Use Of Principal Component Analysis Research Articles

A Choice of Representative Sections for the Estimation of the Transport Network Loading

The problem of a choice of representative sections for transport network loading management is considered in the following article. To solve the problem, the use of Principal component analysis and the procedures of cluster analysis are offered. The example of the choice of representative sections at network traffic control is presented.

Simultaneous determination of organic acids and sugars in fruit juices by High performance liquid chromatography: characterization and differentiation of commercial juices by principal component analysis

ABSTRACT: The present research presents an analytical methodology based on High Performance Liquid Chromatography (HPLC) and Principal Component Analyses (PCA) for simultaneous quantification and analytical differentiation of organic acids and sugars in commercial fruit juice samples (orange, grape, apple and tangerine). In addition to the development of the method that generated suitable validation paramters for quantitative analytical applications, the analysis of fourteen commercial samples and the use of Principal Component Analysis indicated the relationship between the constituents and the very constitutional chemical nature of the juice. In general, in grape and apple juices, ascorbic acid was not quantified and the citric acid content was very low; however, the concentrations of fructose and glucose were the highest in both juices. In orange and mandarin orange juices, the content of all analytes, except acorbic acid, did not differ statistically from each other. However, these differed significantly from the others, mainly in relation to sucrose content. Finally, the apple juice samples differed according to the content of fructose and malic acid, the predominant constituint of the apple. Results showed that the simultaneous chromatographic method associated with principal component analysis generated important information about characteristics of commercial juices, with the potential to be used in systems of quality control and identification of adulterations.

Application of the principal component analysis (PCM) as an innovative technology for assessing the morphological and functional state of agricultural poultry with diseases of bacterial genesis

The possibility of using the method of principal components (PCM) for analyzing the results of hematological studies of blood samples of broiler chickens has been studied. It was found that the graphs of the residual dispersion show a clear clustering of samples into the control and experimental groups after infection in the PC1-PC2 space. The graphs of the scores, built for the higher BG models, showed changes in the values for the GC1 spectrum of leukocytes, and for the GC2 of erythrocytes, hemoglobin. Thus, the use of PCM analysis of hematological blood data makes it possible to separate blood samples from healthy broiler chickens and those susceptible to infection with various infections. PCM is a promising approach for rapid assessment of hematological data.

USED EIGENVALUES AND EIGENVECTORS TO COMPRESS THE IMAGE

The article’s main aim is to point out the significant applications of the linear algebra in the medical engineering field. Hence, the eigenvectors and eigenvalues which represent the core of linear algebra are discussed in details in order to show how they can be used in many engineering applications. The principal components analysis is one of the most important compression and feature extraction algorithms used in the engineering field (1). It mainly depends on the calculation and extraction of eigenvalues and eigenvectors that then used to represent an input; whether it's the image or a simple matrix. In this article, the use of principal component analysis for medical image compression is an important and novel application of linear algebra (2).

Convolutional Neural Networks with Transfer Learning for Recognition of COVID-19: A Comparative Study of Different Approaches

To judge the ability of convolutional neural networks (CNNs) to effectively and efficiently transfer image representations learned on the ImageNet dataset to the task of recognizing COVID-19 in this work, we propose and analyze four approaches. For this purpose, we use VGG16, ResNetV2, InceptionResNetV2, DenseNet121, and MobileNetV2 CNN models pre-trained on ImageNet dataset to extract features from X-ray images of COVID and Non-COVID patients. Simulations study performed by us reveal that these pre-trained models have a different level of ability to transfer image representation. We find that in the approaches that we have proposed, if we use either ResNetV2 or DenseNet121 to extract features, then the performance of these approaches to detect COVID-19 is better. One of the important findings of our study is that the use of principal component analysis for feature selection improves efficiency. The approach using the fusion of features outperforms all the other approaches, and with this approach, we could achieve an accuracy of 0.94 for a three-class classification problem. This work will not only be useful for COVID-19 detection but also for any domain with small datasets.

