Automatic Recognition of Giant Panda Attributes from Their Vocalizations Based on Squeeze-and-Excitation Network
The giant panda (<i>Ailuropoda melanoleuca</i>) has long attracted the attention of conservationists as a flagship and umbrella species. Collecting attribute information on the age structure and sex ratio of the wild giant panda populations can support our understanding of their status a...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/20/8015 |
| _version_ | 1797469945747996672 |
|---|---|
| author | Qijun Zhao Yanqiu Zhang Rong Hou Mengnan He Peng Liu Ping Xu Zhihe Zhang Peng Chen |
| author_facet | Qijun Zhao Yanqiu Zhang Rong Hou Mengnan He Peng Liu Ping Xu Zhihe Zhang Peng Chen |
| author_sort | Qijun Zhao |
| collection | DOAJ |
| description | The giant panda (<i>Ailuropoda melanoleuca</i>) has long attracted the attention of conservationists as a flagship and umbrella species. Collecting attribute information on the age structure and sex ratio of the wild giant panda populations can support our understanding of their status and the design of more effective conservation schemes. In view of the shortcomings of traditional methods, which cannot automatically recognize the age and sex of giant pandas, we designed a SENet (Squeeze-and-Excitation Network)-based model to automatically recognize the attributes of giant pandas from their vocalizations. We focused on the recognition of age groups (juvenile and adult) and sex of giant pandas. The reason for using vocalizations is that among the modes of animal communication, sound has the advantages of long transmission distances, strong penetrating power, and rich information. We collected a dataset of calls from 28 captive giant panda individuals, with a total duration of 1298.02 s of recordings. We used MFCC (Mel-frequency Cepstral Coefficients), which is an acoustic feature, as inputs for the SENet. Considering that small datasets are not conducive to convergence in the training process, we increased the size of the training data via SpecAugment. In addition, we used focal loss to reduce the impact of data imbalance. Our results showed that the F1 scores of our method for recognizing age group and sex reached 96.46% ± 5.71% and 85.85% ± 7.99%, respectively, demonstrating that the automatic recognition of giant panda attributes based on their vocalizations is feasible and effective. This more convenient, quick, timesaving, and laborsaving attribute recognition method can be used in the investigation of wild giant pandas in the future. |
| first_indexed | 2024-03-09T19:30:07Z |
| format | Article |
| id | doaj.art-cf9d3c40dc664878b4502f293f0628be |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T19:30:07Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-cf9d3c40dc664878b4502f293f0628be2023-11-24T02:30:23ZengMDPI AGSensors1424-82202022-10-012220801510.3390/s22208015Automatic Recognition of Giant Panda Attributes from Their Vocalizations Based on Squeeze-and-Excitation NetworkQijun Zhao0Yanqiu Zhang1Rong Hou2Mengnan He3Peng Liu4Ping Xu5Zhihe Zhang6Peng Chen7National Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, ChinaNational Key Laboratory of Fundamental Science on Synthetic Vision, Sichuan University, Chengdu 610065, ChinaChengdu Research Base of Giant Panda Breeding, Sichuan Key Laboratory of Conservation Biology for Endangered Wildlife, Chengdu 610086, ChinaChengdu Research Base of Giant Panda Breeding, Sichuan Key Laboratory of Conservation Biology for Endangered Wildlife, Chengdu 610086, ChinaChengdu Research Base of Giant Panda Breeding, Sichuan Key Laboratory of Conservation Biology for Endangered Wildlife, Chengdu 610086, ChinaGiant Panda National Park Chengdu Administration, Chengdu 610086, ChinaSichuan Academy of Giant Panda, Chengdu 610086, ChinaChengdu Research Base of Giant Panda Breeding, Sichuan Key Laboratory of Conservation Biology for Endangered Wildlife, Chengdu 610086, ChinaThe giant panda (<i>Ailuropoda melanoleuca</i>) has long