Joint Principal Component Analysis Research Articles

Joint principal component analysis and BP neural network to measure the development level of modern logistics in China

Joint principal component analysis and BP neural network to measure the development level of modern logistics in China

Joint Principal Component Analysis and Supervised k Means Algorithm via Non-Iterative Analytic Optimization Approach

Joint Principal Component Analysis and Supervised <i>k</i> Means Algorithm via Non-Iterative Analytic Optimization Approach

Segmentation of unsteady cavitation flow fields based on multivariate spatiotemporal hierarchical clustering

Clustering applied to unsteady flow fields can simplify flow field data and partition the flow field into regions of interest. Unfortunately, these areas are often unexplored when applied to complex fluid mechanics problems because multivariate data are difficult to express, and the relationships between flow field snapshots in a time series are difficult to preserve. In this paper, we use joint principal component analysis (JPCA) and fusion principal component analysis (FPCA) to process multivariate data to obtain the static and dynamic characteristics of the cavitation flow field. Based on the static characteristics of the flow field, we use the K-means algorithm and cohesive hierarchical clustering to obtain static flow field segmentation at different levels. Based on the dynamic characteristics of the flow field, we use the proposed time series K-means (TK-means) algorithm and cohesive hierarchical clustering to obtain dynamic flow field segmentation at different levels. The results show that JPCA or FPCA is effective in expressing multivariate features. Static flow field segmentation can obtain time-invariant, physically related structures of unsteady flow. Dynamic flow field segmentation can obtain time-varying, physically related structures of unsteady flow.

Joint principal component analysis and total variation for infrared and visible image fusion

Joint principal component analysis and total variation for infrared and visible image fusion

A Novel Approach to Measuring Spatiotemporal Changes in Social Vulnerability at the Local Level in Portugal

Social vulnerability, as one of the risk components, partially explains the magnitude of the impacts observed after a disaster. In this study, a spatiotemporally comparable assessment of social vulnerability and its drivers was conducted in Portugal, at the civil parish level, for three census frames. The first challenging step consisted of the selection of meaningful and consistent variables over time. Data were normalized using the Adjusted Mazziotta-Pareto Index (AMPI) to obtain comparable adimensional-normalized values. A joint principal component analysis (PCA) was applied, resulting in a robust set of variables, interpretable from the point of view of their self-grouping around vulnerability drivers. A separate PCA for each census was also conducted, which proved to be useful in analyzing changes in the composition and type of drivers, although only the joint PCA allows the monitoring of spatiotemporal changes in social vulnerability scores and drivers from 1991 to 2011. A general improvement in social vulnerability was observed for Portugal. The two main drivers are the economic condition (PC1), and aging and depopulation (PC2). The remaining drivers highlighted are uprooting and internal mobility, and daily commuting. Census data proved their value in the territorial, social, and demographic characterization of the country, to support medium- and long-term disaster risk reduction measures.

Development of a Novel Neuro-immune and Opioid-Associated Fingerprint with a Cross-Validated Ability to Identify and Authenticate Unknown Patients with Major Depression: Far Beyond Differentiation, Discrimination, and Classification.

Major depressive disorder (MDD) is characterized by signaling aberrations in interleukin (IL)-6, IL-10, beta-endorphins as well as μ (MOR) and κ (KOR) opioid receptors. Here we examined whether these biomarkers may aid in the classification of unknown subjects into the target class MDD. The aforementioned biomarkers were assayed in 60 first-episode, drug-naïve depressed patients and 30 controls. We used joint principal component analysis (PCA) performed on all subjects to check whether subjects cluster by classes; support vector machine (SVM) with 10-fold validation; and linear discriminant analysis (LDA) and SIMCA performed on calibration and validation sets and we computed the figures of merit and learnt from the data. PCA shows that both groups were well separated using the first three PCs, while correlation loadings show that all five biomarkers have discriminatory value. SVM and LDA yielded an accuracy of 100% in validation samples. Using SIMCA, there was a highly significant discrimination of both groups (model-to-model distance = 110.2); all biomarkers showed a significant discrimination and modeling power, while 100% of the patients were authenticated as MDD cases with a specificity of 93.3%. We have delineated that MDD is a distinct class with respect to neuro-immune and opioid biomarkers and that future unknown subjects can be authenticated as having MDD using this SIMCA fingerprint. Precision psychiatry should employ SIMCA to (a) authenticate patients as belonging to the claimed target class and identify other subjects as outsiders, members of another class, or aliens; and (b) acquire knowledge through learning from the data by constructing a biomarker fingerprint of the target class.

