gibbonNetR

gibbonNetR: an R Package for the Use of Convolutional Neural Networks for Automated Detection of Acoustic Data - Published in JOSS (2025)

https://github.com/denajgibbon/gibbonnetr

Scientific Fields

Engineering Computer Science - 40% confidence

Last synced: 6 months ago · JSON representation

Repository

R package to use 'torch for R' for automated detection using convolutional neural nets in passive acoustic monitoring (PAM) data

Basic Info

Host: GitHub
Owner: DenaJGibbon
License: other
Language: HTML
Default Branch: main
Homepage: https://denajgibbon.github.io/gibbonNetR/
Size: 643 MB

Statistics

Stars: 2
Watchers: 1
Forks: 2
Open Issues: 2
Releases: 3

Created over 2 years ago · Last pushed 8 months ago

Metadata Files

Readme Contributing License Codemeta

README.Rmd

---
title: "gibbonNetR R Package"
author: "Dena J. Clink and Abdul Hamid Ahmad"
date: "`r Sys.Date()`"
output: github_document
---

```{r setup, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  out.width = "400px", dpi = 120
)

knitr::opts_knit$set(root.dir = "/Users/denaclink/Desktop/RStudioProjects/gibbonNetR_notgithub/")
```

# Overview

This README provides code for training, testing, and deploying, different convolutional neural network model architectures for automated detection and classification of acoustic data.

Users can train both binary and multi-class classification models on spectrogram images, and evaluate their performance on test datasets. The package includes tools for performance evaluation, allowing easy identification of the best-performing model. Once the best-performing model is identified, it can be deployed for large-scale inference on multiple sound files. In addition to classification, trained CNNs can be used as feature extractors. Combined with unsupervised clustering, this enables visualization of differences in acoustic signals.

# Usage

A detailed usage guide can be found at: 

Link to paper in the Journal of Open Source Software: 
[![DOI](https://joss.theoj.org/papers/10.21105/joss.07250/status.svg)](https://doi.org/10.21105/joss.07250)

# Prerequisites
This package assumes a basic understanding of machine learning, deep learning, and convolutional neural networks (CNNs). Users should be familiar with training and evaluating models, as well as handling spectrogram image data. For those new to these concepts, we recommend reviewing foundational machine learning and deep learning resources before using this package. a good starting point would be: 

Stowell, Dan. "Computational bioacoustics with deep learning: a review and roadmap." PeerJ 10 (2022): e13152. https://peerj.com/articles/13152/

Some practical information on improving model performance can be found here: https://kahst.github.io/BirdNET-Analyzer/best-practices/training.html#

# Installation

You can install the `gibbonNetR` package from its repository using `devtools`:

```{r eval = FALSE}
# If you don't have devtools installed
install.packages("devtools")

# Install gibbonNetR
devtools::install_github("https://github.com/DenaJGibbon/gibbonNetR")

# The first time you use the package 'torch' will need to install additional packages. You can start the process using the following:
library(torch)
```

```{r, message=FALSE, echo=FALSE, warning=FALSE}
devtools::load_all("/Users/denaclink/Desktop/RStudioProjects/gibbonNetR")
# library(gibbonNetR)
# Load other required libraries
library(dplyr)
library(torch)
library(torchvision)
library(purrr)
```

# Quickstart guide

```{r eval = FALSE}
library(gibbonNetR)

# Set file path to spectrogram images
filepath <- system.file("extdata", "multiclass/", package = "gibbonNetR")

# Train simple CNN model
train_CNN_multi(
  input.data.path = filepath,
  test.data = paste(filepath, "/test/", sep = ""),
  architecture = "alexnet", # Choose 'alexnet', 'vgg16', 'vgg19', 'resnet18', 'resnet50', or 'resnet152'
  unfreeze.param = TRUE,
  batch_size = 6,
  class_weights = rep((1 / 5), 5),
  learning_rate = 0.001,
  epoch.iterations = 1, # Or any other list of integer epochs
  early.stop = "yes",
  save.model = FALSE,
  output.base.path = file.path(tempdir(), "/MultiDir/", sep = ""),
  trainingfolder = "test_multi",
  noise.category = "noise"
)
```

Owner

Name: Dena J. Clink
Login: DenaJGibbon
Kind: user
Company: K. Lisa Yang Center for Conservation Bioacoustics

Website: www.denaclink.com
Twitter: BorneanGibbons
Repositories: 4
Profile: https://github.com/DenaJGibbon

I am a biological anthropologist, bioacoustician, and avid R user. I use innovative bioacoustics techniques to answer evolutionary questions.

