Performance of the detector.
(a) Histogram with a logarithmic scale showing the call count for Cascadia Initiative station J28A for the automatic detector as a function of the peak recognition score (dark gray) and the calls that were identified independently by an analyst as a definite blue whale (light gray). The scaling of t...
| Main Authors: | , |
|---|---|
| Format: | Still Image |
| Language: | unknown |
| Published: |
2021
|
| Subjects: | |
| Online Access: | https://doi.org/10.1371/journal.pone.0260273.g003 |
| id |
ftsmithonian:oai:figshare.com:article/17207601 |
|---|---|
| record_format |
openpolar |
| spelling |
ftsmithonian:oai:figshare.com:article/17207601 2023-05-15T15:36:24+02:00 Performance of the detector. William S. D. Wilcock (3749737) Rose S. Hilmo (4537330) 2021-12-15T18:23:25Z https://doi.org/10.1371/journal.pone.0260273.g003 unknown https://figshare.com/articles/figure/Performance_of_the_detector_/17207601 doi:10.1371/journal.pone.0260273.g003 CC BY 4.0 CC-BY Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Physical Sciences not elsewhere classified studying marine mammals passive acoustic monitoring ocean bottom seismometers many spurious solutions increasing sampling rates future experiments might div >< p balaenoptera musculus </ widely spaced network false positives must obtain tracks using least 20 locations earliest arrival time different b calls true positives large network b call vocalize extensively smooth paths seismic frequencies requiring groups pacific northwest obtained iteratively minimize changes localize calls including constraints important tool follow within first harmonic feasible time distance window detecting harmonics describe methods calls identified approaches lead 15 hz Image Figure 2021 ftsmithonian https://doi.org/10.1371/journal.pone.0260273.g003 2021-12-19T19:26:41Z (a) Histogram with a logarithmic scale showing the call count for Cascadia Initiative station J28A for the automatic detector as a function of the peak recognition score (dark gray) and the calls that were identified independently by an analyst as a definite blue whale (light gray). The scaling of the peak recognition score is arbitrary. (b) Precision (number of true positives divided by the sum of true positive and false positives) of automatic blue whale detections as a function of the minimum peak recognition score determined by treating the analyst identifications as ground truth (solid line and circles) and as inferred by comparing detection rates between the calling and non-calling season for blue whales (dashed line and triangles). (c) Precision-recall curve for the automated detection based on treating the analyst detections as ground truth. The recall is the number of true positives divided by the sum of true positives and false negatives. Labels indicate the threshold for the peak recognition score. Still Image Balaenoptera musculus Blue whale Unknown Pacific |
| institution |
Open Polar |
| collection |
Unknown |
| op_collection_id |
ftsmithonian |
| language |
unknown |
| topic |
Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Physical Sciences not elsewhere classified studying marine mammals passive acoustic monitoring ocean bottom seismometers many spurious solutions increasing sampling rates future experiments might div >< p balaenoptera musculus </ widely spaced network false positives must obtain tracks using least 20 locations earliest arrival time different b calls true positives large network b call vocalize extensively smooth paths seismic frequencies requiring groups pacific northwest obtained iteratively minimize changes localize calls including constraints important tool follow within first harmonic feasible time distance window detecting harmonics describe methods calls identified approaches lead 15 hz |
| spellingShingle |
Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Physical Sciences not elsewhere classified studying marine mammals passive acoustic monitoring ocean bottom seismometers many spurious solutions increasing sampling rates future experiments might div >< p balaenoptera musculus </ widely spaced network false positives must obtain tracks using least 20 locations earliest arrival time different b calls true positives large network b call vocalize extensively smooth paths seismic frequencies requiring groups pacific northwest obtained iteratively minimize changes localize calls including constraints important tool follow within first harmonic feasible time distance window detecting harmonics describe methods calls identified approaches lead 15 hz William S. D. Wilcock (3749737) Rose S. Hilmo (4537330) Performance of the detector. |
| topic_facet |
Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Physical Sciences not elsewhere classified studying marine mammals passive acoustic monitoring ocean bottom seismometers many spurious solutions increasing sampling rates future experiments might div >< p balaenoptera musculus </ widely spaced network false positives must obtain tracks using least 20 locations earliest arrival time different b calls true positives large network b call vocalize extensively smooth paths seismic frequencies requiring groups pacific northwest obtained iteratively minimize changes localize calls including constraints important tool follow within first harmonic feasible time distance window detecting harmonics describe methods calls identified approaches lead 15 hz |
| description |
(a) Histogram with a logarithmic scale showing the call count for Cascadia Initiative station J28A for the automatic detector as a function of the peak recognition score (dark gray) and the calls that were identified independently by an analyst as a definite blue whale (light gray). The scaling of the peak recognition score is arbitrary. (b) Precision (number of true positives divided by the sum of true positive and false positives) of automatic blue whale detections as a function of the minimum peak recognition score determined by treating the analyst identifications as ground truth (solid line and circles) and as inferred by comparing detection rates between the calling and non-calling season for blue whales (dashed line and triangles). (c) Precision-recall curve for the automated detection based on treating the analyst detections as ground truth. The recall is the number of true positives divided by the sum of true positives and false negatives. Labels indicate the threshold for the peak recognition score. |
| format |
Still Image |
| author |
William S. D. Wilcock (3749737) Rose S. Hilmo (4537330) |
| author_facet |
William S. D. Wilcock (3749737) Rose S. Hilmo (4537330) |
| author_sort |
William S. D. Wilcock (3749737) |
| title |
Performance of the detector. |
| title_short |
Performance of the detector. |
| title_full |
Performance of the detector. |
| title_fullStr |
Performance of the detector. |
| title_full_unstemmed |
Performance of the detector. |
| title_sort |
performance of the detector. |
| publishDate |
2021 |
| url |
https://doi.org/10.1371/journal.pone.0260273.g003 |
| geographic |
Pacific |
| geographic_facet |
Pacific |
| genre |
Balaenoptera musculus Blue whale |
| genre_facet |
Balaenoptera musculus Blue whale |
| op_relation |
https://figshare.com/articles/figure/Performance_of_the_detector_/17207601 doi:10.1371/journal.pone.0260273.g003 |
| op_rights |
CC BY 4.0 |
| op_rightsnorm |
CC-BY |
| op_doi |
https://doi.org/10.1371/journal.pone.0260273.g003 |
| _version_ |
1766366746052132864 |