|
|
基于多模态特征融合与集成学习的心音信号分类研究
|
Abstract:
针对心音分类中存在的数据不平衡、特征提取不足与模型泛化能力有限等问题，本文提出了一种基于多模态特征融合与高级集成学习的心音异常检测方法。首先，采用Challenge2016数据集，通过带通滤波与归一化预处理，并提出异常类别导向的数据增强策略以解决样本不平衡问题。其次，综合提取时域统计、频域谱质心及小波域能量熵等多维特征，构建全方位特征空间。在模型构建上，设计了CNN-BiLSTM深度神经网络以捕捉局部与长时依赖特征，并结合支持向量机(SVM)的稳定性优势。最后，提出包含动态加权、置信度加权及元学习等六种集成策略。实验结果表明，元学习集成策略性能最佳，准确率达98.89%，F1-score为0.9872。该方法在保证高精度的同时也具备良好的鲁棒性，为心脏瓣膜疾病的智能诊断提供了有效方案。
To address the challenges of data imbalance, insufficient feature extraction, and limited model generalization in heart sound classification, this paper proposes a heart sound anomaly detection method based on multi-modal feature fusion and advanced ensemble learning. Firstly, using the Challenge2016 dataset, data preprocessing including band-pass filtering and normalization is applied, and an anomaly-oriented data augmentation strategy is proposed to mitigate sample imbalance. Secondly, multi-dimensional features, including time-domain statistics, frequency-domain spectral centroid, and wavelet-domain energy entropy, are extracted to construct a comprehensive feature space. In terms of model construction, a CNN-BiLSTM deep neural network is designed to capture local and long-term dependency features, combined with the stability of Support Vector Machine (SVM). Finally, six ensemble strategies, including dynamic weighting, confidence weighting, and meta-learning, are proposed. Experimental results show that the meta-learning ensemble strategy performs the best, with an accuracy of 98.89% and an F1-score of 0.9872. This method ensures high accuracy while maintaining good robustness, providing an effective solution for intelligent diagnosis of valvular heart diseases.
| [1] | 张文波. 心音图在慢性收缩性心力衰竭患者中诊断价值的研究[D]: [硕士学位论文]. 杭州: 浙江大学, 2013. |
| [2] | Marcus, G., Vessey, J., Jordan, M.V., Huddleston, M., McKeown, B., Gerber, I.L., et al. (2006) Relationship between Accurate Auscultation of a Clinically Useful Third Heart Sound and Level of Experience. Archives of Internal Medicine, 166, 617-622. https://doi.org/10.1001/archinte.166.6.617 |
| [3] | Lehmann, S.J. (1972) Auscultation of Heart Sounds. AJN, American Journal of Nursing, 72, 1242-1246. https://doi.org/10.1097/00000446-197207000-00030 |
| [4] | Yupapin, P., Wardkein, Yupapin, P., Phanphaisarn, Koseeyaporn, Roeksabutr, et al. (2011) Heart Detection and Diagnosis Based on ECG and EPCG Relationships. Medical Devices: Evidence and Research, 2011, 133-144. https://doi.org/10.2147/mder.s23324 |
| [5] | Liang, H. and Nartimo, I. (1998) A Feature Extraction Algorithm Based on Wavelet Packet Decomposition for Heart Sound Signals. Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis (Cat. No.98TH8380), Pittsburgh, 9 October 1998, 93-96. https://doi.org/10.1109/tfsa.1998.721369 |
| [6] | Springer, D., Tarassenko, L. and Clifford, G. (2015) Logistic Regression-HSMM-Based Heart Sound Segmentation. IEEE Transactions on Biomedical Engineering, 63, 822-832. https://doi.org/10.1109/tbme.2015.2475278 |
| [7] | Yaseen, Son, G. and Kwon, S. (2018) Classification of Heart Sound Signal Using Multiple Features. Applied Sciences, 8, 2344. https://doi.org/10.3390/app8122344 |
| [8] | Raza, A., Mehmood, A., Ullah, S., Ahmad, M., Choi, G.S. and On, B. (2019) Heartbeat Sound Signal Classification Using Deep Learning. Sensors, 19, Article 4819. https://doi.org/10.3390/s19214819 |
| [9] | Khan, K.N., Khan, F.A., Abid, A., Olmez, T., Dokur, Z., Khandakar, A., et al. (2021) Deep Learning Based Classification of Unsegmented Phonocardiogram Spectrograms Leveraging Transfer Learning. Physiological Measurement, 42, Article ID: 095003. https://doi.org/10.1088/1361-6579/ac1d59 |
| [10] | Chen, H. and Gu, W.Y. (2025) A Dual Branch Feature Extraction Network for Heart Sound Signal Analysis. Scientific Reports, 15, Article No. 27557. https://doi.org/10.1038/s41598-025-12303-0 |
| [11] | Sun, S., Wang, H., Jiang, Z., Fang, Y. and Tao, T. (2014) Segmentation-Based Heart Sound Feature Extraction Combined with Classifier Models for a VSD Diagnosis System. Expert Systems with Applications, 41, 1769-1780. https://doi.org/10.1016/j.eswa.2013.08.076 |
