Creating an RFM Classification Job

Random Forest Model

This is a classification method that uses the Random Forest model to classify the entire recordings dataset. The Random Forest model and Threshold model can both be applied to all recordings. Each model will classify the presence or absence of the species call in each recording. 

How to Run a Random Forest Model

Before running a Classification, create a playlist with the recordings that will be classified (e.g. nighttime, site or validated recordings, etc.). Each playlist should have no more than 20,000 recordings. 

*Please ensure your model is trained on files with the SAME sampling rate as the files used for classification, otherwise the job will not run correctly.* 

1. Go to the project menu and click Audio analyses, then Random Forest Models.

2. Go to the Classifications tab and click the Classifications New Job icon.

3. Enter a name for the classification job, select the existing Random Forest Model (RFM) you want to use, and select the playlist you want to run the mode over. 

Click Create. 

You can view the status of the job by going to the project menu and clicking Audio analyses, then Active Jobs.

4. The new job will appear in the Classifications list. Click on Show Details to view the results.

5. Click the Download icon to download the results in a spreadsheet. 

6. Click on Show Details per Recording to view the results per recording in the playlist.

7. You can download the results of the classification job in a spreadsheet by clicking the Download icon.