Principal Component Analysis

Energy Dispersive X-Ray Fluorescence and its Sensitivity to Thermally Induced Changes in Clay Bodies

by Field Notes: A Journal of Collegiate Anthropology

By Elissa Hulit

Published in Field Notes: A Journal of Collegiate Anthropology 4(1): 216-226. (May 2012) Copyright ©2012 by Field Notes: A Journal of Collegiate Anthropology

The use of portable X-Ray fluorescence spectrometry in the study of prehistoric ceramics has gained popularity... more The use of portable X-Ray fluorescence spectrometry in the study of prehistoric ceramics has gained popularity recently due to the many benefits of this technology. Portable Energy Dispersive X-Ray Fluourescence (XRF) is non-destructive, relatively inexpensive, and capable of detecting a range of the elements that commonly distinguish clay bodies. It has been used successfully as a means of differentiating prehistoric pottery from different sources and has provided new insights into pottery manufacture and trade networks. However, when it comes to clay sourcing, the high degree of sensitivity in XRF analysis may present new challenges that must be considered before XRF can be used effectively. Natural clay deposits can be expected to vary in composition as the result of formation or deposition processes. During pottery production, humans introduce new sources of compositional variation at various stages of manufacture. While the compositional variation resulting from the subtraction of natural inclusions and from the addition of tempering materials and decorative slips or paints has received attention, no attempt has been made to determine if XRF alone has the capability to identify compositional variation resulting from different fire temperatures. This paper presents an attempt to identify such differences between a set of control samples. These vessels were made from the same stock clay, but vary in tempering materials and firing temperatures. A principal components analysis of the compositions suggests that chemical changes as a result of firing temperature can be detected by the XRF device. Clay sourcing studies using XRF technology should take this source of variation into account. Furthermore, the interaction between firing temperature and the temper material indicates that while knowledge of the pottery firing temperature may be needed, knowledge of how the tempering material reacts to firing atmosphere may also help refine clay sourcing methodology.

Epiphytic lichens as indicator of land-use pattern and forest harvesting in a community forest in west Nepal

by Himanshu Rai

Coauthored With:

Pramod Nag, Dalip Kumar Upreti, Sanjeeva Nayaka, Rajan Kumar Gupta

Human inhabitance and agriculture have fundamentally altered global pattern of biodiversity and ecosystem processes.... more Human inhabitance and agriculture have fundamentally altered global pattern of biodiversity and ecosystem processes. Therefore, integration of community-based approach is an effective conservation strategy. Community forestry is an important community-based approach, which can help in conserving local ecological assets in a sustainable manner. Lichens are known to be more sensitive indicators of ecosystem functions and disturbances than any other cryptogam and vascular plant community. Present study reports a preliminary assessment of epiphytic lichens in a community forest in Dadeldhura district, west Nepal, in order to identify potential indicator of forest health and land-use pattern. Epiphytic (corticolous) lichens were sampled from ten land-use units (LUU), using narrow frequency grids of 10 cm × 50 cm, each divided into five sampling units of 10 cm × 10 cm, on the bark of selected tree species. Quercus leucotrichophora was the dominant phorophyte followed by Pinus roxburghii, Rhododendron arboreum and Myrica esculenta. Foliose parmeloid (Parmotrema spp., Heterodermia spp., Hypotrachyna spp., Bulbothrix spp., Canoparmelia spp., Canomaculina spp.) was the most abundant lichen group, found inhabiting all the phorophytes followed by crustose, fruticose and dimorphic growth forms. Maximum diversity of parmeloid lichens was recorded on older stand of Quercus while younger stands usually harbored crustose lichens (e.g., Lecanora spp., Basidia spp.). Though the lichen diversity increased from outer fringes of the forest to the core, the vegetation stand age was not distributed in any consistent pattern suggesting unconstrained harvesting of the forest. Lichen diversity was found constrained by phorophyte determinants (stand age, aspect, and bark properties) and community harvesting of the forest

A New Approach to Content-based File Type Detection

by Mohsen Toorani

Proceedings of the 13th IEEE Symposium on Computers and Communications (ISCC'08), pp.1103-1108, July 2008

Matlab PhD face recognition toolbox: toolbox description and user manual

by Vitomir Struc

User manual of my Matlab toolbox for face recognition. The toolbox itself is available from: http://luks.fe.uni-lj.si/sl/osebje/vitomir/face_tools/PhDface/index.html

The PhD (Pretty helpful Development functions for) face recognition toolbox is a collection of Matlab functions and... more The PhD (Pretty helpful Development functions for) face recognition toolbox is a collection of Matlab functions and scripts intended to help researchers working in the field of face recognition. The toolbox was produced as a byproduct of my research work and is freely available for download.

