency using GA-based support vector machines. Lecture Notes in Computer Science, 2005, 3828: 336-345.
[106]Fong B, Fong ACM, Hong GY, et al. An empirical study of volatility predictions: Stock market analysis using neural networks. Lecture Notes in Computer Science, 2005, 3828: 473-480.
[107]Shi, XH, Liang, YC, Lee, HP, Lin, WZ, Xu X, Lim, SP. Improved Elman networks and applications for controlling ultrasonic motors. Applied Artificial Intelligence, 2004, 18: 603-629.
[108]姜静情,梁艳春,孙延风,吴春国. 引入收益因素的 RBF 神经网络及其应用. 吉林大学学报(信息科学版),2002,20(3):68-72.
[109]Jingtao YAO, Chew LT. Time dependent Directional Profit Model for Financial Time Series Forecasting. International Joint Conference on Neural Networks, 2000, 291-296.
[110]Caldwell RB. Performances Metrics for Neural Network-based Trading System Development. Neurovest Journal, 1995, 3(2): 22-26.
[111]Refenes AN, Brntz, Y, Bunn DW, Burgess, AN, Zapranis AD. Financial Time Series Modeling with Discounted Least Squares Back Propagation. Neural Computing, 1997, 14(2): 123-138.
[112]Yao JT, Tan CL, Time dependent Directional Profit Model for Financial Time Series Forecasting. International Joint Conference on Neural Networks 2000, IEEE Computer Society, 2000, 291-296.
[113]赵振权,陈守东. 股票基本定价与定价模型的选择. 数量经济技术经济研究,2000,(1):52-55.
[114]蔡华. BP 神经网络与股票发行定价. 计算技术与自动化,2003,22(1):34-39.
[115]何斌,谭界忠. 大气环境质量综合评价的污染损失率法.环境保护,1998,(9):21-24.
[116]李祚泳,张欣莉,丁晶. 水质污染损害指数评价的普适公式. 水科学进展,2001,12(2):161-163.
[117]虞统. 空气质量日报中的空气污染指数. 城市管理与科技,2000,2(1):23-26.
[118]张文艺,蔡建安,朱静,渣胜国,朱晓庆. API 法在马鞍山市空气质量评价中的应用. 植物资源与环境学报,2003,12(1):62-63.
[119]Kennedy J, Eberhart R. Particle swarm optimization. Proc IEEE Int Conf on Neural Networks, 1995, 1942-1948.
[120]Eberhart R, Kennedy J. A new optimizer using particle swarm theory. Proc 6th Int Symposium on Micro Machine and Human Science, 1995, 39-43.
[121]李爱国,覃征,鲍复民,贺开平. 粒子群优化算法. 计算机工程与应用,2002,21:1-3.
[122]Angeline PJ. Evolutionary optimization versus particle swarm optimization: philosophy and performance differences. Evolutionary Programming, 1998, 7: 601-610.
[123]Clerc M, Kennedy J. The particle swarm-explosion, stability, and convergence in a multidimensional complex space. IEEE Transactions on Evolutionary Computation, 2002, 6: 58-73.
[124]Ioan CT. The particle swarm optimization algorithm: convergence analysis and parameter selection. Information Processing Letters, 2003, 85: 317–325.
[125]Shigenori N, Takamu G, Toshiki Y, Yoshikazu F. A hybrid particle swarm optimization for distribution state estimation. IEEE Transactions on Power Systems, 2003, 18: 60-68.
[126]Shi Y, Eberhart R. Parameter selection in particle swarm optimization. Proceedings of the Seventh Annual Conference on Evolutionary Programming, 1998, 591-600.
[127]Mikki S, Kishk A. Improved particle swarm optimization technique using hard boundary conditions. Microwave and Optical Technology Letters, 2005, 46 (5): 422-426.
[128]Liu B, Wang L, Jin YH, Tang F, Huang DX. Improved particle swarm optimization combined with chaos. Chaos Solitons Fractals, 2005, 25(5): 1261-1271.
[129]Jian W, Xue YC, Qian JX. An improved particle swarm optimization algorithm with disturbance. IEEE International Conference on Systems, Man and Cybernetics, 2004, 6: 5900-5904.
[130]Shi Y, Eberhart R. A modified particle swarm optimizer. IEEE World Congress on Computational Intelligence, 1998, 69-73.
[131]何斌, 谭界忠. 大气环境质量综合评价的污染损失率法. 环境保护,1998,(9):21-24.
[132]李祚泳,王钰,刘国东. 大气污染损失率评价模型参数的 GA 优化[J].环境科学研究,2001,14(2):7-10.
[133]钱莲文,吴承祯,宏伟,陈睿,宋萍,范海兰. 大气质量评价的污染危害指数法的改进. 福建林学院学报,2003,23(3):249-252.
[134]李祚泳,张欣莉,丁晶. 水质污染损害指数评价的普适公式. 水科学进展,2001,12(2):161-163.
[135]王俭,胡筱敏,郑龙熙,刘振山. BP 模型的改进及其在大气污染预报中的应用. 城市环境与城市生态,2002,15(5):17-19.
[136]Lu WZ, Fan HY, Leung AYT, Wong JCK. Analysis of pollutant level optimization. Environmental Monitoring and Assessment, 2002, 79: 217-223.
[137]Kesarkar AP, Dalvi M, Kaginalkar A. Coupling of the Weather Researchand Forecasting Model with AERMOD for pollutant dispersion modeling. A case study for PM10 dispersion over Pune, India. Atmospheric Environment, 2007, 41 (9): 1976-1988.
