Classification of multiple M-ary frequency-shift keying signals over a Rayleigh fading channel

El-Mahdy, Ahmed; Namazi, N.M.

doi:10.1109/tcomm.2002.1010616

Cited by 50 publications

(30 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At present, AMR is implemented using the three types of methods listed in Figure 1: (1) The first method is based on the likelihood ratio test (LRT), such as the average LRT proposed by ElMahdy et al [4], the general LRT proposed by Panagiotou et al [5], and the hybrid LRT proposed by Hameed et al [6]. The disadvantage of this type of algorithm is that the assumption that the symbols are independent and identically distributed is usually not true in reality, and the complexity increases with an increase in the number of unknown parameters.…”

Section: Introductionmentioning

confidence: 99%

Implementation of Deep Learning-Based Automatic Modulation Classifier on FPGA SDR Platform

Tang

2018

Electronics

View full text Add to dashboard Cite

Intelligent radios collect information by sensing signals within the radio spectrum, and the automatic modulation recognition (AMR) of signals is one of their most challenging tasks. Although the result of a modulation classification based on a deep neural network is better, the training of the neural network requires complicated calculations and expensive hardware. Therefore, in this paper, we propose a master-slave AMR architecture using the reconfigurability of field-programmable gate arrays (FPGAs). First, we discuss the method of building AMR, by using a stack convolution autoencoder (CAE), and analyze the principles of training and classification. Then, on the basis of the radiofrequency network-on-chip architecture, the constraint conditions of AMR in FPGA are proposed from the aspects of computing optimization and memory access optimization. The experimental results not only demonstrated that AMR-based CAEs worked correctly, but also showed that AMR based on neural networks could be implemented on FPGAs, with the potential for dynamic spectrum allocation and cognitive radio systems.

show abstract

Section: Introductionmentioning

confidence: 99%

Implementation of Deep Learning-Based Automatic Modulation Classifier on FPGA SDR Platform

Tang

2018

Electronics

View full text Add to dashboard Cite

show abstract

“…The other trend is signal statistical features [2]. In order to improve PCC for modulation classification, [3][4][5][6] established different Maximum Likelihood (ML) functions. This method was optimized to estimate parameters, such as modulation mode, carrier frequency, phase, and channel response.…”

Section: Introductionmentioning

confidence: 99%

“…Instantaneous signal feature was obtained to reduce the complexity. In [5,6], the optimization method based on different Maximum Likelihood was proposed for MFSK signal modulation. Thus a higher PCC had been obtained.…”

Section: Introductionmentioning

confidence: 99%

“…Different ML functions and Bayesian decision networks must be evaluated carefully. According to different modulation types, literature [3][4][5][6][7] proposed different likelihood ratio functions, which could obtain the theoretical optimal result under the Gaussian white noise condition. However, multipath fading channel would seriously impact on modulation classification.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Modulation Classification Based on Extensible Neural Networks

Yang

2017

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A deep learning architecture based on Extensible Neural Networks is proposed for modulation classification in multipath fading channel. Expanded Neural Networks (ENN) are established based on energy natural logarithm model. The model is set up using hidden layers. Modulation classification based on ENN is implemented through the amplitude, phase, and frequency hidden network, respectively. In order to improve Probability of Correct classification (PCC), one or more communication signal features are extracted using hidden networks. Through theoretical proof, ENN learning network is demonstrated to be effective in improving PCC using amplitude, phase, and the frequency weight subnetwork, respectively. Compared with the traditional algorithms, the simulation results show that the proposed ENN has higher PCC than traditional algorithm for modulation classification within the same training sequence and Signal to Noise Ratio (SNR).

show abstract

“…The LB approach was studied by Beidas and Weber [5]- [6], who additionally proposed a higher-order correlation-based algorithm starting from the LB method. El-Mahdy and Namazi [7] developed an LB approach for Rayleigh fading channels, with unknown signal parameters, such as timing and phase offset; the likelihood function was calculated by averaging over these unknowns. For the FB approach, various features were chosen for classification, such as wavelet transform magnitude [8], number of peaks in the signal spectrum [9], mean of the complex signal envelope [10], zero-crossing sequence [11], instantaneous frequency [12], and signal cyclostationarity [13]- [15].…”

Section: Introductionmentioning

confidence: 99%

Experimental results for M-FSK signal classification and parameter estimation

Wang

Dobre

et al. 2013

2013 IEEE International Instrumentation and Measurement Technology Conference (I2MTC)

View full text Add to dashboard Cite

Blind signal classification and parameter estimation have important applications in both military and commercial communications. This paper proposes a cyclostationarity-based approach for M-FSK signal classification and estimation of the tone frequency spacing. Relying on the number and position of the first-order cycle frequencies (CFs), the proposed approach requires neither recovery of the carrier and symbol timing, nor estimation of the channel, and signal and noise powers. The performance of this algorithm was investigated using both laboratory and simulation experiments.

show abstract

Classification of multiple M-ary frequency-shift keying signals over a Rayleigh fading channel

Cited by 50 publications

References 9 publications

Implementation of Deep Learning-Based Automatic Modulation Classifier on FPGA SDR Platform

Implementation of Deep Learning-Based Automatic Modulation Classifier on FPGA SDR Platform

Modulation Classification Based on Extensible Neural Networks

Experimental results for M-FSK signal classification and parameter estimation

Contact Info

Product

Resources

About