Group Method of Data Handling (GMDH) Lithology Identification Based on Wavelet Analysis and Dimensionality Reduction as Well Log Data Pre-Processing Techniques

Although the group method of data handling (GMDH) is a self-organizing metaheuristic neural network capable of developing a classification function using influential input variables, the results can be improved by using some pre-processing steps. In this paper, we propose a joint principal component analysis (PCA) and GMDH (PCA-GMDH) classifier method. We investigated well log data pre-processing techniques composed of dimensionality reduction (DR) and wavelet analysis (WA), using the southern basin of the South Yellow Sea as a case study, with the aim of improving the lithology classification accuracy of the GMDH. Our results showed that the dimensionality reduction method, which is composed of PCA and linear discriminant analysis (LDA), minimized the complexity of the classifier by reducing the number of well log suites to the relevant components and factors. On the other hand, the WA decomposed the well log signals into time-frequency wavelets for the GMDH algorithm. Of all the pre-processing methods, only the PCA was able to significantly increase the classification accuracy rate of the GMDH. Finally, the proposed joint PCA-GMDH classifier not only increased the accuracy but also was able to distinguish between all the classes of lithofacies present in the southern basin of the South Yellow Sea.

A general framework for multivariate functional principal component analysis of amplitude and phase variation

Functional data typically contain amplitude and phase variation. In many data situations, phase variation is treated as a nuisance effect and is removed during preprocessing, although it may contain valuable information. In this note, we focus on joint principal component analysis (PCA) of amplitude and phase variation. As the space of warping functions has a complex geometric structure, one key element of the analysis is transforming the warping functions to . We present different transformation approaches and show how they fit into a general class of transformations. This allows us to compare their strengths and limitations. In the context of PCA, our results offer arguments in favour of the centred log‐ratio transformation. We further embed two existing approaches from the literature for joint PCA of amplitude and phase variation into the framework of multivariate functional PCA, where we study the properties of the estimators based on an appropriate metric. The approach is illustrated through an application from seismology.

Are vital exhaustion and depression independent risk factors for cardiovascular disease morbidity?

The aim of this study was to examine the concurrent effects of vital exhaustion and depression on the development of cardiovascular disease (CVD) morbidity. The sample of this representative, 4-year longitudinal study comprised 2,725 participants (43.56% male, Mage = 58.39 years, SDage = 14.39 years). Individuals being treated for hypertension (n = 277) and cardio- and/or cerebrovascular incidents (n = 131) for the first time during the follow-up period were compared with participants never treated for CVD (n = 2,317). Joint principal component analysis was conducted on the items of the vital exhaustion (shortened Maastricht Questionnaire) and depression (shortened Beck Depression Inventory) measures simultaneously resulting in 3 components representing depression, vital exhaustion, and sleep difficulties. The role of these 3 components in predicting the incidence of CVD morbidity was examined using logistic regression-controlling for traditional risk factors such as sex, age, education, body mass index, smoking, alcohol use, and physical inactivity. In the multivariate analyses, vital exhaustion (OR = 1.20, CI = 1.03-1.39, p = .021) and sleep-related problem (OR = 1.16, CI = 1.00-1.33, p = .044) scores proved to be independent predictors of treatment initiation for hypertension, while sleep-related difficulties predicted CVD event incidence (OR = 1.27, CI = 1.06-1.52, p = .009). However, depressive symptomatology factor scores were not associated with either cardiovascular outcome in the regression analyses. Vital exhaustion and depressive symptomatology showed a different pattern in their relationship with CVD incidence, with vital exhaustion being the more robust predictor. These results suggest that the 2 constructs are not identical and that vital exhaustion deserves consideration when planning and implementing interventions to reduce CVD risk. (PsycINFO Database Record

Strategije prevladavanja stresa u kontekstu Teorije osetljivosti na potkrepljenje

