Whale cocktail party: Real-time multiple tracking and signal analyses
Bibliographic record
Abstract
This paper provides a real-time passive acoustic method to track multiple vocalizing whales using four or more omni-directional widely-spaced bottom-mounted hydrophones.Since the interest in marine mammals has increased, robust and real-time systems are required.To meet these demands, a real-time tracking algorithm was developed.After non-parametric Teager-Kaiser-Mallat signal filtering, rough Time Delays Of Arrival are calculated, selected and filtered, and used to estimate the positions of whales for a constant, linear or estimated sound speed profile.The complete algorithm is tested on real data from NUWC1 and AUTEC2.Our model is validated by similar results from the US Navy3 and SOEST4 University o f Hawaii Laboratory in the case o f one whale, and by similar results from the Columbia University ROSA5 Laboratory for the case of multiple whales.At this time, our tracking method is the only one which provides typical speed and depth estimates for multiple vocalizing whales. r é s u m éCe papier propose une méthode temps-réel de trajectographie par acoustique passive de plusieurs cétacés émettant simultanément en utilisant un réseau d 'au moins 4 hydrophones espacés de quelques centaines de mètres.Etant donné l 'intérêt accru pour les mammifères marins, des systèmes temps-réel et robustes sont nécessaires.Pour répondre à cette demande, un algorithme temps-réel de trajectographie multiple a été développé.Après un filtrage non paramétrique Teager-Kaiser-Mallat du signal, les différences de temps d 'arrivée aux hydrophones sont estimées, sélectionnées, filtrées, et permettent d 'estimer les positions des baleines pour un profil de célérité constant, linéaire ou estimé.L 'algorithme est testé sur des données réelles du NUWC1 et de l 'AUTEC2.Notre modèle est validé par des résultats similaires de l 'US Navy3 et du laboratoire SOEST4 de l'université d 'Hawaii dans le cas d 'émissions simples, et par une estimation du nombre de baleines du laboratoire ROSA5 de l 'université de Columbia dans le cas de plusieurs émissions simultanées.Actuellement, notre méthode de trajectographie est la seule donnant, dans le cas de plusieurs baleines, des vitesses et des profondeurs vraisemblables.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| 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 | 0.000 |
| 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".