An extensible,generic environmental process modelling framework with an example for a watershed of a shallow lake

We present a modelling framework for the generation of environmental process models. The framework builds on the Direct Computer Mapping method with an editable, process network based expert module and interpreter. The expert interface supports mapping of objects from the GIS layers onto the prototyped state, transition and connection elements of the case specific generic process model. The developed general purpose interpreter generates the standardized declarative facts and clauses, describing the actual model with the locally executable program prototypes. This input is executed by the general kernel. The model interpreter generates also the case specific templates for the (optionally web based) user interface, while map-server utilizes the GIS shape files of expert model. The implementation supports the extension of the model with new components in space and time. The framework is illustrated by an example for the watershed of Lake Balaton.     

An ecological risk assessment for managing and predicting trophic shifts in estuarine ecosystems using a Bayesian network

Estuaries are dynamic systems at the transition between freshwater and marine ecosystems. In this study, a spatially and temporally explicit Bayesian network (BN) was developed for a tidally connected estuary in southeastern Australia. The BN provides an environmental risk assessment (ERA) for the probability of a shift to a eutrophied state based on markers of pelagic and benthic primary production. The model was created to provide an initial framework of system knowledge based on empirical data, with the intention that the model and its linkages be iteratively developed as more information becomes available. The BN was investigated for its potential to predict trophic shifts and provide a framework for evidence-based decision making. Model assessment was conducted through both sensitivity analysis and scenario tests. Through evaluation and updating, the BN can provide information on the key nutrients and bio-physical mechanisms regulating changes in trophic state in estuarine ecosystems.     

A framework for use of wireless sensor networks in forest fire detection and monitoring

Forest fires are one of the main causes of environmental degradation nowadays. Current surveillance systems for forest fires lack in supporting real-time monitoring of every point of a region at all times and early detection of fire threats. Solutions using wireless sensor networks, on the other hand, can gather sensory data values, such as temperature and humidity, from all points of a field continuously, day and night, and, provide fresh and accurate data to the fire-fighting center quickly. However, sensor networks face serious obstacles like limited energy resources and high vulnerability to harsh environmental conditions, that have to be considered carefully. In this paper, we propose a comprehensive framework for the use of wireless sensor networks for forest fire detection and monitoring. Our framework includes proposals for the wireless sensor network architecture, sensor deployment scheme, and clustering and communication protocols. The aim of the framework is to detect a fire threat as early as possible and yet consider the energy consumption of the sensor nodes and the environmental conditions that may affect the required activity level of the network. We implemented a simulator to validate and evaluate our proposed framework. Through extensive simulation experiments, we show that our framework can provide fast reaction to forest fires while also consuming energy efficiently.     

The Cost of Environmental Constraints in Traffic Networks: Assessing the Loss of Optimality

Increasing numbers of hard environmental constraints are being imposed in urban traffic networks by authorities in an attempt to mitigate pollution caused by traffic. However, it is not trivial for authorities to assess the cost of imposing such hard environmental constraints. This leads to difficulties when setting the constraining values as well as implementing effective control measures. For that reason, quantifying the cost of imposing hard environmental constraints for a certain network becomes crucial. This paper first indicates that for a given network, such cost is not only related to the attribution of environmental constraints but also related to the considered control measures. Next, we present an assessment criterion that quantifies the loss of optimality under the control measures considered by introducing the environmental constraints. The criterion can be acquired by solving a bi-level programming problem with/without environmental constraints. A simple case study shows its practicability as well as the differences between this framework and other frameworks integrating the environmental aspects. This proposed framework is widely applicable when assessing the interaction of traffic and its environmental aspects.     

