Application of BP neural network model in Iris classification
DOI:
https://doi.org/10.54097/7fkge937Keywords:
BP neural network, iris classification, UCI dataset warehouse, horticultural variety screening.Abstract
In the field of machine learning, iris classification is a classic problem of pattern recognition, and its accurate identification is of great significance to botanical research, ecological protection and horticultural practice, but the existing methods have shortcomings such as complex computation and insufficient generalization ability. The BP neural network model constructed in this paper solves the problem of iris classification prediction, and a stable iris classification prediction model is trained, which effectively fits the mapping relationship between features and categories through the nonlinear transformation of multi-layer neurons. After pretreatment and multiple rounds of training, the model achieved an accuracy rate of 0.91 and an F1 score of 0.86 on the test set, indicating that it could reliably distinguish iris varieties. This study provides efficient classification tools and optimization ideas for practitioners in the fields of horticultural variety screening, botanical classification statistics, and ecological survey.
Downloads
References
[1] Zewen Hu, Jingjing Cui, Angela Lin, Identifying potentially excellent publications using a citation-based machine learning approach [J]. ScienceDirect, 2023-05-01.
[2] Liu Ying, Zhang Zhe, Li Xiangyu, et al. Creation of Butterfly Diversity Habitat Environment Mainly Flowering Plants [J]. Sichuan Forestry Science and Technology, 2023, 44 (3): 54−63.
[3] Cheng Lin, Feng Shucheng, Xiao Yue'e, et al. Research progress on molecular phylogeny of Iris [J]. Guangxi Botany, 2021, 41 (1): 31-39.
[4] He Dasi, Jin Luqi, Zhang Zuming, et al. Improvement of BP neural network regression prediction model [J]. Mechanical Engineering and Automation, 2025, 54 (01): 224-226.
[5] Chen Xiyuan. Research on Iris Classification Problem Based on BP Neural Network Model [J]. New Generation Information Technology, 2022, 5 (5): 146-148.
[6] Zhou Junbo, Liu Guangrong, Zeng Shan. Application of improved BP neural network in irises classification and recognition [J]. Journal of Wuhan University of Light Industry, 2021, 40 (6): 41-46.
[7] Wu Yinting. An Adversarial Training Framework for Initializing Noise Design and Sample Selection [D]. Central China Normal University, 2024.
[8] Chang Xilong, Liang Kun, Li Wentao. Computer Engineering and Applications, 2024,60 (07): 1-12.
[9] Xu Duo. Discussion on Database Query Performance Optimization Method Based on Machine Learning [J]. Information and Computer, 2025, 37 (08): 176-178.
[10] Xiong Kuan. Research on Text Classification Method Based on Deep Learning and Attention Mechanism [D]. Jiangxi Normal University, 2020.
[11] Fan Wei, Kong Qiuyue, Hu Jie, et al. Screening of mulberry germplasm resources suitable for high-calcium environment [J]. Journal of Southwest University (Natural Science Edition), 2024, 46 (10): 90-98.
[12] Introduction to the ecological investigation, evaluation and restoration project of granite weathered shell rare earth ore of the National Geological Experiment and Testing Center of the China Geological Survey [J]. China Geology, 2025, 52 (03): 768.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Highlights in Science, Engineering and Technology
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
