Principal Component Selection Research Articles

Remote sensing data in lithium (Li) exploration: A new approach for the detection of Li-bearing pegmatites

Remote sensing has proved to be a powerful resource in geology capable of delineating target exploration areas for several deposit types. Only recently, these methodologies have been used for the detection of lithium (Li)-bearing pegmatites. This happened because of the growing importance and demand of Li for the construction of Li-ion batteries for electric cars. The objective of this study was to develop innovative and effective remote sensing methodologies capable of identifying Li-pegmatites through alteration mapping and through the direct identification of Li-bearing minerals. For that, cloud free Landsat-5, Landsat-8, Sentinel-2 and ASTER images with low vegetation coverage were used. The image processing methods included: RGB (red, green, blue) combinations, band ratios and selective principal component analysis (PCA). The study area of this work is the Fregeneda (Salamanca, Spain)-Almendra (Vila Nova de Foz Côa, Portugal) region, where different known types of Li-pegmatites have been mapped. This study proposes new RGB combinations, band ratios and subsets for selective PCA capable of differentiating the spectral signatures of the Li-bearing pegmatites from the spectral signatures of the host rocks. The potential and limitations of the methodologies proposed are discussed, but overall there is a great potential for the identification of Li-bearing pegmatites using remote sensing. The results obtained could be improved using sensors with a better spatial and spectral resolution.

Evaluation of Optical and Radar Images Integration Methods for LULC Classification in Amazon Region

The main objective of this study is to evaluate different methods to integrate (fusion and combination) Synthetic Aperture Radar (SAR) Advanced Land Observing Satellite (ALOS) Phased Arrayed L-band SAR (PALSAR-1) (Fine Beam Dual mode-FDB) and LANDSAT images in order to identify those which lead to higher accuracy of land-use and land-cover (LULC) mapping in an agricultural frontier region in Amazon. One method used to integrate the multipolarized information in SAR images before the fusion process was also evaluated. In this method, the first principal component (PC1) of SAR data was used. Color compositions of fused data that presented better LULC classification were visually analyzed. Considering the proposed objective, the following fusion methods must be highlighted: Ehlers , Wavelet a trous, Intensity, Hue and Saturation (IHS), and selective principal component analysis (SPC). These latter three methods presented good results when processed using PC1 from ALOS/PALSAR-1 FBD backscatter filtered image or three SAR extracted and selected features. These results corroborate with the applicability of the proposed method for SAR data information integration. Distinct methods better discriminate different LULC classes. In general, densely forested classes were better characterized by the Ehlers _TM6 fusion method, in which at least the polarization HV was used. Intermediate and initial regeneration classes were better discriminated using SPC-fused data with PC1 of ALOS/PALSAR-1 FBD data. Bare soil and pasture classes were better discriminated in optical features and the PC1 of ALOS/PALSAR-1 FBD data fused by the IHS method. Soybean with approximately 40 days from seeding was better discriminated in image classification obtained from ALOS/PALSAR-1 FBD image.

Integrating geologic and Landsat-8 and ASTER remote sensing data for gold exploration: a case study from Zarshuran Carlin-type gold deposit, NW Iran

The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) and the Landsat-8 data were integrated with geological data to map lithologic units, lineament features, hydrothermal alteration zones, and distribution of Fe3+-bearing minerals in the Zarshuran Carlin-type gold deposit. The dominant hydrothermal alterations related to the gold mineralization in the study area, consist of argillic, alunite, silicified, and decalcified alterations of carbonate host rocks. The alteration assemblages are accompanied by ferric iron minerals such as jarosite and hematite. The red-green-blue (RGB) combination of bands 5, 2, and 1 of the ASTER sensor provides excellent criteria for the separation of the host rock lithologic boundaries, particularly for the Oligo-Miocene andesitic volcanic rocks covering the vast parts of the study area. The ASTER lithologic map derived from RGB combination of bands 5, 2, and 1 is represented by a set of lineaments in which both the thrust and normal faults were enhanced. The band ratios obtained by the Landsat-8 and the ASTER datasets have been effectively used to delineate the alteration halos characterized by kaolinite, alunite, quartz, and ferric iron minerals both in regional and local (the Zarshuran gold mine) scales. In addition, methods such as the principal component analysis (PCA) and the selective principal component analysis (Crosta) were exerted on the ASTER data to identify the hydrothermal alteration zones. The spectral angle mapper (SAM) algorithm using the ASTER data could better differentiate the various alteration (e.g., argillic, alunite, and silicified) zones existing in the study area. The matched filtering (MF) technique processed on the Landsat-8 data was applied to characterize the ferric iron minerals (jarosite and hematite) and separate the hydrothermal alteration zones as well. The integration and combination of various image processing techniques indicated that the alteration zones at Zarshuran are affiliated with normal faults within the carbonate host rocks and can be used for prospection mapping purposes in regional scale.

