A strategy for feature extraction of high dimensional noisy data
Document Type
Conference Proceeding
Publication Date
12-1-2006
Abstract
This paper proposes a strategy for feature extraction of noisy high dimensional data. Firstly, the moving median filter is used for reducing the effect of noise and outliers in the measurement data. Then, the data is projected to a lower dimension feature space using radial basis function (RBF) network and polygonal line (PL). A case study based on a simulated continuos stirred tank reactor (CSTR) has been investigated to check the effectiveness of the proposed strategy. The result shows that it is very effective for dimensionality reduction with minimum loss of information.
Publication Source (Journal or Book title)
Proceedings of the IASTED International Conference on Modelling, Identification, and Control, MIC
First Page
441
Last Page
445
Recommended Citation
Bhushan, B., & Romagnoli, J. (2006). A strategy for feature extraction of high dimensional noisy data. Proceedings of the IASTED International Conference on Modelling, Identification, and Control, MIC, 441-445. Retrieved from https://repository.lsu.edu/chem_engineering_pubs/651