连续型Schaefer产量模型和BP网络模型在渔业中的应用研究
|
摘要
在渔业资源评估中,传统的评估模型有产量模型、消耗模型和年龄结构模型。随着计算机技术的发展,地理信息系统、遥感技术和人工神经网络技术型等逐步应用到渔业资源的评估和预测当中。
剩余产量模型(surplus production model)是现代渔业资源评估和管理的主要理论模型之一。该模型不像动态模型考虑资源群体的年龄结构等因素,它把资源群体的补充、生长和自然死亡综合起来作为资源群体大小的一个单变函数进行分析,然后推导出我们所需要的剩余产量模型的数学公式。剩余产量模型(surplusproduction model)具有简单的形式和所需数据和参数相对较少的特点,在渔业研究中可以被简单的应用,并且它估计的管理参数(最大持续产量和最佳捕捞努力量)比较容易得出和理解,为渔业动态研究提供不同的思路。BP网络模型是近年来新兴的评估方法,因其高度并行性、自适性和自学习功能而备受人们关注。
本研究以丹江口水库翘嘴鲌资源和东海区总渔获量为例,对连续型Schaefer模型和BP网络模型进行了比较研究,研究内容和主要结果如下:
(1)利用连续型Schaefer模型及丹江口水库翘嘴鲌的产量和捕捞努力量估算B_i(初始生物量)、r(种群内禀增长率)、K(最大环境容纳量)、q(可捕系数),MSY(最大可持续产量)和相应的f_(MSY)(最适捕捞努力量),得到结果为:B_1=186302 kg,r=0.1965,K=2200429 kg,q=0.2123,MSY=113216 kg,f_(MSY)=458172。
(2)利用连续型Schaefer模型对东海区总渔获量进行评估,估算结果为:B_1=12236567 t,K=29546790,q=0.398,MSY=4109876 t,f_(MSY)=13.63。
(3)利用BP神经网络模型建立丹江口水库翘嘴鲌渔获量预测系统,利用1981～1985年渔获量作为可信度比较指标,估算结果为:1981～1985年渔获量预测值分别为108150kg,119339kg,126845kg,114010kg,109652kg。
(4)利用BP神经网络模型建立东海区年总渔获量预测系统,利用1991～1995年渔获量作为可信度比较指标,估算结果为:1991～1995年渔获量预测值分别为4094768t,4709258t,5349900t,6349296t,7314227t。
(5)比较两种模型在不同渔业应用中的评价结果准确度。参数估计偏差值为:在丹江口水库中,B_1:9.7,r:2.7,K:3.9,q:2.3,MSY:1.6,f_(MSY):1.0;在东海区渔业中:B_1:17,r:8.8,K:12,q:7.5,MSY:1.7,f_(MSY):1.3。渔获量预测值与真实值之间的误差率结果为:在丹江口水库中,1981～1985年依次是0.0672,0.0621,0.0503,0.0341,0.0485;在东海区渔业中,1991～1995年依次是0.0040,0.052 1,0.0745,0.0736,0.0767。
In fish stock assessment,traditional models have three main types,there are production models,depletion models,and age-structured models.With the development of computer technology,geographic information system、remote sensing technology and artificial neural networks technology gradually applied to the assessment and prediction of fisheries resources.
Surplus production models are major academic models in assessment and management of modern fishery resources.Surplus production models can be simply used in fishery assessment because of their simplicity and relatively undemanding data needs.Surplus-production models generally do not incorporate age structure which is useful for fish population dynamics.These models are of particular value when the catch can not be aged,or can not be aged precisely.Moreover, Surplus-production models are classical methods to predict the MSY(maximum sustainable yield) for fisheries management,which is one of the major fisheries management goals.BP neural network model is emerging in recent years,because of its high degree of parallelism,adaptive self-leaming function,it has people's attention.
In this study,the author using the Culter alburnus resources in DanJiangkou Reservoir and the annual fish catch in East China Sea as an example,to compare Schaefer model and BP model,the contents and main results as follows:
(1) Using the continuous Schaefer model and C.alburnus resources in DanJiangkou Reservoir to estimate B_1(initial biomass),r(innate rate of increase),K (environmental carrying capacity),q(quotiety of catch),MSY(maximum sustainable fishing yield) and f_(MSY).The results are:B_1=186302 kg,K=2200429 kg,q=0.2123, MSY=113216 kg,f_(MSY)=458172.
(2) Using the continuous Schaefer model to estimate the total catch in East China.Sea,results are:B_1=12236567 t,K=29546790,q=0.398,MSY=4109876 tk f_(MSY)=13.63.