Cyberattack Detection Framework Using Machine Learning and User Behavior Analytics

This paper proposes a novel framework to detect cyber-attacks using Machine Learning coupled with User Behavior Analytics. The framework models the user behavior as sequences of events representing the user activities at such a network. The represented sequences are then fitted into a recurrent neural network model to extract features that draw distinctive behavior for individual users. Thus, the model can recognize frequencies of regular behavior to profile the user manner in the network. The subsequent procedure is that the recurrent neural network would detect abnormal behavior by classifying unknown behavior to either regular or irregular behavior. The importance of the proposed framework is due to the increase of cyber-attacks especially when the attack is triggered from such sources inside the network. Typically detecting inside attacks are much more challenging in that the security protocols can barely recognize attacks from trustful resources at the network, including users. Therefore, the user behavior can be extracted and ultimately learned to recognize insightful patterns in which the regular patterns reflect a normal network workflow. In contrast, the irregular patterns can trigger an alert for a potential cyber-attack. The framework has been fully described where the evaluation metrics have also been introduced. The experimental results show that the approach performed better compared to other approaches and AUC 0.97 was achieved using RNN-LSTM 1. The paper has been concluded with providing the potential directions for future improvements.     

局部加权回归LSTM的带宽异常值预测

CDN带宽异常值的预测和准确告警一直是网络运营的重点和难点,为此在时间序列LSTM(long short term memory network)基础之上,提出并实现了一套新的算法框架——局部加权回归串行LSTM.框架采用时序插值采样方法构造数据集,局部加权算法融入最小二乘回归拟合模型进行初始预测,预测结果串行LSTM...     

A co-simulation framework for design of time-triggered automotive cyber physical systems

Designing cyber-physical systems (CPS) is challenging due to the tight interactions between software, network/platform, and physical components. Automotive control system is a typical CPS example and often designed based on a time-triggered paradigm. In this paper, a co-simulation framework that considers interacting CPS components for assisting time-triggered automotive CPS design is proposed. Virtual prototyping of automotive vehicles is the core of this framework, which uses SystemC to model the cyber components and integrates CarSim to model the vehicle dynamics. A network/platform model in SystemC forms the backbone of the virtual prototyping. The network/platform model consists of processing elements abstracted by real-time operating systems, communication systems, sensors, and actuators. The framework is also integrated with a model-based design tool to enable rapid prototyping. The framework is validated by comparing simulation results with the results from a hardware-in-the-loop automotive simulator. The framework is also used for design space exploration (DSE).     

Stochastic comparisons for rooted butterfly networks and tree networks, with random environments

Consider a rooted tree network, where the items enter at the system and they proceed away from the root until they reach their destination and exit the system, and they are served by a FIFO policy at each arc (server) of the network. The routing is defined by a discrete probability distribution with a given probability for each destination. For such systems, stochastic modelling of the departure times and the delay times is proposed, by the incorporation of random parameters of the inter-arrival times and of the service times, describing dynamic environments. A mixture model for the departure times is introduced. This mixture has an arbitrary mixing distribution defined by the environmental parameter distributions and the routing distribution. The main results provide conditions to compare stochastically the departure times (delay times) for two rooted tree networks characterized by different routing disciplines or by environmental and correlated random vectors of parameters. Furthermore, bounds for these measures are obtained from some well-known dependence concepts, as the PQD property, and ageing properties of the random environment. Similar results for butterfly networks, tree networks with possible failure during the service and other networks are provided. Within the computer networks, our framework and our results provide explorative tools to assess the design, the performance and the security of communication systems.     

Environmental map building for a mobile robot using infrared range-finder sensors

This paper presents a methodology for building a high-accuracy environmental map using a mobile robot. The design approach uses low-cost infrared range-finder sensors incorporating with neural networks. To enhance the map quality, the errors occurring from the sensors are corrected. The non-linearity error of the sensors is compensated using a backpropagation neural network and the random error of readings including the uncertainty of the environment is taken into a sensor model as a probabilistic approach. The map is represented by an occupancy grid framework and updated by the Bayesian estimation mechanism. The effectiveness of the proposed method is verified through a series of experiments.     

