Signal Classification Based on Spectral Correlation Analysis and SVM in Cognitive Radio

Hu, Hao; Song, Junde; Wang, Yujing

doi:10.1109/aina.2008.27

Cited by 69 publications

(37 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When the input signal x(t) is considered as ACS, the output signal y(t) through the LTV fading channel is also ACS with the same cyclic components as x(t), since we can see from (13) and (14) the autocorrelation function R yy (t, τ ) is also almost periodic with the same period as R xx (t, τ ).…”

Section: Cyclostationary Featuresmentioning

confidence: 98%

See 1 more Smart Citation

Wideband Spectrum Sensing and Non-Parametric Signal Classification for Autonomous Self-Learning Cognitive Radios

Bkassiny

Jayaweera

et al. 2012

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

This paper presents an autonomous cognitive radio (CR) architecture, referred to as the Radiobot. This model goes beyond adaptive radio systems to exploit the main ingredients of cognition which, in this context, are mainly self-learning and self-reconfiguration. Without any prior knowledge of the RF environment, the Radiobot applies a sequence of increasingly sophisticated processing steps to detect and identify the sensed signals. In particular, in this paper, it applies a blind energy detection followed by a cyclostationary detection method to detect the active signals and extract their underlying periodic properties as reflected in cyclic frequencies. These extracted signal features are classified based on the Chinese restaurant process (CRP) and a learning algorithm is applied to achieve autonomous selfreconfiguration of the sensing module. We analyze the impact of fading and Doppler frequency shift on both the energy and cyclostationary detections, and show the receiver operating characteristic (ROC) of the carrier frequency detector. We show the robustness of the cyclostationary detection against channel fading and wide-sense stationary noise. Simulation results are presented to verify the multi-band operability and the reconfiguration ability of the Radiobot and to verify the convergence of the proposed learning algorithm.

show abstract

Section: Cyclostationary Featuresmentioning

confidence: 98%

“…Several signal classification and feature extraction methods for CR spectrum sensing have been proposed in the literature, including the models in [12], [13] which rely on support vector machines (SVM's). In this paper, however, we employ non-parametric learning for autonomous signal identification/classification.…”

Section: Introductionmentioning

confidence: 99%

Wideband Spectrum Sensing and Non-Parametric Signal Classification for Autonomous Self-Learning Cognitive Radios

Bkassiny

Jayaweera

et al. 2012

IEEE Trans. Wireless Commun.

View full text Add to dashboard Cite

show abstract

“…Several approaches exist for solving signal classification problems, such as the one described in [9] (based on spectral analysis and relying on feed-forward neural networks), however considering that no training data is available when the algorithm starts (because each signature pattern is, practically, unique to each device, in every household) and that new patterns need to be absorbed into the database as they appear in time, we have used another approach (described in [10]) that uses a variation of the fast Aho-Corasick multiple pattern-matching algorithm [11] with support for simple regular expressions [12].…”

Section: B System Architecturementioning

confidence: 99%

A Model for Energy-Efficient Household Maintenance through Behavioral Analysis of Electrical Appliances

Pungila

2010

2010 IEEE 7th International Conference on E-Business Engineering

View full text Add to dashboard Cite

Reducing electrical energy consumption has become an important goal that needs to be achieved in the near future in order to reduce CO2 emissions. In this paper we are presenting a model that, through human intervention at certain points in time, aims to achieve that goal. By analyzing the behavior of electrical appliances and classifying the results the system is capable of offering to the end-user suggestions on how to reduce the energy consumption of their corresponding energy-depending activities.

show abstract

“…Support vector machine, the representative of large mar-gin classifiers, enjoys a sound theoretical foundation based on Structural Risk Minimization [11,12]. It has achieved many successes in various empirical applications thanks to its superior generalization performance.…”

Section: Introductionmentioning

confidence: 99%

Primary User Signal Type Recognition Algorithm of Cognitive Radio Networks based on Active Learning in Building Indoors

Wang¹,

Gao²,

Kan³

et al. 2016

Advances in Computer Science Research

View full text Add to dashboard Cite

Abstract-Primary user signal modulation type recognition performance of building indoor environment has been the focus of attention and research in low signal-to-noise ratio. In this paper, a method based on active learning and support vector machine (SVM) for the primary user signal modulation type recognition is proposed in low signal to noise ratio. Three spectral coherence characteristic parameters are chosen via spectral correlation analysis, and the training samples and testing samples are formed for classification. Then, active learning algorithm is applied to obtain samples improved classification through a number of iterations, and SVM is formed. Finally, the formed SVM is utilized to recognize the primary user signal modulation type. Compared to the existing methods including the classifiers based on MME and ANN, the proposed approach is more effective in the case of low SNR and limited training numbers. The results show that the validity and superiority of the proposed algorithm on primary user signal modulation type recognition in building indoor environment.

show abstract

Signal Classification Based on Spectral Correlation Analysis and SVM in Cognitive Radio

Cited by 69 publications

References 8 publications

Wideband Spectrum Sensing and Non-Parametric Signal Classification for Autonomous Self-Learning Cognitive Radios

Wideband Spectrum Sensing and Non-Parametric Signal Classification for Autonomous Self-Learning Cognitive Radios

A Model for Energy-Efficient Household Maintenance through Behavioral Analysis of Electrical Appliances

Primary User Signal Type Recognition Algorithm of Cognitive Radio Networks based on Active Learning in Building Indoors

Contact Info

Product

Resources

About