Scholarlink

In this section, a hybrid combinatorial deep learning model combining both ConvLSTM with Transformer-block neural networks is proposed. Our proposed modulation classifier architecture can learn the signal for both low and high SNR and get better accuracy for signals with high noise. For learning persistent features from a time series data, Recurrent Neural Networks (RNN) are utilized. However, these models using RNNs suffer from much slower training time. LSTM efficient in learning long-term dependencies is a special type of RNN. ConvLSTM Convolutional Long Short-term is a special type of RNN which integrates both CNN with LSTM. ConvLSTM is a modification and extended version of LSTM as shown in Fig. 3.1.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Radio Modulation Classification Optimization Using Combinatorial Deep Learning Technique

  • 章节

  • 发表日期：

    2025年

查看全文
  • Ziad El-Khatib,
  • Sherif Moussa

摘要

In this section, a hybrid combinatorial deep learning model combining both ConvLSTM with Transformer-block neural networks is proposed. Our proposed modulation classifier architecture can learn the signal for both low and high SNR and get better accuracy for signals with high noise. For learning persistent features from a time series data, Recurrent Neural Networks (RNN) are utilized. However, these models using RNNs suffer from much slower training time. LSTM efficient in learning long-term dependencies is a special type of RNN. ConvLSTM Convolutional Long Short-term is a special type of RNN which integrates both CNN with LSTM. ConvLSTM is a modification and extended version of LSTM as shown in Fig. 3.1.