摘要
本研究致力于提升深度学习在肺音分析领域的应用效率和准确性.针对现有深度学习模型在肺音分析中表现出的鲁棒性不足和泛化能力有限的问题,本研究提出了一种方法,该方法通过整合卷积神经网络(convolutional neural network,CNN)、长短时记忆(long short-term memory,LSTM)网络和支持向量机(SVM),实现了对肺音信号的高效和深入分析.首先对肺音信号进行预处理,提取出重构信号和其对应的希尔伯特谱图;其次设计并构建了一个集成CNN、LSTM和SVM的深度学习网络模型;最后将处理后的信号数据输入到CNN-LSTM-SVM的深度学习网络中,以提取并融合肺音信号的时域和频域特征.实验结果表明,该方法在召回率、精确率和F1-score这3个关键性能指标上分别达到96.20%、96.56%和0.96的高水平.这些结果证实了所提方法的高效性和可靠性,为肺部疾病的早期诊断提供了一种技术途径,并有潜力显著提升临床诊断的速度和准确性.
This study is dedicated to enhancing the application efficiency and accuracy of deep learning in lung sound analysis.In view of the insufficient robustness and limited generalization capabilities of existing deep learning models in lung sound analysis,it proposes a method that integrates the convolutional neural networks(CNN),long short-term memory network(LSTM),and support vector machine(SVM)to achieve efficient and in-depth analysis of lung sound signals.The method begins with the preprocessing of lung sound signals to extract reconstructed signals and their corresponding Hilbert spectra.Secondly,a deep learning network model that integrates CNN,LSTM,and SVM is designed and built.Finally,the processed signal data are input into the CNN-LSTM-SVM deep learning network to extract and fuse the time-domain and frequency-domain features of lung sound signals.Experimental results show that the method achieves high levels of 96.20%for the recall,96.56%for accuracy,and 0.96 for F1-score.These results confirm the efficiency and reliability of the proposed method,providing a new technological approach for the early diagnosis of lung diseases,and potentially significantly enhancing the speed and accuracy of clinical diagnosis.
作者
赵静
杜永飞
韦海成
张志鹏
许洋
ZHAO Jing;DU Yong-Fei;WEI Hai-Cheng;ZHANG Zhi-Peng;XU Yang(School of Information Engineering,Ningxia University,Yinchuan 750021,China;School of Medical Technology,North Minzu University,Yinchuan 750021,China;School of Electrical and Information Engineering,North Minzu University,Yinchuan 750021,China)
出处
《计算机系统应用》
2026年第1期219-227,共9页
Computer Systems & Applications
基金
宁夏回族自治区自然科学基金(2022AAC03006)
宁夏先进智能感知与控制技术创新团队支持计划。
关键词
肺音分析
特征融合
变分模态分解
卷积神经网络
长短时记忆网络
支持向量机
lung sound analysis
feature fusion
variational mode decomposition
convolutional neural network(CNN)
long short-term memory(LSTM)network
support vector machine(SVM)
