Cargando…
Investigating Explanatory Factors of Machine Learning Models for Plant Classification
Recent progress in machine learning and deep learning has enabled the implementation of plant and crop detection using systematic inspection of the leaf shapes and other morphological characters for identification systems for precision farming. However, the models used for this approach tend to beco...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8708324/ https://www.ncbi.nlm.nih.gov/pubmed/34961145 http://dx.doi.org/10.3390/plants10122674 |
_version_ | 1784622655679234048 |
---|---|
author | Wöber, Wilfried Mehnen, Lars Sykacek, Peter Meimberg, Harald |
author_facet | Wöber, Wilfried Mehnen, Lars Sykacek, Peter Meimberg, Harald |
author_sort | Wöber, Wilfried |
collection | PubMed |
description | Recent progress in machine learning and deep learning has enabled the implementation of plant and crop detection using systematic inspection of the leaf shapes and other morphological characters for identification systems for precision farming. However, the models used for this approach tend to become black-box models, in the sense that it is difficult to trace characters that are the base for the classification. The interpretability is therefore limited and the explanatory factors may not be based on reasonable visible characters. We investigate the explanatory factors of recent machine learning and deep learning models for plant classification tasks. Based on a Daucus carota and a Beta vulgaris image data set, we implement plant classification models and compare those models by their predictive performance as well as explainability. For comparison we implemented a feed forward convolutional neuronal network as a default model. To evaluate the performance, we trained an unsupervised Bayesian Gaussian process latent variable model as well as a convolutional autoencoder for feature extraction and rely on a support vector machine for classification. The explanatory factors of all models were extracted and analyzed. The experiments show, that feed forward convolutional neuronal networks ([Formula: see text] and [Formula: see text] mean accuracy) outperforms the Bayesian Gaussian process latent variable pipeline ([Formula: see text] and [Formula: see text] mean accuracy) as well as the convolutional autoenceoder pipeline ([Formula: see text] and [Formula: see text] mean accuracy) based approaches in terms of classification accuracy, even though not significant for Beta vulgaris images. Additionally, we found that the neuronal network used biological uninterpretable image regions for the plant classification task. In contrast to that, the unsupervised learning models rely on explainable visual characters. We conclude that supervised convolutional neuronal networks must be used carefully to ensure biological interpretability. We recommend unsupervised machine learning, careful feature investigation, and statistical feature analysis for biological applications. |
format | Online Article Text |
id | pubmed-8708324 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-87083242021-12-25 Investigating Explanatory Factors of Machine Learning Models for Plant Classification Wöber, Wilfried Mehnen, Lars Sykacek, Peter Meimberg, Harald Plants (Basel) Article Recent progress in machine learning and deep learning has enabled the implementation of plant and crop detection using systematic inspection of the leaf shapes and other morphological characters for identification systems for precision farming. However, the models used for this approach tend to become black-box models, in the sense that it is difficult to trace characters that are the base for the classification. The interpretability is therefore limited and the explanatory factors may not be based on reasonable visible characters. We investigate the explanatory factors of recent machine learning and deep learning models for plant classification tasks. Based on a Daucus carota and a Beta vulgaris image data set, we implement plant classification models and compare those models by their predictive performance as well as explainability. For comparison we implemented a feed forward convolutional neuronal network as a default model. To evaluate the performance, we trained an unsupervised Bayesian Gaussian process latent variable model as well as a convolutional autoencoder for feature extraction and rely on a support vector machine for classification. The explanatory factors of all models were extracted and analyzed. The experiments show, that feed forward convolutional neuronal networks ([Formula: see text] and [Formula: see text] mean accuracy) outperforms the Bayesian Gaussian process latent variable pipeline ([Formula: see text] and [Formula: see text] mean accuracy) as well as the convolutional autoenceoder pipeline ([Formula: see text] and [Formula: see text] mean accuracy) based approaches in terms of classification accuracy, even though not significant for Beta vulgaris images. Additionally, we found that the neuronal network used biological uninterpretable image regions for the plant classification task. In contrast to that, the unsupervised learning models rely on explainable visual characters. We conclude that supervised convolutional neuronal networks must be used carefully to ensure biological interpretability. We recommend unsupervised machine learning, careful feature investigation, and statistical feature analysis for biological applications. MDPI 2021-12-05 /pmc/articles/PMC8708324/ /pubmed/34961145 http://dx.doi.org/10.3390/plants10122674 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Wöber, Wilfried Mehnen, Lars Sykacek, Peter Meimberg, Harald Investigating Explanatory Factors of Machine Learning Models for Plant Classification |
title | Investigating Explanatory Factors of Machine Learning Models for Plant Classification |
title_full | Investigating Explanatory Factors of Machine Learning Models for Plant Classification |
title_fullStr | Investigating Explanatory Factors of Machine Learning Models for Plant Classification |
title_full_unstemmed | Investigating Explanatory Factors of Machine Learning Models for Plant Classification |
title_short | Investigating Explanatory Factors of Machine Learning Models for Plant Classification |
title_sort | investigating explanatory factors of machine learning models for plant classification |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8708324/ https://www.ncbi.nlm.nih.gov/pubmed/34961145 http://dx.doi.org/10.3390/plants10122674 |
work_keys_str_mv | AT woberwilfried investigatingexplanatoryfactorsofmachinelearningmodelsforplantclassification AT mehnenlars investigatingexplanatoryfactorsofmachinelearningmodelsforplantclassification AT sykacekpeter investigatingexplanatoryfactorsofmachinelearningmodelsforplantclassification AT meimbergharald investigatingexplanatoryfactorsofmachinelearningmodelsforplantclassification |