An overview of learning mechanisms for cognitive systems

Bantouna, Aimilia; Stavroulaki, Vera; Kritikou, Yiouli; Tsagkaris, Kostas; Demestichas, Panagiotis; Moessner, Klaus

doi:10.1186/1687-1499-2012-22

Cited by 12 publications

(4 citation statements)

References 31 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…If a 'wireless society' [174] vision is to materialize in the not so distant future, it is imperative that researchers focus on seamless integration of user preferences, and awareness of (identity, location, time, activity-based) context into cognitive networking design. There has been some initial work done in this area [175] but a lot more work needs to be done.…”

Section: A Incorporation Of User Preferences and Context-awarenessmentioning

confidence: 99%

Artificial intelligence based cognitive routing for cognitive radio networks

Qadir

2015

Artif Intell Rev

View full text Add to dashboard Cite

Abstract-Cognitive radio networks (CRNs) are networks of nodes equipped with cognitive radios that can optimize performance by adapting to network conditions. While cognitive radio networks (CRN) are envisioned as intelligent networks, relatively little research has focused on the network level functionality of CRNs. Although various routing protocols, incorporating varying degrees of adaptiveness, have been proposed for CRNs, it is imperative for the long term success of CRNs that the design of cognitive routing protocols be pursued by the research community. Cognitive routing protocols are envisioned as routing protocols that fully and seamless incorporate AI-based techniques into their design. In this paper, we provide a self-contained tutorial on various AI and machine-learning techniques that have been, or can be, used for developing cognitive routing protocols. We also survey the application of various classes of AI techniques to CRNs in general, and to the problem of routing in particular. We discuss various decision making techniques and learning techniques from AI and document their current and potential applications to the problem of routing in CRNs. We also highlight the various inference, reasoning, modeling, and learning sub tasks that a cognitive routing protocol must solve. Finally, open research issues and future directions of work are identified.

show abstract

Section: A Incorporation Of User Preferences and Context-awarenessmentioning

confidence: 99%

Artificial intelligence based cognitive routing for cognitive radio networks

Qadir

2015

Artif Intell Rev

View full text Add to dashboard Cite

show abstract

“…Uma das principais vantagens no uso de algoritmos de AMé a sua capacidade de modelar o comportamento da rede em intervalos futuros, permitindo a aplicação de soluções em tempo hábil, como a troca de canal [7]. Em aplicações onde nãoé possível obter informações do meio em tempo real, são usadas técnicas alternativas como os modelos estatísticos de uso do espectro, propostos por [8].…”

Section: Conceitos E Trabalhos Relacionadosunclassified

Spectrum Decision in Wireless Sensor Networks Employing Machine Learning

Silva

Macedo

Leoni

2014

2014 Brazilian Symposium on Computer Networks and Distributed Systems

View full text Add to dashboard Cite

Wireless Sensor Networks (WSNs) employ ISM spectrum bands for communication, which are overloaded due to various technologies such as WLANs and other WSNs. Therefore, such networks must employ intelligent methods such as Cognitive Radio to coexist with other networks. This study evaluates the use of Supervised Machine Learning (ML) for channel selection in WSNs, considering the channel quality and communication metrics. The methods were evaluated experimentally and compared with energy-based methods. The results show that ML-based methods increase the communication performance by reducing the number of transmission attempts and therefore also reducing the delivery delay. I. INTRODUÇÃOUm estudo da FCC (Federal Communications Commision) [1] mostrou que as regras atuais adotadas para alocação de canal causam perdas consideráveis na eficiência e aproveitamento do espectro, pois em inúmeros intervalos de tempo os usuários licenciados ao uso desses canais não estão em operação [2], [3]. Além disso, o acúmulo de usuários não licenciados em frequências livres gera interferências, causando perdas de informação e um aumento no consumo de energia. Redes de Sensores Sem Fio (RSSFs) são suscetíveis a esse problema, o que levà a redução do seu tempo de vida.Por isso, as RSSFs deveriam adotar técnicas que explorem o espectro com mais eficiência, de forma a coexistir com usuários de diferentes redes sem causar conflitos entre elas. Os Rádios Cognitivos (RCs) permitem uma melhor exploração de faixas de frequência pouco utilizadas [3]. Neste trabalho seguimos a definição de [4], onde o RC mensura o ambiente eletromagnético no qual ele opera, para ajustar seus parâmetros de forma autônoma e dinâmica, de forma a aumentar o fluxo de dados, reduzir a interferência e facilitar a interoperabilidade.No caso das RSSFs, que empregam a faixa de frequência não licenciada ISM (Industrial, Scientific and Medical), as funções de RC são utilizadas para aumentar a coexistência de múltiplas redes, ao mesmo tempo que garantem uma comunicação mais eficiente e confiável [5]. Enquanto nos RCs "tradicionais" procura-se selecionar faixas de frequência livres de usuários licenciados (também chamados de Usuários Primários), nas RSSFs os RCs selecionam canais com melhores condições para a comunicação, evitando a interferência tanto de outras RSSFs instaladas na região quanto de outros tipos de redes operando na faixa ISM (Wi-Fi, Bluetooth, etc). Entretanto, o principal desafio na implementação de RCs em RSSFś e a limitação de recursos de processamento, memória e energia destas redes. Assim, as soluções de RC existentes devem ser adequadasàs restrições das RSSFs.Neste trabalho propomos o emprego de Aprendizado de Máquina (AM) para a seleção de canais em RSSFs. As soluções propostas são avaliadas experimentalmente, comparando o seu desempenho com soluções baseadas somente em energia, as quais são populares em ambientes reais. Foram coletados dados de desempenho acerca de uma sequência de transmissões e recepções realizadas, como forma de quantificar o nível...

show abstract

“…As revolutionary development of Intelligent Radio (IR), CR implements Soft Radio by adding Knowledge Base, Reasoning Engine, and Learning Engine to be an independent Cognitive Engine (CE), which makes the radio capable of learning and adapting to the surrounding radio environment [12]. Knowledge Base which stores variety of cases, relations, and rules can be seen as memory in human's brain and is very common in Artificial Intelligence (AI) logic planning.…”

Section: Introductionmentioning

confidence: 99%

Fast Channel Selection Strategy in Cognitive Wireless Sensor Networks

Sun

Qian

2015

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

In order to meet the practical requirement for Cognitive Wireless Sensor Networks applications, this paper proposes innovative fast channel selection algorithm to solve the shortcomings of original Experience-Weighted Attraction algorithm's complexity, higher energy consuming, and the nodes’ hardware restrictions of real-time data processing capabilities. Research is conducted by comparing channel selection differences and timeliness with traditional Experience-Weighted Attraction learning. Though not as stable as traditional Experience-Weighted Attraction learning, fast channel selection algorithm has effectively reduced the complexity of the original algorithm and has superior performance than Q learning.

show abstract

An overview of learning mechanisms for cognitive systems

Cited by 12 publications

References 31 publications

Artificial intelligence based cognitive routing for cognitive radio networks

Artificial intelligence based cognitive routing for cognitive radio networks

Spectrum Decision in Wireless Sensor Networks Employing Machine Learning

Fast Channel Selection Strategy in Cognitive Wireless Sensor Networks

Contact Info

Product

Resources

About