Learning modulation filter networks for weak signal detection in noise

Zhang, Duona; Ding, Wenrui; Zhang, Baochang; Liu, Chunhui; Han, Jungong; Doermann, David

doi:10.1016/j.patcog.2020.107590

Cited by 14 publications

(7 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The classical AG TDL models include the LOS and up to seven intermittent MPCs. After normalization of the delay on each tap, the CIR of the TDL model can be approximated as follow [30] :…”

Section: Intermittent Multipath Componentsmentioning

confidence: 99%

“…According to the previous work [30] , the neural network structure with two layers MCNN and three layers Bi-LSTM has the relatively optimal performance, while the size of convolution filter can be set as , and the number of original filters can be set as 8 in the MCNNs. For the off-line training process, the training set and test set have 10000 and 1000 samples, respectively.…”

Section: System Settingsmentioning

confidence: 99%

“…where

*

is the element‐wise multiplication operator, also named Schur product operation [ 31 ] . By introducing modulation process, each convolution layer shares the same modulation filter.…”

Section: Modulated Learning Networkmentioning

confidence: 99%

See 2 more Smart Citations

Time‐Varying Channel Estimation Based on Air‐Ground Channel Modelling and Modulated Learning Networks

Liu

WANG²,

DONG³

et al. 2022

Chinese J of Electronics

Self Cite

View full text Add to dashboard Cite

To improve the time-varying channel estimation accuracy of orthogonal frequency division multiplexing air-ground datalink in complex environment, this paper proposes a time-varying air-ground channel estimation algorithm based on the modulated learning networks, termed as MB-ChanEst-TV. The algorithm integrates the modulated convolutional neural networks (MCNN) with the bidirectional long short term memory (Bi-LSTM), where the MCNN subnetworks accomplish channel interpolation in frequency domain and compress the network model while the Bi-LSTM subnetworks achieve channel prediction in time domain. Considering the unique characteristics of airframe shadowing for unmanned aircraft systems, we propose to combine the classical 2-ray channel model with the tapped delay line model and present a more realistic channel impulse response samples generation approach, whose code and dataset have been made publicly available. We demonstrate the effectiveness of our proposed approach on the generated dataset, where experimental results indicate that the MB-ChanEst-TV model outperforms existing state-of-the-art methods with a lower estimation error and better bit error ratio performance under different signal to noise ratio conditions. We also analyze the effect of roll angle of the aircraft and the duration percentage of the airframe shadow on the channel estimation.

show abstract

“…The classical AG TDL models include the LOS and up to seven intermittent MPCs. After normalization of the delay on each tap, the CIR of the TDL model can be approximated as follow [30] :…”

Section: Intermittent Multipath Componentsmentioning

confidence: 99%

Section: System Settingsmentioning

confidence: 99%

See 1 more Smart Citation

Time‐Varying Channel Estimation Based on Air‐Ground Channel Modelling and Modulated Learning Networks

Liu

WANG²,

DONG³

et al. 2022

Chinese J of Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Weak signal detection and parameter estimation methods in complex noise environments have been widely used in other fields, such as scientific research [8,9], bioscience [10], chemistry [11], and so on. To extract enough useful information from the low signal-tonoise ratio (SNR) signals, researchers proposed a variety of detection methods from the aspect of linear theory, such as time-frequency analysis and adaptive filters [12], to the aspect of nonlinear theory, such as the chaos system [13], stochastic resonance [14], and machine learning methods [15].…”

Section: Introductionmentioning

confidence: 99%

A Software Digital Lock-In Amplifier Method with Automatic Frequency Estimation for Low SNR Multi-Frequency Signal

et al. 2022

View full text Add to dashboard Cite

In the fault diagnosis field, the fault feature signal is weak and contaminated by the noise. The lock-in amplifier is a useful tool for weak signal detection. Aiming to the amplitude error of the lock-in amplifier caused by frequency deviation between the measured signal and the reference signal, a DFT-based automatic signal frequency estimation method is studied to improve the frequency accuracy of the reference signal. Based on this frequency estimation method, a software digital lock-in amplifier method is proposed to detect the multiple frequencies signals. This proposed method can automatically measure the frequency value of the measured signal without prior frequency information. Then, the reference signals are generated through this frequency value to make the digital lock-in amplifier estimate the amplitude of the measured signal. Moreover, an iterative structure is used to implement the multiple frequencies signal measurement. The frequencies and amplitudes measurement accuracies are tested. Under different SNR conditions, the frequency relative error is less than 0.1%. In addition, the amplitude relative error with different signal frequencies is less than 1.7% when the SNR is −1 dB. This proposed software digital lock-in amplifier method has a higher signal frequency tracking ability and amplitude measurement accuracy.

show abstract

“…Besides, the detection performance deteriorates sharply or even fails in a low SNR environment. In time-frequency analysis methods, Hilbert-Huang transform [10], Empirical mode decomposition(EMD) [11], learning modulation filter network (LMFN) [12],and Convolutional Neural Network [13,14] are introduced to preprocess transient signals. However, in essence, the transient energy is used as the measurement, which increases the amount of calculation in the process of signal extraction, and its applicability is poor.…”

Section: Introductionmentioning

confidence: 99%

Transient Electromagnetic Weak Signal Extraction Method Based on Multi-Scale Combined Difference Product Morphological Filtering

et al. 2022

View full text Add to dashboard Cite

To solve the problem of poor recognition effect of transient signal in low Signal-to-Noise ratio(SNR) and strong interference electromagnetic environment, a morphological filtering method based on the multi-scale combined difference product (MCDPMF) was proposed. This paper concentrates on the issues of sudden changes in transient electronic signal, such as impulses and edges. Firstly, it provides a difference product morphological filter. Moreover, the extended and multi-origin morphological Structural Elements (SEs) is constructed, combining with the multi-structural layers a (a indicates the structural layers of the MCDPMF), the transient electromagnetic weak signal is multi-scale filtered. They are used to optimize the number of the structure layers a adaptively based on the amplitude characteristic ratio of the positive and negative polarity of the filtered signal(HML value), combining the kurtosis-SNR(k x − SN R) ratio characteristic coefficient. MCDPMF is proposed to enhance the filtering results and suppress the noise frequency points. Meanwhile, it can extract the structure components and identify the features of the transient electromagnetic weak signal. It can be shown from simulation and experimental results that the proposed method is superior to EMD, AVG, OCCO, and other methods in subjective evaluation and objective indicators.

show abstract

Learning modulation filter networks for weak signal detection in noise

Cited by 14 publications

References 23 publications

Time‐Varying Channel Estimation Based on Air‐Ground Channel Modelling and Modulated Learning Networks

Time‐Varying Channel Estimation Based on Air‐Ground Channel Modelling and Modulated Learning Networks

A Software Digital Lock-In Amplifier Method with Automatic Frequency Estimation for Low SNR Multi-Frequency Signal

Transient Electromagnetic Weak Signal Extraction Method Based on Multi-Scale Combined Difference Product Morphological Filtering

Contact Info

Product

Resources

About