Wide spectrum feature selection (WiSe) for regression model building
Wide spectrum feature selection (WiSe) for regression model building
复制标题
用于构建回归模型的宽谱特征选择 (WiSe)
DOI：
10.1016/j.compchemeng.2018.10.005
复制
发表时间：
2019
期刊：
影响因子：
--
通讯作者：
M. Reis
中科院分区：
文献类型：
--
作者：
Ricardo R. Rendall;Ivan Castillo;Alix Schmidt;S. Chin;Leo H. Chiang;M. Reis
从工业数据集开发预测模型意味着要考虑许多可能的预测变量（特征）。不建议使用所有可用的特征进行数据驱动建模，因为它们中的大多数都是不相关的，并且将它们包含在模型中可能会损害鲁棒性和准确性。在这项工作中，我们提出，测试和比较了一种新的两阶段特征选择方法，称为宽谱特征选择回归（WiSe）。在第一阶段，有效的二元滤波器组合分析预测因子和响应之间的线性和非线性关联模式，筛选出明显的噪声特征。在第二阶段，在考虑的预测方法范围内进一步选择保留特征的约简集，优化其预测性能。三个模拟数据集和一个工业案例说明了在广泛的高维回归问题中应用WiSe来支持模型开发的有效性和好处。
Developing predictive models from industrial datasets implies the consideration of many possible predictor variables (features). Using all available features for data-driven modelling is not recommended, as most of them are expected to be irrelevant and their inclusion in the model may compromise robustness and accuracy. In this work, we present, test and compare a new two-stage feature selection method called wide spectrum feature selection for regression (WiSe). In the first stage, a combination of efficient bivariate filters analyzes linear and non-linear association patterns between predictors and responses, screening out clearly noisy features. In the second stage, the reduced set of retained features is subject to further selection in the scope of the predictive methods considered, optimizing their predictive performance. Three simulated datasets and an industrial case illustrate the effectiveness and benefits of applying WiSe to support model development in a wide range of high-dimensional regression problems.
影响因子：
8.9
作者：
Liu, H;Yu, L
通讯作者：
Yu, L