Modulation Recognition Method for Underwater Acoustic Communication Signal Based on Relation Network under Small Sample Set

Deep learning (DL)-based modulation recognition methods of underwater acoustic communication signals are mostly applied to a single hydrophone reception scenario. In this paper, we propose a novel end-to-end multihydrophone fusion network (MHFNet) for multisensory reception scenarios. MHFNet consists of a feature extraction module and a fusion module. The feature extraction module extracts the features of the signals received by the multiple hydrophones. Then, through the neural network, the fusion module fuses and classifies the features of the multiple signals. MHFNet takes full advantage of neural networks and multihydrophone reception to effectively fuse signal features for realizing improved modulation recognition performance. Experimental results on simulation and practical data show that MHFNet is superior to other fusion methods. The classification accuracy is improved by about 16%.

Modulation recognition of non-cooperation underwater acoustic communication signals using principal component analysis

Objective. Intracortical brain–machine interfaces (iBMIs) aim to restore efficient communication and movement ability for paralyzed patients. However, frequent recalibration is required for consistency and reliability, and every recalibration will require relatively large most current sample set. The aim in this study is to develop an effective decoder calibration method that can achieve good performance while minimizing recalibration time. Approach. Two rhesus macaques implanted with intracortical microelectrode arrays were trained separately on movement and sensory paradigm. Neural signals were recorded to decode reaching positions or grasping postures. A novel principal component analysis-based domain adaptation (PDA) method was proposed to recalibrate the decoder with only ultra small current sample set by taking advantage of large historical data, and the decoding performance was compared with other three calibration methods for evaluation. Main results. The PDA method closed the gap between historical and current data effectively, and made it possible to take advantage of large historical data for decoder recalibration in current data decoding. Using only ultra small current sample set (five trials of each category), the decoder calibrated using the PDA method could achieve much better and more robust performance in all sessions than using other three calibration methods in both monkeys. Significance. (1) By this study, transfer learning theory was brought into iBMIs decoder calibration for the first time. (2) Different from most transfer learning studies, the target data in this study were ultra small sample set and were transferred to the source data. (3) By taking advantage of historical data, the PDA method was demonstrated to be effective in reducing recalibration time for both movement paradigm and sensory paradigm, indicating a viable generalization. By reducing the demand for large current training data, this new method may facilitate the application of intracortical brain–machine interfaces in clinical practice.

In the realm of communication reconnaissance, the accuracy of modulation recognition is of paramount importance. The modulation recognition task mainly encompasses two key aspects: the dataset and the network model. To enhance the recognition rate across diverse signal-to-noise ratio (SNR) conditions, this paper initiates from the current mainstream modulation recognition methods. It endeavors to identify a methodology capable of achieving a higher recognition rate in both low SNR and high SNR scenarios. Feature extraction in the transform domain of the dataset can, to a certain extent, improve the modulation recognition accuracy. However, it significantly prolongs the algorithm's running time. Consequently, from the dataset perspective, this study incorporates data augmentation techniques and amplitude-phase features to enhance the modulation recognition performance. Regarding the network model design, the baseline modulation recognition model is first replicated multiple times. Through numerous comparisons across different datasets, the features among various models are identified. Concentrating on the high-recognition-rate models, the design is ultimately optimized based on the characteristics of two specific models, taking into account different SNRs, datasets, and the number of network layers. This results in the formation of a novel dual-spliced deep-learning modulation recognition model. Deployed separately in the - 20-0 dB and 0-20 dB intervals, the model was tested on six datasets and achieved remarkable results. Simulation results show that the proposed method outperforms the other 11 types of modulation recognition methods in terms of modulation recognition rates on six major datasets. Moreover, it can address the recognition confusion between AM-DSB and AM-SSB, as well as between 16QAM and 64QAM to a certain extent.

With the successful application of deep learning in communications systems, deep neural networks are becoming the preferred method for Automatic Modulation Recognition (AMR). Although these AMR models yield impressive results, they often come with high computational complexity and large model sizes, which hinders their practical deployment in communication systems. To address this challenge, we propose a novel layer pruning method, PSR. Specifically, we decompose the AMR model into several consecutive blocks, each containing consecutive layers with similar semantics. Then, we identify layers that need to be preserved within each block based on their contribution. Finally, we reassemble the pruned blocks and fine-tune the compact model. Extensive experiments on five datasets demonstrate the efficiency and effectiveness of PSR over a variety of state-of-the-art baselines, including layer pruning and channel pruning methods.