The PhD face recognition toolbox includes implementations of some of the most popular face recognition techniques, such as Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), Kernel Principal Component Analysis (KPCA), Kernel Fisher Analysis (KFA). It features functions for Gabor filter construction, Gabor filtering, and all other tools necessary for building Gabor-based face recognition techniques.

In addition to the listed techniques there are also a number of evaluation tools available in the toolbox, which make it easy to construct performance curves and performance metrics for the face recognition you are currently assessing. These tools allow you to compute ROC (Receiver Operating Characteristics) curves, EPC (Expected performance curves) curves, and CMC (cumulative match score curves) curves.

Most importantly (especially for beginners in this field), the toolbox also contains several demo scripts that demonstrate how to build and evaluate a complete face recognition system. The demo scripts show how to align the face images, how to extract features from the aligned, cropped and normalized images, how to classify these features and finally how to evaluate the performance of the complete system and present the results in the form of performance curves and corresponding performance metrics.

This document describes the basics of the toolbox, from installation to usage. It contains some simple examples of the usage of each function and the corresponding results. However, for more information on the theoretical background of the functions, the reader is referred to papers from the literature, which is vast. Hence, it shouldn't be to difficult to find the information you are looking for.

Temperature estimation for a plasma-propelled rocket engine

by Shane Lynn

IEEE Control Systems Magazine (Applications of Control) (Dec. 2009)
Co-authored with John V. Ringwood and J. I. del Valle Gamboa

The VASIMR propulsion system is an ion propulsion system for spacecraft that uses magnetic fields to accelerate plasma... more The VASIMR propulsion system is an ion propulsion system for spacecraft that uses magnetic fields to accelerate plasma to produce thrust. Undesired heat produced in the helicon section of VASIMR must be monitored and removed safely to avoid damage to system components, especially when higher power operating regimes are explored. This article demonstrates a strategy for distributed temperature estimation, based on OES measurement, and a model where the states represent the distributed temperature profile. OES provides a noninvasive measurement technique, which can be used as an output "correction" term for a state-estimation scheme. In this application, it is shown that the 2048 OES channels recorded can be accurately represented by only three principal components for temperature estimation. Use of the principal components as corrector terms in the state-space model dramatically improve model accuracy and the capability of the model to recover from unknown initial conditions and multiple system input changes.

An Atomic Theory of Flow Behavior

by Stefan Karpinski

Morphological differentiation and hybridization between Quercus alnifolia Poech and Quercus coccifera L.(Fagaceae) in Cyprus

by Charalambos Neophytou

Multivariate approach in Lichen biomonitoring studies: Validation of Lichens as an efficient bioindicator

by Himanshu Rai

Conference Proceedings:
Himanshu Rai,Rajan K. Gupta, D.K. Upreti,  Multivariate approach in Lichen biomonitoring studies: Validation of Lichens as an efficient bioindicator,1st World Congress for Man and Nature, Global Climate Change & Biodiversity Conservation, 11-13 Nov. 201, Gurukul Kangri Vishwavidyalaya, Haridwar, Uttarakhand, India,pp.427.

A flexible framework for sparse simultaneous component based data integration

by Katrijn Van Deun

Background

High throughput data are complex and methods that reveal structure underlying the data are... more Background

High throughput data are complex and methods that reveal structure underlying the data are most useful. Principal component analysis, frequently implemented as a singular value decomposition, is a popular technique in this respect. Nowadays often the challenge is to reveal structure in several sources of information (e.g., transcriptomics, proteomics) that are available for the same biological entities under study. Simultaneous component methods are most promising in this respect. However, the interpretation of the principal and simultaneous components is often daunting because contributions of each of the biomolecules (transcripts, proteins) have to be taken into account.

Results

We propose a sparse simultaneous component method that makes many of the parameters redundant by shrinking them to zero. It includes principal component analysis, sparse principal component analysis, and ordinary simultaneous component analysis as special cases. Several penalties can be tuned that account in different ways for the block structure present in the integrated data. This yields known sparse approaches as the lasso, the ridge penalty, the elastic net, the group lasso, sparse group lasso, and elitist lasso. In addition, the algorithmic results can be easily transposed to the context of regression. Metabolomics data obtained with two measurement platforms for the same set of Escherichia coli samples are used to illustrate the proposed methodology and the properties of different penalties with respect to sparseness across and within data blocks.

Conclusion

Sparse simultaneous component analysis is a useful method for data integration: First, simultaneous analyses of multiple blocks offer advantages over sequential and separate analyses and second, interpretation of the results is highly facilitated by their sparseness. The approach offered is flexible and allows to take the block structure in different ways into account. As such, structures can be found that are exclusively tied to one data platform (group lasso approach) as well as structures that involve all data platforms (Elitist lasso approach).

Availability

The additional file contains a MATLAB implementation of the sparse simultaneous component method.

