Gibbon dataset - PAMGuard deep learning tutorial

Deep learning and bats - PAMGuard tutorial dataset

General Information

Overview

This is a dataset to be used in part three of the PAMGuard tutorial *Deep learning in PAMGuard * (www.pamgaurd.org). The dataset is from a 4 channel TREX recorder deployed in Xe Sap national park in Laos. 

Year of data collection

2024

Geographic location of data collection

Xe Sap national park, Laos

Funding sources that supported the collection of the data

Arcus Foundation grant “Production of Acoustic Recorders for Gibbon Surveys”.

Recommended citation for this dataset

10.5281/zenodo.15045966

Data & File Overview

Description of dataset

These data contain a small raw data sample from an experimental 4 channel trex recorder along with a PAMGuard compatible deep learning model which can detect three types of Northern white-cheeked gibbon (_Nomascus leucogenys_) calls. The deep learning model was devleoped by Arbimon (www.arbimon.org). 

Files

The files are 4 channel .wav files made on a Trex recorder. These are 16 bit files with an unknown clip levels. 

The folder structure is as follows:

```md├── wav                                         #Folder of .wav files│   └── 20240205_230252.wav            #Sample wave file├── README.md                                   #This readme file├── gibbon_model.zip     #PAMGaurd deep learning model└── ```

Device locations

Confidential

Sharing and access

These data are open source under Creative Commons Attribution 4.0 International. This means that these data can be used in other tutorials as long as the original authors are credited. Using these data for scientific purposes requires the permission of the authors. 

```