基于BP人工神经网络的价值链风险的评价

通过对价值链管理深入研究,利用BP人工神经网络对价值链风险管理进行评价,采用专家评分法,获得实际的数据,对模型进行仿真和测试,证实价值链风险管理的指标体系的实用性和BP人工神经网络模型的价值。     

浅谈人工湿地污水处理技术及应用

本文简单介绍了人工湿地污水处理系统的分类,讲解了人工湿地污水处理系统对污染物的去除原理,最后论述了人工湿地污水处理系统我国的应用及今后主要研究方向。     

人工智能技术在认知无线电中的应用

认知无线电技术为无线通信的发展提供了新的机遇和挑战。认知无线电的一个重要特征就是智能,人工智能技术是实现其智能性的关键所在。本文首先提出了自己的认知无线电研究框架,然后对多种人工智能技术在认知无线电中的应用进行了概述,最后详细介绍了人工神经网络在认知无线电中的应用,并进行了仿真验证。     

MISO的普适性人工噪声保密容量

当MISO(Multi Input Single Output)系统存在的加性人工噪声服从一般分布时,系统保密容量讨论难度较大。为推导一般意义多天线系统下的保密容量,引入了信道等效特征的概念。利用信道特征阐明了人工噪声方法的物理概念,并推导出了具有普适性的人工噪声方法保密容量上下限,进一步结合熵功率,推导出AWGN信道下的保密容量解析式。理论分析和仿真得出,通过人工噪声可使平均保密容量增大,从而提高MISO系统的安全性。     

用局部和半局部转移函数实现RBF型神经网络的逼近和分类

增量神经网络(IncNet)的结构是由增长和剪枝控制,并且与训练数据的复杂性相匹配。用扩展卡尔曼滤波算法作为其学习算法。双径向转移函数比其它常用于人工神经网络的转移函数更具有灵活性。最新的改进是在多维空间中(具有N-1个参数)增加转移函数的旋转常数值。通过对逼近基准和心理分类问题的结果分析,清楚地表明比其他分类网络模型具有更强的泛化性。     

Intelligent Systems in Accounting,Finance and Management: ISI journal and proceeding citations,and research issues from most‐cited papers

This paper analyses the citations from Intelligent Systems in Accounting, Finance and Management that have occurred in ISI's Web of Knowledge in February 2010. I found roughly 1000 citations to the journal under 10 different journal name abbreviations, with roughly 25% of the citations occurring during 2008–2009, associated with 27 of the more frequently cited papers. Using that citation data, the H‐index and the 40 (42 with ties) most‐cited papers are presented. I found that ISI's new proceedings data appear to have a different citation pattern than ISI's journal citation data, resulting in citations to more sources, but fewer citations per source. I also examine the research methodologies and applications of the most‐cited papers in an attempt to determine what areas have been cited most and where there are potential gaps in the research. Copyright © 2010 John Wiley & Sons, Ltd.     

Artificial Reefs as Recreational Scuba Diving Resources: A Critical Review of Research

This paper reports on the increasing practice of developing and promoting artificial reefs as sites for scuba diving tourism and recreation. A comprehensive definition of artificial reefs is presented that encapsulates the diversity of structures used by marine recreationists, particularly scuba divers, followed by a review of existing literature that specifically examines artificial reefs as a resource for the conduct of recreational scuba diving. Three main thematic areas were identified in the existing literature: social dimensions, socioeconomic impacts and environmental engineering. A typology of artificial reefs is offered to better describe and categorise artificial reef structures according to unit characteristics that may influence recreational use such as material used, appearance, complexity and cost. The paper presents a conceptual model that identifies the components of an artificial reef scuba diving experience and discusses the potential of artificial reefs to act as tourism resources and management tools to redistribute scuba diver numbers away from natural reefs. Directions for future research are suggested, emphasising collection of data on aspects of the artificial reef scuba diving experience to better inform marine resource management.     

Effectiveness of Q-learning as a tool for calibrating agent-based supply network models

This paper examines effectiveness of Q-learning as a tool for specifying agent attributes and behaviours in agent-based supply network models. Agent-based modelling (ABM) has been increasingly employed to study supply chain and supply network problems. A challenging task in building agent-based supply network models is to properly specify agent attributes and behaviours. Machine learning techniques, such as Q-learning, can be a useful tool for this purpose. Q-learning is a reinforcement learning technique that has been shown to be an effective adaptation and searching mechanism in distributed settings. In this study, Q-learning is employed by supply network agents to search for ‘optimal’ values for a parameter in their operating policies simultaneously and independently. Methods are designed to identify the ‘optimal’ parameter values against which effectiveness of the learning is evaluated. Robustness of the learning's effectiveness is also examined through consideration of different model settings and scenarios. Results show that Q-learning is very effective in finding the ‘optimal’ parameter values in all model settings and scenarios considered.     

基于人工神经网络的矿山经营绩效综合评价模型

建立了矿山经营绩效综合评价指标体系 ,并利用 BP神经网络建立了矿山经营绩效的综合评价模型该评价方法克服了许多人为的因素 ,具有误差小、动态性好、方便可靠等优点     

人工繁殖真鲷苗种标志放流理论基础研究

真鲷为我国重要的近海经济鱼类，近年来大规模人工放流增殖真鲷活动成为近海恢复渔业资源、提高渔业经济产值的重要手段之一。目前，亟需有效研究放流后真鲷的移动、生长、回捕率、资源量及死亡率等问题，以及大规模人工放流苗种对于天然群体和环境的影响。本文通过对人工放流增殖效果评估研究方法和相关结论进行综述，综合比较了各种标志方法，建立了真鲷标志放流效果评价的理论基础和技术体系，为进一步开展真鲷放流增殖效果评价提供科学指导。