A workflow for the automated detection and classification of female gibbon calls from long-term acoustic recordings
Passive acoustic monitoring (PAM) allows for the study of vocal animals on temporal and spatial scales difficult to achieve using only human observers. Recent improvements in recording technology, data storage, and battery capacity have led to increased use of PAM. One of the main obstacles in imple...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-02-01
|
| Series: | Frontiers in Ecology and Evolution |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fevo.2023.1071640/full |
| _version_ | 1811168245207531520 |
|---|---|
| author | Dena J. Clink Isabel Kier Abdul Hamid Ahmad Holger Klinck |
| author_facet | Dena J. Clink Isabel Kier Abdul Hamid Ahmad Holger Klinck |
| author_sort | Dena J. Clink |
| collection | DOAJ |
| description | Passive acoustic monitoring (PAM) allows for the study of vocal animals on temporal and spatial scales difficult to achieve using only human observers. Recent improvements in recording technology, data storage, and battery capacity have led to increased use of PAM. One of the main obstacles in implementing wide-scale PAM programs is the lack of open-source programs that efficiently process terabytes of sound recordings and do not require large amounts of training data. Here we describe a workflow for detecting, classifying, and visualizing female Northern grey gibbon calls in Sabah, Malaysia. Our approach detects sound events using band-limited energy summation and does binary classification of these events (gibbon female or not) using machine learning algorithms (support vector machine and random forest). We then applied an unsupervised approach (affinity propagation clustering) to see if we could further differentiate between true and false positives or the number of gibbon females in our dataset. We used this workflow to address three questions: (1) does this automated approach provide reliable estimates of temporal patterns of gibbon calling activity; (2) can unsupervised approaches be applied as a post-processing step to improve the performance of the system; and (3) can unsupervised approaches be used to estimate how many female individuals (or clusters) there are in our study area? We found that performance plateaued with >160 clips of training data for each of our two classes. Using optimized settings, our automated approach achieved a satisfactory performance (F1 score ~ 80%). The unsupervised approach did not effectively differentiate between true and false positives or return clusters that appear to correspond to the number of females in our study area. Our results indicate that more work needs to be done before unsupervised approaches can be reliably used to estimate the number of individual animals occupying an area from PAM data. Future work applying these methods across sites and different gibbon species and comparisons to deep learning approaches will be crucial for future gibbon conservation initiatives across Southeast Asia. |
| first_indexed | 2024-04-10T16:22:57Z |
| format | Article |
| id | doaj.art-e467b2002b72431884e07ccc7427ced8 |
| institution | Directory Open Access Journal |
| issn | 2296-701X |
| language | English |
| last_indexed | 2024-04-10T16:22:57Z |
| publishDate | 2023-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Ecology and Evolution |
| spelling | doaj.art-e467b2002b72431884e07ccc7427ced82023-02-09T11:06:49ZengFrontiers Media S.A.Frontiers in Ecology and Evolution2296-701X2023-02-011110.3389/fevo.2023.10716401071640A workflow for the automated detection and classification of female gibbon calls from long-term acoustic recordingsDena J. Clink0Isabel Kier1Abdul Hamid Ahmad2Holger Klinck3K. Lisa Yang Center for Conservation Bioacoustics, Cornell Lab of Ornithology, Cornell University, Ithaca, NY, United StatesK. Lisa Yang Center for Conservation Bioacoustics, Cornell Lab of Ornithology, Cornell University, Ithaca, NY, United StatesInstitute for Tropical Biology and Conservation, Universiti Malaysia Sabah, Kota Kinabalu, Sabah, MalaysiaK. Lisa Yang Center for Conservation Bioacoustics, Cornell Lab of Ornithology, Cornell University, Ithaca, NY, United StatesPassive acoustic monitoring (PAM) allows for the study of vocal animals on temporal and spatial scales difficult to achieve using only human observers. Recent improvements in recording technology, data storage, and battery capacity have led to increased use of PAM. One of the main obstacles in implementing wide-scale PAM programs is the lack of open-source programs that efficiently process terabytes of sound recordings and do not require large amounts of training data. Here we describe a workflow for detecting, classifying, and visualizing female Northern grey gibbon calls in Sabah, Malaysia. Our approach detects sound events using band-limited energy summation and does binary classification of these events (gibbon female or not) using machine learning algorithms (support vector machine and random forest). We then applied an unsupervised approach (affinity propagation clustering) to see if we could further differentiate between true and false positives or the number of gibbon females in our dataset. We used this workflow to address three questions: (1) does this automated approach provide reliable estimates of temporal patterns of gibbon calling activity; (2) can unsupervised approaches be applied as a post-processing step to improve the performance of the system; and (3) can unsupervised approaches be used to estimate how many female individuals (or clusters) there are in our study area? We found that performance plateaued with >160 clips of training data for each of our two classes. Using optimized settings, our automated approach achieved a satisfactory performance (F1 score ~ 80%). The unsupervised approach did not effectively differentiate between true and false positives or return clusters that appear to correspond to the number of females in our study area. Our results indicate that more work needs to be done before unsupervised approaches can be reliably used to estimate the number of individual animals occupying an area from PAM data. Future work applying these methods across sites and different gibbon species and comparisons to deep learning approaches will be crucial for future gibbon conservation initiatives across Southeast Asia.https://www.frontiersin.org/articles/10.3389/fevo.2023.1071640/fullmachine learningHylobatesR programing languagesignal processingbioacousticsSoutheast Asia |
| spellingShingle | Dena J. Clink Isabel Kier Abdul Hamid Ahmad Holger Klinck A workflow for the automated detection and classification of female gibbon calls from long-term acoustic recordings Frontiers in Ecology and Evolution machine learning Hylobates R programing language signal processing bioacoustics Southeast Asia |
| title | A workflow for the automated detection and classification of female gibbon calls from long-term acoustic recordings |
| title_full | A workflow for the automated detection and classification of female gibbon calls from long-term acoustic recordings |
| title_fullStr | A workflow for the automated detection and classification of female gibbon calls from long-term acoustic recordings |
| title_full_unstemmed | A workflow for the automated detection and classification of female gibbon calls from long-term acoustic recordings |
| title_short | A workflow for the automated detection and classification of female gibbon calls from long-term acoustic recordings |
| title_sort | workflow for the automated detection and classification of female gibbon calls from long term acoustic recordings |
| topic | machine learning Hylobates R programing language signal processing bioacoustics Southeast Asia |
| url | https://www.frontiersin.org/articles/10.3389/fevo.2023.1071640/full |
| work_keys_str_mv | AT denajclink aworkflowfortheautomateddetectionandclassificationoffemalegibboncallsfromlongtermacousticrecordings AT isabelkier aworkflowfortheautomateddetectionandclassificationoffemalegibboncallsfromlongtermacousticrecordings AT abdulhamidahmad aworkflowfortheautomateddetectionandclassificationoffemalegibboncallsfromlongtermacousticrecordings AT holgerklinck aworkflowfortheautomateddetectionandclassificationoffemalegibboncallsfromlongtermacousticrecordings AT denajclink workflowfortheautomateddetectionandclassificationoffemalegibboncallsfromlongtermacousticrecordings AT isabelkier workflowfortheautomateddetectionandclassificationoffemalegibboncallsfromlongtermacousticrecordings AT abdulhamidahmad workflowfortheautomateddetectionandclassificationoffemalegibboncallsfromlongtermacousticrecordings AT holgerklinck workflowfortheautomateddetectionandclassificationoffemalegibboncallsfromlongtermacousticrecordings |