JOSS Publication

gibbonNetR: an R Package for the Use of Convolutional Neural Networks for Automated Detection of Acoustic Data

Published

June 07, 2025

DOI

10.21105/joss.07250

Volume 10, Issue 110, Page 7250

Authors

Dena Jane Clink

K. Lisa Yang Center for Conservation Bioacoustics, Cornell Lab of Ornithology, Cornell University, Ithaca, New York, United States

Abdul Hamid Ahmad

Institute for Tropical Biology and Conservation, Universiti Malaysia Sabah (UMS), Kota Kinabalu, Sabah, Malaysia

Editor

Fabian-Robert Stöter

CodeMeta (codemeta.json)

{
  "@context": "https://doi.org/10.5063/schema/codemeta-2.0",
  "@type": "SoftwareSourceCode",
  "identifier": "gibbonNetR",
  "description": "R Package for the Use of CNNs on Acoustic Data.",
  "name": "gibbonNetR: gibbonNetR: R Package for the Use of CNNs and Transfer Learning on\n    Acoustic Data",
  "codeRepository": "https://github.com/DenaJGibbon/gibbonNetR",
  "issueTracker": "https://github.com/DenaJGibbon/gibbonNetR/issues",
  "license": "https://spdx.org/licenses/MIT",
  "version": "1.0.0",
  "programmingLanguage": {
    "@type": "ComputerLanguage",
    "name": "R",
    "url": "https://r-project.org"
  },
  "runtimePlatform": "R version 4.4.0 (2024-04-24)",
  "author": [
    {
      "@type": "Person",
      "givenName": "Dena J.",
      "familyName": "Clink",
      "email": "dena.clink@cornell.edu",
      "@id": "https://orcid.org/0000-0003-0363-5581"
    }
  ],
  "maintainer": [
    {
      "@type": "Person",
      "givenName": "Dena J.",
      "familyName": "Clink",
      "email": "dena.clink@cornell.edu",
      "@id": "https://orcid.org/0000-0003-0363-5581"
    }
  ],
  "softwareSuggestions": [
    {
      "@type": "SoftwareApplication",
      "identifier": "devtools",
      "name": "devtools",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=devtools"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "knitr",
      "name": "knitr",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=knitr"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "rmarkdown",
      "name": "rmarkdown",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=rmarkdown"
    },
    {
      "@type": "SoftwareApplication",
      "identifier": "testthat",
      "name": "testthat",
      "version": ">= 3.0.0",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=testthat"
    }
  ],
  "softwareRequirements": {
    "1": {
      "@type": "SoftwareApplication",
      "identifier": "luz",
      "name": "luz",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=luz"
    },
    "2": {
      "@type": "SoftwareApplication",
      "identifier": "R",
      "name": "R",
      "version": ">= 2.10"
    },
    "3": {
      "@type": "SoftwareApplication",
      "identifier": "torch",
      "name": "torch",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=torch"
    },
    "4": {
      "@type": "SoftwareApplication",
      "identifier": "torchvision",
      "name": "torchvision",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=torchvision"
    },
    "5": {
      "@type": "SoftwareApplication",
      "identifier": "tuneR",
      "name": "tuneR",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=tuneR"
    },
    "6": {
      "@type": "SoftwareApplication",
      "identifier": "aricode",
      "name": "aricode",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=aricode"
    },
    "7": {
      "@type": "SoftwareApplication",
      "identifier": "caret",
      "name": "caret",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=caret"
    },
    "8": {
      "@type": "SoftwareApplication",
      "identifier": "coro",
      "name": "coro",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=coro"
    },
    "9": {
      "@type": "SoftwareApplication",
      "identifier": "cowplot",
      "name": "cowplot",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=cowplot"
    },
    "10": {
      "@type": "SoftwareApplication",
      "identifier": "data.table",
      "name": "data.table",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=data.table"
    },
    "11": {
      "@type": "SoftwareApplication",
      "identifier": "dbscan",
      "name": "dbscan",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=dbscan"
    },
    "12": {
      "@type": "SoftwareApplication",
      "identifier": "dplyr",
      "name": "dplyr",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=dplyr"
    },
    "13": {
      "@type": "SoftwareApplication",
      "identifier": "ggplot2",
      "name": "ggplot2",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=ggplot2"
    },
    "14": {
      "@type": "SoftwareApplication",
      "identifier": "ggpubr",
      "name": "ggpubr",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=ggpubr"
    },
    "15": {
      "@type": "SoftwareApplication",
      "identifier": "grDevices",
      "name": "grDevices"
    },
    "16": {
      "@type": "SoftwareApplication",
      "identifier": "magrittr",
      "name": "magrittr",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=magrittr"
    },
    "17": {
      "@type": "SoftwareApplication",
      "identifier": "purrr",
      "name": "purrr",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=purrr"
    },
    "18": {
      "@type": "SoftwareApplication",
      "identifier": "readr",
      "name": "readr",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=readr"
    },
    "19": {
      "@type": "SoftwareApplication",
      "identifier": "ROCR",
      "name": "ROCR",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=ROCR"
    },
    "20": {
      "@type": "SoftwareApplication",
      "identifier": "seewave",
      "name": "seewave",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=seewave"
    },
    "21": {
      "@type": "SoftwareApplication",
      "identifier": "stats",
      "name": "stats"
    },
    "22": {
      "@type": "SoftwareApplication",
      "identifier": "stringr",
      "name": "stringr",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=stringr"
    },
    "23": {
      "@type": "SoftwareApplication",
      "identifier": "tibble",
      "name": "tibble",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=tibble"
    },
    "24": {
      "@type": "SoftwareApplication",
      "identifier": "tidyr",
      "name": "tidyr",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=tidyr"
    },
    "25": {
      "@type": "SoftwareApplication",
      "identifier": "torchdatasets",
      "name": "torchdatasets",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=torchdatasets"
    },
    "26": {
      "@type": "SoftwareApplication",
      "identifier": "umap",
      "name": "umap",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=umap"
    },
    "27": {
      "@type": "SoftwareApplication",
      "identifier": "utils",
      "name": "utils"
    },
    "28": {
      "@type": "SoftwareApplication",
      "identifier": "viridis",
      "name": "viridis",
      "provider": {
        "@id": "https://cran.r-project.org",
        "@type": "Organization",
        "name": "Comprehensive R Archive Network (CRAN)",
        "url": "https://cran.r-project.org"
      },
      "sameAs": "https://CRAN.R-project.org/package=viridis"
    },
    "SystemRequirements": null
  },
  "fileSize": "126647.829KB",
  "citation": [
    {
      "@type": "SoftwareSourceCode",
      "datePublished": "2025",
      "author": [
        {
          "@type": "Person",
          "givenName": [
            "Dena",
            "J."
          ],
          "familyName": "Clink"
        },
        {
          "@type": "Person",
          "givenName": [
            "Abdul",
            "Hamid"
          ],
          "familyName": "Ahmad"
        }
      ],
      "name": "gibbonNetR: R Package for the Use of CNNs and Transfer Learning on Acoustic Data",
      "url": "https://github.com/DenaJGibbon/gibbonNetR",
      "isPartOf": {
        "@type": "PublicationIssue",
        "datePublished": "2025",
        "isPartOf": {
          "@type": [
            "PublicationVolume",
            "Periodical"
          ],
          "name": "GitHub"
        }
      }
    }
  ],
  "relatedLink": "https://denajgibbon.github.io/gibbonNetR/",
  "readme": "https://github.com/DenaJGibbon/gibbonNetR/blob/main/README.md"
}

