Enhancing Underwater Acoustic Signal Classification with CAM++ and Change Point Features
Bibliographic record
Abstract
The effective classification of vessel acoustic signals is critical for marine environment monitoring. In this paper, we introduce two innovations: First, we developed a novel preprocessing method that combines Constant Q Transform (CQT) with a feature extraction technique introduced through dynamic programming, aiming to enhance the representation of signals by identifying statistical characteristics among signal change points. Second, we applied the CAMPPlus model, originally designed for speaker verification, to the classification of vessel acoustic signals, demonstrating its capability to significantly improve classification performance. Utilizing a dataset from Ocean Networks Canada, which contains signals recorded in the Strait of Georgia during the summer and fall of 2017, we classified the acoustic data into five categories: Tug, Passenger Ship, Cargo, Tanker, and Background Noise. A comparative performance analysis of the CAMPPlus model against the traditional ResNETSE model on this dataset revealed that CAMPPlus, combined with our proposed preprocessing and feature extraction techniques, significantly outperforms ResNETSE in terms of classification accuracy. This research not only enhances the accuracy of acoustic signal classification but also successfully transfers a mature deep learning model to a new application scenario. It demonstrates the potential of deep learning in model transfer and provides a new perspective for further research in the field of marine traffic monitoring, adhering to the standards of academic presentation in the process.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".