Dynamic Cognitive Networks Research Articles

Improved decomposition-based multi-objective cuckoo search algorithm for spectrum allocation in cognitive vehicular network

The allocation of spectrum resources efficiently and equitably in dynamic cognitive vehicular networks is more challenging than static cognitive networks. Currently, most spectrum allocation algorithms are on the basis of a fixed network topology, thereby ignoring the mobility of cognitive vehicular users (CVUs), timeliness of licensed channels, and uncertainty of spectrum sensing in complex environments. In this paper, a cognitive vehicular network spectrum allocation model for maximizing the network throughput and fairness is established considering these factors. A rapid convergence, improved performance algorithm for solving this multi-objective problem is necessary to adapt to a dynamic network environment. Therefore, an improved decomposition-based multi-objective cuckoo search (MOICS/D) algorithm is proposed. This algorithm integrates a decomposition-based multi-objective optimization framework and an improved CS algorithm. The multi-objective problem is decomposed into multiple scalar sub-problems with different weight coefficients, and the cuckoo algorithm with adaptive steps is used to optimize these sub-problems simultaneously. Simulation results show that the MOICS/D algorithm has faster and more stable convergence than the MOEA/D and NSGA-II algorithms and can improve the throughput and fairness of the network.

A Subsumption Architecture to Develop Dynamic Cognitive Network-Based Models With Autonomous Navigation Application

This work proposes an original approach based on subsumption architecture to build dynamic cognitive networks (DCN). Dynamic cognitive network is a soft computing technique similar to fuzzy cognitive maps (FCM) which are able to easily model cause–effect behaviors. FCMs have been applied in several areas of knowledge; however, they present some restrictions for modeling dynamic systems, specifically temporal dependencies among events. Due to these restrictions, alternative approaches based on FCM and also fuzzy networks have appeared in the literature. Dynamic cognitive networks are one of these techniques. Hence, this study presents a new type of DCN which incorporates different types of concepts and causal relations able to circumvent the main drawbacks of FCM modeling. The new approach is based on the subsumption architecture, which allows to represent, model, and implement several behaviors of a dynamic systems through a composition of hierarchical DCNs. An application of the new DCN technique in autonomous navigation is also developed in order to validate the approach.

Redes Cognitivas Dinâmicas, Fundamentos e Aplicações

This study presents the proposal of dynamic cognitive networks (DCN), and also the evolution of Cognitive Maps and Fuzzy Cognitive Maps. Fuzzy Cognitive Maps (FCM) can be applied in several areas of knowledge; however, it presents some restrictions in dynamic systems. Due to these restrictions, some architectures proposals are based on FCM and also classical proposals for cognitive models based on these concepts are available in the literature. Dynamic Cognitive Networks is one of these approaches. Hence, this study presents an original proposal with background for the construction of DCN and applications in process control and autonomous navigation.

Redes dinâmicas cognitivas aplicadas no controle supervisório de um fermentador

Este trabalho usa redes cognitivas dinâmicas (Dynamic Cognitive Networks - (DCN), como uma ferramenta inteligente para controle supervisório. As DCNs são uma evolução dos mapas cognitivos fuzzy (Fuzzy Cognitve Map - FCM). Os sistemas inteligentes se baseiam no conhecimento de especialistas a fim de construir modelos com capacidade de inferência e/ou tomada de decisão. Uma arquitetura de controle supervisório para um processo de fermentação alcoólica é desenvolvida a partir da aquisição de conhecimento empírico de um especialista. O objetivo do supervisor é operar o processo em situações normal e crítica. Para isto, propõe-se o uso de uma DCN que incorpora novos tipos de conceitos e relações que não apenas as relações de causa-efeito presentes nos modelos baseados em FCMs. Resultados de simulação são apresentados para validar a arquitetura desenvolvida.

Development of dynamic cognitive networks as complex systems approximators: validation in financial time series

Dynamic cognitive networks (DCNs) define a novel approach to functionalize cognitive mapping and complex systems analysis, which were recently supported by fuzzy cognitive maps (FCMs). The modeling and inference limitations met in FCMs, especially in situations with strong nonlinearity and temporal phenomena, pushed towards DCNs; their theoretical framework is scheduled to confront the preceding weaknesses and offer wider possibilities in causal structures management. Trying to contribute to the enhancement of DCNs, at first, systemic and environmental metaphors are introduced with practical mathematical formalisms and generalized nomenclature. Nonlinear and asymmetric cause-effect relationships, decaying mechanisms, inertial forces, diminishing effects and biases formulate a powerful set of adaptive characteristics that strengthen the operational behavior of DCNs. Second, the strategic reorientation of DCNs is attempted as generalized approximation tools. This new strategic option is verified not only in classical function approximation tests, but also in the challenging area of securities markets. The platform of evaluation of DCNs involves comparisons with a linear multiple regression model, a feed-forward neural network trained with both back-propagation and evolution strategies, a radial basis function network, and an adaptive network-based fuzzy inference system (ANFIS). Through the experiments for short-term stock price predictions, multiple issues are analyzed not only about the role of diverse DCN parameters, but also about the given problem of financial markets modeling and forecasting. Simulations distinguish DCNs as a strong methodology with noticeable adaptability in complicated patterns and broad generalization capabilities while, at the same time, the all-embracing outcomes support previous findings of partially random walk phenomena in short-term stock market forecasting attempts.