We use Active Queue Management (AQM) strategy for congestion avoidance in Transmission Control Protocol (TCP) networks to regulate queue size close to a reference level. In this paper we present two efficient and new ...
详细信息
ISBN:
(纸本)9783540896180
We use Active Queue Management (AQM) strategy for congestion avoidance in Transmission Control Protocol (TCP) networks to regulate queue size close to a reference level. In this paper we present two efficient and new AQM systems as a queue controller. These methods are designed using Improved Neural Network (INN) and Adaptive Neuro-Fuzzy Inference Systems (ANFIS). Our aim is low queue variation, low steady state error and fast response with using these methods in different conditions. Performance of the proposed controllers and disturbance rejection is compared with two well-known AQM methods, Adaptive Random Early Detection (ARED), and Proportional-Integral (PI). Our AQM methods are evaluated through simulation experiments using MATLAB.
People who attend to the problem of underwater port protection usually use sonar based systems. Recently it has been shown that integrating a sonar system with an auxiliary array of magnetic sensors can improve the ef...
详细信息
ISBN:
(纸本)9783642040900
People who attend to the problem of underwater port protection usually use sonar based systems. Recently it has been shown that integrating a sonar system with an auxiliary array of magnetic sensors can improve the effectiveness of the intruder detection system. One of the major issues that arise from the integrated magnetic and acoustic system is the interpretation of the magnetic signals coming from the sensors. In this paper a machine learning approach is explored for the detection of divers or, in general, of underwater magnetic sources that should ultimately support an automatic detection system which currently requires a human online monitoring or an offline signal processing. The research proposed here, by means of a windowing of the signals, uses Support Vector Machines for classification, as tool for the detection problem. Empirical results show the effectiveness of the method.
Initially, genomic sequences have been known by their linear form. However, they have also a three-dimensional structure, which can be useful for genomes analysis. This 3D structure representation brings a new point o...
详细信息
ISBN:
(纸本)9783642032011
Initially, genomic sequences have been known by their linear form. However, they have also a three-dimensional structure, which can be useful for genomes analysis. This 3D structure representation brings a new point of view for the sequences analysis. Therefore, several studies have described the design of software for 3D molecular visualization. The search that we have carried out enabled us to see the various modeling systems and their principles, and we have to classify them in two great families: the class of the visualization systems and the class of 3D interactive modeling. Each one of these classes is divided into two common sub-classes: systems based prediction and systems based 3D data.
In this study two bio-inspired communication schemes (stigmergy and hormone based communication) are evaluated according to the contribution of each to the self organisation of a multi agent robotic system. The evalua...
详细信息
ISBN:
(纸本)9783642004865
In this study two bio-inspired communication schemes (stigmergy and hormone based communication) are evaluated according to the contribution of each to the self organisation of a multi agent robotic system. The evaluation is carried on by the simulation of a test case scenario and it is based on measurable criteria that only depend on triggered agent actions. The results present the different Situations where each of the communication schemes performs better in terms of task accomplishment.
This paper presents how functionalities are distributed my means of FUSION@. a SOA-based multi-agent architecture. FUSION@ introduces a new perspective for constructing multiagent systems, facilitating the integration...
详细信息
ISBN:
(纸本)9783642004865
This paper presents how functionalities are distributed my means of FUSION@. a SOA-based multi-agent architecture. FUSION@ introduces a new perspective for constructing multiagent systems, facilitating the integration with service-oriented architectures, and the agents act as coordinators and administrators of services. FUSION@ makes use of several mechanisms for managing and optimizing the services distribution. The results obtained demonstrate that FUSION@ can efficiently distribute functionalities in dynamic scenarios at execution time.
A new approach to determination of similarity of dc machine sounds is presented. This approach is based on Linear Predictive Coding (LPC) algorithm and some metrics of distance in multidimensional solution space. The ...
详细信息
ISBN:
(纸本)9783642032011
A new approach to determination of similarity of dc machine sounds is presented. This approach is based on Linear Predictive Coding (LPC) algorithm and some metrics of distance in multidimensional solution space. The aim of this paper is analysis of a system which enables sound recognition. Developed sound recognition system consists of preliminary data processing, feature extraction and classification algorithms. There were applied eight various distance metrics. Investigations were carried out for direct current machine because it produces characteristic sounds. It can be noticed that sound of faultless dc machine is different from sound of faulty dc machine, what can be used to determine the state of dc machine performance. Investigations of the sound recognition were carried out for faultless machine and machine with shorted rotor coils. The results of sound recognition are discussed in this paper.
