Department of Computer Science and Technology, Harbin University of Science and Technology, Harbin, Heilongjiang 150000, China.
Comput Intell Neurosci. 2022 Apr 13;2022:8431912. doi: 10.1155/2022/8431912. eCollection 2022.
Cardiovascular disease is one of the most serious diseases that threaten human health in the world today. Therefore, establishing a high-quality disease prediction model is of great significance for the prevention and treatment of cardiovascular disease. In the feature selection stage, three new strong feature vectors are constructed based on the background of disease prediction and added to the original data set, and the relationship between the feature vectors is analyzed by using the correlation coefficient map. At the same time, a random forest algorithm is introduced for feature selection, and the importance ranking of features is obtained. In order to further improve the prediction effect of the model, a cardiovascular disease prediction model based on R-Lookahead-LSTM is proposed. The model based on the stochastic gradient descent algorithm of the fast weight part of the Lookahead algorithm is optimized and improved to the Rectified Adam algorithm; the Tanh activation function is further improved to the Softsign activation function to promote model convergence; and the R-Lookahead algorithm is used to further optimize the long-term memory network model. Therefore, the long- and short-term memory network model can be better improved so that the model tends to be stable as soon as possible, and it is applied to the cardiovascular disease prediction model.
心血管疾病是当今世界威胁人类健康的最严重疾病之一。因此，建立高质量的疾病预测模型对于心血管疾病的预防和治疗具有重要意义。在特征选择阶段，基于疾病预测的背景构建了三个新的强特征向量，并通过相关系数图分析了特征向量之间的关系。同时，引入随机森林算法进行特征选择，得到特征的重要性排序。为了进一步提高模型的预测效果，提出了一种基于 R-Lookahead-LSTM 的心血管疾病预测模型。该模型基于 Lookahead 算法的快速权重部分的随机梯度下降算法进行优化和改进，得到 Rectified Adam 算法；进一步改进 Tanh 激活函数为 Softsign 激活函数，促进模型收敛；使用 R-Lookahead 算法进一步优化长期记忆网络模型。因此，可以更好地改进长短时记忆网络模型，使模型尽快趋于稳定，并将其应用于心血管疾病预测模型中。
