Moving window KPCA with reduced complexity for nonlinear dynamic process monitoring

Jaffel, Ines; Taouali, Okba; Harkat, Mohamed-Faouzi; Messaoud, Hassani

doi:10.1016/j.isatra.2016.06.002

Cited by 74 publications

(27 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Khediri et al [126] then proposed a variable moving window scheme where the model can be updated with a block of new data instead of a single data point. Meanwhile, Jaffel et al [191] proposed a moving window reduced kernel PCA, where "reduced" pertains to an approach for easing the computational burden as discussed in Section 4.8. Other related works that utilize the moving window concept can be found in [190,[207][208][209]238,293].…”

Section: Time-varying Behavior and Adaptive Kernel Computationmentioning

confidence: 99%

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

et al. 2019

View full text Add to dashboard Cite

Kernel methods are a class of learning machines for the fast recognition of nonlinear patterns in any data set. In this paper, the applications of kernel methods for feature extraction in industrial process monitoring are systematically reviewed. First, we describe the reasons for using kernel methods and contextualize them among other machine learning tools. Second, by reviewing a total of 230 papers, this work has identified 12 major issues surrounding the use of kernel methods for nonlinear feature extraction. Each issue was discussed as to why they are important and how they were addressed through the years by many researchers. We also present a breakdown of the commonly used kernel functions, parameter selection routes, and case studies. Lastly, this review provides an outlook into the future of kernel-based process monitoring, which can hopefully instigate more advanced yet practical solutions in the process industries.

show abstract

Section: Time-varying Behavior and Adaptive Kernel Computationmentioning

confidence: 99%

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The value for σ 2 is chosen according to an empirical selection criterion: [12,17,47,48], where m is a predetermined value. In this paper, the value of m is naively set to 1.…”

Section: Kernel Principal Component Analysismentioning

confidence: 99%

“…In addition to inheriting several related properties from PCA, KPCA does not suffer from some practical problems faced by other nonlinear PCA extensions, such as nonconvergence or convergence to local minima [10]. KPCA and its extensions have proven to be powerful tools for feature extraction and image denoising [10][11][12][13][14][15][16][17].…”

Section: Introductionmentioning

confidence: 99%

Hyperspectral Dimensionality Reduction Based on Multiscale Superpixelwise Kernel Principal Component Analysis

Zhang

Shen

2019

Remote Sensing

View full text Add to dashboard Cite

Dimensionality reduction (DR) is an important preprocessing step in hyperspectral image applications. In this paper, a superpixelwise kernel principal component analysis (SuperKPCA) method for DR that performs kernel principal component analysis (KPCA) on each homogeneous region is proposed to fully utilize the KPCA’s ability to acquire nonlinear features. Moreover, for the proposed method, the differences in the DR results obtained based on different fundamental images (the first principal components obtained by principal component analysis (PCA), KPCA, and minimum noise fraction (MNF)) are compared. Extensive experiments show that when 5, 10, 20, and 30 samples from each class are selected, for the Indian Pines, Pavia University, and Salinas datasets: (1) when the most suitable fundamental image is selected, the classification accuracy obtained by SuperKPCA can be increased by 0.06%–0.74%, 3.88%–4.37%, and 0.39%–4.85%, respectively, when compared with SuperPCA, which performs PCA on each homogeneous region; (2) the DR results obtained based on different first principal components are different and complementary. By fusing the multiscale classification results obtained based on different first principal components, the classification accuracy can be increased by 0.54%–2.68%, 0.12%–1.10%, and 0.01%–0.08%, respectively, when compared with the method based only on the most suitable fundamental image.

show abstract

“…In SVM-TLBO, the SVM generalizes the results obtained from learning's where as TLBO evaluates the optimal output of the free parameters of SVM. Jaffel, I. et al [18] analyzed that moving window reduced kernel principal component analysis MW-RKPCA are perform better results than and MW-KPCA applied to monitoring the nonlinear dynamic system. Das, S. P. [19] designed a hybrid model of DR-SVM-TLBO and applied different dimension reduction method i.e PCA, KPCA and ICA to reduce the features of supplied data.…”

Section: Literature Reviewmentioning

confidence: 99%

Prediction of Stock Index of Tata Steel using Hybrid Machine Learning Based Optimization Techniques

Siddique¹,

Panda²

2019

IJRTE

View full text Add to dashboard Cite

The trend of stock price prediction has always been in the focal point of analytical activity in financial domain for both the researchers and investors. Prediction with accuracy is very essential for improved investment decisions that imbibe minimum risk factors. Due to this, majority of investors depend upon that intelligent trading system which generates better forecasting results. As forecasting stock market price with high accuracy is quite a challenging task for the analysts, machine learning has been adopted as one of the popular techniques to predict future trends. Even if there are many recognized analytical time series analysis that are categorized either under soft computing or under conventional statistical techniques like fuzzy logic, artificial neural networks and genetic algorithms, researchers have been looking for more appropriate techniques which can exhibit improved results. In this paper, we developed different hybrid machine learning based prediction models and compared their efficiency. Dimension reduction techniques such as orthogonal forward selection (OFS) and kernel principal component analysis (KPCA) are used separately with support vector regression (SVR) and teaching learning based optimization (TLBO) to predict the stock price of Tata Steel. The performance of both the proposed approach is evaluated with 4143days daily transactional data of Tata steels stocks price, which was collected from Bombay Stock Exchange (BSE). We compared the results of both OFS-SVR-TLBO and KPCA-SVR-TLBO hybrid models and concludes that by incorporating KPCA is more practicable and performs better results than OFS

show abstract

Moving window KPCA with reduced complexity for nonlinear dynamic process monitoring

Cited by 74 publications

References 41 publications

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

A Review of Kernel Methods for Feature Extraction in Nonlinear Process Monitoring

Hyperspectral Dimensionality Reduction Based on Multiscale Superpixelwise Kernel Principal Component Analysis

Prediction of Stock Index of Tata Steel using Hybrid Machine Learning Based Optimization Techniques

Contact Info

Product

Resources

About