Reconstruction and fusion of perceptual features for automatic classification of sonar echoes
Bibliographic record
Abstract
The long detection ranges provided by low-frequency active sources present many advantages to localize and track underwater threats from safe distances. However, in littoral environments, echoes from naturally occurring features cause false alarms which degrade the overall system performance. The use of perceptual features derived from those used in the human auditory system (aural features), has been shown to allow discrimination between target and clutter echoes for both impulsive and coherent sources. The present work extends these findings by examining the effect of the sonar bandwidth on these kinds of features using a large data set gathered during an experiment on the Malta Plateau. Two separate bandwidths corresponding to those of two acoustic sources used during the experiment are considered independently. Using echoes from the two sources considered separately, it is possible to effectively reconstruct many of the features that would be derived with a full bandwidth signal. The results have implications for the use of fusion techniques where two separate sources are employed cooperatively and fused at the feature level to classify targets. Next, by using only those features that can effectively be reconstructed, it is possible to examine the full effect of bandwidth on the performance of a classification system which uses aural features. Results show that the system performance can be maintained with a narrower bandwidth if the center frequency is shifted downwards. Finally, fusion of the two sources at the decision-level is presented. Using the technique described, it is possible to achieve the same performance as a system using a single broadband source.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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 teacher head, 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".