Application of Multi-Sensor Satellite Data for Exploration of Zn–Pb Sulfide Mineralization in the Franklinian Basin, North Greenland

Geological mapping and mineral exploration programs in the High Arctic have been naturally hindered by its remoteness and hostile climate conditions. The Franklinian Basin in North Greenland has a unique potential for exploration of world-class zinc deposits. In this research, multi-sensor remote sensing satellite data (e.g., Landsat-8, Phased Array L-band Synthetic Aperture Radar (PALSAR) and Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER)) were used for exploring zinc in the trough sequences and shelf-platform carbonate of the Franklinian Basin. A series of robust image processing algorithms was implemented for detecting spatial distribution of pixels/sub-pixels related to key alteration mineral assemblages and structural features that may represent potential undiscovered Zn–Pb deposits. Fusion of Directed Principal Component Analysis (DPCA) and Independent Component Analysis (ICA) was applied to some selected Landsat-8 mineral indices for mapping gossan, clay-rich zones and dolomitization. Major lineaments, intersections, curvilinear structures and sedimentary formations were traced by the application of Feature-oriented Principal Components Selection (FPCS) to cross-polarized backscatter PALSAR ratio images. Mixture Tuned Matched Filtering (MTMF) algorithm was applied to ASTER VNIR/SWIR bands for sub-pixel detection and classification of hematite, goethite, jarosite, alunite, gypsum, chalcedony, kaolinite, muscovite, chlorite, epidote, calcite and dolomite in the prospective targets. Using the remote sensing data and approaches, several high potential zones characterized by distinct alteration mineral assemblages and structural fabrics were identified that could represent undiscovered Zn–Pb sulfide deposits in the study area. This research establishes a straightforward/cost-effective multi-sensor satellite-based remote sensing approach for reconnaissance stages of mineral exploration in hardly accessible parts of the High Arctic environments.

Information Theoretic Approaches to Principal Component Selection

SYNOPTIC ABSTRACTComponent selection in principal component analysis is the main step for dimension reduction and working further with extracted factors. A range of component selection methods include hypothesis testing and subjective judgement of graphical representation of eigenvalues, and most of them are not suitable for automatic selection of number of principal components. Though several versions of description length criteria have been developed for automatic selection of principal components, each of the criteria has its own methodological advantages and disadvantages, and no single method always performs the best in all datasets. With the lack of general guidance and criteria for using a particular method, component selection procedures largely depend on personal preferences rather than real statistics. In this article, we survey theoretical grounds of three commonly used minimum description length criteria based on the inherent Karhunen-Loève expansion of the observed process, and examine their performances by employing a series of simulation experiments. Finally, we present some empirical results to demonstrate that the theoretical properties of these criteria are reflected in simulation experiments, and results obtained in simulation experiments are also reflected in real data analysis.

Identification of hydrothermal alteration minerals associated with geothermal system using ASTER and Hyperion satellite data: a case study from Yankari Park, NE Nigeria

Concealed and fossilized geothermal systems are not characterized by obvious surface manifestations like hotsprings and fumaroles, therefore, could not be easily identifiable using conventional techniques. In this investigation, the applicability of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) and Hyperion data-sets were evaluated in discriminating hydrothermal alteration minerals associated with geothermal systems as a proxy in identifying subtle Geothermal systems at Yankari Park, Nigeria. Feature-oriented principal component selection, spectral angle mapper, linear spectral unmixing were applied to ASTER data based on spectral characteristics of hydrothermal alteration key minerals for a systematic selective extraction of the information of interest. Analytical imaging and geophysics-developed processing methods were applied to Hyperion data for mapping iron oxide/hydroxide minerals and clay mineral assemblages in hydrothermal alteration zones. The results indicate that ASTER and Hyperion could be complemented for reconnaissance stage of targeting subtle alteration mineral assemblages associated with geothermal systems.

