Search research articles

关于 JoVE

概览领导团队博客 JoVE 帮助中心

作者

出版流程编辑委员会范围与政策同行评审常见问题投稿

图书馆员

用户评价订阅访问资源图书馆顾问委员会常见问题

研究

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序

Same author

EAACI Guidelines on Environmental Science for Allergy and Asthma-Evidence-Based Recommendations for Prevention and Public Health Action to Mitigate the Impact of Pollen Exposure on Respiratory Allergy.

Allergy·2026

Same author

Listening to MS: AI-assisted speech analysis for diagnosis and fatigue prediction (COMMITMENT).

Frontiers in digital health·2026

Same author

Prior-aligned frequency-domain explanations for heart sound classification: a scale-consistent attribution approach.

Frontiers in artificial intelligence·2026

Same author

Ozone alters the allergenicity of Ambrosia artemisiifolia pollen in a dose-dependent manner.

Environment international·2026

Same author

Defining in vivo and in vitro models for evaluating the sensitising potential of birch pollen extracts.

Allergology international : official journal of the Japanese Society of Allergology·2026

Same author

Explainable detection of machine generated music and early systematic evaluation.

Scientific reports·2026

Same journal

Novel Parent Survey Measures Sensory Behaviors Incorporating Sensory Modality and Stimulus Intensity.

Heliyon·2026

Same journal

Expression of concern: "SQSTM1/p62 promotes the progression of gastric cancer through epithelial-mesenchymal transition" [Heliyon 10 (2024) e24409].

Heliyon·2026

Same journal

Expression of concern: "TL1A promotes metastasis and EMT process of colorectal cancer" [Heliyon 10 (2024) e24392].

Heliyon·2026

Same journal

Expression of concern: "Factors affecting timing of surgery following neoadjuvant chemoradiation for esophageal cancer" [Heliyon 9 (2023) e23212].

Heliyon·2026

Same journal

Expression of concern: "On stratified single-valued soft topogenous structures" [Heliyon 10 (2024) e27926].

Heliyon·2026

Same journal

Expression of concern: "Artifact removal and motor imagery classification in EEG using advanced algorithms and modified DNN" [Heliyon 10 (2024) e27198].

Heliyon·2026

查看所有相关文章

Search research articles

相关实验视频

Updated: May 29, 2025

Collection and Identification of Pollen from Honey Bee Colonies

Collection and Identification of Pollen from Honey Bee Colonies

Published on: January 19, 2021

自动化空气中花粉分类:为分类器识别和解释硬样本.

Manuel Milling^1,2,3, Simon D N Rampp³, Andreas Triantafyllopoulos^1,2,3

¹CHI - Chair of Health Informatics, MRI, Technical University of Munich, Munich, Germany.

|February 3, 2025

概括

此摘要是机器生成的。

对于花粉分类的深度学习面临的挑战包括每张图像的多个粒,标记器封闭和模糊的特征. 了解这些问题是改善自动空中花粉监测系统的关键.

关键词:

深度学习是一种深度学习.识别花粉的识别方法样本难度分析的分析

更多相关视频

Collection and Extraction of Occupational Air Samples for Analysis of Fungal DNA

Collection and Extraction of Occupational Air Samples for Analysis of Fungal DNA

Published on: May 2, 2018

Composition and Distribution Analysis of Bioaerosols Under Different Environmental Conditions

Composition and Distribution Analysis of Bioaerosols Under Different Environmental Conditions

Published on: January 7, 2019

相关实验视频

Last Updated: May 29, 2025

Collection and Identification of Pollen from Honey Bee Colonies

Collection and Identification of Pollen from Honey Bee Colonies

Published on: January 19, 2021

Collection and Extraction of Occupational Air Samples for Analysis of Fungal DNA

Collection and Extraction of Occupational Air Samples for Analysis of Fungal DNA

Published on: May 2, 2018

Composition and Distribution Analysis of Bioaerosols Under Different Environmental Conditions

Composition and Distribution Analysis of Bioaerosols Under Different Environmental Conditions

Published on: January 7, 2019

科学领域:

环境科学环境科学
计算机科学计算机科学
植物学植物学

背景情况:

自动监测空气中的花粉对于过敏管理和生态研究至关重要.
深度学习模型在花粉粒分类方面表现有前途,但它们的性能局限性尚未得到充分理解.

研究的目的:

识别和分析阻碍基于深度学习的花粉分类准确性的关键挑战.
调查为什么某些花粉样本和种群对深度学习算法来说特别困难.

主要方法:

从显微镜图像中对大量自动生成的花粉粒数据集进行了样本级难度分析.
利用基于概率的指标来评估单个样本和种类的分类难度.

主要成果:

确定了三个主要的挑战: (A) 在单个图像中同时出现多个花粉粒, (B) 在二维显微镜图像中遮住花粉标记,以及 (C) 在某些花粉种群中缺乏独特的突出特征.
分析揭示了深度学习模型中分类错误的具体原因.

结论:

解决像图像复杂性,特征封闭和固有的特征变化等挑战对于在自动花粉监测中推进深度学习至关重要.
这些发现为开发更强大,更准确的花粉分类算法提供了洞察力.