Energy conservation in wireless sensor networks: a rule-based approach

The research reported in this paper addresses the problem of energy conservation in wireless sensor networks (WSNs). It proposes concepts and techniques to extract environmental information that are useful for controlling sensor operations, in order to enable sensor nodes to conserve their energy, and consequently prolong the network lifetime. These concepts and techniques are consolidated in a generic framework we term CASE: Context Awareness in Sensing Environments framework. CASE targets energy conservation at the network level. A subset framework of CASE, we term CASE Compact, targets energy conservation at the sensor node level. In this paper, we elaborate on these two frameworks, elucidate the requirements for them to operate together within a WSN and evaluate the applications they can be applied to for energy conservation.     

基于多信道博弈的ICPS虚假注入攻击防御策略

工业信息物理系统(ICPS)与基础设施的连接越来越密切,同时通信网络也易受到环境干扰和虚假数据注入攻击的影响.鉴于此,研究基于多信道传输框架和minimax控制器,提高ICPS在攻击、环境和噪声干扰下的弹性.通过设计minimax控制器以增强ICPS在噪音和干扰下的弹性,基于多信道传输框架建立发射机与攻击者之间的攻防博...     

无人机集群编队自组网可靠性评估

针对无人机集群编队自组网的可靠性评估问题,考虑无人机集群编队在执行任务时对信息交互的时效性需求,提出一种自组网可靠性评估方案.首先,分析消息传输的可用时间;其次,通过排队论建立消息传输延迟模型以计算消息传输所需时间;然后,以消息传输所需时间小于可用时间的概率作为评估指标建立消息传输可靠性计算模型,进而为无人机集群编队提供一个动态可靠性评估框架以适应集群编队体系配置和环境变化的随机性与时变特性;最后,仿真分析在不同传输任务需求下,编队构型、无人机数量、编队缩放因子、传输速率、信息交互强度以及环境干扰对消息传输可靠性的影响.仿真结果可以为集群编队的队形设计以及集群编队的体系配置提供一定参考依据.     

Tradeoff between utility and lifetime in energy-constrained wireless sensor networks

We study the tradeoff between network utility and network lifetime using a cross-layer optimization approach. The tradeoff model in this paper is based on the framework of layering as optimization decomposition. Our tradeoff model is the first one that incorporates time slots allocation into this framework. By using Lagrangian dual decomposition method, we decompose the tradeoff model into two subproblems: routing problem at network layer and resource allocation problem at medium access control (MAC) layer. The interfaces between the layers are precisely the dual variables. A partially distributed algorithm is proposed to solve the nonlinear, convex, and separable tradeoff model. Numerical simulation results are presented to support our algorithm.     

基于Self-Attention模型的机器翻译系统

近几年来神经机器翻译（Neural Machine Translation, NMT）发展迅速，Seq2Seq框架的提出为机器翻译带来了很大的优势，可以在观测到整个输入句子后生成任意输出序列。但是该模型对于长距离信息的捕获能力仍有很大的局限，循环神经网络（RNN）、 LSTM网络都是为了改善这一问题提出的，但是效果并不明显。注意力机制的提出与运用则有效地弥补了该缺陷。Self-Attention模型就是在注意力机制的基础上提出的，本文使用Self-Attention为基础构建编码器-解码器框架。本文通过探讨以往的神经网络翻译模型，分析Self-Attention模型的机制与原理，通过TensorFlow深度学习框架对基于Self-Attention模型的翻译系统进行实现，在英文到中文的翻译实验中与以往的神经网络翻译模型进行对比，表明该模型取得了较好的翻译效果。     

Credibility-based fuzzy mathematical programming model for green logistics design under uncertainty

Measuring and controlling emissions across the logistics network is an important challenge for today’s firms according to increasing concern about the environmental impact of business activities. This paper proposes a bi-objective credibility-based fuzzy mathematical programming model for designing the strategic configuration of a green logistics network under uncertain conditions. The model aims to minimize the environmental impacts and the total costs of network establishment simultaneously for the sake of providing a sensible balance between them. A popular but credible environmental impact assessment index, i.e., CO₂ equivalent index is used to model the environmental impact across the concerned logistics network. Since transportation mode and production technology play important roles on the concerned objectives, the proposed model integrates their respective decisions with those of strategic network design ones. In addition, to solve the proposed bi-objective fuzzy optimization model, an interactive fuzzy solution approach based upon credibility measure is developed. An industrial case study is also provided to show the applicability of the proposed model as well as the usefulness of its solution method.     

