Forest quality assessment based on bird sound recognition using convolutional neural networks
Deforestation in Indonesia is in a status that is quite alarming. From year to year, deforestation is still happening. The decline in fauna and the diminishing biodiversity are greatly affected by deforestation. This paper proposes a bioacoustics-based forest quality assessment tool using Nvidia Jet...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article PeerReviewed |
| Language: | English |
| Published: |
Institute of Advanced Engineering and Science
2022
|
| Subjects: | |
| Online Access: | https://repository.ugm.ac.id/283970/1/Effendy_TK.pdf https://repository.ugm.ac.id/283970/ https://ijece.iaescore.com/index.php/IJECE/article/view/26231 http://doi.org/10.11591/ijece.v12i4.pp4235-4242 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universitas Gadjah Mada |
| Language: | English |
| Summary: | Deforestation in Indonesia is in a status that is quite alarming. From year to year, deforestation is still happening. The decline in fauna and the diminishing biodiversity are greatly affected by deforestation. This paper proposes a bioacoustics-based forest quality assessment tool using Nvidia Jetson Nano and convolutional neural networks (CNN). The device, named GamaDet, is a portable physical product based on the microprocessor and equipped with a microphone to record the sounds of birds in the forest and display the results of their analysis. In addition, a Google Collaboratory-based GamaNet digital product is also proposed. GamaNet requires forest recording audio files to be further analyzed into a forest quality index. Testing the forest recording for 60 seconds at an arboretum forest showed that both products could work well. The GamaDet takes 370 seconds, while the GamaNet takes 70 seconds to process the audio data into a forest quality index and a list of detected birds. |
|---|