呼吸疾病呼吸音分类跨数据集泛化性能数据集
包含两个呼吸音临床数据集，用于评估多模态深度学习模型E-RespiNet在呼吸系统疾病诊断中的泛化性能，涵盖五种疾病状态，准确率达98.9%。
基本信息
资源简介
呼吸疾病呼吸音分类跨数据集泛化性能数据集
【数据集背景】
本数据集源站标题为《Cross-dataset generalization performance.》。源站首次发布：2025-11-04。
【数据内容】
源站原始描述：Respiratory disease diagnosis remains challenging in resource-constrained settings, where limited specialist expertise contributes to diagnostic uncertainties affecting over 300 million people worldwide. This study presents E-RespiNet, a novel multi-modal deep learning architecture that integrates ELECTRA’s discriminative pre-training with a triple-stream convolutional neural network framework, enhanced through Harmony Search with Opposition-Based Learning optimization for automated respiratory…
【数据结构与技术规格】
文件数 1 个，合计 5.63 KB。Table 6.xls：application/vnd.ms-excel，5.63 KB。数据集 DOI：10.1371/journal.pone.0334528.t006。
【主题与分类】
源站学科分类：Space Science、Medicine、Sociology、Biological Sciences not elsewhere classified、Information Systems not elsewhere classified、Cancer。主题标签：frequency cepstral coefficients、establishing important benchmarks、discrete wavelet transforms、diagnostic uncertainties affecting、based contextual enhancement、parallel cnn streams、based learning optimization、study presents e、demonstrated exceptional performance、electra driven triple。
【适用方向】
音频数据可用于声学信号分析建模，如语音与呼吸音相关研究。
【获取与许可】
源站页面：https://plos.figshare.com/articles/dataset/Cross-dataset_generalization_performance_/30534320
使用许可：CC BY 4.0（https://creativecommons.org/licenses/by/4.0/）。
规范引用：Tawfik, Mohammed; Fathi, Islam S.; Nimbhore, Sunil S.; Alsmadi, Issa M.; Sawah, Mohamed S. (2025). Cross-dataset generalization performance.. PLOS ONE. Dataset
下载信息
注册下载
需要注册 Kaggle 账号并登录后下载，适合需要跟踪下载记录和使用 API 的用户。
暂未开放公开下载
无需注册即可直接获取公开样本或文档，适合快速预览和评估数据集质量。
免登录有偿下载
公开数据集受托下载与技术交付服务。
提供高速下载与技术交付服务（收技术服务费，非数据销售）
暂未开放当前数据集主要来源为 Kaggle 公开托管，完整影像包建议通过原始链接或 Kaggle API 获取。
使用方式
数据集获取（Figshare）
- 源站标题：Cross-dataset generalization performance.
- DOI：10.1371/journal.pone.0334528.t006
- 发布日期：2025-11-04
- 文件数：1 个
- 文件总体积：5.63 KB
- 源站页面：https://plos.figshare.com/articles/dataset/Cross-dataset_generalization_performance_/30534320
命令行下载
curl -L -o "Table 6.xls" "https://ndownloader.figshare.com/files/59300072"
文件清单
Table 6.xls（5.63 KB）
文件总体积 5.63 KB（源站 API 实测）。
数据说明
Respiratory disease diagnosis remains challenging in resource-constrained settings, where limited specialist expertise contributes to diagnostic uncertainties affecting over 300 million people worldwide. This study presents E-RespiNet, a novel multi-modal deep learning architecture that integrates ELECTRA’s discriminative pre-training with a triple-stream convolutional neural network framework, enhanced through Harmony Search with Opposition-Based Learning optimization for automated respiratory sound classification. The architecture simultaneously processes mel-frequency cepstral coefficients, discrete wavelet transforms, and mel-spectrograms through parallel CNN streams, with features integrated through hierarchical fusion and ELECTRA-based contextual enhancement. Comprehensive evaluations on two independent clinical datasets—the Asthma Detection Dataset Version 2 (1,211 recordings across five conditions) and King Abdullah University Hospital dataset (940 samples from 81 subjects across four conditions)—demonstrated exceptional performance with 98.9% and 98.8% accuracy respectively, representing 5.0% and 4.3% improvements over baseline configurations. Cross-institutional validation revealed 75.7% average accuracy with a 23.3% generalization gap, substantially better than typical medical AI cross-domain performance. Gradient-weighted class activation mapping provided clinically relevant interpretability, while the Harmony Search optimization framework enhanced both performance and cross-institutional robustness. These results demonstrate significant advances in automated respiratory sound analysis through discriminative language model integration and metaheuristic optimization, establishing important benchmarks for deployable respiratory diagnostic tools in diverse healthcare settings.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.1371/journal.pone.0334528.t006（source: https://plos.figshare.com/articles/dataset/Cross-dataset_generalization_performance_/30534320）。
数据缺失？
依托陕西、四川两大基地，我们与超过十家三甲医院建立直接合作关系，覆盖合规授权、采集治理、专业标注、数据交付的全流程，为AI医疗团队提供即拿即用的高质量临床数据。
⚡️ 需要数据支持或标注服务？立即联系我们获取专业方案。