Large Dataset Classification Using Parallel Processing Concept

Much attention has been paid to large data technologies in the past few years mainly due to its capability to impact business analytics and data mining practices, as well as the possibility of influencing an ambit of a highly effective decision-making tools. With the current increase in the number of modern applications (including social media and other web-based and healthcare applications) which generates high data in different forms and volume, the processing of such huge data volume is becoming a challenge with the conventional data processing tools. This has resulted in the emergence of big data analytics which also comes with many challenges. This paper introduced the use of principal components analysis (PCA) for data size reduction, followed by SVM parallelization. The proposed scheme in this study was executed on the Spark platform and the experimental findings revealed the capability of the proposed scheme to reduce the classifiers’ classification time without much influence on the classification accuracy of the classifier.

Two centuries of painted plasters from the Lateran suburban villa (Rome): investigating supply routes and manufacturing of pigments

• Combined non-destructive analytical approach using portable instrumentation • Complementary techniques and multivariate analysis allow characterization of pigments • Improved knowledge on pigments production, sourcing and use in 27 BC – 193 AD Rome Polychrome painted plasters from a suburban villa of Imperial epoch were recovered during the 1930s, and are currently exhibited in the galleries underneath the St. John in Lateran Church, Rome. As wall paintings from the Rome area are a rare find, and as the fragments were never subjected to conservation treatments, it was chosen to non-invasively characterize 113 coloured areas, representative of colours and decorative systems. The chemical and mineralogical information collected from this measurement campaign were interpreted in the light of archaeological context (i.e. the high status of the family who owned the villa , the different renovation works that affected it, the identification of decorative systems linked to such works), as well as of published data from contemporary wall paintings in the Rome area. A multi-analytical, non-destructive characterization of the painted surfaces was carried out in situ by means of portable Raman spectroscopy (pRS) and X-ray fluorescence (pXRF), in the framework of a wider project concerning the study of raw materials and paintings of archaeological interest. The combination of pXRF and pRS allowed to characterize the whole palette, as well as to discriminate among different pigments sharing the same key element, and to identify degradation issues. In this context, the use of principal component analysis gave an important contribution to the interpretation of data ant to the individuation and characterization of pigments such as ochres, green earths, lead based pigments, Egyptian blue, cinnabar, Tyrian purple. Calcium and magnesium carbonates are present, as expected, in the plaster, and are often associated with their sulphates and nitrates, and Ca-oxalates indicating degradation. Lead white and bone white have been used. Some peculiar yellow pigments have been identified, such as realgar/pararealgar and Naples’ yellow, in addition to ochres. Hematite, minium and cinnabar were all identified, alone or in mixtures. The presence of the precious dye Tyrian purple is very likely, but could not be confirmed univocally. Green earths and complex mixtures of iron and copper compounds were detected. Egyptian blue was used, highlighting different production processes for this artificial glassy material. For the blacks, we hypothesize the use of carbon-based pigments. The obtained data confirms the general palette used by Roman painters, and sheds new light on the materials used in the Lateran area across two centuries, including their provenance and manufacturing. It appears that different earths and ochres were used diachronically, and that the owners could afford very expensive pigments, such as cinnabar and Tyrian purple.

Environmental Impact Assessment of Taza City's Wastewater: Application through Principal Component Analysis.

Taza City is among the Moroccan cities which is in full urban expansion, with a daily wastewater discharge volume estimated at 16534 m3/d in 2020, and expected to reach 20056 m3/d by 2030. These waters, collected in a combined sewerage network, are directly released into the natural environment without any treatment. Indeed, a large part of this water is discharged into Oued Defali, the main tributary of Oued Larbâa. In order to manage and better understand these discharges impact on the streams crossing this city, wastewater sampling campaigns were carried out for one year from May 2018 to April 2019 at domestic (S1) and industrial (S2) sites. The wastewater physicochemical characterization revealed that these discharges are highly loaded with organic matter in terms of chemical oxygen demand (S1 avg = 1231.44 mg/l and S2 avg = 933.03 mg/l), biochemical oxygen demand (S1 avg = 511.87 mg/l and S2 avg = 464.35 mg/l), and suspended matter (S1 avg = 744.11 mg/l and S2 avg = 578.13 mg/l). The use of principal component analysis (PCA) has allowed us to collect as much information as possible from the database of the physicochemical analyses performed for the studied parameters.