Research on the Prediction Model of Transformer Bidding

Aiming at the problem of transformer manufacturing enterprises bidding is lacking scientific theoretical guidance and low bid probability, in order to predict the next bid price, based on principal component analysis (PCA) and artificial neural network (ANN) pre-tender estimate forecast model is proposed. The model uses PCA to preprocess the original high dimensional data, select principal components (PC) as the radial basis function (RBF) neural network's input. PCA eliminates the correlation of the input variables, at the same time of simplifying the structure of ANN, improving the accuracy of the prediction model. The simulation results show the applicability of the pre-tender estimate forecast model.

HYDROTHEMAL ALTERATION MAPPING USING FEATURE-ORIENTED PRINCIPAL COMPONENT SELECTION (FPCS) METHOD TO ASTER DATA:WIKKI AND MAWULGO THERMAL SPRINGS, YANKARI PARK, NIGERIA

Abstract. Geothermal systems are essentially associated with hydrothermal alteration mineral assemblages such as iron oxide/hydroxide, clay, sulfate, carbonate and silicate groups. Blind and fossilized geothermal systems are not characterized by obvious surface manifestations like hot springs, geysers and fumaroles, therefore, they could not be easily identifiable using conventional techniques. In this investigation, the applicability of Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) were evaluated in discriminating hydrothermal alteration minerals associated with geothermal systems as a proxy in identifying subtle Geothermal systems at Yankari Park in northeastern Nigeria. The area is characterized by a number of thermal springs such as Wikki and Mawulgo. Feature-oriented Principal Component selection (FPCS) was applied to ASTER data based on spectral characteristics of hydrothermal alteration minerals for a systematic and selective extraction of the information of interest. Application of FPCS analysis to bands 5, 6 and 8 and bands 1, 2, 3 and 4 datasets of ASTER was used for mapping clay and iron oxide/hydroxide minerals in the zones of Wikki and Mawulgo thermal springs in Yankari Park area. Field survey using GPS and laboratory analysis, including X-ray Diffractometer (XRD) and Analytical Spectral Devices (ASD) were carried out to verify the image processing results. The results indicate that ASTER dataset reliably and complementarily be used for reconnaissance stage of targeting subtle alteration mineral assemblages associated with geothermal systems.

Application of Landsat-8 and ASTER satellite remote sensing data for porphyry copper exploration: a case study from Shahr-e-Babak, Kerman, south of Iran

The Shahr-e-Babak region located in the Kerman metallogenic belt is one of the high potential segments of Urumieh–Dokhtar magmatic arc for porphyry copper and epithermal gold mineralization in the south of Iran. This high potential zone encompasses several porphyry copper deposits under exploitation, development and exploration stages. The aim of this study is to evaluate Landsat-8 data and comparison with the Advanced Spaceborne Thermal Emission and Reflection Radiometer data-sets for mapping hydrothermal alteration zones related to Cenozoic magmatic intrusions in Shahr-e-Babak region. Previous studies have proven the robust application of ASTER in lithological mapping and mineral exploration; nonetheless, the Landsat-8 data have high capability to map and detect hydrothermal alteration zones associated with porphyry copper and epithermal gold mineralization. In this investigation, several band combinations and multiplications, developed selective principal component analysis and image transformations were developed for discriminating hydrothermal alteration zones associated with porphyry copper mineralization using Landsat-8 data.

Abstract P6-01-18: Early detection of development of a pre-metastatic niche in lungs in response to primary breast tumor using Raman spectroscopy

