The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Neste artigo, propomos um novo esquema de detecção primária de usuário para detecção de espectro em rádio cognitivo. Inspirado na abordagem convencional de classificação de sinais, o sensoriamento de espectro é traduzido em um problema de classificação. Com base na classificação baseada em características, a correlação espectral de uma análise cicloestacionária de segunda ordem é aplicada como método de extração de características, enquanto uma rede de autoencoders com eliminação de ruído empilhada é aplicada como classificador. Dois métodos de treinamento para detecção de sinais, detecção baseada em interceptação e detecção baseada em simulação, são considerados, para diferentes informações prévias e condições de implementação. Em um método de detecção baseado em interceptação, inspirado no sensoriamento em duas etapas, obtemos dados de treinamento a partir da interceptação de sinais reais após um procedimento de sensoriamento sofisticado, para obter detecção sem informação a priori. Além disso, beneficiando-se de dados de treinamento prático, esta detecção baseada em interceptação é superior sob condições reais do ambiente de transmissão. A alternativa, um método de detecção baseado em simulação, utiliza alguns parâmetros indisfarçáveis do usuário principal no espectro de interesse. Devido aos diversificados dados de treinamento predeterminados, a detecção baseada em simulação exibe robustez transcendental contra ambientes de ruído severo, embora exija uma estrutura de rede classificadora mais complicada. Além disso, para os métodos de treinamento descritos acima, discutimos a complexidade do classificador sobre as condições de implementação e o compromisso entre robustez e desempenho de detecção. Os resultados da simulação mostram as vantagens do método proposto sobre os esquemas convencionais de detecção de espectro.
Hang LIU
The University of Electro-Communications
Xu ZHU
The University of Electro-Communications
Takeo FUJII
The University of Electro-Communications
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Hang LIU, Xu ZHU, Takeo FUJII, "A New Classification-Like Scheme for Spectrum Sensing Using Spectral Correlation and Stacked Denoising Autoencoders" in IEICE TRANSACTIONS on Communications,
vol. E101-B, no. 11, pp. 2348-2361, November 2018, doi: 10.1587/transcom.2017EBP3447.
Abstract: In this paper, we propose a novel primary user detection scheme for spectrum sensing in cognitive radio. Inspired by the conventional signal classification approach, the spectrum sensing is translated into a classification problem. On the basis of feature-based classification, the spectral correlation of a second-order cyclostationary analysis is applied as the feature extraction method, whereas a stacked denoising autoencoders network is applied as the classifier. Two training methods for signal detection, interception-based detection and simulation-based detection, are considered, for different prior information and implementation conditions. In an interception-based detection method, inspired by the two-step sensing, we obtain training data from the interception of actual signals after a sophisticated sensing procedure, to achieve detection without priori information. In addition, benefiting from practical training data, this interception-based detection is superior under actual transmission environment conditions. The alternative, a simulation-based detection method utilizes some undisguised parameters of the primary user in the spectrum of interest. Owing to the diversified predetermined training data, simulation-based detection exhibits transcendental robustness against harsh noise environments, although it demands a more complicated classifier network structure. Additionally, for the above-described training methods, we discuss the classifier complexity over implementation conditions and the trade-off between robustness and detection performance. The simulation results show the advantages of the proposed method over conventional spectrum-sensing schemes.
URL: https://global.ieice.org/en_transactions/communications/10.1587/transcom.2017EBP3447/_p
Copiar
@ARTICLE{e101-b_11_2348,
author={Hang LIU, Xu ZHU, Takeo FUJII, },
journal={IEICE TRANSACTIONS on Communications},
title={A New Classification-Like Scheme for Spectrum Sensing Using Spectral Correlation and Stacked Denoising Autoencoders},
year={2018},
volume={E101-B},
number={11},
pages={2348-2361},
abstract={In this paper, we propose a novel primary user detection scheme for spectrum sensing in cognitive radio. Inspired by the conventional signal classification approach, the spectrum sensing is translated into a classification problem. On the basis of feature-based classification, the spectral correlation of a second-order cyclostationary analysis is applied as the feature extraction method, whereas a stacked denoising autoencoders network is applied as the classifier. Two training methods for signal detection, interception-based detection and simulation-based detection, are considered, for different prior information and implementation conditions. In an interception-based detection method, inspired by the two-step sensing, we obtain training data from the interception of actual signals after a sophisticated sensing procedure, to achieve detection without priori information. In addition, benefiting from practical training data, this interception-based detection is superior under actual transmission environment conditions. The alternative, a simulation-based detection method utilizes some undisguised parameters of the primary user in the spectrum of interest. Owing to the diversified predetermined training data, simulation-based detection exhibits transcendental robustness against harsh noise environments, although it demands a more complicated classifier network structure. Additionally, for the above-described training methods, we discuss the classifier complexity over implementation conditions and the trade-off between robustness and detection performance. The simulation results show the advantages of the proposed method over conventional spectrum-sensing schemes.},
keywords={},
doi={10.1587/transcom.2017EBP3447},
ISSN={1745-1345},
month={November},}
Copiar
TY - JOUR
TI - A New Classification-Like Scheme for Spectrum Sensing Using Spectral Correlation and Stacked Denoising Autoencoders
T2 - IEICE TRANSACTIONS on Communications
SP - 2348
EP - 2361
AU - Hang LIU
AU - Xu ZHU
AU - Takeo FUJII
PY - 2018
DO - 10.1587/transcom.2017EBP3447
JO - IEICE TRANSACTIONS on Communications
SN - 1745-1345
VL - E101-B
IS - 11
JA - IEICE TRANSACTIONS on Communications
Y1 - November 2018
AB - In this paper, we propose a novel primary user detection scheme for spectrum sensing in cognitive radio. Inspired by the conventional signal classification approach, the spectrum sensing is translated into a classification problem. On the basis of feature-based classification, the spectral correlation of a second-order cyclostationary analysis is applied as the feature extraction method, whereas a stacked denoising autoencoders network is applied as the classifier. Two training methods for signal detection, interception-based detection and simulation-based detection, are considered, for different prior information and implementation conditions. In an interception-based detection method, inspired by the two-step sensing, we obtain training data from the interception of actual signals after a sophisticated sensing procedure, to achieve detection without priori information. In addition, benefiting from practical training data, this interception-based detection is superior under actual transmission environment conditions. The alternative, a simulation-based detection method utilizes some undisguised parameters of the primary user in the spectrum of interest. Owing to the diversified predetermined training data, simulation-based detection exhibits transcendental robustness against harsh noise environments, although it demands a more complicated classifier network structure. Additionally, for the above-described training methods, we discuss the classifier complexity over implementation conditions and the trade-off between robustness and detection performance. The simulation results show the advantages of the proposed method over conventional spectrum-sensing schemes.
ER -