A one-class peeling method for multivariate outlier detection with applications in phase I SPC

In phase I of statistical process control (SPC), control charts are often used as outlier detection methods to assess process stability. Many of these methods require estimation of the covariance matrix, are computationally infeasible, or have not been studied when the dimension of the data, $p$, is large. We propose the one-class peeling (OCP) method, a flexible framework that combines statistical and machine learning methods to detect multiple outliers in multivariate data. The OCP method can be applied to phase I of SPC, does not require covariance estimation, and is well suited to high-dimensional data sets with a high percentage of outliers. Our empirical evaluation suggests that the OCP method performs well in high dimensions and is computationally more efficient and robust than existing methodologies. We motivate and illustrate the use of the OCP method in a phase I SPC application on a $N=354$, $p=1917$ dimensional data set containing Wikipedia search results for National Football League (NFL) players, teams, coaches, and managers. The example data set and R functions, OCP.R and OCPLimit.R, to compute the respective OCP distances and thresholds are available in the supplementary materials.     

基于多变量时间序列及向量自回归机器学习模型的水驱油藏产量预测方法

提出了一种基于多变量时间序列(MTS)及向量自回归(VAR)机器学习模型的水驱油藏产量预测方法,并进行了实例应用。该方法在井网分析的基础上通过MTS分析对注采井组数据进行优选,并将井组内不同采出井产油量及注入井注水量作为彼此相关的时间序列,通过建立VAR模型从多个时间序列中提取出相互作用规律,挖掘注采井间流量的依赖关系从而进行产量预测。水驱油藏历史生产数据分析结果表明,与数值模拟历史拟合结果相比,机器学习模型产量预测结果具有更高精度,同时不确定性分析提升了预测结果的安全性。通过脉冲响应分析对注入井的采油贡献量进行评价,可为注水开发方案调整提供理论指导。     

Direct model-based predictive control scheme without cost function for voltage source inverters with reduced common-mode voltage

This paper presents a direct model-based predictive control scheme for voltage source inverters (VSIs) with reduced common-mode voltages (CMVs). The developed method directly finds optimal vectors without using repetitive calculation of a cost function. To adjust output currents with the CMVs in the range of –V_dc/6 to +V_dc/6, the developed method uses voltage vectors, as finite control resources, excluding zero voltage vectors which produce the CMVs in the VSI within ±V_dc/2. In a model-based predictive control (MPC), not using zero voltage vectors increases the output current ripples and the current errors. To alleviate these problems, the developed method uses two non-zero voltage vectors in one sampling step. In addition, the voltage vectors scheduled to be used are directly selected at every sampling step once the developed method calculates the future reference voltage vector, saving the efforts of repeatedly calculating the cost function. And the two non-zero voltage vectors are optimally allocated to make the output current approach the reference current as close as possible. Thus, low CMV, rapid current-following capability and sufficient output current ripple performance are attained by the developed method. The results of a simulation and an experiment verify the effectiveness of the developed method.     

Using electroencephalogram to continuously discriminate feelings of personal thermal comfort between uncomfortably hot and comfortable environments

Thermal comfort is an important factor for the design of buildings. Although it has been well recognized that many physiological parameters are linked to the state of thermal comfort or discomfort of humans, how to use physiological signal to judge the state of thermal comfort has not been well studied. In this paper, the feasibility of continuously determining feelings of personal thermal comfort was discussed by using electroencephalogram (EEG) signals in private space. In the study, 22 subjects were exposed to thermally comfortable and uncomfortably hot environments, and their EEG signals were recorded. Spectral power features of the EEG signals were extracted, and an ensemble learning method using linear discriminant analysis or support vector machine as a sub-classifier was used to build the discriminant model. The results show that an average discriminate accuracy of 87.9% can be obtained within a detection window of 60 seconds. This study indicates that it is feasible to distinguish whether a person feels comfortable or too hot in their private space by multi-channel EEG signals without interruption and suggests possibility for further applications in neuroergonomics.     

