Automatic Modulation Recognition of Underwater Acoustic Signals Using a Two-Stream Transformer
Bibliographic record
Abstract
Automatic modulation recognition (AMR) of underwater acoustic (UWA) signals is incredibly challenging due to the complexity of UWA channels and the severity of ocean noise. In the presence of noise interference, single-modal features fail to fully represent the characteristics of different modulated signals. While the in-phase/quadrature (I/Q) and time-frequency maps can adequately represent the signal features in the time, frequency, and time-frequency domains, the direct integration of the two modalities is ineffective because of the variations in shape, information granularity, and noise manifestation. To address the low recognition rate caused by the above issues, we propose a two-stream transformer (TSTR) based network for AMR of UWA signals. First, the input pre-processing layer obtains the I/Q and time-frequency features from the received signals. Then, the feature capture layer extracts high-dimensional signal features in the time, frequency, and time-frequency domains. Finally, the classification layer estimates the modulation of the signals. A multi-head self-attention module with adaptive soft thresholding is used in the feature capture layer to provide noise reduction and redundant feature rejection while retaining context information. Moreover, multi-scale ghost convolution is employed to address the inability of the transformer to efficiently extract spatial characteristics from the signals. Results are presented using real UWA channels from the Watermark dataset for two different seas which show that the TSTR improves recognition by 1.2% and 5.9% over the best existing model. Further, it has better generalization capabilities and the model has a small number of parameters so the time complexity is low.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".