(3) Using the BP neural network model to build an yield prediction model for DanJiangkou Reservoir,using the data from 1981 to 1985 as indicate of comparison, the results are:predictive value from 1981 to 1985 followed by 108150 kg,119339 kg, 126845 kg,114010 kg,109652 kg.
(4) Using the BP neural network model to build an yield prediction model for East China Sea,using the data from 1991 to 1995 as indicate of comparison,the results are:predictive value from 1991 to 1995 followed by 4094768 t,4709258 t, 5349900 t,6349296 t,7314227t.
(5) Compare the results' accuracy of assessment using Schaefer model and BP model in different fisheries.Deviation of parameters are: in DanJiangkou Reservoir,B_1:9.7,r:2.7,K:3.9,q:2.3,MSY:1.6,f_(MSY):1.0; in East China Sea:B_1:17,r:8.8,K:12,q:7.5,MSY:1.7,f_(MSY):1.3. The error rate between predictive value and true value are:in DanJiangkou Reservoir, from 1981 to 1985 followed by 0.0672,0.0621,0.0503,0.0341,0.0485;in East China Sea:from 1991 to 1995 followed by 0.0040,0.0521,0.0745,0.0736,0.0767.
剩余产量模型(surplus production model)是现代渔业资源评估和管理的主要理论模型之一。该模型不像动态模型考虑资源群体的年龄结构等因素,它把资源群体的补充、生长和自然死亡综合起来作为资源群体大小的一个单变函数进行分析,然后推导出我们所需要的剩余产量模型的数学公式。剩余产量模型(surplusproduction model)具有简单的形式和所需数据和参数相对较少的特点,在渔业研究中可以被简单的应用,并且它估计的管理参数(最大持续产量和最佳捕捞努力量)比较容易得出和理解,为渔业动态研究提供不同的思路。BP网络模型是近年来新兴的评估方法,因其高度并行性、自适性和自学习功能而备受人们关注。
本研究以丹江口水库翘嘴鲌资源和东海区总渔获量为例,对连续型Schaefer模型和BP网络模型进行了比较研究,研究内容和主要结果如下:
(1)利用连续型Schaefer模型及丹江口水库翘嘴鲌的产量和捕捞努力量估算B_i(初始生物量)、r(种群内禀增长率)、K(最大环境容纳量)、q(可捕系数),MSY(最大可持续产量)和相应的f_(MSY)(最适捕捞努力量),得到结果为:B_1=186302 kg,r=0.1965,K=2200429 kg,q=0.2123,MSY=113216 kg,f_(MSY)=458172。
(2)利用连续型Schaefer模型对东海区总渔获量进行评估,估算结果为:B_1=12236567 t,K=29546790,q=0.398,MSY=4109876 t,f_(MSY)=13.63。
(3)利用BP神经网络模型建立丹江口水库翘嘴鲌渔获量预测系统,利用1981～1985年渔获量作为可信度比较指标,估算结果为:1981～1985年渔获量预测值分别为108150kg,119339kg,126845kg,114010kg,109652kg。
(4)利用BP神经网络模型建立东海区年总渔获量预测系统,利用1991～1995年渔获量作为可信度比较指标,估算结果为:1991～1995年渔获量预测值分别为4094768t,4709258t,5349900t,6349296t,7314227t。
(5)比较两种模型在不同渔业应用中的评价结果准确度。参数估计偏差值为:在丹江口水库中,B_1:9.7,r:2.7,K:3.9,q:2.3,MSY:1.6,f_(MSY):1.0;在东海区渔业中:B_1:17,r:8.8,K:12,q:7.5,MSY:1.7,f_(MSY):1.3。渔获量预测值与真实值之间的误差率结果为:在丹江口水库中,1981～1985年依次是0.0672,0.0621,0.0503,0.0341,0.0485;在东海区渔业中,1991～1995年依次是0.0040,0.052 1,0.0745,0.0736,0.0767。
In fish stock assessment,traditional models have three main types,there are production models,depletion models,and age-structured models.With the development of computer technology,geographic information system、remote sensing technology and artificial neural networks technology gradually applied to the assessment and prediction of fisheries resources.
Surplus production models are major academic models in assessment and management of modern fishery resources.Surplus production models can be simply used in fishery assessment because of their simplicity and relatively undemanding data needs.Surplus-production models generally do not incorporate age structure which is useful for fish population dynamics.These models are of particular value when the catch can not be aged,or can not be aged precisely.Moreover, Surplus-production models are classical methods to predict the MSY(maximum sustainable yield) for fisheries management,which is one of the major fisheries management goals.BP neural network model is emerging in recent years,because of its high degree of parallelism,adaptive self-leaming function,it has people's attention.
