Detection and Classification of Marine mammals using an LFAS system
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
World wide a concern is emerging about the influence of man-made sound in the sea on marine life, and particularly about high power active sonars systems. Most concern lies with marine mammals, which fully depend on sound in their natural behaviour (foraging, navigation and communication). One of the sonars under debate is the Low Frequency Active Sonar (LFAS). This type of system is designed for long range detection of submarines. It consists of a powerful source and a towed array receiver. Incidents with marine mammals could be avoided if the receiver that is dedicated to detection of submarine echoes, is equipped with Detection, Classification and Localisation capabilities for marine mammals as well. In this paper the development of a prototype transient detector and classifier for the TNO-FEL LFAS array (named CAPTAS) is described. A broadband beamformer is developed that creates 8 beams (sectors) that are equally wide over the whole frequency band. A multi-beam LOFAR display is presented. On the normalised data a Page’s test detector is applied that is “optimum” for signals with unknown duration. Detected transients are sent to a classifier that tries to discriminate between biological and man-made or natural transients. Time-frequency analysis is performed and in the resulting timefrequency plot structures are determined by means of cluster analysis after which the sound is classified. Detection results of the prototype are very good, the Classification module is under development and the Localisation module is part of future research. Part of this research is sponsored by the Royal NetherLands Navy (RNLN).
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.
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) | 0.000 | 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 it