GitHub Events

Total

Create event: 1
Release event: 1
Issues event: 16
Issue comment event: 17
Push event: 178
Pull request review event: 1
Pull request event: 2
Fork event: 1

Last Year

Create event: 1
Release event: 1
Issues event: 16
Issue comment event: 17
Push event: 178
Pull request review event: 1
Pull request event: 2
Fork event: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 8
Total pull requests: 2
Average time to close issues: 4 months
Average time to close pull requests: about 2 months
Total issue authors: 3
Total pull request authors: 2
Average comments per issue: 1.25
Average comments per pull request: 1.0
Merged pull requests: 1
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 7
Pull requests: 2
Average time to close issues: 3 months
Average time to close pull requests: about 2 months
Issue authors: 3
Pull request authors: 2
Average comments per issue: 1.43
Average comments per pull request: 1.0
Merged pull requests: 1
Bot issues: 0
Bot pull requests: 0

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science

gibbonNetR

Science Score: 93.0%

Scientific Fields

Repository

Basic Info

Statistics

Metadata Files

README.Rmd

Owner

JOSS Publication

gibbonNetR: an R Package for the Use of Convolutional Neural Networks for Automated Detection of Acoustic Data

Authors

Editor

Tags

CodeMeta (codemeta.json)

GitHub Events

Total

Last Year

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Dependencies