In this study,the author using the Culter alburnus resources in DanJiangkou Reservoir and the annual fish catch in East China Sea as an example,to compare Schaefer model and BP model,the contents and main results as follows:
(1) Using the continuous Schaefer model and C.alburnus resources in DanJiangkou Reservoir to estimate B_1(initial biomass),r(innate rate of increase),K (environmental carrying capacity),q(quotiety of catch),MSY(maximum sustainable fishing yield) and f_(MSY).The results are:B_1=186302 kg,K=2200429 kg,q=0.2123, MSY=113216 kg,f_(MSY)=458172.
(2) Using the continuous Schaefer model to estimate the total catch in East China.Sea,results are:B_1=12236567 t,K=29546790,q=0.398,MSY=4109876 tk f_(MSY)=13.63.
(3) Using the BP neural network model to build an yield prediction model for DanJiangkou Reservoir,using the data from 1981 to 1985 as indicate of comparison, the results are:predictive value from 1981 to 1985 followed by 108150 kg,119339 kg, 126845 kg,114010 kg,109652 kg.
(4) Using the BP neural network model to build an yield prediction model for East China Sea,using the data from 1991 to 1995 as indicate of comparison,the results are:predictive value from 1991 to 1995 followed by 4094768 t,4709258 t, 5349900 t,6349296 t,7314227t.
(5) Compare the results' accuracy of assessment using Schaefer model and BP model in different fisheries.Deviation of parameters are: in DanJiangkou Reservoir,B_1:9.7,r:2.7,K:3.9,q:2.3,MSY:1.6,f_(MSY):1.0; in East China Sea:B_1:17,r:8.8,K:12,q:7.5,MSY:1.7,f_(MSY):1.3. The error rate between predictive value and true value are:in DanJiangkou Reservoir, from 1981 to 1985 followed by 0.0672,0.0621,0.0503,0.0341,0.0485;in East China Sea:from 1991 to 1995 followed by 0.0040,0.0521,0.0745,0.0736,0.0767.
引文
1.陈鸿.人工神经网络在宏观经济预测中的应用研究.[硕士学位论文].重庆大学图书馆,2005
2.陈莉.安徽省农民收入预测与分析.技术经济,2003,9
3.陈新军,周应祺.基于BP模型的渔业资源可持续利用预警系统评价.中国渔业经济,2003,3
4.陈作志,邱永松,贾晓平,黄梓荣,王跃中.基于EcopNh模型的北部湾生态系统结构和功能.中国水产科学,2008,5
5.从爽.面向MATLAB工具箱的神经网络理论与应用.北京:中国科学技术大学出版社,2003,12
6.崔雪森,樊伟,沈新强.西北太平洋柔鱼渔情速报系统的开发.水产学报,2003,27(6)
7.杜云艳,周成虎,崔海燕等.遥感与GIS支持下的海洋渔业空间分布研究.海洋学报,2002,24(5)
8.高隽.神经网络原理及仿真.北京:机械工业出版社,2003
9.高俊斌.MATLAB6.5语言与程序设计.武汉:华中理工大学出版社,1998
10.郭晶,杨章玉.MATLAB6.5辅助神经网络分析与设计.北京:电子工业出版社,2004
11.何耀华,夏志忠.BP网络的快速自适应学习算法.系统工程理论与实践,2000,1
12.胡建军.BP网络的权值诱导与层次训练算法,计算机科学,1998,25(1):60-63
13.胡守仁,余少波,戴葵.神经网络导论.北京:国防科技大学出版社,1993
14.姜涛,刘玉,李适宇,王晓红,段丽杰.南海北部大陆架海洋生态系统Ecosmi 模型的动态模拟.中山大学学报,2007,46(4)
15.焦李成.神经网络计算.西安:西安电子科技大学出版社,1992
16.李晓蜂,刘光中.人工神经网络BP算法的改进及其应用.四川大学学报,2000,3
17.刘光中.人工神经网络BP算法的改进和结构的自调整.运筹学学报,2001 5(1)
18.刘群,任一平,沈海学,王艳君,尤凯.渔业资源评估在渔业管理中的作用.海洋湖沼通报,2003,1
19.刘曙光.前馈神经网络中的反向传播算法及其改进.进展与展望,计算机科学,1996,23(1)
20.刘玉,姜涛,李适宇.南海北部大陆架海洋生态系统Ecopath模型的应用与分析.中山大学学报,2007,46(1):123-127
21.楼顺天,施阳.基于MATLAB的系统分析与设计-神经网络.西安:西安电子科技大学出版社,1998
22.沈新强,樊伟,韩士鑫.中心渔场智能预报系统的设计与实现.中国水产科学,2000,2
23.石山铭,刘豹.神经网络模型用于多变量综合预测.系统工程学报,1994,9(1)
24.孙明玺.预测学概论.杭州:浙江教育出版社,1989
25.覃光华,丁晶,刘国东.自适应BP算法及其在河道洪水预报上的应用.水科学进展,2002(1):37-41