The difficulty of feature extraction and the small sample size are two challenges in the field of mechanical fault diagnosis for a long time. Here we propose an intelligent mechanical fault diagnosis method for scenario with small sample datasets. This method can not only diagnose bearing faults but also gear faults, and has strong generalization performance. We use convolutional neural network to realize automatic feature extraction. Through sliding window scanning, one sample set is expanded to three sub-sample sets with different scales to meet the needs of deep learning training. Three convolutional networks are used to extract the features of the subsets respectively to ensure that their useful features are fully extracted. After feature extraction, the feature is reconstructed through feature splicing. Because of the unique advantages of SVM in dealing with small sample sets, we use SVM to classify the reconstructed features. We use the bearing data set collected by Case Western Reserve University in the United States, the bearing fault data set collected by Xi'an Jiaotong University in China, and the gearbox fault data collected by the University of Connecticut in the United States to conduct experiments. The experimental results show that the accuracy of training, validation and testing of the proposed method on the three data sets all reach 100%. This proves that our method can not only tackle the two challenges, but also has high fault diagnosis accuracy and strong generalization performance. It is hoped that our proposed method can contribute to the development of mechanical fault diagnosis.

ABSTRACTModulation recognition in underwater acoustic (UWA) signals is challenging due to the intricate marine environment and substantial underwater noise. Wavelet‐based denoising lacks adaptivity and can be affected by the wavelet function, the number of decomposition layers, and the threshold function. Although the denoising method based on deep learning has achieved a good denoising effect, it fails to integrate with the physical model and lacks certain theoretical support. To address these problems, this paper proposes a deep fusion network for signal denoising, named WDNet, based on wavelet denoising theory and deep learning techniques. We initialize the tap coefficients of the wavelet decomposition and reconstruction filters as learnable parameter matrices and use the soft threshold function as the activation function so as to realize the decomposition, thresholding, and reconstruction of the signal. The filter and threshold are adjusted adaptively by backpropagation to achieve optimal signal denoising. Simulation results demonstrate that our model achieves a higher signal‐to‐noise ratio (SNR) gain and lower root mean square error (RMSE) compared to other methods. After denoising, the recognition rate of UWA modulation signals significantly improves.

Modulation recognition accuracy is crucial in communication reconnaissance. In this study, we propose DiDbKDT, a dual-input dual-branch network architecture for cross-SNR modulation recognition. The model leverages knowledge distillation and integrates IQ-AP data as inputs. Considering the differences in data features under different SNR scenarios and combining the respective features of IQ and AP data, we divide the SNR interval into two segments and use the IQ and AP data as the inputs of the low-SNR and high-SNR networks respectively. To balance the computational complexity and recognition rate, in the DiDbKDT network model, we utilize the knowledge distillation technique. We deploy the Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) in the low-SNR and high-SNR scenarios respectively as teacher models to quickly learn the internal modulation features of IQ and AP data. In the student model, we adopt the Transformer to further mine the global features of the data and the correlation relationships between different features, thus achieving more accurate modulation recognition and classification. We also introduce a data augmentation technique based on the channelization scenario to further improve the robustness of the model. Experimental results on six types of datasets, namely RML2016.10a/b/c, RML2018.01a, HisarMod, and MiGouMod, demonstrate that the proposed DiDbKDT outperforms the existing Automatic Modulation Recognition (AMR) methods and has higher parameter efficiency.

The development of targeted assays that monitor biomedically relevant proteins is an important step in bridging discovery experiments to large scale clinical studies. Targeted assays are currently unable to scale to hundreds or thousands of targets. We demonstrate the generation of large-scale assays using a novel hybrid nominal mass instrument. The scale of these assays is achievable with the Stellar mass spectrometer through the accommodation of shifting retention times by real-time alignment, while being sensitive and fast enough to handle many concurrent targets. Assays were constructed using precursor information from gas-phase fractionation data-independent acquisition (DIA). We demonstrate the ability to schedule methods from orbitrap and linear ion trap acquired gas-phase fractionation DIA library, and compare the quantification of a matrix-matched calibration curve from orbitrap DIA and linear ion trap parallel reaction monitoring (PRM). Two applications of these proposed workflows are shown with a cerebrospinal fluid neurodegenerative disease protein PRM assay and with a Mag-Net enriched plasma extracellular vesicle protein survey PRM assay. In cerebrospinal fluid, our assay targets proteins discovered previously to be associated with Alzheimer's disease in a small independent sample set. For the Mag-Net enriched plasma survey assay, we observe that proteins selected based on their measurement robustness are still able to capture differences in abundance across disease groups in a small sample set. These highlight the application of highly multiplex, targeted protein assays in clinical research.

The Automatic Modulation Classification (AMC) of the underwater acoustic communication signals is still difficult via traditional methods in the case of poor underwater acoustic channels condition and impulse noise. In this paper, we propose a novel deep neural network model for AMC of underwater acoustic communication combining the convolutional neural network (CNN) and the long short-term memory network (LSTM). The CNN learns from time domain IQ data and LSTM learns from amplitude and phase. Multipath fading underwater acoustic channels with alpha-stable impulse noise and doppler frequency shift are modeled for signal dataset generation based on the real marine environment data. Experimental results validate this approach has a high recognition rate with the burst low SNR signal and has a performance stability under the Alpha-stable impulse noise, which is better compared to other existing schemes.

