A hybrid model for automatic modulation classification based on residual neural networks and long short term memory

Elsagheer, M.; Ramzy, Safwat M.

doi:10.1016/j.aej.2022.08.019

Cited by 21 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy performance of the proposed deep learning model per various modulation type versus SNR from 0 dB to 20 dB is shown in Table 10. SCRNN [45] ResNet [54] Transformerblock + ConvLSTM (this work) As can be seen in Fig. 38, X. Hao [18] used CLDNN+GRU model achieving accuracy of 90% at 0 dB SNR and less than 20% at -16 dB SNR.…”

Section: Classification Performance Simulation Resultsmentioning

confidence: 90%

Radio Modulation Classification Optimization Using Combinatorial Deep Learning Technique

Elkhatib,

Kamalov,

Moussa

et al. 2024

IEEE Access

View full text Add to dashboard Cite

We present an automatic signal modulation classification model using combinatorial deep learning technique. Our proposed deep learning model increase accuracy for low Signal-to-Noise Ratio (SNR) and maintain a high classification accuracy for high SNR signals. Using a hybrid deep learning model combining both ConvLSTM with Transformer-block neural networks, the proposed modulation classifier architecture can learn the signal for both low and high SNR and get better accuracy for signals with high noise. The proposed deep learning modulation classification technique achieves improved classification accuracy of 66% for low SNR signals and 93.5% at high SNR showing that our model is robust under noisy signal modulation. Thus, getting better accuracy in lower SNR signals without sacrifice accuracy for higher SNR signals. An adaptive weighted focal loss function is proposed as an optimized loss function for efficient classification which can be used to control the outliers within a class imbalance and avoid underflow issues. Our deep learning radio modulation classification model works using raw signal without the need of denoising the noisy signal. INDEX TERMS Automatic modulation classification, dynamic spectrum allocation, deep learning techniques, transformer-block convLSTM, feature-based extraction, AI-based wireless communications.

show abstract

Section: Classification Performance Simulation Resultsmentioning

confidence: 90%

Radio Modulation Classification Optimization Using Combinatorial Deep Learning Technique

Elkhatib,

Kamalov,

Moussa

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…First, we compare our method with three different state-of-the-art models of deep neural networks as examples. The models we examine are ResNet [ 21 ], DenseNet [ 22 ], LSTM [ 10 ], FLANs [ 8 ] and VGG [ 23 ]. We aim to compare our model to the neural networks in two manners.…”

Section: Simulation and Resultsmentioning

confidence: 99%

“…These packets serve as inputs to our classification algorithm. For each packet received, we use the set of Equations ( 5) through (10) to extract the features vector of the cumulants. This feature extraction process is computationally straightforward, involving a singular pass through the packet data, which aligns with the predetermined packet length of the communication network's settings.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Cumulant-Based Automatic Modulation Classification Using Machine Learning

Dgani,

Cohen

2024

Sensors

View full text Add to dashboard Cite

This paper introduces a new technique for automatic modulation classification (AMC) in Cognitive Radio (CR) networks. The method employs a straightforward classifier that utilizes high-order cumulant for training. It focuses on the statistical behavior of both analog modulation and digital schemes, which have received limited attention in previous works. The simulation results show that the proposed method performs well with different signal-to-noise ratios (SNRs) and channel conditions. The classifier’s performance is superior to that of complex deep learning methods, making it suitable for deployment in CR networks’ end units, especially in military and emergency service applications. The proposed method offers a cost-effective and high-quality solution for AMC that meets the strict demands of these critical applications.

show abstract

“…Reference [2] proposes a hybrid deep learning framework that integrates 1D convolution, 2D convolution, and LSTM layers, which achieves promising performance. Reference [3] proposes an automatic modulation classification model that combines the residual neural network (ResNet) and the long short-term memory network (LSTM), achieving 92% classification accuracy on the RML2016B dataset at 18 dB SNR. Reference [4] presents a multi-scale network for AMR and proposes a new loss function combining the center loss and cross entropy loss.…”

Section: Introductionmentioning

confidence: 99%

Data-Transform Multi-Channel Hybrid Deep Learning for Automatic Modulation Recognition

Qi,

Shi,

Wang

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Automatic modulation recognition (AMR) is an essential topic of cognitive radio, which is of great significance for the analysis of wireless signals and is one of the current research hotspots. Traditional AMR approaches predominantly utilize raw in-phase/quadrature symbols (I/Q), amplitude/phase (A/P), or pre-processed data (e.g., high-order cumulates, spectrum images, or constellation diagrams) as inputs for the recognition model. However, it is difficult to achieve superior performance with only a single type of data as input. This paper proposes a novel multi-channel hybrid learning framework that integrates convolutional layers, Long Short-Term Memory (LSTM) layers, fully connected layers and classification layers. The model is built for modeling spatial-temporal correlations from four signal cues (including I/Q signals, A/P signals, I, and Q signals), which aims to explore various differences and leverage the complements from multiple data-form. Two functions employed during the data conversion process further enhance the non-linear representational capacity of the model, thereby boosting the recognition accuracy of the model. Experimental results demonstrate that the proposed framework effectively addresses the classification challenges of QAM16 and QAM64. For the RAML2016A dataset, our model achieves an impressive recognition accuracy of 95% at an SNR of 0 dB. Extensive experiments indicate that the proposed framework outperforms other current networks in terms of recognition accuracy.

show abstract

A hybrid model for automatic modulation classification based on residual neural networks and long short term memory

Cited by 21 publications

References 23 publications

Radio Modulation Classification Optimization Using Combinatorial Deep Learning Technique

Radio Modulation Classification Optimization Using Combinatorial Deep Learning Technique

Efficient Cumulant-Based Automatic Modulation Classification Using Machine Learning

Data-Transform Multi-Channel Hybrid Deep Learning for Automatic Modulation Recognition

Contact Info

Product

Resources

About