[138]Eder B, Kang D, Mathur R. An operational evaluation of the Eta-CMAQ air quality forecast model. Atmospheric Environment, 2006, 40 (26): 4894-4905.
[139]Ozcan HK, Bilgil E, Sahin U, Ucan ON, Bayat C. Modeling of trophospheric ozone concentrations using genetically trained multi-level cellular neural networks. Advances in Atmospheric Sciences, 2007, 24 (5): 907-914.
[140]Li ZY, Wang Y, Liu GD. Optimum estimation of parameters on assessment model of pollution loss rate of atmospheric environmental quality using genetic algorithm. Research of Environmental Sciences, 2001, 14: 7-10.
[141]Qian LW, Wu CZ, Hong W, Chen R, Fan HL. Study on the improvement of index formula of pollution harm for atmosphere quality assessment. Journal of Fujian College of Forestry, 2003, 23: 249-252.
[142]Schlink U, Herbarth O, Richter M. Statistical models to assess the health effects and to forecast ground-level ozone. Environmental Modelling & Software, 2006, 21 (4): 547-558.
[143]Farago I, Georgiev K, Havasi. An Advances in Air Pollution Modeling for Environmental Security. Advances in Air Pollution Modeling for Environmental Security, 2005.
[144]San JR, Perez JL, Gonzalez RM. The use of MM5-CMAQ air pollution modelling system for real-time and forecasted air quality impact ofindustrial emissions. Advances in Air Pollution Modeling for Environmental Security, 2005, 327-336.
[145]Lu WZ, Wang WJ. Potential assessment of the “support vector machine” method in forecasting ambient air pollutant trends. Chemosphere, 2005, 59 (5): 693-701.
[146]Pohjola MA, Rantamaki M, Kukkonen J. Meteorological evaluation of a severe air pollution episode in Helsinki on 27-29 December 1995. Boreal Environment Research, 2004, 9(1): 75-87 27.
[147]Rochelle NEJ, Winter C, Barron C, et al. Artificial neural network analysis of factors controling ecosystem metabolism in coastal systems. Ecological Applications, 2007, 17 (5): S185-S196.
[148]Sterjovski Z, Pitrun M, Nolan D, et al. Artificial neural networks for predicting diffusible hydrogen content and cracking susceptibility in rutile flux-cored arc welds. Journal of Materials Processing Technology, 2007, 184 (1-3): 420-427.
[149]Boulanger JP, Martinez F, Segura EC. Projection of future climate change conditions using IPCC simulations, neural networks and Bayesian statistics. Part 2: Precipitation mean state and seasonal cycle in South America. Climate Dynamics, 2007, 28 (2-3): 255-271.
[150]Dall OM, Harrison RM. Chemical characterisation of single airborne particles in Athens (Greece) by ATOFMS. Atomspheric Environment, 2006, 40 (39): 7614-7631.
[151]Barthes L, Mallet C, Brisseau O. A neural network model for the separation of atmospheric effects on attenuation: Application to frequency scaling. Radio Science, 2006, 41 (4): Art. No. RS4012.
[152]Martin JD, Morton YT, Zhou QH. Neural network development for the forecasting of upper atmosphere parameter distributions. Advances in Space Research, 2005, 36 (12): 2480-2485.
[153]Fatemi MH. Prediction of ozone tropospheric degradation rate constant of organic compounds by using artificial neural networks. Analytica Chimica Acta, 2006, 556 (2): 355-363.
[154]Pasini A, Lore M, Ameli F. Neural network modelling for the analysis of forcings/temperatures relationships at different scales in the climate system. Ecological Modelling, 2006, 191 (1): 58-67.
[155]Del FF, Iapaolo MF, Casadio S. Intercomparison between GOME ozone profiles retrieved by neural network inversion schemes and ILAS products. Journal of Atmospheric and Oceanic Technology, 2005, 22 (9): 1433-1440.
[156]Abdul WSA. IER photochemical smog evaluation and forecasting of short-term ozone pollution levels with artificial neural networks. Process Safety and Environmental Protection, 2001, 79 (B2): 117-128.
[157]Niang A, Gross L, Thiria S, et al. Automatic neural classification of ocean colour reflectance spectra at the top of the atmosphere with introduction of expert knowledge. Remote Sensing of Environment, 2003, 86 (2): 257-271.
[158]Krasnopolsky VM, Schiller H. Some neural network applications in environmental sciences. Part I: forward and inverse problems in geophysical remote measurements. Neural Networks, 2003, 16 (3-4): 321-334.
[159]Brunelli U, Piazza V, Pignato L, Sorbello F, Vitabile S. Two-days aheadprediction of daily maximum concentrations of SO2, O-3, PM10, NO2, CO in the urban area of Palermo, Italy. Atmospheric Environment, 2007, 41 (14): 2967-2995.
[160] Del FF, Ortenzi A, Casadio S, et al. Application of neural algorithms for a real-time estimation of ozone profiles from GOME measurements. IEEE Transctions on Geoscience and Remote Sensing, 2002, 40 (10): 2263-2270.
[161]Nasseh S, Mohebbi A, Jeirani Z, Sarrafi A. Predicting pressure drop in venturi scrubbers with artificial neural networks. Journal of Hazardous Materials, 2007, 143 (1-2): 144-149.
[162]Shi XH, Liang YC, Lee HP, Lin WZ, Xu X, Li M. Improved Elman networks and applications for controlling ultrasonic motors. Applied Artificial Intelligence, 2004, 18: 603-629.