Cross-layer routing metrics for mesh networks: Current status and research directions

Despite efforts to improve the current IEEE 802.11 standard to fully optimize the physical layer, the performance of wireless mesh networks still depends on the routing process for a correct selection of routes. With regard to this question, several cross-layer routing metrics have been developed to improve wireless multi-hop mesh routing. This paper sets out a new taxonomy that can be used to help understand, classify and compare the state-of-the-art situation with regard to cross-layer routing metrics for wireless mesh networks. A simulation study has been carried out to evaluate the capability of the most recent and promising cross-layer routing metrics to support multimedia applications, such as Voice over IP. The evaluation of the routing metrics has been undertaken from three main perspectives: user perception, network performance, and routing stability. The simulation results show that the impact of routing metrics is more noticeable on the network and routing stability evaluation parameters than on the user-perception parameters. Furthermore, the results show that the routing metrics, the level of stability attained, and the application performance are interdependent. Finally, there is a discussion of the direction that future research might take with regard to some open issues in the design of routing metrics for wireless mesh networks.     

Review of literature on decision support systems for natural hazard risk reduction: Current status and future research directions

Natural hazard risk is largely projected to increase in the future, placing growing responsibility on decision makers to proactively reduce risk. Consequently, decision support systems (DSSs) for natural hazard risk reduction (NHRR) are becoming increasingly important. In order to provide directions for future research in this growing area, a comprehensive classification system for the review of NHRR-DSSs is introduced, including scoping, problem formulation, the analysis framework, user and organisational interaction with the system, user engagement, monitoring and evaluation. A review of 101 papers based on this classification system indicates that most effort has been placed on identifying areas of risk and assessing economic consequences resulting from direct losses. However, less effort has been placed on testing risk-reduction options and considering future changes to risk. Furthermore, there was limited evidence within the reviewed papers on the success of DSSs in practice and whether stakeholders participated in DSS development and use.     

Application of artificial neural networks for water quality prediction

The term “water quality” is used to describe the condition of water, including its chemical, physical, and biological characteristics. Modeling water quality parameters is a very important aspect in the analysis of any aquatic systems. Prediction of surface water quality is required for proper management of the river basin so that adequate measure can be taken to keep pollution within permissible limits. Accurate prediction of future phenomena is the life blood of optimal water resources management. The artificial neural network is a new technique with a flexible mathematical structure that is capable of identifying complex non-linear relationships between input and output data when compared to other classical modeling techniques. Johor River Basin located in Johor state, Malaysia, which is significantly degrading due to human activities and development along the river. Accordingly, it is very important to implement and adopt a water quality prediction model that can provide a powerful tool to implement better water resource management. Several modeling methods have been applied in this research including: linear regression models (LRM), multilayer perceptron neural networks and radial basis function neural networks (RBF-NN). The results showed that the use of neural networks and more specifically RBF-NN models can describe the behavior of water quality parameters more accurately than linear regression models. In addition, we observed that the RBF finds a solution faster than the MLP and is the most accurate and most reliable tool in terms of processing large amounts of non-linear, non-parametric data.

     

Prediction of job characteristics for intelligent resource allocation in HPC systems: a survey and future directions

Nowadays, high-performance computing (HPC) clusters are increasingly popular. Large volumes of job logs recording many years of operation traces have been accumulated. In the same time, the HPC cloud makes it possible to access HPC services remotely. For executing applications, both HPC end-users and cloud users need to request specific resources for different workloads by themselves. As users are usually not familiar with the hardware details and software layers, as well as the performance behavior of the underlying HPC systems. It is hard for them to select optimal resource configurations in terms of performance, cost, and energy efficiency. Hence, how to provide on-demand services with intelligent resource allocation is a critical issue in the HPC community. Prediction of job characteristics plays a key role for intelligent resource allocation. This paper presents a survey of the existing work and future directions for prediction of job characteristics for intelligent resource allocation in HPC systems. We first review the existing techniques in obtaining performance and energy consumption data of jobs. Then we survey the techniques for single-objective oriented predictions on runtime, queue time, power and energy consumption, cost and optimal resource configuration for input jobs, as well as multi-objective oriented predictions. We conclude after discussing future trends, research challenges and possible solutions towards intelligent resource allocation in HPC systems.     

A comparison of neural networks and adaptive neuro-fuzzy inference systems for the prediction of water diffusion through carbon nanotubes

Given the fact that artificial intelligence tools such as neural network and fuzzy logic are capable of learning and inferencing from the past to capture the patterns that exist in the data, this study presents an intelligent method for the forecasting of water diffusion through carbon nanotubes where predictions are generated from neuro-fuzzy structures using molecular dynamics data. Therefore, this research was mainly focused on combining molecular dynamics with artificial intelligence methods in order to reduce the computational time of biomolecular and nanofluidic simulations. Two different artificial intelligence methods are applied for the time-dependent water diffusion forecasting: artificial neural network (ANN) and adaptive neuro-fuzzy inference systems (ANFISs). The effects of different sizes of training sample sets on forecasting performance of ANN and ANFIS are investigated as well. Four different evaluation methods are used to measure the performance and forecasting accuracy of these two methods. As a result, ANFIS presents the higher accuracy than neural network method based on the comparison of these different evaluation methods adopted in this research. The results reported in this research demonstrate that combining of molecular dynamics with artificial intelligence methods can be one of the most powerful and beneficial tools for prediction of important nanofluidic parameters.     