Abstract Background: An alarmingly large proportion of cancer-related deaths result from metastatic cancers. Development of quick, reliable and non-invasive or minimally invasive approaches to objectively assess the secondary tissues (potentially in vivo) will be instrumental in substantially reducing the cancer burden due to metastasis, which accounts for majority of cancer related mortality. In our study we report the utilization of Raman spectroscopy and chemometric techniques in identifying formation of pre-metastatic niche in lungs prior to observing morphological changes. Methods: Six-week-old female athymic nu/nu mice (NCI, MD) were implanted with 2x106 cells of human breast cancer cell lines - MDA-MB-231 (n=3), and MCF-7 (n=3) in their fourth right mammary fat pad orthotopically. And control mice (n=3) without tumor cell implantation were also employed. The primary tumor size was monitored and the mice were sacrificed within 8-12 weeks of cell implantation when the primary tumors volume grew to 500-600 mm3. Control mice were also sacrificed in this timeframe. The freshly excised lungs of the mice were cleaned in PBS and utilized for obtaining Raman spectra (830 nm, thermoelectrically cooled CCD). Each tissue was collected from multiple points. Principal component analysis (PCA) and Partial least squares discriminant analysis (PLS-DA) were employed as discriminating algorithm. Following spectral acquisition, the tissues were fixed in 10% formalin, embedded in paraffin, and then HE staining, and Masson's trichrome staining for collagen. Collagen quantification of Masson's trichrome stained slides was achieved using MATLAB (Mathworks, MA). The Institutional Animal Care and Use Committee at Johns Hopkins University School of Medicine approved the protocol of the study. Results: 900 Raman spectra each acquired from the lungs of the control mice and mice bearing MCF-7 and MDA-MB-231 tumor xenografts were assigned class labels - 'Control', 'MCL' and 'MDL' respectively for further analysis. Select principal components from those obtained by subjecting all the chosen 900 spectra to PCA clearly evident that the differences in the Raman spectra belonging to tissues being primed by derivatives of different primary cells are quite pronounced. The average correct rates of PLS-DA prediction of 90.1%, 97.7% and 78.4% were obtained for the spectra belonging to the classes - Control, MCL and MDL respectively. The HE images are negative for any signs of cancerous lesions. Masson's trichrome staining results show that the metastatic potential of the cell lines responsible for the primary tumor is positively correlated with the collagen density in the pre-metastatic niche, the MDL shows the highest collagen density (P<0.001). These differences clearly indicate the remodeling of extracellular matrix anticipating incoming tumor cells in response to primary tumor derived factors occurs very early in the metastatic cascade. Conclusion: The current study introduces Raman spectroscopy in conjunction with chemometric techniques as are liable and minimally invasive tool for diagnosis of metastatic cancers significantly early in the metastatic cascade, and also opens a new route for early targeting of cancer metastasis and its associated burden. Citation Format: Zheng C, Rizwan A, Paidi SK, Yu Z, Barman I, Glunde K. Early detection of development of a pre-metastatic niche in lungs in response to primary breast tumor using Raman spectroscopy [abstract]. In: Proceedings of the 2016 San Antonio Breast Cancer Symposium; 2016 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2017;77(4 Suppl):Abstract nr P6-01-18.

Lithological Analysis of Nain Ophiolitic Zone Using ASTER Data

The Mesozoic ophiolitic Melange, north of Nain in the Central-East Iran Microplate (CEIM) comprises serpentinized ultramafic rocks, harzburgites, dunite, gabbro, peridotite, pelagic limestone and other carbonate rocks. The excellent and vast exposure of this desert region is well suited for geologic mapping of this rock suite using remote sensing, especially using data from the satellite-borne advanced Space borne Thermal Emission and Reflection Radiometer (ASTER) imaging system which was designed for mapping mineral information. In this study, data processing methods like Method Minimum noise fraction (MNF), Feature Oriented Principal Components Selection (FPCS), Band Ratios (BR) and Optimum Index Factor (OIF) were used to process ASTER data to optimize the mapping of ophiolite rock types. For example, a simple color composites of OIF (Red: B3, Green: B4, and Blue: B8) and Band ratios (e.g. Red: (B2 + B4)/B3, Green: (B5 + B7)/B6, Blue: (B7 + B9)/B8) were useful for discriminating serpentinite, meta-basalt and granite rock types. It is concluded here that proposed ASTER data has the potential for mapping similar ophiolites elsewhere using the global archive of ASTER imagery.

Fault Detection and Diagnosis in Chemical Processes Using Sparse Principal Component Selection

Fault Detection and Diagnosis in Chemical Processes Using Sparse Principal Component Selection

Principal Component Selection for Neural Network Classification of Active Ingredients from Near Infrared Spectra

This paper presents results from an investigation into the capability of reflectance Near-Infrared (NIR) spectroscopy in the classification of pharmaceutical tablets based on their active ingredients. The part of the process selected for this study is the packaging step in the manufacture of pharmaceuticals because in older processing lines the product was classified after tablet coating and before blister packaging using visual automatic inspection techniques. However, for 100% conformance, a more discriminating technique is required. In this investigation, NIR spectra (with wavelengths between 400nm and 1100nm) were obtained for samples relating to 3 different types of pharmaceuticals: Quetiapine, Ibuprofen and Paracetamol. The dimensionality of the dataset was reduced using Principal Components and then different combinations of Principal Components were fed into a Neural Network that was configured to classify the tablets based on their active ingredients. The recognition rates achieved in this study were high enough to suggest that NIR spectroscopy is a viable method of ensuring 100% identification of pharmaceutical tablet type prior to packaging for the pharmaceuticals tested.