While human hearing can easily identify whistle-like sounds made by dolphins and whales, manually identifying them from the increasingly variety and quantity of underwater acoustic signals (such as other marine life sounds and underwater acoustic communication signals) is undoubtedly laborious. To solve this question, a recognition method based on the frequency modulated feature and harmonic characteristic is analyzed in this paper. A harmonic energy analysis algorithm is proposed and is compared to a harmonic detection method. The experimental results prove that the proposed method could identify the whistle-like sounds with an accuracy over 90% and the traditional one could only reach 50%. The recognition method may be applied to the investigation of marine biological habits and the monitoring of marine ecological environment, and can also potentially be further applied to the detection of bionic communication signal.

The difficulties of obtaining sufficient labeled samples have always been one of the factors hindering deep learning models from obtaining high accuracy in hyperspectral image (HSI) classification. To reduce the dependence of deep learning models on training samples, meta learning methods have been introduced, effectively improving the classification accuracy in small sample set scenarios. However, the existing methods based on meta learning still need to construct a labeled source data set with several pre-collected HSIs, and must utilize a large number of labeled samples for meta-training, which is actually time-consuming and labor-intensive. To solve this problem, this paper proposes a novel unsupervised meta learning method with multiview constraints for HSI small sample set classification. Specifically, the proposed method first builds an unlabeled source data set using unlabeled HSIs. Then, multiple spatial-spectral multiview features of each unlabeled sample are generated to construct tasks for unsupervised meta learning. Finally, the designed residual relation network is used for meta-training and small sample set classification based on the voting strategy. Compared with existing supervised meta learning methods for HSI classification, our method can only utilize HSIs without any label for unsupervised meta learning, which significantly reduces the number of requisite labeled samples in the whole classification process. To verify the effectiveness of the proposed method, extensive experiments are carried out on 8 public HSIs in the cross-domain and in-domain classification scenarios. The statistical results demonstrate that, compared with existing supervised meta learning methods and other advanced classification models, the proposed method can achieve competitive or better classification performance in small sample set scenarios.

Digital modulation recognition is an important part of signal processing. With inherent anti-noise performance, High-Order Cumulants have natural advantage in recognizing digital modulation pattern, and is widely studied in the past several decades. On the basis of high-order cumulants, combined with peak feature of FFT spectrum and instantaneous signal feature, this paper proposed a new method for digital modulation recognition based on mixed signal features, which took advantage of classical decision-tree classifier. Simulation results showed that the method proposed in this paper can recognize six classical digital modulation pattern efficiently, and achieved satisfactory recognition result even at rather low SNR.

In signal communication based on a non-cooperative communication system, the receiver is an unlicensed third-party communication terminal, and the modulation parameters of the transmitter signal cannot be predicted in advance. After the RF signal passes through the RF band-pass filter, low noise amplifier, and image rejection filter, the intermediate frequency signal is obtained by down-conversion, and then the IQ signal is obtained in the baseband by using the intermediate frequency band-pass filter and down-conversion. In this process, noise and signal frequency offset are inevitably introduced. As the basis of subsequent analysis and interpretation, modulation recognition has important research value in this environment. The introduction of deep learning also brings new feature mining tools. Based on this, this paper proposes a signal modulation recognition method based on multi-feature fusion and constructs a deep learning network with a double-branch structure to extract the features of IQ signal and multi-channel constellation, respectively. It is found that through the complementary characteristics of different forms of signals, a more complete signal feature representation can be constructed. At the same time, it can better alleviate the influence of noise and frequency offset on recognition performance, and effectively improve the classification accuracy of modulation recognition.

Deep learning has significantly advanced automatic modulation recognition (AMR), yet existing deep learning-based AMR methods struggle to adapt to the rapid evolution of 6G and beyond. A key challenge is their inability to incrementally integrate new modulation types without catastrophic forgetting of previously learned ones. Additionally, the annotation of wireless signals remains difficult, further limiting adaptability. To address these challenges, we introduce few-shot class-incremental learning for AMR (FSCIL-AMR) and propose the orthogonal pseudo-prototype and pseudo-target (O3PT) method. O3PT generates orthogonal pseudo-prototypes to replace ambiguous class prototypes caused by high signal feature similarity, thereby mitigating classification confusion when computing cosine similarities between features and prototypes. It also implicitly preserves feature space for future modulation types and reformulates complex prototype constraints into a more manageable alignment task. Furthermore, O3PT exploits inter-class feature similarities to generate pseudo-targets and utilizes supervised contrastive learning to impose adaptive constraints, enhancing inter-class separability while mitigating overfitting caused by limited incremental training signals. By training a lightweight projector, O3PT enables efficient network expansion as new modulation types emerge. Extensive experiments on the RML2018.01A and RML2016.10A datasets validate its effectiveness.