26.唐晓萍.数据挖掘与知识发现综述.电脑开发与应用,2002,15
27.王文剑.一种确定网络结构的自适应方法.中国人工智能学会第八届年会论文集,1994
28.王雪辉,杜飞雁.大亚湾海域生态系统模型研究Ⅰ:能量流动模型初探.南方水产,2005,1(3):1-8
29.王宗军.基于B-P神经网络的复杂对象系统多目标综合评价方法及其应用.小型微型计算机系统,1995,16(1):27-28
30.闻新,周露.MATLAB神经网络仿真与应用.北京:科学出版社,2003
31.吴秀清,徐云翔,周蓉.面向MATLAB神经网络工具箱的图像数据融合算法及实现.计算机工程,2000,26
32.向小东.基于神经网络及混沌理论的非线性时间序列预测研究.[博士学位论文].成都:西南交通大学,2001
33.熊国胜.丹江口水库翘嘴红鲌资源评析与合理利用.水产学报,1990,14(2)
34.徐克学.生物数学.北京:科学出版社,1999:76-83
35.许东,吴铮.基于MATLAB6.x的系统分析与设计—神经网络.西安:西安电子科技大学出版社,2002,21-24
36.阎平凡,张长水.人工神经网络与模拟进化计算.北京:清华大学出版社,2000
37.杨再福,陈立侨,陈勇.太湖渔业资源变化与对策.淡水渔业,2004,34(6):3-5
38.叶昌臣,黄斌.渔业生物数学-资源的评估与管理.北京:农业出版社.1990
39.袁曾任.人工神经网络及其应用.北京:清华大学出版社,1999,120-130
40.詹秉义.渔业资源评估.北京:农业出版社,1995
41.战培荣,赵吉伟,董崇智.兴凯湖翘嘴鱼自的生长特性海洋与湖沼,2005,36(2):146-151
42.张海燕,冯天瑾.新的组合激活函数BP网络模型研究.青岛海洋大学学报,2002,32
43.张家波.丹江口水库凶猛鱼集团生长特性组型的聚类分析.水生生物学报,1999,23(6):689-695
44.张家波,樊启学,王卫民.老江河鲤鱼种群动态研究.华中农业大学,1998,17(4):395-400
45.张建军,李国平.ANN模型的经济学应用及其发展趋势.经济学家,2006,5
46.张健东.中华乌塘鳄的生长、生长模型和生活史类型.生态学报,2002,22(6):841-846
47.张立明.人工神经网络的模型及其应用.上海:复旦大学出版社,1993
48.张鹏.基于神经网络的预测方法及其在物流系统中应用研究.[硕士学位论文].武汉:武汉理工大学,2002,2.
49.张堂林,崔奕波,方榕乐,谢松光,李钟杰.保安湖麦穗鱼种群生物学种群动态水生生物学报,2000,24(5):537-544
50.张月霞,苗振清.渔业资源的评估方法和模型研究进展.浙江海洋学院学报,2006,25(3)
51.张志涌.掌握和精通MATLAB.北京:北京航空航天大学出版社,1997
52.郑立群.人工神经网络方法在投资风险评价中的应用..管理科学学报,19992(4)
53.周开利,康耀红.神经网络模型及其MATLAB仿真程序设计.北京:清华大学出版社,2005
54.Allen K R,Hancock D A.A personal retrospect of the history of fisheries modeling.In population dynamics for fisheries management.Australian society for fish Biology.1994:21-28
55.ALLEN K R.Some methods for estimating exploited populations.Fish Res Bd can,1966,23:1553-1574
56.Barber W E.Maximum sustainable yield lives on.North American J.of Fisheries Management,1988,8:153-157
57.Butterworth D S,Andrew P A.Dynamic catch-effort models for the hake stocks in ICSEAF Divisions.Comm SE Atl Fish,1984,11(1):29-58
58.Caddy J F,McGarvey R.Targets or limits for management of fisheries.North American J.of Fisheries Management,1996,16:479-487
59.Caddy J,Deffeo O.Fitting the exponential and logistic surplus yield models with mortality data:some explorations and new perspectives.Fish Res,1996,25:39-62
60.Chapman D G..Estimation of population size and sustainable yield of sea whales in the Antarctic.Rep Int whal comm,1974,24:82-90
61.Chapman D W.Production.In:Methods for assessment of fish population in fresh waters.IBP Handbook No.3.Blackwell Scientific Publications,Oxford,U.K.1971
62.Chen P,Fernandez B.R.,Gosh J.Artificial Neural Networks,ASME Press,1995
63.Chua B L,Khalid M,Yusof R.An enhanced intelligent database engine by neural network and data mining:TENCON 2000.Proceedings,2000,2
64.DELURG D B.On estimation of biological populations.Biometrics,1947,3:145-167
65.Demuth,Howard B.Neural network design.Beijing:China Machine Press,2002
66. DERSOR B. Harvesting strategies and parameter estimation for an age-structured model. Can J Fish Aquat Sci, 1980, 37: 339-348.