Fusing ASTER and QuickBird-2 Satellite Data for Detailed Investigation of Porphyry Copper Deposits Using PCA; Case Study of Naysian Deposit, Iran

Hydrothermal alteration mineral zones associated with porphyry copper mineralization can be identified and discriminated based on distinctive spectral properties of the ASTER satellite data. Image processing techniques are mostly used for regional scale mapping but in this study, we aimed to evaluate them for more detailed exploration studies by fusing ASTER and QuickBird-2 satellite data using Gram-Schmidt sharpening method to enhance the spatial resolution of the imagery. Selective principal component analysis (PCA) technique is used to provide mineral distribution maps from the spatially improved ASTER data. PCA was applied to ASTER bands with the objective of mapping the occurrence of mineral end-members related to a porphyry copper deposit named Naysian in Iran. The results illustrate the ability of ASTER data for extracting information on alteration minerals which are valuable for mineral exploration studies and support the role of PCA as a very robust image processing technique for that purpose. The spatial distribution of hydrothermal alteration zones has been verified by insitu field observations. This investigation indicated that applying image processing techniques has a great ability to obtain significant and comprehensive information in detailed stages of porphyry copper deposit exploration at a local scale. The results of this research can assist exploration geologists to make a better planning for more detailed stages of exploring porphyry copper and even gold deposits in other virgin regions before costly detailed ground investigations. Consequently, the introduced image processing approach can present an optimum idea about the application of remote sensing in final stages of mineral exploration.

Screening of inbred popcorn lines for tolerance to low phosphorus.

Increasing phosphorus use efficiency in agriculture is essential for sustainable food production. Thus, the aims of this study were: i) to identify phosphorus use efficiency (PUE) in popcorn lines during the early plant stages, ii) to study the relationship between traits correlated with PUE, and iii) to analyze genetic diversity among lines. To accomplish this, 35 popcorn lines from Universidade Estadual de Maringá breeding program were studied. The experiment was conducted in a growth chamber using a nutrient solution containing two concentrations of phosphorus (P): 2.5 μM or low P (LP) and 250 μM or high P (HP). After 13 days in the nutrient solution, root morphology traits, shoot and root dry weight, and P content of the maize seedlings were measured. A deviance analysis showed there was a high level of genetic variability. An unweighted pair group method with arithmetic mean (UPGMA) clustering analysis identified three groups for the LP treatment (efficient, intermediate, and inefficient) and three groups for the HP treatment (responsive, moderately responsive, and unresponsive). The results of a principal component analysis and selection index were consistent with the UPGMA analysis, and lines 1, 2, 13, 17, 26, and 31 were classified as PUE.

Alteration zone Mapping in the Meiduk and Sar Cheshmeh Porphyry Copper Mining Districts of Iran using Advanced Land Imager (ALI) Satellite Data

Abstract. This study evaluates the capability of Earth Observing-1 (EO1) Advanced Land Imager (ALI) data for hydrothermal alteration mapping in the Meiduk and Sar Cheshmeh porphyry copper mining districts, SE Iran. Feature-oriented principal components selection, 4/2, 8/9, 5/4 band ratioing were applied to ALI data for enhancing the hydrothermally altered rocks associated with porphyry copper mineralization, lithological units and vegetation. Mixture-tuned matched-filtering (MTMF) was tested to discriminate the hydrothermal alteration areas of porphyry copper mineralization from surrounding environment using the shortwave infrared bands of ALI. Results indicate that the tested methods are able to yield spectral information for identifying vegetation, iron oxide/hydroxide and clay minerals, lithological units and the discrimination of hydrothermally altered rocks from unaltered rocks using ALI data.

Remote detection of fluid-related diagenetic mineralogical variations in the Wingate Sandstone at different spatial and spectral resolutions