A Systematic Review of Methods and Criteria Standard Proposal for the Use of Principal Component Analysis in Team's Sports Science.

The availability of critical information about training and competition is fundamental on performance. Principal components analysis (PCA) is widely used in sports as a multivariate technique to manage big data from different technological assessments. This systematic review aimed to explore the methods reported and statistical criteria used in team’s sports science and to propose a criteria standard to report PCA in further applications. A systematic electronic search was developed through four electronic databases and a total of 45 studies were included in the review for final analysis. Inclusion criteria: (i) of the studies we looked at, 22.22% performed factorability processes with different retention criteria (r > 0.4–0.7); (ii) 21 studies confirmed sample adequacy using Kaiser-Meyer-Olkim (KMO > 5–8) and 22 reported Bartlett’s sphericity; (iii) factor retention was considered if eigenvalues >1–1.5 (n = 29); (iv) 23 studies reported loading retention (>0.4–0.7); and (v) used VariMax as the rotation method (48.9%). A lack of consistency and serious voids in reporting of essential methodological information was found. Twenty-one items were selected to provide a standard quality criterion to report methods sections when using PCA. These evidence-based criteria will lead to a better understanding and applicability of the results and future study replications.

Application of machine learning techniques in operating parameters prediction of Stirling cryocooler

The Stirling cryocoolers are widely used in the military and the aerospace fields due to many advantages such as high efficiency and compact structure. The output performance is affected by three parameters: compressor stroke, expander stroke, and the phase shift between them. How to quickly and effectively adjust the three parameters to meet the required cooling capacity with a higher COP is of great significance to the actual engineering application. When the cooling demand is changed, it takes a long time to calculate the corresponding high-efficiency operating parameters using the Stirling cryocooler simulation model on the market. In this paper, the prediction models of the optimal combination of operating parameters based on particle swarm optimization and commonly used machine learning techniques of back propagation neural network, support vector regression and random forest regression are established for the Stirling cryocooler. Besides, the impact of the two data preprocessing methods (min–max normalization and principal component analysis) on the PV power models and compressor stroke regression models based on three different machine learning techniques is analyzed, which shows that the use of principal component analysis can significantly enhance the performance of the back propagation neural network, and the normalization of the cryocooler parameters can improve the convergence of the support vector regression and the random forest regression. The results show that the regression models established by the three machine learning algorithms all have high accuracy and generalization. The regression model based on support vector machine has the best performance on the prediction of PV power and compressor stroke with small mean squared error, mean absolute error, average relative error, and high Pearson correlation coefficient. In addition, the research on the prediction models for the output performance is beneficial to propose a new control strategy, so as to improve the control system of the Stirling cryocooler.

Feature Selection for Monitoring Erosive Cavitation on a Hydroturbine

This paper presents a method for comparing and evaluating cavitation detection features - the first step towards estimating remaining useful life (RUL) of hydroturbine runners that areimpacted by erosive cavitation. The method can be used to quickly compare features created from cavitation survey data collected on any type of hydroturbine, sensor type, sensor location, and cavitation sensitivity parameter (CSP). Although manual evaluation and knowledge of hydroturbine cavitation is still required for our feature selection method, the use of principal component analysis greatly reduces the number of plots that require evaluation. We present a case study based on a cavitation survey data collected on a Francis hydroturbine located at a hydroelectric plant and demonstrate the selection of the most advantageous sensor type, sensor location, and CSP to use on this hydroturbine for long-term monitoring of erosive cavitation. Our method provides hydroturbine operators and researchers with a clear and effective means to determine preferred sensors, sensor placements, and CSPs while also laying the groundwork for determining RUL in the future.

