Skip to main content
main-content

Über dieses Buch

These transactions publish research in computer-based methods of computational collective intelligence (CCI) and their applications in a wide range of fields such as the semantic web, social networks, and multi-agent systems. TCCI strives to cover new methodological, theoretical and practical aspects of CCI understood as the form of intelligence that emerges from the collaboration and competition of many individuals (artificial and/or natural). The application of multiple computational intelligence technologies, such as fuzzy systems, evolutionary computation, neural systems, consensus theory, etc., aims to support human and other collective intelligence and to create new forms of CCI in natural and/or artificial systems. This eleventh issue contains 9 carefully selected and thoroughly revised contributions.

Inhaltsverzeichnis

Frontmatter

Taming Complex Beliefs

Abstract
A novel formalization of beliefs in multiagent systems has recently been proposed by Dunin-Kęplicz and Szałas. The aim has been to bridge the gap between idealized logical approaches to modeling beliefs and their actual implementations. Therefore the stages of belief acquisition, intermediate reasoning and final belief formation have been isolated and analyzed. In conclusion, a novel semantics reflecting those stages has been provided. This semantics is based on the new concept of epistemic profile, reflecting agent’s reasoning capabilities in a dynamic and unpredictable environment. The presented approach appears suitable for building complex belief structures in the context of incomplete and/or inconsistent information. One of original ideas is that of epistemic profiles serving as a tool for transforming preliminary beliefs into final ones. As epistemic profile can be devised both on an  individual and a  group level in analogical manner, a uniform treatment of single agent and group beliefs has been achieved.
In the current paper these concepts are further elaborated. Importantly, we indicate an implementation framework ensuring tractability of reasoning about beliefs, propose the underlying methodology and illustrate it on an example.
Barbara Dunin-Kęplicz, Andrzej Szałas

Ideal Chaotic Pattern Recognition Is Achievable: The Ideal-M-AdNN - Its Design and Properties

Abstract
This paper deals with the relatively new field of designing a Chaotic Pattern Recognition (PR) system. The benchmark of such a system is the following: First of all, one must be able to train the system with a set of “training” patterns. Subsequently, as long as there is no testing pattern, the system must be chaotic. However, if the system is, thereafter, presented with an unknown testing pattern, the behavior must ideally be as follows. If the testing pattern is not one of the trained patterns, the system must continue to be chaotic. As opposed to this, if the testing pattern is truly one of the trained patterns (or a noisy version of a trained pattern), the system must switch to being periodic, with the specific trained pattern appearing periodically at the output. This is truly an ambitious goal, with the requirement of switching from chaos to periodicity being the most demanding. Some related work has been done in this regard. The Adachi Neural Network (AdNN) [1-5] has properties which are pseudo-chaotic, but it also possesses limited PR characteristics. As opposed to this, the Modified Adachi Neural Network (M-AdNN) proposed by Calitoiu et al [6], is a fascinating NN which has been shown to possess the required periodicity property desirable for PR applications. However, in this paper, we shall demonstrate that the PR properties claimed in [6] are not as powerful as originally reported. Indeed, the claim of the authors of [6] is true, in that it resonates periodically for trained input patterns. But unfortunately, the M-AdNN also resonates for unknown patterns and produces these unknown patterns at the output periodically. However, we describe how the parameters of the M-AdNN for its weights, steepness and external inputs, can be specified so as to yield a new NN, which we shall refer to as the Ideal-M-AdNN. Using a rigorous Lyapunov analysis, we shall analyze the chaotic properties of the Ideal-M-AdNN, and demonstrate its chaotic characteristics. Thereafter, we shall verify that the system is also truly chaotic for untrained patterns. But most importantly, we demonstrate that it is able to switch to being periodic whenever it encounters patterns with which it was trained. Apart from being quite fascinating, as far as we know, the theoretical and experimental results presented here are both unreported and novel. Indeed, we are not aware of any NN that possesses these properties!
Ke Qin, B. John Oommen

A Framework for an Adaptive Grid Scheduling: An Organizational Perspective

Abstract
Grid systems are complex computational organizations made of several interacting components evolving in an unpredictable and dynamic environment. In such context, scheduling is a key component and should be adaptive to face the numerous disturbances of the grid while guaranteeing its robustness and efficiency. In this context, much work remains at low-level focusing on the scheduling component taken individually. However, thinking the scheduling adaptiveness at a macro level with an organizational view, through its interactions with the other components, is also important. Following this view, in this paper we model a grid system as an agent-based organization and scheduling as a cooperative activity. Indeed, agent technology provides high level organizational concepts (groups, roles, commitments, interaction protocols) to structure, coordinate and ease the adaptation of distributed systems efficiently. More precisely, we make the following contributions. We provide a grid conceptual model that identifies the concepts and entities involved in the cooperative scheduling activity. This model is then used to define a typology of adaptation including perturbing events and actions to undertake in order to adapt. Then, we provide an organizational model, based on the Agent Group Role (AGR) meta-model of Freber, to support an adaptive scheduling at the organizational level. Finally, a simulator and an experimental evaluation have been realized to demonstrate the feasibility of our approach.
Inès Thabet, Chihab Hanachi, Khaled Ghédira

Data Extraction from Online Social Networks Using Application Programming Interface in a Multi Agent System Approach