Istraživanje predstavljeno ovim radom imalo je za cilj sagledavanje strukturalnih sličnosti Grejovog reformulisanog modela osetljivosti na potkrepljenje i Amirkhanovog trokomponentnog modela strategija prevladavanja stresa. U istraživanju je učestvovalo 297 ispitanika, od toga 186 ženskog te 111 muškog pola prosečne starosti 21.5 godinu. Primenjen je Indikator strategija prevladavanja (CSI; Amirkhan, 1990) i Upitnik za procenu osetljivosti na potkrepljenje (UOP; Mitrović, Smederevac i Čolović, 2008). Objedinjena analiza glavnih komponenti nad sumativnim skorovima supskala oba upitnika dala je tri nekorelirane komponente koje ukupno objašnjavaju 68.81% varijanse, od kojih prva okuplja izbegavajuće strategije prevladavanja, te anksioznost, borbu i blokiranje, dok se druge dve komponente okupljaju isključivo strategije prevladavanja, odnosno varijable ličnosti. Konfirmatornom faktorskom analizom testirano je ukupno šest modela od kojih poslednja dva ostvaruju najbolje indikatore fita. Dobijeni nalazi obezbeđuju nedvosmislenu potvrdu povezanosti jedino dimenzije anksioznosti i izbegavajućih strategija prevladavanja, ali je dodatnim analizama otkrivena i blago pozitivna relacija strategije traženja socijalne podrške i impulsivnosti kao manifestacije sistema bihejvioralne aktivacije, koja je njihovim pojedinačnim korelacijama sa supsistemom Borbe bila maskirana. Generalno, možemo zaključiti da strategije izbegavanja i traženja socijalne podrške dele prostor merenja sa dimenzijama ličnosti, dok se strategija usmerenosti na problem zbog svoje specifične upitničke operacionalizacije izoluje kao specifičan konstrukt. Smatramo da bi uključivanje seta mera kognitivne efikasnosti u postojeći nacrt dalo potpuniju sliku o bazičnoj dinamici latentnog prostora ovih konstrukata.

How Are Traits Related to Problem Behavior in Preschoolers? Similarities and Contrasts Between Temperament and Personality

The lack of empirical research relating temperament models and personality hinders conceptual integration and holds back research linking childhood traits to problem behavior or maladjustment. This study evaluates, within a sample of 443 preschoolers, the relationships between children's maladaptation and traits measured by three temperament models (Thomas and Chess, Buss and Plomin, and Rothbart), and a Five-Factor based personality model. Adequate reliabilities and expected factor structures are demonstrated for most scales. A joint principal component analysis combining 28 temperament and 18 personality scales indicates a six-factor model, distinguishing Sociability, Activity, Conscientiousness, Disagreeableness, Emotionality, and Sensitivity. Regression analyses reveal that although single temperament and personality scales explain from 23% to 37% of problem behavior variance, the six components explain from 41% to 49% and provide a clearer differentiation among CBCL-problem scales. This age-specific taxonomy refines and corroborates conclusions based on narrative reviews and furnishes a more balanced view of trait-maladjustment relationships.

High seedling recruitment of indigenous tree species in forest plantations in Kakamega Forest, western Kenya

Tree plantations are often used to compensate for the destruction and conversion of natural forests in the tropics. An important question is whether these plantations allow for the regeneration of indigenous tree species and are expected to transform into more natural forests in the future. To evaluate the potential of differently managed forest types for seedling recruitment of indigenous tree species we studied structural characteristics as well as tree and seedling communities in stands of natural forest, different types of tree plantations and secondary forest in Kakamega Forest, western Kenya. Forest types differed considerably in structural characteristics and tree composition with stands of natural forest significantly differing from all other forest types in vertical foliage height diversity and number of late-successional tree species. By contrast, total seedling species richness and number did not differ among the forest types. Yet, number of seedlings of late-successional species decreased from natural forest and plantations of a mixture of indigenous tree species towards monocultures and secondary forests while number of seedlings of early-successional species increased in the same order. A joint Principal Component Analysis (PCA) corroborated higher similarity among seedling communities than among tree communities. Our results indicate a convergence of recruiting seedling communities in different forest management types suggesting that tree plantations might buffer forest loss to a certain extent and may have the potential to develop into more natural forest over time.

Construct validity of multidimensional personality questionnaire (MPQ)

The paper presents two studies aimed at the examination of the factor structure of The Multidimensional Personality Questionnaire (MPQ) and joint factor structure of the scales of MPQ and SPSRQ (The Sensitivity to Punishment and Sensitivity to Reward Questionnaire). In the first research conducted on the sample of 1127 participants of both sexes, age 18 to 67, the results of the principal component analysis of the MPQ scales point to the existence of three higher-order dimensions, named General Adaptedness, Psychopathic Tendencies and Negative Emotionality. These dimensions correspond to the dimensions of the Eysenck?s PEN model to the greater extent than they achieve the assumed similarity with the dimensions of the Reinforcement Sensitivity Theory. In the second study conducted on the sample of 199 respondents of both sexes, age 18 to 59, the results of the joint principal component analysis of the MPQ and SPSRQ scales point to the existence of three higher order dimensions, which correspond to the Tellegen?s Positive Emotionality, Negative Emotionality, and Constraint. .