Principal component analysis under population genetic models of range expansion and admixture

by Mathias Currat

Processing of Spectral X-ray Data with Principal Components Analysis

by Raphael Grasset

Anthony P.H.Butler, Jochen Butzer, Nanette Schleich, Nicholas J.Cook, NigelG Anderson, Nicola Scott, Niels de Ruiter, Raphael Grasset, Lukas Tlustos, Philip H.Butler
Nuclear Instruments and Methods in Physics Research Section A, Volume 633, p. S140-S142, May 2011.

Predicting the regional onset of the rainy season in West Africa

by Patrick Laux

Int. J. Climatol. 28: 329–342 (2008)

Particularly in regions, where precipitation is limited to a few months per year only, reliable determination of the... more Particularly in regions, where precipitation is limited to a few months per year only, reliable determination of the onset of the rainy season and the start of the sowing time is of crucial importance to sustainable food production.
Especially since the mid-1980s, an increasing delay of onset dates in the Volta basin of West Africa has been suspected by local farmers. To investigate this speculation and develop a reliable tool to find the optimal sowing date, the onset of the rainy season in the region was analysed by means of several statistical techniques. The focus was put on the region of the Volta basin in Ghana and Burkina Faso.
In a first step, two fuzzy logic based definitions of the onset were developed using daily precipitation data and additionally accounting for important plant physiological aspects. In this context, only one definition is potentially useful to judge whether the current onset of the rainy season has already begun. In a second step, methods for predicting the onset date of the ongoing season were investigated. In this context, the detection of onset controlling variables plays a major role. Two strategies are investigated and evaluated for the prediction of the monsoon’s onset dates:
1) A combination of regionalized synoptic rainfall data by means of principal component analysis (PCA) in a spatial mode and linear discriminant analysis in order to detect reliable prediction parameters and allow for a classification of the rainy season, dry season, and the onset of the rainy season using current rainfall data.
2) Linear regression models were generated to estimate the onset of the rainy season for certain regions using the onset dates of regions, where the onset has already begun.
To enhance the predictability, optimized definition parameterisation in the field of both strategies was applied.
Copyright 2007 Royal Meteorological Society

KEY WORDS onset of the rainy season; West Africa; Volta basin; farming management strategies; decision support system; linear discriminant analysis; principal component analysis; fuzzy logic

Casting credibility: Patterns of audience assessment of TV news programs

by Omar Dumdum

* Published in "Plaridel: A Philippine Journal of Communication, Media and Society" (2011)
* Presented during the 59th ICA Conference in Chicago (2009)
* Co-authored by Ma. Criselda A. Garcia

Abstract: This study describes the patterns of television (TV) viewers' assessment of news program credibility by... more Abstract: This study describes the patterns of television (TV) viewers' assessment of news program credibility by utililzing secondary data from a survey of 1,100 Metro Manila respondents. Through principal component analyses and multiple regressions, the survey reveals that certain attributes of newscasters/reporters, interviewed sources,a nd news content/programming are significantly associated with three dimensions of news program credibility - competence, trustworthiness, and goodwill. It also finds that viewers within specific demographic attributes tend to give high credibility ratings for TV news programs. Implications on TV news broadcasting in the Philippines are discussed.

Antifungal Activity of a Common Himalayan Foliose Lichen Parmotrema tinctorum ( Despr. ex Nyl.) Hale.

by Himanshu Rai

Priti Tiwari, Himanshu Rai, D.K.Upreti, Suman Trivedi, Preeti Shukla. Antifungal Activity of a Common Himalayan Foliose Lichen Parmotrema tinctorum ( Despr. ex Nyl.) Hale. Nature and Science 2011; 9(9):167-171, (ISSN:1545-0740).

In-vitro antifungal activity of acetone, methanol and chloroform extracts of Parmotrema tinctorum (Despr.ex.Nyl.)... more In-vitro antifungal activity of acetone, methanol and chloroform extracts of Parmotrema tinctorum (Despr.ex.Nyl.) Hale. was investigated against ten plant pathogenic fungi viz. Aspergillus niger, Aspergillus flavus, Aspergillus fumigatus, Alternaria alternata, Fusarium oxysporum, Fusarium solani, Fusarium roseum, Ustilago spp., Albugo candida and Penicillium citrinum , with reference to commercially available synthetic antifungal drug Ketoconazole (positive control) using disk diffusion assay. Methanol extract was most effective against all investigated fungi followed by acetone and chloroform extract. Principal component analysis (PCA) concluded that though Ketoconazole was effective against five of the investigated fungi, the extracts of Parmotrema tinctorum were more effective against rest of the five broad spectrum plant pathogenic fungi (Aspergillus fumigatus,Fusarium solani, Fusarium roseum, Penicillium citrinum and Ustilago spp.).

