| 1. | Using auc to evaluate predictive performance of classifiers
评估分类器的预测性能 |
| 2. | It is in better agreement with experimental data than existing models
结果表明本文的转换模型预测性能较好。 |
| 3. | In the experiment the validity of the method is proved and impact on the prediction performance about some key parameters is analyzed
实验验证了该方法的有效性，并考察了一些关键参数对于预测性能的影响。 |
| 4. | In this paper we adopt this new chain to construct chained dls - icbp network and greatly boost the performance of multi - steps time series prediction
实验证实基于dls的新型链结构网络较传统的dls - icbp和icbp链结构网络的多步预测性能有较大提高。 |
| 5. | The global mlp neural network with 3 layers and the local linear polynomial map with first order are used to model the reverberation sequence
本文分别用三层mlp神经网络和线性一阶映射多项式对混响进行全局非线性建模和局部线性建模及预测性能分析。 |
| 6. | While present parallel programs mostly machine dependent , so the transportability of parallel programs are very poor and it is very difficult to predict the program performance
而现有的并行程序绝大多数是依赖机器的，因此并行程序的可移植性差且难于预测性能。 |
| 7. | This control method addopted the idea of prediction control , which can improve the prediction capability of the system by regulating gain parameter , reset parameter and stroke parameter
这种控制方式应用了预测控制的思想，通过增益系数、复位系数、行程系数的调整来改善控制系统的预测性能。 |
| 8. | Microarchitecture , research triangle park , north carolina , dec . 1997 , pp . 281 - 290 . 9 rychlik b , faitl j , krug b , shen j p . efficacy and performance impact of value prediction . in proc
文中对影响值预测性能的各种因素，如预测失败开销指令窗口大小处理器发射宽度及分支预测机制等进行了详细的测试和分析。 |
| 9. | In the research of the protein modification of n - acetylation , by properly using prior knowledge and upgrading the pattern extraction method , improvement in performance of the svm model was achieved
在对蛋白质的乙酰化修饰的预测过程中，通过合理地利用先验信息，改进模式提取方法，能够显著地提高支持向量机模型的预测性能。 |
| 10. | In chapter 4 , we present a method of neural network inverse dynamic control under the mutli - step predictive index function . the direct multi - step predictive approach and the recursive multi - step predictive method are adopted
第四章：提出对被控对象进行直接多步预测，利用多步预测性能指标函数对系统实现基于神经网络的逆控制。 |
