|
|
基于改进的LSTM-CNN高血压组合预测模型
|
Abstract:
据国内外研究表明，高血压是危害人生命健康的重要疾病，如何及时的对血压升高进行预警成为一个研究的热点问题。为解决这一问题提出了一种融合注意力(Attention)机制的长–短期记忆网络(Long Short-Term Memory, LSTM)–卷积神经网络(Convolutional Neural Network, CNN)短期血压预测方法，该方法可以减少历史信息的丢失，实现短期血压预测。将此预测方法与单一的LSTM模型、CNN模型和LSTM-CNN组合模型进行对比，实验采用均方根误差(RMSE)、平均绝对误差(Mean Absolute Error, MAE)和平均绝对百分比误差(MAPE)对其进行评价，结果我们的方法误差最小，预测准确度最高，验证了我们模型的有效性和可扩展性。
According to studies at home and abroad, hypertension is an important disease endangering peo-ple’s life and health. How to give early warning of high blood pressure has become a hot issue. To solve this problem, a short-term blood pressure prediction method based on long short-term memory (LSTM)-convolutional neural network (CNN) and attention mechanism is proposed. This method can reduce the loss of historical information and achieve short-term blood pressure pre-diction. This prediction method is compared with single LSTM model, CNN model and LSTM-CNN combination model. Root mean square error (RMSE), mean absolute error (MAE) and mean abso-lute percentage error (MAPE) are used to evaluate this prediction method. As a result, our method has the smallest error and the highest prediction accuracy, which verifies the effectiveness and scalability of our model.
| [1] | Su, P., Ding, X., Zhang, Y., Liu, J., Miao, F. and Zhao, N. (2018) Long-Term Blood Pressure Prediction with Deep Recurrent Neural Networks. 2018 IEEE EMBS International Conference on Biomedical & Health Informatics, Las Vegas, 4-7 March 2018, 323-328. https://doi.org/10.1109/BHI.2018.8333434 |
| [2] | El-Hajj, C. and Kyriacou, P.A. (2021) Deep Learning Models for Cuffless Blood Pressure Monitoring from PPG Signals Using Attention Mechanism. Biomedical Signal Processing and Control, 65, Article ID: 102301.
https://doi.org/10.1016/j.bspc.2020.102301 |
| [3] | Lo, F.P., Li, C.X., Wang, J., Cheng, J. and Meng, M.Q. (2017) Continuous Systolic and Diastolic Blood Pressure Estimation Utilizing Long Short-Term Memory Network. 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Jeju, 11-15 July 2017, 1853-1856.
https://doi.org/10.1109/EMBC.2017.8037207 |
| [4] | Kurylyak, Y., Barbe, K., Lamonaca, F., Grimaldi, D. and Van Moer, W. (2013) Photoplethysmogram-Based Blood Pressure Evaluation Using Kalman Filtering and Neural Networks. 2013 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Gatineau, 4-5 May 2013, 170-174.
https://doi.org/10.1109/MeMeA.2013.6549729 |
| [5] | Peter, L., Noury, N. and Cerny, M. (2014) A Review of Methods for Non-Invasive and Continuous Blood Pressure Monitoring: Pulse Transit Time Method Is Promising? IRBM, 35, 271-282. https://doi.org/10.1016/j.irbm.2014.07.002 |
| [6] | Li, X.H., Wu, S. and Wang, L. (2017) Blood Pressure Prediction via Recurrent Models with Contextual Layer. Proceedings of the 26th International Conference on World Wide Web, Perth, 3-7 April 2017, 685-693.
https://doi.org/10.1145/3038912.3052604 |
| [7] | Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780.
https://doi.org/10.1162/neco.1997.9.8.1735 |
| [8] | 郭蕴颖, 丁云峰. 基于CNN和LSTM联合预测并修正的电量缺失数据预测[J]. 计算机系统应用, 2020, 29(8): 192-198. |
| [9] | Fischer, T. and Krauss, C. (2017) Deep Learning with Long Short-Term Memory Networks for Financial Market Predictions. European Journal of Operational Research, 270, 654-669. https://doi.org/10.1016/j.ejor.2017.11.054 |
| [10] | 胡晓丽, 张会兵, 董俊超, 吴冬强. 基于CNN-LSTM的用户购买行为预测模型[J]. 计算机应用与软件, 2020, 37(6): 59-64. |
| [11] | Johnson, M., Schuster, M., Le, Q.V., Krikun, M., Wu, Y., Chen, Z., et al. (2017) Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation. Transactions of the Association for Computational Linguistics, 5, 339-351. https://doi.org/10.1162/tacl_a_00065 |
| [12] | Xu, K., Ba, J., Kiros, R., Courville, A., Salakhutdinov, R., Zemel, R. and Bengio, Y. (2015) Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. arXiv:1502.03044. |
| [13] | Chorowski, J., Bahdanau, D., Serdyuk, D., Cho, K. and Bengio, Y. (2015) Attention-Based Models for Speech Recognition. Proceedings of the 28th International Conference on Neural Information Processing Systems, Montreal, 7-10 December 2015, 577-585. |
| [14] | Abedinia, O., Amjady, N. and Zareipour, H. (2017) A New Feature Selection Technique for Load and Price Forecast of Electrical Power Systems. IEEE Transactionson Power Systems, 32, 62-74.
https://doi.org/10.1109/TPWRS.2016.2556620 |
| [15] | Lecun, Y. and Bengio, Y. (1995) Convolutional Networks for Images, Speech, and Timeseries. MIT Press, Cambridge, MA. |
| [16] | Yamashita, R., Nishio, M., Do, R.K.G. and Togashi, K. (2018) Convolutional Neural Networks: An Overview and Application in Radiology. Insights Imaging, 9, 611-629. https://doi.org/10.1007/s13244-018-0639-9 |
| [17] | Wang, Z., Yan, W. and Oates, T. (2017) Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline. 2017 International Joint Conference on Neural Networks, Anchorage, 14-19 May 2017, 1578-1585.
https://doi.org/10.1109/IJCNN.2017.7966039 |
| [18] | Moody, G.B. and Mark, R.G. (1996) A Database to Support Development and Evaluation of Intelligent Intensive Care Monitoring. Computers in Cardiology 1996, Indianapolis, 8-11 September 1996, 657-660.
https://doi.org/10.1109/CIC.1996.542622 |
| [19] | Physionet (2020) The MIMIC Project Data Base via the Physionet Website.
https://archive.physionet.org/cgi-bin/atm/ATM |