Current and future development in neural computation in steel processing

A rolling mill process control system calculates the setup for the mill's actuators based on models of the technological process. Neural networks are applied as components of hybrid neuro/analytical process models. They are the keys to fit the general physical models to the needs of the automation of a specific mill. Besides present applications, the paper describes future trends in application of neural networks in process control.     

Group awareness tools for learning: Current and future directions

Group awareness has become an important concept since it was introduced into the field of computer-supported collaborative learning. This paper discusses current trends and future directions in this research field. It is argued that the development and implementation of tools should be complemented by systematic explorations into the mechanisms that moderate the relationship between group awareness and learning. It is suggested that variations in tool design features are a starting point for furthering our understanding of the processes involved in group awareness. Based on the contributions in this special issue, eight areas for future empirical investigations are identified. The paper concludes with some theoretical considerations on the nature of group awareness.     

Semantic-based QoS management in cloud systems: Current status and future challenges

Cloud Computing and Service Oriented Architectures have seen a dramatic increase of the amount of applications, services, management platforms, data, etc. gaining momentum for the necessity of new complex methods and techniques to deal with the vast heterogeneity of data sources or services. In this sense Quality of Service (QoS) seeks for providing an intelligent environment of self-management components based on domain knowledge in which cloud components can be optimized easing the transition to an advanced governance environment. On the other hand, semantics and ontologies have emerged to afford a common and standard data model that eases the interoperability, integration and monitoring of knowledge-based systems. Taking into account the necessity of an interoperable and intelligent system to manage QoS in cloud-based systems and the emerging application of semantics in different domains, this paper reviews the main approaches for semantic-based QoS management as well as the principal methods, techniques and standards for processing and exploiting diverse data providing advanced real-time monitoring services. A semantic-based framework for QoS management is also outlined taking advantage of semantic technologies and distributed datastream processing techniques. Finally a discussion of existing efforts and challenges is also provided to suggest future directions.     

车载导航系统的研究现状及未来发展

介绍了车载导航系统的发展历程、实现功能和实际应用中存在的突出问题。对基于实时交通信息的动态车载导航系统的结构组成、功能实现及两种系统的区别进行了重点介绍,最后对动态车载导航的未来研究做了展望,并提出了动态车载导航系统的建设思路。     

Agricultural production systems modelling and software: Current status and future prospects

During the past decade, the application of agricultural production systems modelling has rapidly expanded while there has been less emphasis on model improvement. Cropping systems modelling has become agricultural modelling, incorporating new capabilities enabling analyses in the domains of greenhouse gas emissions, soil carbon changes, ecosystem services, environmental performance, food security, pests and disease losses, livestock and pasture production, and climate change mitigation and adaptation. New science has been added to the models to support this broadening application domain, and new consortia of modellers have been formed that span the multiple disciplines.There has not, however, been a significant and sustained focus on software platforms to increase efficiency in agricultural production systems research in the interaction between the software industry and the agricultural modelling community. This paper describes the changing agricultural modelling landscape since 2002, largely from a software perspective, and makes a case for a focussed effort on the software implementations of the major models.     

Neural networks for the prediction and forecasting of water resources variables: a review of modelling issues and applications

Artificial Neural Networks (ANNs) are being used increasingly to predict and forecast water resources variables. In this paper, the steps that should be followed in the development of such models are outlined. These include the choice of performance criteria, the division and pre-processing of the available data, the determination of appropriate model inputs and network architecture, optimisation of the connection weights (training) and model validation. The options available to modellers at each of these steps are discussed and the issues that should be considered are highlighted. A review of 43 papers dealing with the use of neural network models for the prediction and forecasting of water resources variables is undertaken in terms of the modelling process adopted. In all but two of the papers reviewed, feedforward networks are used. The vast majority of these networks are trained using the backpropagation algorithm. Issues in relation to the optimal division of the available data, data pre-processing and the choice of appropriate model inputs are seldom considered. In addition, the process of choosing appropriate stopping criteria and optimising network geometry and internal network parameters is generally described poorly or carried out inadequately. All of the above factors can result in non-optimal model performance and an inability to draw meaningful comparisons between different models. Future research efforts should be directed towards the development of guidelines which assist with the development of ANN models and the choice of when ANNs should be used in preference to alternative approaches, the assessment of methods for extracting the knowledge that is contained in the connection weights of trained ANNs and the incorporation of uncertainty into ANN models.     

离散时间系统零动态的研究现状和未来挑战

在数字控制系统的分析与设计中, 零动态是一个被广泛关注的重要概念, 近年来取得了诸多新的理论与方法进展. 本文首先描述了离散时间系统零动态理论的研究背景和研究意义, 同时简要介绍了离散时间系统零动态理论所涉及到的3个相关问题, 如: 信号的采样与重建、连续时间系统的等价离散时间系统模型以及在离散连续时间系统过程中所需要的工具(q算子和±算子). 其次, 立足现有文献, 针对离散零动态的特点, 从线性离散时间系统和非线性离散时间系统两个方面全面而深入地介绍了近年来离散零动态研究工作的进展. 最后分析了零动态在数字控制系统分析与设计中的局限性以及出现的挑战性课题, 并指明未来工作的研究方向.     

