Signal Classification Based on Cyclostationary Spectral Analysis and HMM/SVM in Cognitive Radio

He, Xinying; Zeng, Zhimin; Guo, Caili

doi:10.1109/icmtma.2009.283

Cited by 18 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A second strategy focuses on a single transmission [84], [88], which does not fit the multiband model. Alternative approaches apply machine learning tools to the modulation classification of a single signal with unknown carrier frequency and symbol rate [89]- [92]. Besides being only suitable for a single transmission, these methods require a training phase.…”

Section: B Cyclostationary Detectionmentioning

confidence: 99%

Analog-to-Digital Cognitive Radio: Sampling, Detection, and Hardware

Cohen

Tsiper

Eldar

2018

IEEE Signal Process. Mag.

View full text Add to dashboard Cite

Section: B Cyclostationary Detectionmentioning

confidence: 99%

Analog-to-Digital Cognitive Radio: Sampling, Detection, and Hardware

Cohen

Tsiper

Eldar

2018

IEEE Signal Process. Mag.

View full text Add to dashboard Cite

“…Tandra and Sahai (2007) shows that the cyclostationary feature-based signal detector has SNR wall below which detection of signal is not possible when noise ambiguity and frequency selective fading of wireless channel exist. The hidden Markov model (HMM)-based signal classifier was represented in Hu et al (2008), Xu and Wang (2008) and He et al (2009). HMM is dependent on the statistical knowledge of the pre-experimentation and determination of the optimal number of states of HMM is difficult.…”

Section: Related Work and Backgroundmentioning

confidence: 99%

A Novel Channel State Prediction Technique for Overlay Cognitive Radio-based Emergency Sensor Networks

Chatterjee¹,

Chakraborty²,

Saha

2018

IJKEDM

View full text Add to dashboard Cite

For overlay cognitive radio (CR), this paper proposes a knowledge-based spectrum prediction technique using artificial neural network. This is targeted for CR-based emergency sensor networks in real life applications, where extremely reliable data transmission is mandatory. The technique operates in two steps: 1) identification of idle states in primary user bands; 2) prediction of noise level of the idle bands. The goal is to select a less noisy vacant band among the detected idle bands. The system is analysed under both Gaussian mixer noise (GMN) distribution and additive white Gaussian noise (AWGN) by predicting the current state of the channel in low SNR environment. Simulation results using MATLAB R2015b show satisfactory values for probability of false alarm (0.17 and 0.3), and probability of misdetection (0.12 and 0.25) for AWGN and GMN, respectively.

show abstract

“…A hidden Markov model (HMM) approach is considered in [17]. By combining an HMM and a support vector machine (SVM) classifier, the authors in [18] improve the classification performance. The cyclostationary frequencies, namely carrier and symbol rate, are a byproduct of the classification process.…”

Section: Introductionmentioning

confidence: 99%

Carrier frequency and bandwidth estimation of cyclostationary multiband signals

Cohen

Pollak

Eldar

2016

2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

Abstract-Communication signals are often cyclostationary, that is they have statistical characteristics that vary periodically in time. The cyclic spectrum, a characteristic function of such signals, exhibits spectral peaks at certain locations, called cyclic frequencies. These locations as well as the cyclic spectrum support are defined by the signal parameters, in particular carrier frequency, bandwidth and symbol rate. In this paper, we propose an estimation algorithm that extracts these from the signal cyclic spectrum. This algorithm can be applied to multiband signals, namely signals composed of more than one transmission. Prior to parameter estimation, the number of signals is first estimated. Exploiting the cyclostationarity of communication signals improves the robustness to noise of the parameter estimation. In particular, the proposed algorithm can be used for Cognitive Radios, which traditionally deal with low signal to noise ratios multiband signals, for spectrum sensing purposes by estimating the carrier frequencies and bandwidths. Simulations demonstrate estimation from synthesized and RF Nyquist samples as well as subNyquist samples.

show abstract

Signal Classification Based on Cyclostationary Spectral Analysis and HMM/SVM in Cognitive Radio

Cited by 18 publications

References 9 publications

Analog-to-Digital Cognitive Radio: Sampling, Detection, and Hardware

Analog-to-Digital Cognitive Radio: Sampling, Detection, and Hardware

A Novel Channel State Prediction Technique for Overlay Cognitive Radio-based Emergency Sensor Networks

Carrier frequency and bandwidth estimation of cyclostationary multiband signals

Contact Info

Product

Resources

About