Statistical classification of odontocete clicks
Bibliographic record
Abstract
To the best of our knowledge, all odontocetes produce some kind of click like vocalisation, which is used primarily for echolocation but may also play a role in social communication.Characteristics of these echolocation pulses range from the broad band but relatively low frequency clicks of sperm whales to the ultrasonic, narrow-band clicks of harbour porpoise.Although these clicks are often easily detected, it can be difficult to classify them to species, thereby hampering efforts to monitor and study odontocetes using passive acoustics.Candidate clicks from three species were detected using a simple energy trigger, operating in the frequency band of interest.The clicks were then identified to species using two different statistical classifiers to separate beaked whale vocalisations from those of other odontocete sounds.In the first, a number of parameters (peak frequency, mean frequency, sweep frequency, click duration, width of principal spectral peak and the relative energy in different frequency bands) were calculated and a tree classifier was used to separate clicks of different species.In the second, the spectral energy in 32 relatively coarse energy bands 1.5 kHz wide were used as input to a multivariate classifier.Both classifiers were trained and tested using data provided to the 3rd International Workshop on Detection and Classification of Marine Mammals using Passive Acoustics in order to assess the classifiers performance with Blainville's beaked whales, short-finned pilot whales and Risso's dolphin clicks.The methods were also applied to survey data collected using a towed hydrophone deployed from a sailing research vessel in the Bahamas.Some of the towed hydrophone data were collected over the US Navy's AUTEC range where independent confirmation of beaked whale vocal activity was available from bottom-mounted hydrophones. s o m m a i r eL 'état actuel de nos connaissances nous permet d'affirmer que tous les odontocetes émettent des sons de type impulsifs, aussi appelés clics, destinés surtout à l 'écholocation, mais ils peuvent également être utilisés pour la communication.En fonction des espèces, ces clics peuvent couvrir une bande de fréquence plus ou moins large.Le cachalot produit des clics couvrant une large bande de basses fréquences, alors que chez le marsouin, l 'écholocation est caractérisée par des clics ultrasoniques couvrant une bande de fréquence étroite.En sélectionnant les clics ayant une puissance supérieure à un certain seuil avec un simple détecteur d 'énergie dans la bande de fréquence qui nous intéressait, nous avons collecté les clics de 3 espèces (Baleine à bec de Blainville, globicéphale tropical et dauphin de Risso).Deux méthodes d 'analyse nous ont permis de discriminer les sons de la baleine à bec de Blainville de ceux des 2 autres espèces.Pour la première méthode, différent paramètres (pic de fréquence, fréquence moyenne, variation de fréquence, durée du signal, largeur du spectrogramme et énergie relative dans les différentes bandes de fréquences) ont été extraits de chaque clic et utilisés dans un arbre de classification afin de séparer les espèces.Pour la seconde méthode, l'énergie contenue dans 32 bandes de 1.5kHz a servi de données pour une analyse multivariée.Les 2 classificateurs ont été entrainés et testés en utilisant les données de la 3ième commission internationale de détection et de classification des mammifères marins en utilisant l 'acoustique passive.L 'objectif était de mesurer la performance des classificateurs pour discriminer la baleine à bec de Blainvilles, le globicéphale tropical et le dauphin de Risso.Ces 2 méthodes ont ensuite été appliquées sur des données collectées au Bahamas à partir d 'hydrophones tirés par un voilier de recherche.Quelques données furent collectées au dessus de la zone du réseau d 'hydrophone Autec, appartenant à la marine Américaine, permettant d 'obtenir une confirmation indépendante de l'activité sonore des baleines à bec via ce réseau sous-marin.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 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 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".