Abstract
In recent years, Online Social Networks (OSNs) have attracted a significant increased number of users. New methods for extracting data are required to deal with the real time changes of a huge amount of personal information in OSNs. In the past, we implemented a parser as centralized system to retrieve information from OSN profiles source web pages. One of the drawbacks was that the parser had to be updated to reflect the changes in the profiles’ structure. In this paper, we extend our previous work that proposed Online Social Network Retrieval System (OSNRS) to decentralize the retrieving information process from OSN. The novelty of OSNRS, which is based on a Multi Agent System (MAS), is its ability to monitor profiles continuously. The new addition involves replacing the parser with the Application Programming Interface (API) tool to enable OSNRS to be integrated with services that are supported by OSN providers in the absence of the profiles source web page. Also, new algorithms alongside case studies are presented to improve OSNRS. The experimental work shows that using API and MAS simplifies and speeds up tracking the history of OSN profiles. Moreover, combining them with text mining helps us further to understand the dynamic behaviour of OSNs users.
Ruqayya Abdulrahman, Daniel Neagu, D. R. W. Holton, Mick Ridley, Yang Lan

Cooperatively Searching Objects Based on Mobile Agents

Abstract
This paper presents a framework for controlling multiple robots connected by communication networks. Instead of making multiple robots pursue several tasks simultaneously, the framework makes mobile software agents migrate from one robot to another to perform the tasks. Since mobile software agents can migrate to arbitrary robots by wireless communication networks, they can find the most suitably equipped and/or the most suitably located robots to perform their task. In this paper, we propose a multiple robot control approach based on mobile agents for searching targets as one of the effective examples. Though it is a simple task, it can be extended to any other more practial examples, or be used as an element of a real application because of its simplicity. We have conducted two kinds of experiments in order to demonstrate the effectiveness of our approach. One is an actual system with three real robots, and the other is a simulation system with a larger number of robots. The results of these experiments show that our approach achieves reducing the total time cost consumed by all robots while suppressing the energy consumption.
Takashi Nagata, Munehiro Takimoto, Yasushi Kambayashi

Agent Based Optimisation of VoIP Communication

Abstract
An optimisation process implies procedures and actions for decreasing costs and making the system more efficient. This paper proposes a model for simple management and optimisation of VoIP quality of service. The model is proposed in framework of VoIP communication optimisation based on simple measurement information incorporated in agent architecture for VoIP QoS management. The model is based on adapted E-model for packet communication in which MOS values are assigned from objective measurements of QoS parameters. The large set of objective and subjective experimental QoS measurements is performed in order to asses the range of model applicability in operational network. The comparison of the experimental results of MOS values with calculated values of parameter R, as well as the mapping between them, gives a good base for QoS optimisation based on simple real-time measurements. According to agent based architecture the basic operating procedures for VoIP agent management system with assumed optimisation actions are proposed.
Drago Žagar, Hrvoje Očevčić

Towards Rule Interoperability: Design of Drools Rule Bases Using the XTT2 Method

Abstract
Despite the maturity of rule-based technologies and number of rule formalisms, the practical rule interoperability is still challenging. In a distributed environment where many knowledge engineers work in a collective way, this causes severe problems. This is a methodological paper, which introduces an approach that can be considered such an interoperability method. Its aim is to provide a unified and formalized method for knowledge interchange for the most common rule languages. Our approach involves three levels of interoperability abstraction: semantic, model and environment level. On each level different problems are addressed. In order to assess the appropriateness of such decomposition we provide a proof of concept solution concerning the interoperability between the Drools and XTT2 rule bases.
Krzysztof Kaczor, Krzysztof Kluza, Grzegorz J. Nalepa

Artificial Immune System for Forecasting Time Series with Multiple Seasonal Cycles

Abstract
Many time series exhibit seasonal variations related to the daily, weekly or annual activity. In this paper a new immune inspired univariate method for forecasting time series with multiple seasonal periods is proposed. This method is based on the patterns of time series seasonal sequences: input ones representing sequences preceding the forecast and forecast ones representing the forecasted sequences. The immune system includes two populations of immune memory cells – antibodies, which recognize both types of patterns represented by antigens. The empirical probabilities that the forecast pattern is detected by the kth antibody from the second population while the corresponding input pattern is detected by the jth antibody from the first population, are computed and applied to the forecast construction. The empirical study of the model including sensitivity analysis to changes in parameter values and the robustness to noisy and missing data is performed. The suitability of the proposed approach is illustrated through applications to electrical load forecasting and compared with ARIMA and exponential smoothing approaches.
Grzegorz Dudek

Machine Ranking of 2-Uncertain Rules Acquired from Real Data

Abstract
There are many places (e.g. hospital emergency rooms) where reliable diagnostic systems might support people in their work. They could have form of RBSs with uncertainty and use the techniques of forward and backward chaining in their reasoning. The number and the contents of derived hypotheses depend then both on the form of the system’s knowledge base and on the inference engine performance. The paper provides detailed considerations on designing and applying particular uncertain rules, namely 2-uncertain rules. They are equipped with two reliability factors, representing a kind of second order probability. The rules can be acquired from real data of attributive representation. In the paper we propose a method for calculating the two reliability factors. We also suggest how to take advantage of the factors during reasoning, in order to obtain reliable hypotheses. The factors help to rank the rules and to fire them in the best order.
Beata Jankowska, Magdalena Szymkowiak

Backmatter

Weitere Informationen

Premium Partner

    Bildnachweise