In this paper, we present a scalable grouping of distributed objects based on the fuzzy clustering and proposes an intelligent object search with an optimal load sharing. The scalable grouping of objects contributes o...
详细信息
ISBN:
(纸本)9783540896180
In this paper, we present a scalable grouping of distributed objects based on the fuzzy clustering and proposes an intelligent object search with an optimal load sharing. The scalable grouping of objects contributes on identifying the appropriate server to forward the incoming request and efficiently balances the loads using the proposed equally proportional load distribution (EPLD). In the search process, the load balancing service uses the EPLD function to minimize the load variations where the multiple memberships of each object are used to distribute the loads in near equal proportions to the servers. Performance result showed that the proposed scalable grouping classifies more objects for availability of resources and minimizes the load variations within the servers.
Agent-based computing represents a promising paradigm for distributed computing. Unfortunately the lack of security is hindering the application of this paradigm in real world applications. We focus on a new agent mig...
详细信息
ISBN:
(纸本)9783642004865
Agent-based computing represents a promising paradigm for distributed computing. Unfortunately the lack of security is hindering the application of this paradigm in real world applications. We focus on a new agent migration protocol that takes advantage of TPM technology. The protocol has been validated using AVISPA model checking toolsuite. In order to facilitate its adoption, we have developed a software library to access TPM functionality from agents and to support their secure migration. This paper presents hardware-based system to protect agent systems. Concretely our work is based oil trusted platform module (TPM), which is the cornerstone to build the solution. In order to build our solution oil a robust basis, we validate this protocol by means of a model checking tool called AVISPA. Then as final result we provide a library to access to TPM (Trusted Platform Module) functionality from software agents. Along this paper we detail more relevant aspects of this library both in the development stage of it and while we use it to develop a system based agent.
The Second International Workshop on Computational Intelligence for Security in Information Systems (CISIS09) presented the most recent developments in the dynamically expanding realm of several fields such as Data Mi...
ISBN:
(数字)9783642040917
ISBN:
(纸本)9783642040900
The Second International Workshop on Computational Intelligence for Security in Information Systems (CISIS09) presented the most recent developments in the dynamically expanding realm of several fields such as Data Mining and Intelligence, Infrastructure Protection, Network Security, Biometry and Industrial Perspectives. The International Workshop on Computational Intelligence for Security in Information Systems (CISIS) proposes a forum to the different communities related to the field of intelligent systems for security. The global purpose of CISIS conferences has been to form a broad and interdisciplinary meeting ground offering the opportunity to interact with the leading industries actively involved in the critical area of security, and have a picture of the current solutions adopted in practical domains. This volume of advances in intelligent and soft computing contains accepted papers presented at CISIS09, which was held in Burgos, Spain, on September 23rd-26th, 2009.
The selection of combat strategy to oil spill when multi-criteria and multi-person are involved in the decision process is not an easy task. In case of oil spill, urgent decisions must be made so that the available op...
详细信息
ISBN:
(纸本)9783540896180
The selection of combat strategy to oil spill when multi-criteria and multi-person are involved in the decision process is not an easy task. In case of oil spill, urgent decisions must be made so that the available options of responses are activated in such a way that the environmental, social and economic impacts are minimized. In this context, the decision agents involved in the decision process are the environmental agency, a non-governmental organization (NGO), and a company that get in conflict during the decision process because each one defends its own interests. So, a consensus to reach the best viable solution is desirable. The advantages and disadvantages of different types of combat strategy should be weighted, taking into account the preferences and the different point of view of the decision agents. In this context, the process to form a consensus and to elaborate the response strategies necessarily involves a process of decision making with multi-objectives and multi-person (decision agents) so that the importance of social, economic and environmental factors is considered. In this work, the fuzzy evaluation method is applied in order to automatically find the best combat response. The method is applied to evaluate combat response to oil spill in the south coast of the Espirito Santo state, Brazil. Simulation results show the viability of the method.
暂无评论