A wavelet-based method for classification of binary digitally modulated signals

Ho, Ka Mun; Vaz, Canute; Daut, D.G.

doi:10.1109/sarnof.2009.4850369

Cited by 16 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Significant research has been done in choosing the most appropriate feature from modulated waveform for classification. Ho et al [25] used wavelet transform for feature extraction of signals where he is mainly focused on BASK and BPSK modulation type at −5 dB SNR and archives 54.0% accuracy. Moser et al [26] used the Instantaneous feature for the classification of modulated signals, where they take 9 types of modulated signals with 10 dB and 20 dB SNR values at two different threshold levels of 2048 and 8192, out of them at Threshold level of 8192, accuracy of 100% is achieved.…”

Section: Related Workmentioning

confidence: 99%

Automatic classification of multi-carrier modulation signal using STFT spectrogram and deep CNN

Tailor,

Dua,

Verma

2024

Phys. Scr.

View full text Add to dashboard Cite

In the realm of communication systems, categorizing Multi-Carrier Modulation (MCM) signals without cooperative communication poses a significant technical challenge. In this paper, we introduce a novel approach for accurately categorizing five distinct MCM signals, including Orthogonal Frequency Division Multiplexing (OFDM), Filter Bank Multicarrier (FBMC), Filtered Orthogonal Frequency Division Multiplexing (FOFDM), Windowed Orthogonal Frequency Division Multiplexing (WOLA), and Universal Filtered Multicarrier (UFMC). Each signal is considered with two types of subcarrier waveforms, Quadrature Amplitude Modulation 16 (QAM16) and Quadrature Amplitude Modulation 64 (QAM64), resulting in a total of 10 unique MCM signals for classification. Our proposed methodology leverages Short-Time Fourier Transform (STFT) spectrograms for feature extraction at the frontend, while at the backend, we employ three variants of Convolutional Neural Network (CNN) models; CNN, CNN with Dropout (CNN_d), CNN with both Dropout and L1 Regularization (CNN_dL1) and one deep CNN model; Xception, individually. We aim to provide an efficient and reliable means of categorizing MCM signals, with practical applications in signal processing and communication systems. Extensive simulations demonstrate the effectiveness of our approach, achieving remarkable accuracies. Notably, the Xception model exhibits the highest accuracy among the four models considered. Specifically, we attain an accuracy of 98% at 10dB SNR using the Xception model. These results underscore the efficacy of our proposed methodology and highlight the potential for its deployment in real-world scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic classification of multi-carrier modulation signal using STFT spectrogram and deep CNN

Tailor,

Dua,

Verma

2024

Phys. Scr.

View full text Add to dashboard Cite

show abstract

“…The FB-AMC makes feature extraction and classification. In order to extract features, expert systems carefully extract various manual features, such as wavelet-based features [9], instantaneous features [10], and statistical features [3], [11].…”

Section: Introductionmentioning

confidence: 99%

Robust Automatic Modulation Classification in Low Signal to Noise Ratio

Lee

2023

IEEE Access

View full text Add to dashboard Cite

In a non-cooperative communication environment, automatic modulation classification (AMC) is an essential technology for analyzing signals and classifying different kinds of signal modulation before they are demodulated. Deep learning (DL)-based AMC has been proposed as an efficient method of achieving high classification performance. However, most current DL-AMC methods have limited generalization capabilities under varying noise conditions, especially at low signal-to-noise ratios (SNRs). Therefore, these methods can not be directly applied to practical systems. In this paper, we propose a threshold autoencoder denoiser convolutional neural network (TADCNN), which consists of a threshold autoencoder denoiser (TAD) and a convolutional neural network (CNN). TADs reduce noise power and clean input signals, which are then passed on to CNN for classification. The TAD network generally consists of three components: the batch normalization layer, the autoencoder, and the threshold denoise. The threshold denoise component uses an auto-learning threshold sub-network to compute thresholds automatically. According to experiments, AMC with TAD improved classification accuracy by 70% at low SNR compared with a model without a denoiser. Additionally, our model achieves an average accuracy of 66.64% on the RML2016.10A dataset, which is 6% to 18% higher than the current AMC model.

show abstract

“…ECENTY there have been several investigations into whether the mathematical technique of wavelet transforms provides any advantage in the processing of digitally modulated communications signals [1][2][3][4][5]. In these investigations two wavelet-based signal processing strategies have been identified as being especially promising.…”

Section: Introductionmentioning

confidence: 99%

“…The second powerful wavelet-based strategy that has recently been developed is that of blind Automatic Modulation Recognition (AMR) [2][3][4]. It has been found that the waveletbased AMR algorithms developed can provide very high rates of accurate recognition of digital modulation schemes.…”

Section: Introductionmentioning

confidence: 99%

Performance analyses of communications receivers employing wavelet-domain minimum mean-squared error equalizers

Vaz

Daut

2011

2011 5th International Conference on Signal Processing and Communication Systems (ICSPCS)

Self Cite

View full text Add to dashboard Cite

In this paper the strategy of Minimum MeanSquared Error (MMSE) equalization of Discrete Wavelet Transform (DWT) coefficients of received signals is applied in communications receivers. Specifically, the performance of such wavelet-based receivers under a diverse range of conditions is systematically evaluated with the use of Monte Carlo simulations. To determine the robustness of this new type of receiver processing strategy multipath fading channels, four different wavelets, and 16-symbol Quadrature Amplitude Modulation (16-QAM) are used. All faded signals are corrupted with Additive White Gaussian Noise (AWGN). For each case the system performance is quantified by Symbol Error Rates (SERs) obtained from the Monte Carlo simulations. The resulting SER curves show that the performance of DWT-based MMSE equalization is similar to the method implemented in discrete time-domain. Hence, DWT-based MMSE equalization is an effective and practicable technique that can be used in communications receivers. In particular the method can be used in agile radio receivers built upon a wavelet-domain signal processing platform.

show abstract

A wavelet-based method for classification of binary digitally modulated signals

Cited by 16 publications

References 11 publications

Automatic classification of multi-carrier modulation signal using STFT spectrogram and deep CNN

Automatic classification of multi-carrier modulation signal using STFT spectrogram and deep CNN

Robust Automatic Modulation Classification in Low Signal to Noise Ratio

Performance analyses of communications receivers employing wavelet-domain minimum mean-squared error equalizers

Contact Info

Product

Resources

About