A Novel Automatic Modulation Classification Method Using Attention Mechanism and Hybrid Parallel Neural Network

Zhang, Rui; Yin, Zhendong; Wu, Zhilu; Zhou, Siyang

doi:10.3390/app11031327

Cited by 24 publications

(8 citation statements)

References 48 publications

(57 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e existence of the activation function enables the neural network to have the ability to model nonlinear expressions. Activation function is the key to deep learning to obtain strong learning ability [15].…”

Section: Activation and Loss Functions In Neural Networkmentioning

confidence: 99%

Automatic Scoring Model of Japanese Interpretation Based on Semantic Scoring

Wang

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

In order to improve the current level of Japanese teaching and the difficulty of non-standard Japanese spoken language, the author proposes a method for the study of the automatic scoring model of Japanese ants for scoring. The author introduces a semantic scoring model that integrates the long short-term memory neural network and self-attention mechanism, which can be applied to keyword scoring and sentence semantic scoring. The scoring principle of the model is as follows: firstly, extract the word and sentence features and represent them in a vectorized form, then use a bidirectional long short-term memory neural network to optimize the feature vector, and then use the self-attention mechanism to obtain the semantic features of the word or sentence. Finally, the semantic score is calculated by a simple neural network. Experiments show that compared with the semantic scoring model based on a stretchable recursive autoencoder that performs better in semantic scoring, the average correlation between this model and the original score is 0.444; the lowest rate of agreement with the original score is 95%; and the highest rate of agreement with adjacent ones is 74%. The automatic scoring model for Japanese interpreting with semantic scoring is proved to be practical and has excellent results.

show abstract

Section: Activation and Loss Functions In Neural Networkmentioning

confidence: 99%

Automatic Scoring Model of Japanese Interpretation Based on Semantic Scoring

Wang

2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

show abstract

“…Attention mechanisms are crucial in deep learning models [27], and they make the models more effectively focus on input data representing complete characteristic information [28]. We utilize the SE attention mechanism [29], which adaptively adjusts channel weights, to enhance the model's focus on key features in this paper.…”

Section: Attention Mechanismsmentioning

confidence: 99%

Dual-path multi-scale attention residual network for fault diagnosis of rolling bearings under complex operating conditions

Deng,

Zhang,

Zhao

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Rolling bearing faults inevitably occur during the long-term continuous operation of rotating machinery. Therefore, fault diagnosis is greatly important for ensuring the normal and safe operation of rolling bearings. However, the complexity and diversity of working conditions of rolling bearings present a significant challenge in extracting fault characteristics accurately, which further affects the ultimate fault diagnosis results. In this article, we propose a new model, called dual-path multi-scale attention residual network (DPMARN), for diagnosing bearing faults under complex operating conditions. DPMARN can effectively capture the feature-feature correlation information at different scales, which is more beneficial for fusing fault features at different scales to improve the model’s performance. The main contributions of this work are summarized as follows: (1) The designed dual-path network model which incorporates parallel multi-scale branches of convolutional kernels and serially connects skip-layer multi-scale branches can integrate both low-frequency and high-frequency information and enhance the multi-scale feature extraction and complex data representation abilities. (2) The SE attention mechanism is embedded into the residual blocks to improve the ability of learning feature correlations and utilizing feature information effectively, which is helpful for extracting important fault characteristics. Extensive experiments conducted on two public bearing datasets demonstrate the superior performance of the DPMARN model for addressing the complex fault diagnosis problem. These results indicate that our proposed approach provides an effective solution for fault diagnosis of rolling bearings under complex operating conditions.

show abstract

“…The AMC literature is largely divided into two techniques: likelihood-based classification (LBC) and feature-based classification (FBC). The existing work on the likelihood-based AMC can be found in [18][19][20][21][22][23] and feature-based AMC in [24][25][26][27][28][29][30].…”

Section: Related Workmentioning

confidence: 99%

Random Graph-Based M-QAM Classification for MIMO Systems

Sarfraz

Alam

Ghauri

et al. 2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Automatic modulation classification (AMC) has been identified to perform a key role to realize technologies such as cognitive radio, dynamic spectrum management, and interference identification that are arguably pivotal to practical SG communication networks. Random graphs (RGs) have been used to better understand graph behavior and to tackle combinatorial challenges in general. In this research article, a novel modulation classifier is presented to recognize M-Quadrature Amplitude Modulation (QAM) signals using random graph theory. The proposed method demonstrates improved recognition rates for multiple-input multiple-output (MIMO) and single-input single-output (SISO) systems. The proposed method has the advantage of not requiring channel/signal to noise ratio estimate or timing/frequency offset correction. Undirected RGs are constructed based on features, which are extracted by taking sparse Fourier transform (SFT) of the received signal. This method is based on the graph representation of the SFT of the 2nd, 4th, and 8th power of the received signal. The simulation results are also compared to existing state-of-the-art methodologies, revealing that the suggested methodology is superior.

show abstract

A Novel Automatic Modulation Classification Method Using Attention Mechanism and Hybrid Parallel Neural Network

Cited by 24 publications

References 48 publications

Automatic Scoring Model of Japanese Interpretation Based on Semantic Scoring

Automatic Scoring Model of Japanese Interpretation Based on Semantic Scoring

Dual-path multi-scale attention residual network for fault diagnosis of rolling bearings under complex operating conditions

Random Graph-Based M-QAM Classification for MIMO Systems

Contact Info

Product

Resources

About