Well-exposed eolian units of the Jurassic system on the Colorado Plateau including the Wingate Sandstone, show prominent color variations throughout southeastern Utah due to diagenetic changes that include precipitation and/or removal of iron oxide, clay, and carbonate cement. Spatially variable characteristic diagenetic changes suggest fluid-rock interactions through the sandstone. Distinctive spectral signatures of diagenetic minerals can be used to map diagenetic mineral variability and possibly fluid-flow pathways. The main objective of this work was to identify characteristic diagenetic minerals, and map their spatial variability from regional to outcrop scale in Wingate Sandstone exposures of Lisbon Valley, Utah. Laboratory reflectance spectroscopy analysis of the samples facilitated identification of diagnostic spectral characteristics of the common diagenetic minerals and their relative abundances between altered and unaltered Wingate Sandstone. Comparison of reflectance spectroscopy with satellite, airborne, and ground-based imaging spectroscopy data provided a method for mapping and evaluating spatial variations of diagenetic minerals. The Feature-oriented Principal Component Selection method was used on Advanced Spaceborne Thermal Emission and Reflection Radiometer data so as to map common mineral groups throughout the broader Wingate Sandstone exposure in the area. The Minimum Noise Fraction and Spectral Angle Mapper methods were applied on airborne HyMap and ground-based hyperspectral imaging data to identify and map mineralogical changes. The satellite and airborne data showed that out of 25.55km2 total exposure of Wingate Sandstone in Lisbon Valley, unaltered sandstone cover 12.55km2, and altered sandstone cover 8.90km2 in the northwest flank and 5.09km2 in the southern flank of the anticline. The ground-based hyperspectral data demonstrated the ability to identify and map mineral assemblages with two-dimensional lateral continuity on near-vertical rock faces. The results showed that 39.71% of the scanned outcrop is bleached and 20.60% is unbleached while 6.33% remain unclassified, and 33.36% is masked-out as vegetation. The bleached and unbleached areas are alternating throughout the vertical face of the outcrop. The relative hematite abundance observed in the unbleached areas are somewhat symmetrical. This indicates fairly similar reaction intensities along the upper and lower reaction fronts observed in the vertical section. The distribution geometry and relative abundances of diagenetic minerals not only suggest multiple paths of fluid-flow in Wingate Sandstone but also provides some insight about relative direction of past fluid-flow.

Multi-response optimization in small scale resistance spot welding of titanium alloy by principal component analysis and genetic algorithm

The present study aims to solve multi-response optimization problem in small scale resistance spot welding of 0.4-mm-thick TC2 titanium alloy sheets. Welding parameters of electrode force, welding current and welding time were arranged by the central composite experimental design. Principal component analysis was conducted first on quality indicators of nugget diameter, failure load, failure displacement and failure energy. Different weighted principal components selection strategies were performed to calculate the composite weld quality indexes. Multiple stepwise regression analysis was applied to develop the mathematical function for weighted principal components prediction. Welding parameters effects and sensitivity analysis on the composite weld quality index were discussed. Welding current was found the most significant factor affecting weld quality. Optimum welding parameters determined by genetic algorithm were validated through experiments. The first principal component was supposed as the most effective and simplest quality index. Weld quality was considerably improved based on the proposed model.

Principal component selection via adaptive regularization method and generalized information criterion

The principal component analysis has been widely used in various fields of research (e.g., bioinformatics, medical statistics, etc.), especially high dimensional data analysis. Although crucial components selection is a vital matter in principal components analysis, relatively little attention was paid to this issue. The existing studies for principal component analysis were based on ad-hoc methods (e.g., method with cumulative percent variance or average eigenvalue). We propose a novel method for selecting principal component based on L\(_{1}\)-type regularized regression modeling. In order to effectively perform for principal component regression, we consider adaptive L\(_{1}\)-type penalty based on singular values of components, and propose adaptive penalized principal component regression. The proposed method can perform feature selection incorporating explanation power of components for not only high-dimensional predictor variables but also response variable. In sparse regression modeling, choosing the regularization parameter is a crucial issue, since feature selection and estimation heavily depend on the selected regularization parameter. We derive a model selection criterion for choosing the regularization parameter of the proposed adaptive L\(_{1}\)-type regularization method in line with a generalized information criterion. Monte Carlo simulations and real data analysis demonstrate that the proposed modeling strategies outperform for principal component regression modeling.

Principal components selection for dimensionality reduction using discriminant information applied to fault diagnosis

The Principal Component Analysis is one of most applied dimensionality reduction techniques for process monitoring and fault diagnosis in industrial process. This work proposes a procedure based on the discriminant information contained in the principal components to determine the most significant ones in fault separability. The Tennessee Eastman Process industrial benchmark is used to illustrate the effectiveness of the proposal. The use of statistical hypothesis tests as a separability measure between multiple failures is proposed for the selection of the principal components. The classifier profile concept has been introduced for comparison purposes. Results show an improvement in the classification process when compared with traditional techniques and the StepWise selection. This has resulted in a better classification for a fixed number of components, or a smaller number of required components to obtain a prefixed error rate. In addition, the computational advantage is demonstrated.