67. Finlay J. Neural networks and pattern recognition in human-computer interaction. New York: Ellis Horwood, 1992
68. Fox W W. An exponential yield model for equations from fishery science and a new formulation. Trans Amre Fish Soc, 1970, 99: 80-88
69. Fox W W. Fitting the generalized stock production model by least-squares and equilibrium approximation. U. S. Fish Bull, 1975, 73: 23-37
70. Francisco A S, Manuel Z R. Simulated response to harvesting strategies in an exploited ecosystem in the southwestern Gulf of Mexico. Ecological modeling, 2004,172:421-432
71. Freon P, Soria M, Mullon C, Gerlotto F. Diurnal Variation in fish density estimate during acoustic surveys in relation to spatial distribution and avoidance reaction. Aquat Liv Resour, 1993, 6: 221-234
72. Garcia S. Indicators for sustainable development of fisheries: Land quality indicators and their use in sustainable agriculture and rural development. Rome, 1997, 131-162
73. Graham M. Modern theory of exploiting a fishery and applications to North Sea trawling. Cons Int Explor Mer, 1935, 10: 264-274
74. Gulland J A. Fish population dynamics (2nd edition). Chichester: John Wiley and Sons. 1988.
75. Hagan M T, Menhaj M B.Training feed forward networks. with Marquart algorithm. IEEE Trans on Neural Net-works, 1994, 5(6): 989-993
76. Han J W. Conference Tutorial Notes: Data Mling Techniques. Proc the ACM SIGMOD
77. Hema R, Alexey G.. Inductive learning algorthms for complex system modeling. CRC Press Inc, 1994
78. Hilborn R, Walters C J. Quantitative fisheries stock assessment: choice, dynamics & Uncertainty. New York, Chapman and Hall, 1992, 570
79. International Conference on Management of Data, Montrea, Canada, 1996
80. Kimura D K, Balsiger J W. Generalized stock reduction analysis. Can J Fish Aquat Sci, 1984, 41: 1325-1333
81. Kimura D K. Changes to stock reduction analysis indicated by schnutes general theory. Can J Fish Aquat Sci, 1985, 42: 2059-2060
82. Lapeds A, Farber. Genetic Data Base Analysis with Neural Networks. Neural Information Processing System-Nature and Synthetic. 2002, 2(10): 1987
83. Leslie D H, Davis H S.An attempt to determine the absolute number of rats on a given area. Anim Ecol, 1939, 8: 94-113
84. Lippmann R P. An introduction to computing with neural nets. IEEE Acoust. Speech Signal Process, 1987, 4(2): 4-22
85. Moran P A. A mathematical theory of animal trapping. Brometrika, 1951, 38:307-311
86. Omand D N. A study on populations of fish based on catch-effort statistics. J. Mahage, 1951, 15:88-98
87. Pauly D. Theory and management of tropical multispecies stocks: A review with emphasis on the Southeast Asian demersal fisheries. ICLARM Studies and Reviews. 1979, 1:35
