Similarity Principal Component Analysis Research Articles

Global variation of ULF geomagnetic fields and detection of anomalous changes at a certain observatory using reference data

AbstractBy using multiple reference stations, we have developed a method to get reliable ULF global geomagnetic variations. This background is extremely useful for detecting local anomalous behaviors. In this paper we report on variable tools developed to identify the anomalies in two frequency ranges: daily variations and variations of 10‐ to 1000‐second span. For estimating background daily variations, the periodical model has been applied for data observed at three reference stations and a study station. Comparison between the first principal component of the periodical data from the reference stations and the periodical data derived from the target station generally provides high correlation. For data with 100‐second periods after wavelet filtering, the nighttime energy variations have been investigated among three reference stations and a study station. Similar principal component analysis as the diurnal variation has been performed and results also show high correlation between the variation at the target and the global background. These tendencies suggest that the two proposed methods are effective in automatically identifying the anomalous patterns. Examining the original data, we can obtain details of waveforms and distinguish whether the anomalies are related to underground activities or simply to some artificial noises. © 2012 Wiley Periodicals, Inc. Electr Eng Jpn, 182(3): 9–18, 2013; Published online in Wiley Online Library (wileyonlinelibrary.com). DOI 10.1002/eej.22299

Global Variation of ULF Geomagnetic Fields and Detection of Anomalous Changes at a Certain Observatory using Reference Data

By using multiple reference stations, we have developed a method to get reliable ULF global geomagnetic variations. This background is extremely useful for detecting local anomalous behaviors. This paper demonstrates developed variable tools to identify the anomalies in two frequency ranges; daily variation and 10-1000 seconds. For estimating background daily variations, the periodical model has been applied for data observed at 3 reference stations and a study station. Comparison between the first principal component of the periodical data from the reference stations and the periodical data derived from the target station provides high correlation in general. For data with 100 sec periods after wavelet filtering, the nighttime energy variations have been investigated among 3 reference stations and a study station. The similar principal component analysis as the diurnal variation has been performed and results also show high correlation between the variation at the target and the global background. These tendency suggest that the developed two methods are effective to identify the anomalies in automatic. Examining the original data, we can know details of waveform and distinguish whether the anomalies is related to underground activities or just some artificial noises.

Unsupervised classification methods in food sciences: discussion and outlook

AbstractThis paper reviews three unsupervised multivariate classification methods: principal component analysis, principal component similarity analysis and heuristic cluster analysis. The theoretical basis of each method is presented in brief, and assumptions inherent to the methods are highlighted. A literature review shows that these methods have sometimes been used inappropriately or without referencing all essential parameters. The paper also brings to the attention of the reader a relatively unknown method: probabilistic or model‐based cluster analysis. The goal of this method is to uncover the true classification of objects rather than a convenient classification provided by the other methods. For this reason it is felt that model‐based cluster analysis will have broad application in the future. Copyright © 2008 Society of Chemical Industry

Principal component similarity analysis of Raman spectra to study the effects of pH, heating, and kappa-carrageenan on whey protein structure.

Raman spectroscopy was used to elucidate structural changes of beta-lactoglobulin (BLG), whey protein isolate (WPI), and bovine serum albumin (BSA), at 15% concentration, as a function of pH (5.0, 7.0, and 9.0), heating (80 degrees C, 30 min), and presence of 0.24% kappa-carrageenan. Three data-processing techniques were used to assist in identifying significant changes in Raman spectral data. Analysis of variance showed that of 12 characteristics examined in the Raman spectra, only a few were significantly affected by pH, heating, kappa-carrageenan, and their interactions. These included amide I (1658 cm(-1)) for WPI and BLG, alpha-helix for BLG and BSA, beta-sheet for BSA, CH stretching (2880 cm(-1)) for BLG and BSA, and CH stretching (2930 cm(-1)) for BSA. Principal component analysis reduced dimensionality of the characteristics. Heating and its interaction with kappa-carrageenan were identified as the most influential in overall structure of the whey proteins, using principal component similarity analysis.

Classification of pasteurized milk using principal component similarity analysis of off-flavours

This research was undertaken because of the need to develop an objective method for detection of off-flavours in milk. Pasteurized milk was treated to develop different intensities of off-flavour (light-induced, oxidized, cooked and heated). The samples were analyzed with a low cost dynamic headspace gas chromatograph and by sensory evaluation. Gas chromatographic analysis was more effective than sensory evaluation as a means of distinguishing milk samples with various treatments. A new technique, principal component similarity analysis, differentiated milk more clearly than principal component analysis.

Classification of Microbial Defects in Milk Using a Dynamic Headspace Gas Chromatograph and Computer-Aided Data Processing. 1. Principal Component Similarity Analysis

There is a need for reliable objective tests for the detection of off-flavors of milk, some of which are caused by bacteriological growth. The objective of the study was to distinguish abnormal from normal milk samples using a low-cost headspace gas chromatograph and principal component similarity analysis. UHT-sterilized milk was inoculated with Pseudomonas fragi, Pseudomonas fluorescens, Bacillus subtilis, Enterobactor aerogenes, Lactococcus lactis, and a mixed culture (P. fragi:E. aerogenes:L. lactis = 1:1:1) to approximately 4.0 log10 CFU mL-1. The samples were stored at 4 °C for 10 days for P. fragi and P. fluorescens and 30 °C for 24 h for the remaining bacteria. A new multiavariate analysis technique, principal component similarity analysis, was capable of distinguishing milk samples inoculated with P. fragi, P. fluorescnes, L. lactis, E. aerogenes, and a mixed culture from uninoculated samples. Keywords: Dynamic headspace gas chromatography; principal component similarity analysis; mulivariate ana...

Recent advances in structure and function of food proteins: QSAR approach.

QSAR (quantitative structure-activity relationship), widely used in chemistry with hydrophobic, electronic, and steric parameters as structural factors, was found to be appropriate for use with food proteins, despite the difficulty, due to the complexity in macromolecular structure, in defining the steric terms. Emulsifying ability was closely related to hydrophobicity, and incorporation of solubility to hydrophobicity as factors improved the R2 of regression analysis. Foaming activity required both hydrophobicity and other factors pertaining to the adsorption of proteins at the interface in order to obtain adequate foam lamella strength. Hydrophobicity as well as other factors relating to the intermolecular interactions, for example, Ca and SH are involved in thermally induced gelation. For breadmaking, although no extensive QSAR work had been carried out, the important function of high molecular glutenin subunits was confirmed, and, notably, the critical function of hydrophobicity in breadmaking also was demonstrated. PLS (partial least-squares regression) and neural networks classify more correctly than other multivariate techniques, thereby yielding higher r2 values in modeling and prediction. However, multiple regression analysis and PCR (principal component regression) also were found to be effective for modeling because the information useful in elucidating the mechanism of protein function could be readily obtained. A characteristic property of unsupervised learning techniques, especially PCS (principal component similarity analysis), in identifying influential factors in the function mechanisms was demonstrated.

Principal component similarity analysis for classification and its application to GC data of mango

As a method for classification, principal component similarity (PCS) analysis reported previously was modified. It was found by using model computation that PCS was easy to use to interpret the result of discrimination, especially when purposes of classification were not clearly defined in advance (unsupervised). A portable, low-cost headspace gas chromatograph (GC) was used for routine analysis of volatile compounds recovered from mango samples. PCS could classify the mango samples based on cultivars which were ripened in storage and on the tree. PCS was, as a result, found to be useful in processing the obtained GC data for crude classification, preliminary to detailed analysis, e.g. obtained GC data for crude classification, preliminary to detained analysis, e.g. stepwise discriminant analysis.