Reducing data requirements when selecting key performance indicators for supply chain management: The case of a multinational automotive component manufacturer

The recent trend towards collecting large amounts of data potentially allows organisations to identify previously unknown data patterns that can lead to significant improvements in their performance. However, carrying on collecting this data over time and across numerous locations is expensive. Consequently, when monitoring performance, organisations can be faced with a dichotomy between continuing to collect large amounts of data or whether to use a much reduced set of data. This is a particular problem with Key Performance Indicators (KPIs). Additionally, too many indicators can lead to difficulty in data interpretation and significant overlaps between the indicators, making the understanding and managing of changes in performance more difficult. In this paper, a novel statistical approach is introduced based on the use of Principal Component Analysis (PCA) to reduce the number of KPIs, followed by TOPSIS (Technique for Order Performance by Similarity to Ideal Solution) for validating the results. It is applied to the case of a multinational automotive component manufacturer where 28 KPIs were reduced to 8. The performance of the original set of 28 KPIs was compared with that of the reduced set of 8 KPIs. The peaks of the two TOPSIS time-series coincided, and there was a high correlation between them. Therefore, having the extra 20 indicators provided little extra precision for the considered time interval. Hence, the approach is a valuable tool in helping to reduce a large number of KPIs down to a more practical and useable number.

Use of Principal Component Analysis and Cluster Analysis for Differentiation of Traditionally-Manufactured Vinegars Based on Phenolic and Volatile Profiles, and Antioxidant Activity

Use of Principal Component Analysis and Cluster Analysis for Differentiation of Traditionally-Manufactured Vinegars Based on Phenolic and Volatile Profiles, and Antioxidant Activity

A novel approach to stance detection in social media tweets by fusing ranked lists and sentiments

Stance detection is a relatively new concept in data mining that aims to assign a stance label (favor, against, or none) to a social media post towards a specific pre-determined target. These targets may not be referred to in the post, and may not be the target of opinion in the post. In this paper, we propose a novel enhanced method for identifying the writer’s stance of a given tweet. This comprises a three-phase process for stance detection: (a) tweets preprocessing; here we clean and normalize tweets (e.g., remove stop-words) to generate words and stems lists, (b) features generation; in this step, we create and fuse two dictionaries for generating features vector, and lastly (c) classification; all the instances of the features are classified based on the list of targets. Our innovative feature selection proposes fusion of two ranked lists (top-k) of term frequency-inverse document frequency (tf-idf) scores and the sentiment information. We evaluate our method using six different classifiers: K nearest neighbor (K-NN), discernibility-based K-NN, weighted K-NN, class-based K-NN, exemplar-based K-NN, and Support Vector Machines. Furthermore, we investigate the use of Principal Component Analysis and study its effect on performance. The model is evaluated on the benchmark dataset (SemEval-2016 task 6), and the results significance is determined using t-test. We achieve our best performance of macro F-score (averaged across all topics) of 76.45% using the weighted K-NN classifier. This tops the current state-of-the-art score of 74.44% on the same dataset.

Employment and labor policies. The case of Italy

This study analyses the impact of labor policies introduced in the last twenty years in Italy focusing on the direct influence on employment. Using different socio-economic variables and through the use of Principal Component Analysis and a generalized linear model (GLM), the analysis: i) highlights there is no empirical evidence to support that the Monti-Fornero and Jobs Act reforms have a statistically significant impact on the determination of employment levels in recent years.; ii) identifies the main variables that have a significant impact on the determination of employment in Italy. These findings confirm that the current situation is far from being considered desirable, not only for the reduction of workers' rights, but above all because this downsizing has not led to any substantial economic growth and hasn’t helped to improve the structural conditions of the labor market. It would be desirable to understand what are the real determinants of sustainable economic growth, which are not to be found in the management of labor costs (especially in large companies), but instead lie in the dimensions of innovation, technological integration, the capacity of organizations companies to retain talent, human capital and skilled labor and to encourage work productivity through the flexibility of working conditions and the quality of life of employees.