| [12] | Li, F., Liu, M., Zhao, Y., Kong, L., Dong, L., Liu, X., et al. (2019) Feature Extraction and Classification of Heart Sound Using 1D Convolutional Neural Networks. EURASIP Journal on Advances in Signal Processing, 2019, Article No. 59. https://doi.org/10.1186/s13634-019-0651-3 |
| [13] | Guven, M. and Uysal, F. (2023) A New Method for Heart Disease Detection: Long Short-Term Feature Extraction from Heart Sound Data. Sensors, 23, Article 5835. https://doi.org/10.3390/s23135835 |
| [14] | Chauhan, V.K., Dahiya, K. and Sharma, A. (2018) Problem Formulations and Solvers in Linear SVM: A Review. Artificial Intelligence Review, 52, 803-855. https://doi.org/10.1007/s10462-018-9614-6 |
| [15] | Zha, W., Liu, Y., Wan, Y., Luo, R., Li, D., Yang, S., et al. (2022) Forecasting Monthly Gas Field Production Based on the CNN-LSTM Model. Energy, 260, Article ID: 124889. https://doi.org/10.1016/j.energy.2022.124889 |
| [16] | He, K., Gkioxari, G., Dollar, P. and Girshick, R. (2017) Mask R-CNN. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 2980-2988. https://doi.org/10.1109/iccv.2017.322 |
| [17] | Ganaie, M.A., Hu, M., Malik, A.K., Tanveer, M. and Suganthan, P.N. (2022) Ensemble Deep Learning: A Review. Engineering Applications of Artificial Intelligence, 115, Article ID: 105151. https://doi.org/10.1016/j.engappai.2022.105151 |
| [18] | Xiao, Y., Wu, J., Lin, Z. and Zhao, X. (2018) A Deep Learning-Based Multi-Model Ensemble Method for Cancer Prediction. Computer Methods and Programs in Biomedicine, 153, 1-9. https://doi.org/10.1016/j.cmpb.2017.09.005 |
| [19] | Fernando, K.R.M. and Tsokos, C.P. (2022) Dynamically Weighted Balanced Loss: Class Imbalanced Learning and Confidence Calibration of Deep Neural Networks. IEEE Transactions on Neural Networks and Learning Systems, 33, 2940-2951. https://doi.org/10.1109/tnnls.2020.3047335 |
| [20] | Dredze, M., Crammer, K. and Pereira, F. (2008) Confidence-Weighted Linear Classification. Proceedings of the 25th International Conference on Machine Learning—ICML’08, Helsinki, 5-9 July 2008, 264-271. https://doi.org/10.1145/1390156.1390190 |
| [21] | Douglas, J.M. (1985) A Hierarchical Decision Procedure for Process Synthesis. AIChE Journal, 31, 353-362. https://doi.org/10.1002/aic.690310302 |
| [22] | Vilalta, R. and Drissi, Y. (2002) A Perspective View and Survey of Meta-Learning. Artificial Intelligence Review, 18, 77-95. https://doi.org/10.1023/a:1019956318069 |
| [23] | Jafar, U., Aziz, M.J.A. and Shukur, Z. (2021) Blockchain for Electronic Voting System—Review and Open Research Challenges. Sensors, 21, Article 5874. https://doi.org/10.3390/s21175874 |
| [24] | Heydarian, M., Doyle, T.E. and Samavi, R. (2022) MLCM: Multi-Label Confusion Matrix. IEEE Access, 10, 19083-19095. https://doi.org/10.1109/access.2022.3151048 |
| [25] | Ahsan, M., Mahmud, M., Saha, P., Gupta, K. and Siddique, Z. (2021) Effect of Data Scaling Methods on Machine Learning Algorithms and Model Performance. Technologies, 9, Article 52. https://doi.org/10.3390/technologies9030052 |
| [26] | Clifford, G.D., Liu, C., Moody, B., et al. (2016) Classification of Normal/Abnormal Heart Sound Recordings: The PhysioNet/Computing in Cardiology Challenge 2016. 2016 Computing in Cardiology Conference (CinC), IEEE, Vol. 43, 609-612. https://doi.org/10.22489/CinC.2016.179-154 |
| [27] | Messer, S.R., Agzarian, J. and Abbott, D. (2001) Optimal Wavelet Denoising for Phonocardiograms. Microelectronics Journal, 32, 931-941. https://doi.org/10.1016/s0026-2692(01)00095-7 |
| [28] | Cheng, J. and Sun, K. (2023) Heart Sound Classification Network Based on Convolution and Transformer. Sensors, 23, Article 8168. https://doi.org/10.3390/s23198168 |
| [29] | Deng, M., Meng, T., Cao, J., Wang, S., Zhang, J. and Fan, H. (2020) Heart Sound Classification Based on Improved MFCC Features and Convolutional Recurrent Neural Networks. Neural Networks, 130, 22-32. https://doi.org/10.1016/j.neunet.2020.06.015 |