Nonlinear Factor-Augmented Predictive Regression Models with Functional Coefficients

This article introduces a new class of functional-coefficient predictive regression models, where the regressors consist of auto-regressors and latent factor regressors, and the coefficients vary with certain index variable. The unobservable factor regressors are estimated through imposing an approximate factor model on high dimensional exogenous variables and subsequently implementing the classical principal component analysis. With the estimated factor regressors, a local linear smoothing method is used to estimate the coefficient functions (with appropriate rotation) and obtain a one-step ahead nonlinear forecast of the response variable, and then a wild bootstrap procedure is introduced to construct the prediction interval. Under regularity conditions, the asymptotic properties of the proposed methods are derived, showing that the local linear estimator and the nonlinear forecast using the estimated factor regressors are asymptotically equivalent to those using the true latent factor regressors. The developed model and methodology are further generalized to the factor-augmented vector predictive regression with functional coefficients. Finally, some extensive simulation studies and an empirical application to forecast the UK inflation are given to examine the finite-sample performance of the proposed model and methodology.     

鲸鱼优化支持向量机的短期风电功率预测

为提高风电预测的精度,提出一种鲸鱼优化支持向量机SVM(support vector machine)的组合预测模型。该模型针对风电序列的非平稳波动特性,首先应用集合经验模态分解技术EEMD(ensemble empirical mode de?composition)将原始风电序列分解为一系列不同特征尺度的子序列;并引入鲸鱼优化算法WOA(whales optimiza?tion algorithm)解决SVM中学习参数选择难的问题,进而对各子序列建立WOA_SVM预测模型;最后,叠加各子序列的预测值以得到最终预测值。仿真表明,所提EEMD_WOA_SVM模型具有较高的风电预测精度,显著优于其他基本模型。     

基于SARIMA-GRNN-SVM的短期商业电力负荷组合预测方法

针对短期商业电力负荷预测准确性与周期难以满足现有电力现货市场的问题,提出了一种基于SARIMAGRNN-SVM(seasonal autoregressive integrated moving average-generalized regression neural network-support vector machine)的商业电力负荷组合预测模型。首先,对商业电力负荷变化的周期规律与随机因素的复杂影响进行了分析;然后,结合以上分析,选用SARIMA和GRNN为单一预测模型对商业电力负荷进行预测,并利用SVM进行组合,实现日前商业电力负荷预测;最后,通过某商业综合体的电力负荷数据进行验证。所提组合预测模型较单一预测模型拥有更优的预测精度与鲁棒性,可以为短期商业电力负荷预测提供借鉴。     

Multilayer thermal object identification in frequency domain using IR thermography and vector fitting

This paper deals with the identification of the thermal parameters of multilayer objects using the concept of thermal impedance. In order to perform such identification, temperature evolution in time is obtained by an infrared camera after power excitation is applied in the investigated structure. Infrared thermography offers the advantage of being a noncontact temperature detection and measurement method. In many practical cases, it is impossible to use contact temperature measurements. Typically, the power in the form of a step function is applied. In order to calculate the thermal impedance of an object, temperature and power are converted into the frequency domain using the Laplace transform for s = jω. Then, the poles of the thermal impedance are identified using vector fitting, which allows calculating the thermal impedance as a sum of partial fractions. This corresponds directly to the Foster network of a thermal object. In addition, the vector fitting method offers much better convergence in comparison with other methods using the polynomial rational approximation of thermal impedance. A considerable improvement of the numerical Laplace transform in high frequency range is proposed. In this approach, the variable s = jω is replaced by , and then, the integration result is corrected by the Taylor series. It leads to a kind of filtering of the temperature signal.     

A new decomposition based evolutionary algorithm with uniform designs for many-objective optimization

For many-objective optimization problems, how to get a set of solutions with good convergence and diversity is a difficult and challenging work. In this paper, a new decomposition based evolutionary algorithm with uniform designs is proposed to achieve the goal. The proposed algorithm adopts the uniform design method to set the weight vectors which are uniformly distributed over the design space, and the size of the weight vectors neither increases nonlinearly with the number of objectives nor considers a formulaic setting. A crossover operator based on the uniform design method is constructed to enhance the search capacity of the proposed algorithm. Moreover, in order to improve the convergence performance of the algorithm, a sub-population strategy is used to optimize each sub-problem. Comparing with some efficient state-of-the-art algorithms, e.g., NSGAII-CE, MOEA/D and HypE, on six benchmark functions, the proposed algorithm is able to find a set of solutions with better diversity and convergence.