BP及RBF人工神经元网络对臭氧生物活性炭水处理系统建模的比较

运用BP和RBF人工神经元网络建立臭氧生物活性炭系统模型,考察了两个网络对水处理系统建模的适应性。研究表明,BP和RBF人工神经元网络的臭氧生物活性炭系统模型准确地描述了系统影响因素的关系,可以求出系统中臭氧的经济投量;用BP人工神经元网络建立水处理系统模型,泛化能力好,但逼近速度较慢;运用RBF人工神经元网络建模,泛化能力较差,但逼近速度快。该项研究克服了运用传统方法建模的不足,为实现水处理系统的优化设计提供了可行的途径。     

Reliability evaluation of fire alarm systems using dynamic Bayesian networks and fuzzy fault tree analysis

In almost all industries, fire alarm systems play a vital role in the reducing the risks associated with fires and damages. Therefore, it is necessary to evaluate their reliability and performance in emergency situations. The present study aimed to use fault tree analysis (FTA) to determine the root causes involved in the failure of fire alarm systems, to use Fuzzy set theory and expert elicitation to determine relative probabilities, and finally, to evaluate the reliability of a fire alarm system using dynamic Bayesian networks (BNs) during a thirty-six months period. A total of 29 basic events were detected from the FT. The reliability of the fire alarm system was estimated at 0.954 according to the FT and 0.957 according to conventional BNs. The reliability of the fire alarm system after 36 months was estimated at 0.375 according to dynamic BNs. All the events involved in the failure of fire alarm systems were drawn in the fault tree diagram. The results indicate that remodeling of these systems and simultaneous construction activities are the most important factors in the failure of the fire alarm system. System reliability can also be increased to 0.965 by providing preventive and control measures to reduce the probability of critical events.     

Audience perceptions of high-status ties and network advantage: The market for coaching jobs in the National Collegiate Athletic Association (2000–2011)

Social ties with high-status others can be a potent signal of an individual's underlying quality and future promise. Individuals in competitive markets, therefore, have an incentive to publicly claim connections to high-status others. However, cognitive limitations and biases can make social network connections difficult for observers to reliably discern, and claims to high-status ties can go unrecognized by the audience. Our core contention is that claims to high-status affiliation are advantageous only when the audience recognizes the claim—unrecognized claims, like unreliable signals, do not deliver advantage and can backfire. Further, we draw on the literature on imprinting and develop arguments for why some people are more likely to make claims to high-status ties and why some claims to high-status ties are more likely than others to be recognized by the audience. We test our arguments with data from the market for head coaching jobs in NCAA basketball (2000–2011). Our study contributes to the sparse literature on how social network ties that exist in the minds of third-party observers influence individual attainment in market settings; and it offers new insights into how imprinting processes shape the perception and use of high-status network ties.     

Toward Integrative Management Advice of Water Quality, Oil Spills, and Fishery in the Gulf of Finland: A Bayesian Approach

Understanding and managing ecosystems affected by several anthropogenic stressors require methods that enable analyzing the joint effects of different factors in one framework. Further, as scientific knowledge about natural systems is loaded with uncertainty, it is essential that analyses are based on a probabilistic approach. We describe in this article about building a Bayesian decision model, which includes three stressors present in the Gulf of Finland. The outcome of the integrative model is a set of probability distributions for future nutrient concentrations, herring stock biomass, and achieving the water quality targets set by HELCOM Baltic Sea Action Plan. These distributions can then be used to derive the probability of reaching the management targets for each alternative combination of management actions.     

人工神经网络在深圳市水库富营养化评价中的应用

对富营养化评价标准进行插值获取大量的样本,建立了基于BP人工神经网络的富营养化评价模型。将模型应用于评价深圳市13座主要水库的富营养化状况,对其成因进行分析,并提出了对策与建议。研究结果表明,石岩水库与深圳水库为轻度富营养化,占评价水库总数的15.4%;西丽水库等11座水库为中营养,占评价水库总数的84.6%。人工神经网络用于建立湖库富营养评价模型是适合的。     

平原感潮河网地区非点源污染监测方法

平原感潮河网地区非点源污染严重以及交叉污染等特性,造成了严重的环境污染和环境安全问题。由于非点源污染监测资料不完善,相关研究的深度、广度以及监测管理存在不足,确定非点源污染大小、少资料区域污染定量化预测等问题都是亟待解决的难点。以南通平原感潮河网地区为例,对非点源污染中的不确定性及监测方法进行探讨,提出分别针对平原河网圩区和平原河网非圩区的非点源污染监测方法。     

南通平原河网地区典型农田系统地下水硝态氮污染调查

针对平原河网地区典型农田系统灌溉施肥带来的地下水环境污染问题,采集南通地区蔬菜地、水稻-小麦轮作地、水稻-油菜轮作地和桑地地下水样品,分析了不同农田种植体系下的地下水污染程度。结果表明,蔬菜、桑地、水稻-油菜轮作、水稻-小麦轮作地地下水的硝态氮(N)平均值分别为12.2,9.53,7.95和6.12 mg/L,与氮肥用量呈显著的正相关关系;研究区域地下水硝态氮超Ⅲ类标准率(20 mg/L)的为4.8%,表明地下水已部分受到硝态氮污染。     

基于人工神经网络的街道峡谷NOx浓度的数值模型研究

通过对反向传播人工神经网络的算法和网络结构的研究,发现拟牛顿算法训练速度较快,能够较好地接近误差目标值,同时建立了包括输入层、隐含层、输出层的人工神经网络三层拓扑结构。通过对街道峡谷人工神经网络的训练,模拟计算了街道峡谷NOx浓度分布值。结果显示,训练误差和测试误差比为1．11,训练样本的模拟值与实测值的相关系数为0．93,测试样本的模拟值与实测值的相关系数为0．87,模拟值与实测值的相关系数均高于显著水平为α=0．05与α=0．01所对应检验性表的相关系数临界值。该模型能够用于街道峡谷污染物浓度的模拟计算,具有较好的泛化能力。     

'All hazards approach' to disaster management: the role of information and knowledge management, Boyd's OODA Loop, and network-centricity

The ever-increasing complexity of disasters demands utilisation of knowledge that exists outside domains traditionally drawn upon in disaster management. To be operationally useful, such knowledge must he extracted, combined with information generated by the disaster itself, and transformed into actionable knowledge. The process, though, is hampered by existing, business-oriented approaches to knowledge management, by technical issues related to access to relevant, multi-domain information/knowledge, and by executive decision-making processes based predominantly on historical knowledge. Consequently, as shown by many recent incidents, the management of large-scale (mega) disasters is often inefficient and exceedingly costly. This paper demonstrates that the integration of modified information and knowledge management into the concepts of network-centric operations and network-enabled capabilities, and the employment of Boyd's OODA (Observe, Orient, Decide, and Act) Loop-based decision-making in unpredictable and dynamically changing environments, may address some of these problems.     

基于灰色BP网络的火灾事故预测

将BP网络模型与灰色系统预测方法相结合,利用人工神经网络对GM(1,1)模型进行残差修正,建立了火灾事故预测模型.该模型兼具灰色系统与BP网络的优点,不但能体现火灾复杂的灰色系统行为,又能根据每次学习误差的不同调整学习速率,加快收敛速度.与单一的GM(1,1)模型相比,该模型预测结果具有更高的精度.