Phenotype-based chrysanthemum petal classification, integrated with genomic sequencing, is critical for studying chrysanthemum phenotypic taxonomy. In this article, a new pipeline has been established towards automatic classification of chrysanthemum flower petal types. First, a set of phenotypic data of chrysanthemum flowers was collected. Second, we adopted random forest to classify the chrysanthemum flower petal types, and adopted over-sampling techniques to address the imbalanced label problem. Third, we systematically evaluated feature combinations regarding their influences to the classification results. Experimental results show that our method can successfully classify chrysanthemum flower petal types on an imbalanced chrysanthemum data.
|Title of host publication||Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018|
|Editors||Harald Schmidt, David Griol, Haiying Wang, Jan Baumbach, Huiru Zheng, Zoraida Callejas, Xiaohua Hu, Julie Dickerson, Le Zhang|
|Number of pages||4|
|State||Published - Jan 21 2019|
|Event||2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018 - Madrid, Spain|
Duration: Dec 3 2018 → Dec 6 2018
|Name||Proceedings - 2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018|
|Conference||2018 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2018|
|Period||12/3/18 → 12/6/18|
Bibliographical noteFunding Information:
This work is supported by NSFC grants (No.61502236), the Fundamental Research Funds for the Central Universities(No.KYZ201752), and National Science Foundation ABI program (No.1458556).
© 2018 IEEE.
- imbalanced data
- phenotypic classification
- random forest
ASJC Scopus subject areas
- Biomedical Engineering
- Health Informatics