PollenNet:一种通过深度学习和可解释的AI进行高精度花粉粒分类的新架构
F M Javed Mehedi Shamrat1, Mohd Yamani Idna Idris1, Xujuan Zhou2
1Department of Computer System and Technology, Universiti Malaya, Kuala Lumpur, 50603, Malaysia.
Heliyon
|October 21, 2024
概括
一个新的深度学习模型,PollenNet,准确地对花粉粒进行分类,这对环境和过敏研究至关重要. 这种先进的方法显著改进了现有的花粉识别技术.
科学领域:
- 植物学和环境科学 植物学和环境科学
- 计算机科学和人工智能 人工智能
- 生物技术和农业科学 生物技术和农业科学
背景情况:
- 精确的花粉粒分类对于环境,农业和过敏研究至关重要.
- 由于花粉的复杂结构和物种多样性,现有的分类方法面临着挑战.
- 需要先进的计算方法来克服传统花粉识别技术的局限性.
研究的目的:
- 引入和评估PollenNet,这是一个新的深度学习框架,用于增强花粉粒图像分类.
- 与现有的最先进的方法相比,为了证明PollenNet的优越性能.
- 提高生态和医疗应用中花粉识别的准确性和可靠性.
主要方法:
- 开发了PollenNet,这是一个用于花粉图像分类的深度学习框架.
- 实施了严格的数据准备管道,包括删除和图像校正.
- 利用可解释的人工智能 (XAI) 进行模型解释性和接收器操作特征 (ROC) 曲线分析以评估性能.
主要成果:
- 波伦网实现了高性能指标:98.45%的准确性,98.20%的精度,98.40%的特异性,98.30%的回忆力,98.25%的F1得分.
- 该模型显示出较低的误差率,平均平方误差 (MSE) 为0.03,平均绝对误差 (MAE) 为0.02.
- ROC分析证实了模型可靠性,低假阳性率 (FPR) 为0.016和假阴性率 (FNR) 为0.017.
结论:
- "花粉网"显著提高了花粉粒分类的准确性和可靠性.
- 深度学习框架为生态研究和过敏诊断提供了强大的工具.
- 这项工作突出了AI在解决生物和环境科学中复杂挑战方面的潜力.
相关概念视频
02:16Light Acquisition
8.4K
In order to produce glucose, plants need to capture sufficient light energy. Many modern plants have evolved leaves specialized for light acquisition. Leaves can be only millimeters in width or tens of meters wide, depending on the environment. Due to competition for sunlight, evolution has driven the evolution of increasingly larger leaves and taller plants, to avoid shading by their neighbors with contaminant elaboration of root architecture and mechanisms to transport water and nutrients.
8.4K
02:40Pollination and Flower Structure
63.5K
Flowers are the reproductive, seed-producing structures of angiosperms. Typically, flowers consist of sepals, petals, stamens, and carpels. Sepals and petals are the vegetative flower organs. Stamens and carpels are the reproductive organs.
63.5K
03:40Introduction to Seed Plants
60.9K
Most plants are seed plants—characterized by seeds, pollen, and reduced gametophytes. Seed plants include gymnosperms and angiosperms.
60.9K