Next generation insect taxonomic classification by comparing different deep learning algorithms
Insect taxonomy lies at the heart of many aspects of ecology, and identification tasks are challenging due to the enormous inter- and intraspecies variation of insects. Conventional methods used to study insect taxonomy are often tedious, time-consuming, labor intensive, and expensive, and recently,...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
Plos One
2022
|
| Subjects: | |
| Online Access: | https://eprints.ums.edu.my/id/eprint/35440/1/ABSTRACT.pdf https://eprints.ums.edu.my/id/eprint/35440/2/FULL%20TEXT.pdf |
| _version_ | 1796911750200688640 |
|---|---|
| author | Song-Quan Ong Suhaila Ab. Hamid |
| author_facet | Song-Quan Ong Suhaila Ab. Hamid |
| author_sort | Song-Quan Ong |
| collection | UMS |
| description | Insect taxonomy lies at the heart of many aspects of ecology, and identification tasks are challenging due to the enormous inter- and intraspecies variation of insects. Conventional methods used to study insect taxonomy are often tedious, time-consuming, labor intensive, and expensive, and recently, computer vision with deep learning algorithms has offered an alternative way to identify and classify insect images into their taxonomic levels. We designed the classification task according to the taxonomic ranks of insects—order, family, and genus—and compared the generalization of four state-of-the-art deep convolutional neural network (DCNN) architectures. The results show that different taxonomic ranks require different deep learning (DL) algorithms to generate high-performance models, which indicates that the design of an automated systematic classification pipeline requires the integration of different algorithms. The InceptionV3 model has advantages over other models due to its high performance in distinguishing insect order and family, which is having F1- score of 0.75 and 0.79, respectively. Referring to the performance per class, Hemiptera (order), Rhiniidae (family), and Lucilia (genus) had the lowest performance, and we discuss the possible rationale and suggest future works to improve the generalization of a DL model for taxonomic rank classification.. |
| first_indexed | 2024-03-06T03:23:18Z |
| format | Article |
| id | ums.eprints-35440 |
| institution | Universiti Malaysia Sabah |
| language | English English |
| last_indexed | 2024-03-06T03:23:18Z |
| publishDate | 2022 |
| publisher | Plos One |
| record_format | dspace |
| spelling | ums.eprints-354402023-05-22T02:37:37Z https://eprints.ums.edu.my/id/eprint/35440/ Next generation insect taxonomic classification by comparing different deep learning algorithms Song-Quan Ong Suhaila Ab. Hamid Q1-295 General QL461-599.82 Insects Insect taxonomy lies at the heart of many aspects of ecology, and identification tasks are challenging due to the enormous inter- and intraspecies variation of insects. Conventional methods used to study insect taxonomy are often tedious, time-consuming, labor intensive, and expensive, and recently, computer vision with deep learning algorithms has offered an alternative way to identify and classify insect images into their taxonomic levels. We designed the classification task according to the taxonomic ranks of insects—order, family, and genus—and compared the generalization of four state-of-the-art deep convolutional neural network (DCNN) architectures. The results show that different taxonomic ranks require different deep learning (DL) algorithms to generate high-performance models, which indicates that the design of an automated systematic classification pipeline requires the integration of different algorithms. The InceptionV3 model has advantages over other models due to its high performance in distinguishing insect order and family, which is having F1- score of 0.75 and 0.79, respectively. Referring to the performance per class, Hemiptera (order), Rhiniidae (family), and Lucilia (genus) had the lowest performance, and we discuss the possible rationale and suggest future works to improve the generalization of a DL model for taxonomic rank classification.. Plos One 2022 Article PeerReviewed text en https://eprints.ums.edu.my/id/eprint/35440/1/ABSTRACT.pdf text en https://eprints.ums.edu.my/id/eprint/35440/2/FULL%20TEXT.pdf Song-Quan Ong and Suhaila Ab. Hamid (2022) Next generation insect taxonomic classification by comparing different deep learning algorithms. Insect taxonomic classification by deep learning algorithms. pp. 1-11. https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0279094 https://doi.org/10.1371/journal.pone.0279094 https://doi.org/10.1371/journal.pone.0279094 |
| spellingShingle | Q1-295 General QL461-599.82 Insects Song-Quan Ong Suhaila Ab. Hamid Next generation insect taxonomic classification by comparing different deep learning algorithms |
| title | Next generation insect taxonomic classification by comparing different deep learning algorithms |
| title_full | Next generation insect taxonomic classification by comparing different deep learning algorithms |
| title_fullStr | Next generation insect taxonomic classification by comparing different deep learning algorithms |
| title_full_unstemmed | Next generation insect taxonomic classification by comparing different deep learning algorithms |
| title_short | Next generation insect taxonomic classification by comparing different deep learning algorithms |
| title_sort | next generation insect taxonomic classification by comparing different deep learning algorithms |
| topic | Q1-295 General QL461-599.82 Insects |
| url | https://eprints.ums.edu.my/id/eprint/35440/1/ABSTRACT.pdf https://eprints.ums.edu.my/id/eprint/35440/2/FULL%20TEXT.pdf |
| work_keys_str_mv | AT songquanong nextgenerationinsecttaxonomicclassificationbycomparingdifferentdeeplearningalgorithms AT suhailaabhamid nextgenerationinsecttaxonomicclassificationbycomparingdifferentdeeplearningalgorithms |