88. Pella J J, Tomlinson P K. A generalized stock production model. Bull. Inter-Am. Trop. Tuna Comm, 1969, 13: 419-496
89. Pinnegar J K, Polunin V C. Predicting indirect effects of fishing in Mediterranean rocky littoral communities using a dynamic simulation model. Ecological modeling, 2004, 172: 249-267
90. Polacheck T, Hilborn R, Punt A E. Fitting surplus production models: comparing methods and measuring uncertainty. Can J. Fish Aquat Sci, 1993, 50: 2597-2607
91. Prager M H. A suite of extensions to a nonequilibrium surplus-production model. Fishery Bulletin, 1994, 92: 374-389
92. Rumelhart D E, McClellan J L. Parallel Distributed Processing-Exploration in the Microstructure of Cognition. MIT Press, 1986,1
93. Schaefer M B. Some aspects of dynamics of populations important to the management of commercial marine fisheries. Int. Amer. TroP. Tuna Comm Bul, 1954,1:25-56
94. Schunte J. A general theory for analysis of catch and effort docta. Can J Fish Aquat Sci, 1985,42:414-429
95. Walter S C, Chrestense N, Pauly D. Representing density dependent consequences of life history strategies in aquatic ecosystems: Ecosim II. Ecosystems, 2000(3): 70-83
96. Widrow B. 30 years of adaptive neural neworks:perceptron. Madaline and B-P. Proc IEEE, 1990, 78(9): 1415-1442
97. Xiao Y. A general theory of fish stock assessment models. Ecological Modelling, 2000, 128
98. Zippin C. An evaluation of the removal method of estimating animal populations. Biometrics, 1956, 12: 163-189
99. Zippin C. The removal method of population estimation. J wild ugmt, 1958, 22:82-90
2.陈莉.安徽省农民收入预测与分析.技术经济,2003,9
3.陈新军,周应祺.基于BP模型的渔业资源可持续利用预警系统评价.中国渔业经济,2003,3
4.陈作志,邱永松,贾晓平,黄梓荣,王跃中.基于EcopNh模型的北部湾生态系统结构和功能.中国水产科学,2008,5
5.从爽.面向MATLAB工具箱的神经网络理论与应用.北京:中国科学技术大学出版社,2003,12
6.崔雪森,樊伟,沈新强.西北太平洋柔鱼渔情速报系统的开发.水产学报,2003,27(6)
7.杜云艳,周成虎,崔海燕等.遥感与GIS支持下的海洋渔业空间分布研究.海洋学报,2002,24(5)
8.高隽.神经网络原理及仿真.北京:机械工业出版社,2003
9.高俊斌.MATLAB6.5语言与程序设计.武汉:华中理工大学出版社,1998
10.郭晶,杨章玉.MATLAB6.5辅助神经网络分析与设计.北京:电子工业出版社,2004
11.何耀华,夏志忠.BP网络的快速自适应学习算法.系统工程理论与实践,2000,1
12.胡建军.BP网络的权值诱导与层次训练算法,计算机科学,1998,25(1):60-63
13.胡守仁,余少波,戴葵.神经网络导论.北京:国防科技大学出版社,1993
14.姜涛,刘玉,李适宇,王晓红,段丽杰.南海北部大陆架海洋生态系统Ecosmi 模型的动态模拟.中山大学学报,2007,46(4)
15.焦李成.神经网络计算.西安:西安电子科技大学出版社,1992
16.李晓蜂,刘光中.人工神经网络BP算法的改进及其应用.四川大学学报,2000,3
17.刘光中.人工神经网络BP算法的改进和结构的自调整.运筹学学报,2001 5(1)
18.刘群,任一平,沈海学,王艳君,尤凯.渔业资源评估在渔业管理中的作用.海洋湖沼通报,2003,1
19.刘曙光.前馈神经网络中的反向传播算法及其改进.进展与展望,计算机科学,1996,23(1)
20.刘玉,姜涛,李适宇.南海北部大陆架海洋生态系统Ecopath模型的应用与分析.中山大学学报,2007,46(1):123-127
21.楼顺天,施阳.基于MATLAB的系统分析与设计-神经网络.西安:西安电子科技大学出版社,1998
22.沈新强,樊伟,韩士鑫.中心渔场智能预报系统的设计与实现.中国水产科学,2000,2
23.石山铭,刘豹.神经网络模型用于多变量综合预测.系统工程学报,1994,9(1)
24.孙明玺.预测学概论.杭州:浙江教育出版社,1989
25.覃光华,丁晶,刘国东.自适应BP算法及其在河道洪水预报上的应用.水科学进展,2002(1):37-41
26.唐晓萍.数据挖掘与知识发现综述.电脑开发与应用,2002,15
27.王文剑.一种确定网络结构的自适应方法.中国人工智能学会第八届年会论文集,1994
28.王雪辉,杜飞雁.大亚湾海域生态系统模型研究Ⅰ:能量流动模型初探.南方水产,2005,1(3):1-8