A Top-down Strategy with Temporal and Spatial Partition for Fault Detection and Diagnosis of Building HVAC Systems

by Siyu Wu

In Press, 2011, Energy and Buildings

This paper presents a top-down strategy for detecting faulty HVAC units across different levels. Energy flow models of... more This paper presents a top-down strategy for detecting faulty HVAC units across different levels. Energy flow models of HVAC units are developed while the energy is the main feature extracted from the vast amount of real-time data of the HVAC system in a building. A temporal and spatial partition strategy for analyzing HVAC units is proposed. The partition takes into account of architectural, environmental, and human factors. The partition strategy leads to more appropriate thresholds for fault detection. Numerical examples are presented to demonstrate the detection of a systemwide fault and a fault at the VAV level.

Interpreting degenerate solutions in unfolding by use of the vector model and the compensatory distance model

by Katrijn Van Deun

Co-authored with Groenen, P. J. F., Heiser, W. J., Busing, F. M. T. A., & Delbeke, L

VIPSCAL: a combined vector ideal point model

by Katrijn Van Deun

Unpublished manuscript. Contains a model that combines the ideal point and vector representations used in multidimensional unfolding. The combined model was proposed as a solution to the problem of degenerate solutions.

Identification of Distinct Characteristics of Postural Sway In Parkinson's Disease: a Feature Selection Procedure Based on Principal Component Analysis

by Lorenzo Chiari

Principal Components Analysis of the Hypomanic Attitudes and Positive Predictions Inventory and Associations with Measures of Personality, Cognitive Style and Analogue Symptoms in a Student Sample

by Alyson Dodd

Background: An integrative cognitive model proposed that ascribing extreme personal appraisals to changes in internal... more Background: An integrative cognitive model proposed that ascribing extreme personal appraisals to changes in internal state is key to the development of the symptoms of bipolar
disorder. The Hypomanic Attitudes and Positive Predictions Inventory (HAPPI) was developed to measure these appraisals.
Aims: The aim of the current study was to validate an expanded 61-item version of the HAPPI. Method: In a largely female student sample (N = 134), principal components analysis (PCA) was performed on the HAPPI. Associations between the HAPPI and analogue bipolar symptoms after 3 months were examined.
Results: PCA of the HAPPI revealed six categories of belief: Self Activation, Self-and-Other Critical, Catastrophic,Extreme Appraisals of Social Approval, Appraisals of Extreme Agitation, and Loss of Control. The HAPPI predicted all analogue measures of hypomanic symptoms after 3 months when controlling for baseline symptoms. In a more stringent test incorporating other psychological measures, the HAPPI was independently associated only with activation (e.g. thoughts racing) at 3 months. Dependent dysfunctional attitudes predicted greater conflict (e.g. irritability), depression and reduced well-being, hypomanic personality predicted self-reported diagnostic bipolar symptoms, and behavioural dysregulation predicted depression.
Conclusions: Extreme beliefs about internal states show a modest independent association with prospective analogue
bipolar symptoms, alongside other psychological factors. Further work will be required to improve the factor structure of the HAPPI and study its validity in clinical samples.

Statistical Dynamics of On-Line Unsupervised Learning

by Gleb Basalyga

Gleb Basalyga's PhD thesis, University of Manchester, UK, 2003.

This thesis provides a theoretical description of on-line unsupervised learning from high-dimensional data. In... more This thesis provides a theoretical description of on-line unsupervised learning from high-dimensional data. In particular, the learning dynamics of the on-line Hebbian algorithm is studied for the following two popular statistical models—principal component analysis (PCA) and independent component analysis (ICA). The methods of statistical mechanics are used to elucidate the critical transient stages of the learning process.

In the case of on-line PCA, the statistical mechanics approach allows the derivation of a set of deterministic differential equations for a small number of macroscopic self-averaging order parameters which enables an exact calculation of the evolution of the error function in the limit of large data dimension. In the case of ICA learning, it is found that the interesting macroscopic order parameters are not self-averaging in general and the transient dynamics is relatively slow with large fluctuations. The parameter trajectory of the on-line Hebbian ICA algorithm studied here passes through a sequence of metastable states, each of which can be described by a diffusion process in a polynomial potential. The proper treatment of the fluctuations of the order parameters for this case is given by the Fokker-Planck equation.

For both models a natural gradient version of the studied algorithms is constructed using the fact that the parameter space of our models is constrained to a Stiefel manifold of orthogonal rectangular matrices. In the case of on-line ICA, the natural gradient variant exhibits the same stochastic trapping in sub-optimal metastable states during transient learning as in the case of the standard Hebbian ICA algorithm and there is only an advantage in using the natural gradient variant asymptotically.

The problem of the sensitivity of on-line learning to the choice of learning algorithms is considered. Recommendations for proper adjustment of learning parameters in order to improve the performance of studied algorithms are given. Numerical simulations for finite-sized systems are in good agreement with the theoretical results.