Hierarchical neural networks based prediction and control of dynamic reconfiguration for multilevel embedded systems

Multimedia design such as video decoders are typically composed of several communicating tasks. Each task is characterized by its workload variation. The target device of this kind of application contains several processing unit. This calls for a dynamic management of hardware units to improve the QOS of the application and to optimally allocate resources. In this paper, we propose a new architecture based on hierarchical multilevel neural network to model workload variation of each task. The hierarchical structure of this neural network perfectly describes the multilevel decomposition of each hardware unit. The aim of this investigation is to build a design with a control unit that manages the architecture and resource allocation according to the neural network workload prediction.     

Usability of Geographic Information: Current challenges and future directions

The use of Geographic Information or GI, has grown rapidly in recent years. Previous research has identified the importance of usability and user centred design in enabling the proliferation and exploitation of GI. However, the design and development of usable GI is not simply a matter of applying the tried and tested usability methods that have been developed for software and web design. Dealing with data and specifically GI brings with it a number of issues that change the way usability and user centred design can be applied. This paper describes the outcomes of a workshop held in March 2010 exploring the core issues relating to GI usability. The workshop brought together an international group of twenty experts in both human factors and GI, from a wide range of academic and industrial backgrounds. These experts considered three key issues, the stakeholders in GI, key challenges applying usability to GI and the usability methods that can be successfully applied to GI. The result of this workshop was to identify some areas for future research, such as the production of meaningful metadata and the implications of blurring of the line between data producers and data consumers.     

Operations and learning in neural networks for robust prediction

We consider stochastic neural networks, the objective of which is robust prediction for spatial control. We develop neural structures and operations, in which the representations of the environment are preprocessed and provided in quantized format to the prediction layer, and in which the response of each neuron is binary. We also identify the pertinent stochastic network parameters, and subsequently develop a supervised learning algorithm for them. The on-line learning algorithm is based an the Kullback-Leibler performance criterion, it induces backpropagation, and guarantees fast convergence to the prediction probabilities induced by the environment, with probability one.     

快速二阶BP网络及其在城市用水量预测中的应用

针对BP网络收敛速度慢，易导致局部极小值的缺点，提出一种快速二阶BP网络，并以城市年用水量预测为例，与BP网络对比，结果表明，该方法加快了收敛速度，提出了结果的准确度。     

An investigation of artificial neural networks based prediction systems in software project management

A critical issue in software project management is the accurate estimation of size, effort, resources, cost, and time spent in the development process. Underestimates may lead to time pressures that may compromise full functional development and the software testing process. Likewise, overestimates can result in noncompetitive budgets. In this paper, artificial neural network and stepwise regression based predictive models are investigated, aiming at offering alternative methods for those who do not believe in estimation models. The results presented in this paper compare the performance of both methods and indicate that these techniques are competitive with the APF, SLIM, and COCOMO methods.     

Swarm intelligence based routing protocol for wireless sensor networks: Survey and future directions

Swarm intelligence is a relatively novel field. It addresses the study of the collective behaviors of systems made by many components that coordinate using decentralized controls and self-organization. A large part of the research in swarm intelligence has focused on the reverse engineering and the adaptation of collective behaviors observed in natural systems with the aim of designing effective algorithms for distributed optimization. These algorithms, like their natural systems of inspiration, show the desirable properties of being adaptive, scalable, and robust. These are key properties in the context of network routing, and in particular of routing in wireless sensor networks. Therefore, in the last decade, a number of routing protocols for wireless sensor networks have been developed according to the principles of swarm intelligence, and, in particular, taking inspiration from the foraging behaviors of ant and bee colonies. In this paper, we provide an extensive survey of these protocols. We discuss the general principles of swarm intelligence and of its application to routing. We also introduce a novel taxonomy for routing protocols in wireless sensor networks and use it to classify the surveyed protocols. We conclude the paper with a critical analysis of the status of the field, pointing out a number of fundamental issues related to the (mis) use of scientific methodology and evaluation procedures, and we identify some future research directions.     

RBF neural networks for the prediction of building interference effects

Wind loads on tall buildings can be quite different from those on an isolated building due to neighboring building effects. With the increase of number of tall buildings in large cities, there is a growing attention to the interference effects among adjacent buildings under wind action. While wind tunnel tests are of importance in the understanding of the physical process, the general quantitative predictions of interference effects are difficult to reach owing to many variables involved. In the present paper, a radial basis function (RBF) neural network is proposed for its strong ability in nonlinear mapping and its higher training speed. Thus the RBF neural network is applied to evaluate the interference effects (expressed by interference factor, IF) by using experimental data obtained from many sources as training patterns. The results indicate that a very good agreement is found between the predicted IF values and the experimental counterparts.