29.王宗军.基于B-P神经网络的复杂对象系统多目标综合评价方法及其应用.小型微型计算机系统,1995,16(1):27-28
30.闻新,周露.MATLAB神经网络仿真与应用.北京:科学出版社,2003
31.吴秀清,徐云翔,周蓉.面向MATLAB神经网络工具箱的图像数据融合算法及实现.计算机工程,2000,26
32.向小东.基于神经网络及混沌理论的非线性时间序列预测研究.[博士学位论文].成都:西南交通大学,2001
33.熊国胜.丹江口水库翘嘴红鲌资源评析与合理利用.水产学报,1990,14(2)
34.徐克学.生物数学.北京:科学出版社,1999:76-83
35.许东,吴铮.基于MATLAB6.x的系统分析与设计—神经网络.西安:西安电子科技大学出版社,2002,21-24
36.阎平凡,张长水.人工神经网络与模拟进化计算.北京:清华大学出版社,2000
37.杨再福,陈立侨,陈勇.太湖渔业资源变化与对策.淡水渔业,2004,34(6):3-5
38.叶昌臣,黄斌.渔业生物数学-资源的评估与管理.北京:农业出版社.1990
39.袁曾任.人工神经网络及其应用.北京:清华大学出版社,1999,120-130
40.詹秉义.渔业资源评估.北京:农业出版社,1995
41.战培荣,赵吉伟,董崇智.兴凯湖翘嘴鱼自的生长特性海洋与湖沼,2005,36(2):146-151
42.张海燕,冯天瑾.新的组合激活函数BP网络模型研究.青岛海洋大学学报,2002,32
43.张家波.丹江口水库凶猛鱼集团生长特性组型的聚类分析.水生生物学报,1999,23(6):689-695
44.张家波,樊启学,王卫民.老江河鲤鱼种群动态研究.华中农业大学,1998,17(4):395-400
45.张建军,李国平.ANN模型的经济学应用及其发展趋势.经济学家,2006,5
46.张健东.中华乌塘鳄的生长、生长模型和生活史类型.生态学报,2002,22(6):841-846
47.张立明.人工神经网络的模型及其应用.上海:复旦大学出版社,1993
48.张鹏.基于神经网络的预测方法及其在物流系统中应用研究.[硕士学位论文].武汉:武汉理工大学,2002,2.
49.张堂林,崔奕波,方榕乐,谢松光,李钟杰.保安湖麦穗鱼种群生物学种群动态水生生物学报,2000,24(5):537-544
50.张月霞,苗振清.渔业资源的评估方法和模型研究进展.浙江海洋学院学报,2006,25(3)
51.张志涌.掌握和精通MATLAB.北京:北京航空航天大学出版社,1997
52.郑立群.人工神经网络方法在投资风险评价中的应用..管理科学学报,19992(4)
53.周开利,康耀红.神经网络模型及其MATLAB仿真程序设计.北京:清华大学出版社,2005
54.Allen K R,Hancock D A.A personal retrospect of the history of fisheries modeling.In population dynamics for fisheries management.Australian society for fish Biology.1994:21-28
55.ALLEN K R.Some methods for estimating exploited populations.Fish Res Bd can,1966,23:1553-1574
56.Barber W E.Maximum sustainable yield lives on.North American J.of Fisheries Management,1988,8:153-157
57.Butterworth D S,Andrew P A.Dynamic catch-effort models for the hake stocks in ICSEAF Divisions.Comm SE Atl Fish,1984,11(1):29-58
58.Caddy J F,McGarvey R.Targets or limits for management of fisheries.North American J.of Fisheries Management,1996,16:479-487
59.Caddy J,Deffeo O.Fitting the exponential and logistic surplus yield models with mortality data:some explorations and new perspectives.Fish Res,1996,25:39-62
60.Chapman D G..Estimation of population size and sustainable yield of sea whales in the Antarctic.Rep Int whal comm,1974,24:82-90
61.Chapman D W.Production.In:Methods for assessment of fish population in fresh waters.IBP Handbook No.3.Blackwell Scientific Publications,Oxford,U.K.1971
62.Chen P,Fernandez B.R.,Gosh J.Artificial Neural Networks,ASME Press,1995
63.Chua B L,Khalid M,Yusof R.An enhanced intelligent database engine by neural network and data mining:TENCON 2000.Proceedings,2000,2
64.DELURG D B.On estimation of biological populations.Biometrics,1947,3:145-167
65.Demuth,Howard B.Neural network design.Beijing:China Machine Press,2002
66. DERSOR B. Harvesting strategies and parameter estimation for an age-structured model. Can J Fish Aquat Sci, 1980, 37: 339-348.