attracted the attention of conservationists as a flagship and umbrella species. Collecting attribute information on the age structure and sex ratio of the wild giant panda populations can support our understanding of their status and the design of more effective conservation schemes. In view of the shortcomings of traditional methods, which cannot automatically recognize the age and sex of giant pandas, we designed a SENet (Squeeze-and-Excitation Network)-based model to automatically recognize the attributes of giant pandas from their vocalizations. We focused on the recognition of age groups (juvenile and adult) and sex of giant pandas. The reason for using vocalizations is that among the modes of animal communication, sound has the advantages of long transmission distances, strong penetrating power, and rich information. We collected a dataset of calls from 28 captive giant panda individuals, with a total duration of 1298.02 s of recordings. We used MFCC (Mel-frequency Cepstral Coefficients), which is an acoustic feature, as inputs for the SENet. Considering that small datasets are not conducive to convergence in the training process, we increased the size of the training data via SpecAugment. In addition, we used focal loss to reduce the impact of data imbalance. Our results showed that the F1 scores of our method for recognizing age group and sex reached 96.46% ± 5.71% and 85.85% ± 7.99%, respectively, demonstrating that the automatic recognition of giant panda attributes based on their vocalizations is feasible and effective. This more convenient, quick, timesaving, and laborsaving attribute recognition method can be used in the investigation of wild giant pandas in the future.https://www.mdpi.com/1424-8220/22/20/8015giant pandaattribute recognitionbioacousticsspecies conservationdeep learningSENet |
| spellingShingle | Qijun Zhao Yanqiu Zhang Rong Hou Mengnan He Peng Liu Ping Xu Zhihe Zhang Peng Chen Automatic Recognition of Giant Panda Attributes from Their Vocalizations Based on Squeeze-and-Excitation Network Sensors giant panda attribute recognition bioacoustics species conservation deep learning SENet |
| title | Automatic Recognition of Giant Panda Attributes from Their Vocalizations Based on Squeeze-and-Excitation Network |
| title_full | Automatic Recognition of Giant Panda Attributes from Their Vocalizations Based on Squeeze-and-Excitation Network |
| title_fullStr | Automatic Recognition of Giant Panda Attributes from Their Vocalizations Based on Squeeze-and-Excitation Network |
| title_full_unstemmed | Automatic Recognition of Giant Panda Attributes from Their Vocalizations Based on Squeeze-and-Excitation Network |
| title_short | Automatic Recognition of Giant Panda Attributes from Their Vocalizations Based on Squeeze-and-Excitation Network |
| title_sort | automatic recognition of giant panda attributes from their vocalizations based on squeeze and excitation network |
| topic | giant panda attribute recognition bioacoustics species conservation deep learning SENet |
| url | https://www.mdpi.com/1424-8220/22/20/8015 |
| work_keys_str_mv | AT qijunzhao automaticrecognitionofgiantpandaattributesfromtheirvocalizationsbasedonsqueezeandexcitationnetwork AT yanqiuzhang automaticrecognitionofgiantpandaattributesfromtheirvocalizationsbasedonsqueezeandexcitationnetwork AT ronghou automaticrecognitionofgiantpandaattributesfromtheirvocalizationsbasedonsqueezeandexcitationnetwork AT mengnanhe automaticrecognitionofgiantpandaattributesfromtheirvocalizationsbasedonsqueezeandexcitationnetwork AT pengliu automaticrecognitionofgiantpandaattributesfromtheirvocalizationsbasedonsqueezeandexcitationnetwork AT pingxu automaticrecognitionofgiantpandaattributesfromtheirvocalizationsbasedonsqueezeandexcitationnetwork AT zhihezhang automaticrecognitionofgiantpandaattributesfromtheirvocalizationsbasedonsqueezeandexcitationnetwork AT pengchen automaticrecognitionofgiantpandaattributesfromtheirvocalizationsbasedonsqueezeandexcitationnetwork |