Real-Time Radio Modulation Classification With An LSTM Auto-Encoder

Ke, Ziqi; Vikalo, Haris

doi:10.1109/icassp39728.2021.9414351

Cited by 14 publications

(12 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second pipeline connects the encoder with a decoder which minimizes the reconstruction error of source and target data in an unsupervised fashion. A Long-Short Term Memory (LSTM)-based DRCN for AMC is given in [34], while a Convolutional Neural Network (CNN)-based DRCN for AMC is given in [35,36]. Each of unsupervised DA methods relies on the availability of a large amount of class-balanced data what is tough to guarantee in practice.…”

Section: B Unsupervised Damentioning

confidence: 99%

Channel and Hardware Impairment Data Augmentation for Robust Modulation Classification

Perenda,

Bovet,

Zheleva

et al. 2024

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

Deep learning has achieved remarkable results in modulation classification under two assumptions: a large amount of labeled class-balanced data is available, and test data shares the same distribution as data used for training. However, due to dynamic wireless fading channels and hardware imperfections, it is implausible that these assumptions hold in practice. This paper proposes Model-based Data Augmentation for Deep learningbased Modulation Classification (MDA-DMC) to build a highquality dataset from a small amount of labeled seed data. We develop two novel augmentation methods to combat channel and hardware impairments, along with two widely used augmentation methods, adding Gaussian noise and rotation. We are the first to investigate the relationship between augmentation methods and impairments due to channel and hardware imperfections. We show that MDA-DMC can successfully combat the hardware imperfections for the same channel model as the channel model of seed data. Furthermore, with a few AWGN seed data, MDA-DMC achieves an accuracy gain of up to 17.20% in fading channels. By adding a few fading seed data, MDA-DMC improves accuracy by an additional 10.78% in fading channels.

show abstract

Section: B Unsupervised Damentioning

confidence: 99%

Channel and Hardware Impairment Data Augmentation for Robust Modulation Classification

Perenda,

Bovet,

Zheleva

et al. 2024

IEEE Trans. Cogn. Commun. Netw.

View full text Add to dashboard Cite

show abstract

“…Performance comparison between meta-learning (our proposed method, DAELSTM [20] and ProtoNet [18]) and supervised learning (ResNet [5] and CNN [10]) models for all 24 modulations.…”

Section: Comparing Meta-learning and Supervised Learning Figurementioning

confidence: 99%

Meta-Transformer: A Meta-Learning Framework for Scalable Automatic Modulation Classification

Jang,

Pyo,

Yoon

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Recent advances in deep learning (DL) have led many contemporary automatic modulation classification (AMC) techniques to use deep networks in classifying the modulation type of incoming signals at the receiver. However, current DL-based methods face scalability challenges, particularly when encountering unseen modulations or input signals from environments not present during model training,making them less suitable for real-world applications like software-defined radio devices. In this paper, we introduce a scalable AMC scheme that provides flexibility for new modulations and adaptability to input signals with diverse configurations. We propose the Meta-Transformer, a meta-learning framework based on few-shot learning (FSL) to acquire general knowledge and a learning method for AMC tasks. This approach empowers the model to identify new unseen modulations using just a very small number of samples, eliminating the need for a complete model retraining. Furthermore, we enhance the scalability of the classifier by leveraging main-sub transformer-based encoders, enabling efficient processing of input signals with diverse setups. Extensive evaluations demonstrate that the proposed AMC method outperforms existing techniques across all signal-to-noise ratios (SNRs) on RadioML2018.01A.

show abstract

“…One limitation of the JED method is that it currently only works for classification and detection problems. For a time-series prediction problem like the one defined in [38] or an autoencoder used for classification like those seen in [5,39] alternative decision criteria would need to be developed. Figure 10.…”

Section: "Just Enough" Decision Makingmentioning

confidence: 99%

“…In time-sensitive applications like electronic warfare, radar, and dynamic-spectrum access (DSA), decisions need to be made as quickly and accurately as possible. To allow for faster processing, many researchers have focused on reducing network complexity [5][6][7]. However, these approaches result in processing every signal for the same amount of time-regardless of signal complexity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Decoupling RNN Training and Testing Observation Intervals for Spectrum Sensing Applications

Moore

Buehrer

Headley

2022

Sensors

View full text Add to dashboard Cite

Recurrent neural networks have been shown to outperform other architectures when processing temporally correlated data, such as from wireless communication signals. However, compared to other architectures, such as convolutional neural networks, recurrent neural networks can suffer from drastically longer training and evaluation times due to their inherent sample-by-sample data processing, while traditional usage of both of these architectures assumes a fixed observation interval during both training and testing, the sample-by-sample processing capabilities of recurrent neural networks opens the door for alternative approaches. Rather than assuming that the testing and observation intervals are equivalent, the observation intervals can be “decoupled” or set independently. This can potentially reduce training times and will allow for trained networks to be adapted to different applications without retraining. This work illustrates the benefits and considerations needed when “decoupling” these observation intervals for spectrum sensing applications, using modulation classification as the example use case. The sample-by-sample processing of RNNs also allows for the relaxation of the typical requirement of a fixed time duration of the signals of interest. Allowing for variable observation intervals is important in real-time applications like cognitive radio where decisions need to be made as quickly and accurately as possible as well as in applications like electronic warfare in which the sequence length of the signal of interest may be unknown. This work examines a real-time post-processing method called “just enough” decision making that allows for variable observation intervals. In particular, this work shows that, intuitively, this method can be leveraged to process less data (i.e., shorter observation intervals) for simpler inputs (less complicated signal types or channel conditions). Less intuitively, this works shows that the “decoupling” is dependent on appropriate training to avoid bias and ensure generalization.

show abstract

Real-Time Radio Modulation Classification With An LSTM Auto-Encoder

Cited by 14 publications

References 19 publications

Channel and Hardware Impairment Data Augmentation for Robust Modulation Classification

Channel and Hardware Impairment Data Augmentation for Robust Modulation Classification

Meta-Transformer: A Meta-Learning Framework for Scalable Automatic Modulation Classification

Decoupling RNN Training and Testing Observation Intervals for Spectrum Sensing Applications

Contact Info

Product

Resources

About