MétaCan
Menu
Back to cohort
Record W2994445653

A novel multi-class support vector machine classifier for automated classification of beaked whales and other small odontocetes

2008· article· en· W2994445653 on OpenAlexvenueno aff
Susan Jarvis, Nancy DiMarzio, Ronald Morrissey, David Moretti

Bibliographic record

VenueCanadian acoustics · 2008
Typearticle
Languageen
FieldEnvironmental Science
TopicMarine animal studies overview
Canadian institutionsnot available
FundersOffice of Naval Research
KeywordsSupport vector machineMarine mammals and sonarArtificial intelligenceClassifier (UML)SonarBeaked whalePattern recognition (psychology)Computer scienceMarine mammalBioacousticsBinary classificationMulticlass classificationMachine learningSpeech recognitionWhaleBiologyFisheryTelecommunications
DOInot available

Abstract

fetched live from OpenAlex

Navy sonar has recently been implicated in several marine mammal stranding events.Beaked whales (particulary Mesoplodon densirostris) have been the predominant species involved in a number of these strandings.Monitoring and mitigating the effects of anthropogenic noise on marine mammals are active areas of research.Key to both monitoring and mitigation is the ability to automatically detect and classify animals, especially beaked whales.This paper presents a novel support vector machine based methodology for automated, species level classification of small odontocetes.The new classifier, called the classspecific support vector machine (CS-SVM), consists of multiple binary SVM's where each SVM discriminates between a class of interest and a common reference class.A main objective in the development of the CS-SVM was to realize a robust multi-class SVM whose implementation is simpler than existing multi-class SVM methods.A CS-SVM was trained to identify click vocalization from four species of odontocetes including Mesoplodon densirostris.The algorithm processes time series data in a fully automated fashion first detecting and then classifying click events.Results from the application of this automated classifier to the data sets provided by the 3rd International Workshop on Detection and Classification of Marine Mammals Using Passive Acoustics are presented. s o m m a i r eLe sonar a été récemment associé à un certain nombre d'événements de mammifère marin immobilisé en eau peu profond.Les Baleines a bec (en particulier le Mesoplodon densirostris) ont été les espèces prédominantes impliquées dans un certain nombre d'événements d'immobilisation.La surveillance et l'atténuation des effets du bruit synthétique sur les mammifères marins sont des domaines de recherche actifs.Ce qui est importante de la surveillance et la réduction des effets est la capacité automatiquement de détecter et classifier des animaux, particulièrement les baleines a bec.Cet article présente une nouvelle méthodologie basée sur une machine de support vecteur (SVM) pour automatisé le classification de niveau d'espèces de petits odontocetes.Le nouveau classificateur, appelé le "class-specific support vector machine" (CS-SVM), est composé de SVM binaire multiple où chaque SVM se distingue entre une classe d'intérêt et une classe commune de référence.Un objectif principal dans le développement du CS-SVM était de réaliser une multi-classe robuste SVM dont l'exécution est plus simple que des méthodes existantes de la multi-classe SVM.Un CS-SVM a été formé pour identifier le vocalisation de clic de quatre espèces des odontocetes incluant des Mesoplodon densirostris.Les données de série chronologique de processus d'algorithme sont traitées d'une mode entièrement automatisée détectant d'abord et classifiant ensuite des événements de clic.Les résultats de l'application de ce classificateur automatisé fournis par le "Troisième Atelier Internationale de Détection, Localisation, et Classification du Mammifères Marins avec les Acoutiques Passive" sont présentés.

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 imitation

Not 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.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.002
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.003
Threshold uncertainty score0.007

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.002
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0010.000
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0010.001

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.

Opus teacher head0.071
GPT teacher head0.255
Teacher spread0.184 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

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".

Quick stats

Citations31
Published2008
Admission routes1
Has abstractyes

Explore more

Same venueCanadian acousticsSame topicMarine animal studies overviewFrench-language works237,207