67. Finlay J. Neural networks and pattern recognition in human-computer interaction. New York: Ellis Horwood, 1992
68. Fox W W. An exponential yield model for equations from fishery science and a new formulation. Trans Amre Fish Soc, 1970, 99: 80-88
69. Fox W W. Fitting the generalized stock production model by least-squares and equilibrium approximation. U. S. Fish Bull, 1975, 73: 23-37
70. Francisco A S, Manuel Z R. Simulated response to harvesting strategies in an exploited ecosystem in the southwestern Gulf of Mexico. Ecological modeling, 2004,172:421-432
71. Freon P, Soria M, Mullon C, Gerlotto F. Diurnal Variation in fish density estimate during acoustic surveys in relation to spatial distribution and avoidance reaction. Aquat Liv Resour, 1993, 6: 221-234
72. Garcia S. Indicators for sustainable development of fisheries: Land quality indicators and their use in sustainable agriculture and rural development. Rome, 1997, 131-162
73. Graham M. Modern theory of exploiting a fishery and applications to North Sea trawling. Cons Int Explor Mer, 1935, 10: 264-274
74. Gulland J A. Fish population dynamics (2nd edition). Chichester: John Wiley and Sons. 1988.
75. Hagan M T, Menhaj M B.Training feed forward networks. with Marquart algorithm. IEEE Trans on Neural Net-works, 1994, 5(6): 989-993
76. Han J W. Conference Tutorial Notes: Data Mling Techniques. Proc the ACM SIGMOD
77. Hema R, Alexey G.. Inductive learning algorthms for complex system modeling. CRC Press Inc, 1994
78. Hilborn R, Walters C J. Quantitative fisheries stock assessment: choice, dynamics & Uncertainty. New York, Chapman and Hall, 1992, 570
79. International Conference on Management of Data, Montrea, Canada, 1996
80. Kimura D K, Balsiger J W. Generalized stock reduction analysis. Can J Fish Aquat Sci, 1984, 41: 1325-1333
81. Kimura D K. Changes to stock reduction analysis indicated by schnutes general theory. Can J Fish Aquat Sci, 1985, 42: 2059-2060
82. Lapeds A, Farber. Genetic Data Base Analysis with Neural Networks. Neural Information Processing System-Nature and Synthetic. 2002, 2(10): 1987
83. Leslie D H, Davis H S.An attempt to determine the absolute number of rats on a given area. Anim Ecol, 1939, 8: 94-113
84. Lippmann R P. An introduction to computing with neural nets. IEEE Acoust. Speech Signal Process, 1987, 4(2): 4-22
85. Moran P A. A mathematical theory of animal trapping. Brometrika, 1951, 38:307-311
86. Omand D N. A study on populations of fish based on catch-effort statistics. J. Mahage, 1951, 15:88-98
87. Pauly D. Theory and management of tropical multispecies stocks: A review with emphasis on the Southeast Asian demersal fisheries. ICLARM Studies and Reviews. 1979, 1:35
88. Pella J J, Tomlinson P K. A generalized stock production model. Bull. Inter-Am. Trop. Tuna Comm, 1969, 13: 419-496
89. Pinnegar J K, Polunin V C. Predicting indirect effects of fishing in Mediterranean rocky littoral communities using a dynamic simulation model. Ecological modeling, 2004, 172: 249-267
90. Polacheck T, Hilborn R, Punt A E. Fitting surplus production models: comparing methods and measuring uncertainty. Can J. Fish Aquat Sci, 1993, 50: 2597-2607
91. Prager M H. A suite of extensions to a nonequilibrium surplus-production model. Fishery Bulletin, 1994, 92: 374-389
92. Rumelhart D E, McClellan J L. Parallel Distributed Processing-Exploration in the Microstructure of Cognition. MIT Press, 1986,1
93. Schaefer M B. Some aspects of dynamics of populations important to the management of commercial marine fisheries. Int. Amer. TroP. Tuna Comm Bul, 1954,1:25-56
94. Schunte J. A general theory for analysis of catch and effort docta. Can J Fish Aquat Sci, 1985,42:414-429
95. Walter S C, Chrestense N, Pauly D. Representing density dependent consequences of life history strategies in aquatic ecosystems: Ecosim II. Ecosystems, 2000(3): 70-83
96. Widrow B. 30 years of adaptive neural neworks:perceptron. Madaline and B-P. Proc IEEE, 1990, 78(9): 1415-1442
97. Xiao Y. A general theory of fish stock assessment models. Ecological Modelling, 2000, 128
98. Zippin C. An evaluation of the removal method of estimating animal populations. Biometrics, 1956, 12: 163-189
99. Zippin C. The removal method of population estimation. J wild ugmt, 1958, 22:82-90