diachrysia-classification

Classification of two twin moth species using microscopic spectroscopy and machine learning

https://github.com/kadyb/diachrysia-classification

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
○
DOI references
✓
Academic publication links
Links to: sciencedirect.com
○
Academic email domains
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (9.3%) to scientific vocabulary

Keywords

classification dataset machine-learning moths r spectroscopy

Last synced: 4 months ago · JSON representation ·

Repository

Classification of two twin moth species using microscopic spectroscopy and machine learning

Basic Info

Host: GitHub
Owner: kadyb
License: mit
Language: R
Default Branch: main
Homepage:
Size: 9.65 MB

Statistics

Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Releases: 0

Topics

classification dataset machine-learning moths r spectroscopy

Created almost 5 years ago · Last pushed almost 4 years ago

Metadata Files

Readme License Citation

Diachrysia classification

This repository contains the data, code, and results for “Reflectance spectroscopy and machine learning as a tool for the categorization of twin species based on the example of the Diachrysia genus” article.

Dataset

There are two datasets in the data directory - the first containing legislative information on moths (Legislative), the second containing the measured spectra (Spectra). The files are available in two formats - .csv and .xlsx.

Legislative file contains the following columns: - ID - Individual identifier (species-number) - Species - Diachrysia chrysitis or Diachrysia stenochrysis - Sex - Male (♂) or Female (♀) - Year_catch - year of the moth catch - Day_catch - day of the year when the moth was caught - Locality - place where the moth was caught - UTM_code - zone in UTM coordinate system - Longitude - east–west position in degrees - Latitude - north–south position in degrees - Feature_level - level of marking the morphological feature, where 1 means weak, 2 means strong, 3 means very strong

Spectra file contains the following columns: - ID - Individual identifier (species-number) - Species - Diachrysia chrysitis or Diachrysia stenochrysis - Scale - part of the scale on which the spectrometer measurement was made (Glass or Brown) - 400-2100 - spectral band number

Reproduction

Open the diachrysia-classification.Rproj project file in RStudio.
Run 01_randomforest.R to build classification models, assess the performance of classification at the general and individual level and determine the importance of spectral features.
Run 02_KS_test.R to determine importance of the spectral bands for species discrimination using Kolmogorov–Smirnov test.
Run 03_LDA_best_features.R to determine the most useful spectral bands for species classification using Linear Discriminant Analysis and D-statistic.
Run 04_LDA_combinations.R to determine the minimum set of spectral features to distinguish species with 100% accuracy.

Results

The code results were saved in results directory: - ks-test.csv - importance of the spectral bands for species discrimination determined by D-statistic - rf-importance.csv - average importance of the spectral features for classification in the random forest models

Owner

Name: Krzysztof Dyba
Login: kadyb
Kind: user
Location: Poland
Company: Adam Mickiewicz University

Twitter: krzysztof_dyba
Repositories: 9
Profile: https://github.com/kadyb

Spatial Data Science | Remote Sensing | R

Citation (CITATION.cff)

cff-version: 1.2.0
message: "If you use data or code from this repository, please cite it as below."
preferred-citation:
  type: article
  authors:
  - family-names: "Dyba"
    given-names: "Krzysztof"
    orcid: "https://orcid.org/0000-0002-8614-3816"
  - family-names: "Wąsala"
    given-names: "Roman"
    orcid: "https://orcid.org/0000-0001-7348-987X"
  - family-names: "Piekarczyk"
    given-names: "Jan"
    orcid: "https://orcid.org/0000-0002-2405-6741"
  - family-names: "Gabała"
    given-names: "Elżbieta"
    orcid: "https://orcid.org/0000-0002-9296-8208"
  - family-names: "Gawlak"
    given-names: "Magdalena"
    orcid: "https://orcid.org/0000-0001-7994-2882"
  - family-names: "Jasiewicz"
    given-names: "Jarosław"
    orcid: "https://orcid.org/0000-0003-2837-9078"
  - family-names: "Ratajkiewicz"
    given-names: "Henryk"
    orcid: "https://orcid.org/0000-0002-3512-1350"
  title: "Reflectance spectroscopy and machine learning as a tool for the categorization of twin species based on the example of the Diachrysia genus"
  journal: "Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy"
  doi: "10.1016/j.saa.2022.121058"
  url: "https://www.sciencedirect.com/science/article/pii/S1386142522002062"
  volume: 273
  pages: 121058
  year: 2022
  month: 5

GitHub Events

Total

Last Year

Issues and Pull Requests

Last synced: 10 months ago

All Time

Total issues: 0
Total pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Total issue authors: 0
Total pull request authors: 0
Average comments per issue: 0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 0
Pull requests: 0
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 0
Pull request authors: 0
Average comments per issue: 0
Average comments per pull request: 0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science