本文提出了一种利用相邻QRS波的相关性进行最小均方差预测的心电图压缩算法。
A novel electrocardiogram compression algorithm based on minimum root-mean-square error prediction utilizing the correlation of adjacent QRS wave is proposed.
经不同年际独立试验数据的检验，叶片碳氮比监测模型的预测精确R2为0.6824，根均方差（RMSE）为0.4052。
Testing of the monitoring models with independent dataset indicated that the predictive precision (R2 ) was 0.6824, and RMSE was 0.4052.
对结果均方差的分析显示，加权支持向量机的预测精度优于人工神经网络和标准支持向量机模型。
The analysis to the mean square deviation showed us the conclusion, that the prediction accuracy of WSVM was better than the ANN and traditional SVM models.
对结果均方差的分析显示，加权支持向量机的预测精度优于人工神经网络和标准支持向量机模型。
The analysis to the mean square deviation showed us the conclusion, that the prediction accuracy of WSVM was better than the ANN and traditional SVM models.
应用推荐