REN Jinkai,WU Zhaohe,GAO Jingqi,et al.Hypertension prediction model based on artificial neural network[J].Journal of Yanbian University,2024,(02):95-100.
基于人工神经网络的高血压预测模型
- Title:
- Hypertension prediction model based on artificial neural network
- 文章编号:
- 1004-4353（2024）02-0095-06
- Keywords:
- hypertension; prediction model; artificial neural network; auxiliary diagnosis; batch normalization; residual connection
- 分类号:
- TP301.6
- 文献标志码:
- A
- 摘要:
- 为准确预测高血压患者，文章提出了一种基于人工神经网络(artificialneuralnetwork，ANN)的高血压预测模型.该模型在原始的ANN模型中引入了批归一化层（batchnormalization，BN）和残差连接（residualconnection），以改进原始ANN模型所存在的缺陷.实验表明，该模型的收敛速度显著高于原始模型，且可有效加快模型的训练过程.研究结果可为高血压的早期预测和干预提供参考.
- Abstract:
- In order to accurately predict patients with hypertension，the article proposes a hypertension prediction model based on artificial neural network，(artificial neural network，ANN). This model introduces a batch normalization layer (batch normalization，BN) into the original ANN model，and residual connection to improve the defects of the original ANN. Experiments show that the convergence speed of this model is significantly higher than that of the original model，and it can effectively speed up the training process of the model. The results can be used for the treatment of hypertension and provide reference for early prediction and intervention.
参考文献/References:
[1] World Health Organization. Global Report on Hypertension：the Race Against a Silent Killer[M]. Geneva：World Health Organization，2023.
[2] FUCHS F D，WHELTON P K. High blood pressure and cardiovascular disease[J]. Hypertension，2020，75(2)：285-292.
[3] MELIN P，MIRAMONTES I，PRADO-ARECHIGA G. A hybrid model based on modular neural networks and fuzzy systems for classification of blood pressure and hypertension risk diagnosis[J]. Expert Systems with Applications， 2018，107：146-164.
[4] SINGH N，SINGH P，BHAGA D. A rule extraction approach from support vector machines for diagnosing hypertension among diabetics[J]. Expert Systems with Applications，2019，130：188-205.
[5] KANEGAE H，SUZUKI K，FUKATANI K，et al. Highly precise risk prediction model for new–onset hypertension using artificial intelligence techniques[J]. The Journal of Clinical Hypertension，2020，22(3)：445-450.
[6] SARITAS M M，Yasar A. Performance analysis of ANN and Naive Bayes classification algorithm for data classification[J]. International journal of intelligent systems and applications in engineering，2019，7：88-91.
[7] 张婕.基于深度神经网络的智能问答系统性能优化研究[D].南京：南京邮电大学，2020.
[8] DE S，SMITH S. Batch normalization biases residual blocks towards the identity function in deep networks[J]. Advances in Neural Information Processing Systems，2020，33：19964-19975.
[9] HUANG L，QIN J，ZHOU Y，et al. Normalization techniques in training dnns：Methodology，analysis and application[J]. IEEE transactions on pattern analysis and machine intelligence，2023，45(8)：10173-10196.
[10] 胡清礼，胡建强，余小燕.结合批归一化的多层感知机糖尿病预测诊断模型[J].计算机系统应用，2020，29(05)：182-188.
[11] EBRAHIMI M S，ABADI H K. Study of residual networks for image recognition[C]//Intelligent Computing：Proceedings of the 2021 Computing Conference，Volume 2. Berlin ：Springer International Publishing，2021：754-763.
[12] AL-BARAZANCHI H A，QASSIM H，VERMA A. Large-scale scene image categorisation with deep learning-based model[J]. International Journal of Computational Vision and Robotics，2020，10：185-201.
[13] 华琦，李梅，刘力松，等. 高血压病患者动态脉压，收缩压，舒张压，平均动脉压与左心室肥厚的相关性研究[J]. 中国医学影像技术，2003，19(11)：1508-1509.
[14] SALM?N-G?MEZ L，CATAL?N V，FR?HBECK G，et al. Relevance of body composition in phenotyping the obesities[J]. Reviews in Endocrine and Metabolic Disorders，2023，24(5) ：809-823.
备注/Memo
收稿日期：2024-04-14
第一作者：任金闿（1999—），男，硕士研究生，研究方向为深度学习.
通信作者：文正洙（1984—），男，讲师，研究方向为数据通信协议分析和算法分析与优化.