The valve location problem: Minimizing environmental damage of a spill in long oil pipelines

A shutoff valve is a control device that blocks oil flow in a pipeline in order to reduce the oil escape. This paper addresses the valve location problem where, given a pipeline network and a number of valves for installation, the task is to find a valve location that minimizes the maximum environmental damage of an oil spill. We present the first complete framework for fast computing of an optimal valve location in a general oil pipeline network. To achieve this, we formalize the problem and explain how to quantify environmental damages. Next, we present two fast algorithms optimally solving the valve location problem on linear pipeline segments. Further, we show how to extend the algorithms to solve the problem on a general pipeline network. We conclude with a computational study showing that solutions provided by our framework can reduce the adverse effects of a spill by up to 37% compared to the currently used solutions.     

类比治安系统的开放式网络安全管理

网络安全一直是人们研究的热点,但目前重在研究服务器如何对黑客的破坏和攻击严防死守,对整体网络的安全管理模式研究却不成熟.借鉴现实社会中治安管理的思路,建立信息网络安全管理框架是一个有意义的研究课题.本文首先对社会治安管理和网络安全管理进行了类比分析,建立了安全案件受理中心的三层管理框架;接下来就该框架中如何加强端系统安全等关键问题进行了深入讨论;最后给出了模型的模拟测试结果. [     

情景感知的P2P移动社交网络构造及发现算法

如何通过情景感知,获得用户的行为特征,从而自动发现潜在的社会关系,是移动社交网络重要的研究内容之一.该文提出了情景感知的移动P2P社交网络系统架构、聚合模型及发现算法,将用户的位置信息、环境特征、运动轨迹等引入到聚合算法中,智能地聚合成潜在的P2P社交网络,根据用户需求自主发现匹配的社会关系,避免了社交活动的盲目性和随意性.最后对该方案和算法进行了理论分析及实验验证,结果表明该文所提出的方案和算法具有较高的响应速度、准确率及用户满意度.     

Agent-based modeling of energy technology adoption: Empirical integration of social,behavioral, economic,and environmental factors

Agent-based modeling (ABM) techniques for studying human-technical systems face two important challenges. First, agent behavioral rules are often ad hoc, making it difficult to assess the implications of these models within the larger theoretical context. Second, the lack of relevant empirical data precludes many models from being appropriately initialized and validated, limiting the value of such models for exploring emergent properties or for policy evaluation. To address these issues, in this paper we present a theoretically-based and empirically-driven agent-based model of technology adoption, with an application to residential solar photovoltaic (PV). Using household-level resolution for demographic, attitudinal, social network, and environmental variables, the integrated ABM framework we develop is applied to real-world data covering 2004–2013 for a residential solar PV program at the city scale. Two applications of the model focusing on rebate program design are also presented.     

基于生成对抗网络的机载遥感图像超分辨率重建

为解决机载遥感图像质量易受环境影响的问题,对其进行超分辨率重建,对现有深度学习机载遥感图像超分辨率重建方法存在的特征提取能力差、重建图像边缘平滑、模型训练困难的问题进行改进,增强图像重建效果。将生成对抗网络作为模型的整体框架,使用密集剩余残差块增强模型特征提取能力,增加跳跃连接,有效提取机载遥感图像的浅层和深层特征,引入沃瑟斯坦式生成对抗网络优化模型训练。该方法能够有效对机载遥感图像进行4倍重建,在峰值信噪比评价上较对比方法约有2 dB增益,重建出的机载遥感图像在视觉上更清晰、细节更丰富、边缘更锐利。实验结果表明,该方法有效提升了模型特征提取能力,优化了训练过程,重建的机载遥感图像效果较好。