An IL-6-IL-8 score derived from principal component analysis is predictive of adverse outcome in acute myocardial infarction

IntroductionMany studies have shown that elevated biomarkers of inflammation following acute myocardial infarction (AMI) are associated with major adverse cardiovascular events (MACE). However, the optimal way of measuring the complex inflammatory response following AMI has not been determined. In this study we explore the use of principal component analysis (PCA) utilising multiple inflammatory cytokines to generate a combined cytokine score that may be predictive of MACE post-AMI. MethodsThirteen inflammatory cytokines were measured in plasma of 317 AMI patients, drawn 48–72 h following symptom onset. Patients were followed-up for one year to determine the incidence of MACE. PCA was used to generate a combined score using six cytokines that were detectable in the majority of patients (IL-1β, -6, -8, and -10; MCP-1; and RANTES), and using a subset of cytokines that were associated with MACE on univariate analysis. Multivariate models using baseline characteristics, elevated individual cytokines and PCA-derived scores determined independent predictors of MACE. ResultsIL-6 and IL-8 were significantly associated with MACE on univariate analysis and were combined using PCA into an IL-6-IL-8 score. The combined cytokine score and IL-6-IL-8 PCA-derived score were both significantly associated with MACE on univariate analysis. In multivariate models IL-6-IL-8 scores (OR = 2.77, p = 0.007) and IL-6 levels (OR = 2.18, p = 0.035) were found to be independent predictors of MACE. ConclusionAn IL-6-IL-8 score derived from PCA was found to independently predict MACE at one year and was a stronger predictor than any individual cytokine, which suggests this may be an appropriate strategy to quantify inflammation post-AMI. Further investigation is required to determine the optimal set of cytokines to measure in this context.

THE INFLUENCE OF THE PRINCIPAL COMPONENT ANALYSIS OF TEXTURE FEATURES ON THE CLASSIFICATION QUALITY OF SPONGE TISSUE IMAGES

The aim of this article was to determine the effect of principal component analysis on the results of classification of spongy tissue images. Four hundred computed tomography images of the spine (L1 vertebra) were used for the analyses. The images were from fifty healthy patients and fifty patients diagnosed with osteoporosis. The obtained tissue image samples with a size of 50x50 pixels were subjected to texture analysis. As a result, feature descriptors based on a grey level histogram, gradient matrix, RL matrix, event matrix, autoregressive model and wavelet transform were obtained. The results obtained were ranked in importance from the most important to the least important. The first fifty features from the ranking were used for further experiments. The data were subjected to the principal component analysis, which resulted in a set of six new features. Subsequently, both sets (50 and 6 traits) were classified using five different methods: naive Bayesian classifier, multilayer perceptrons, Hoeffding Tree, 1-Nearest Neighbour and Random Forest. The best results were obtained for data on which principal components analysis was performed and classified using 1-Nearest Neighbour. Such an algorithm of procedure allowed to obtain a high value of TPR and PPV parameters, equal to 97.5%. In the case of other classifiers, the use of principal component analysis worsened the results by an average of 2%.

Participation in global value chains and varieties of development patterns

Abstract This paper relates participation in global value chains (GVCs) to development patterns at the country level. It accounts for the diversity and interdependence of development through a cross-country analysis for 51 countries between 1995 and 2008. We identify three patterns of socio-economic development related to various degrees and modes of GVC participation: a social upgrading mirage, the reproduction of the core and unequal growth. This result is achieved thanks to the introduction of two new elements to the literature: first, the introduction of new macroeconomic indicators of GVC participation and economic gains that are explicitly based in a theoretically consistent definition of GVCs; second, the identification of a variety of interdependent development patterns related to GVC participation through the use of principal component analysis and cluster analysis.

Disaggregating Ecosystem Benefits: An Integrated Environmental-Deprivation Index

The valuation of ecosystem services has become an integral part of smart urban planning practices. Traditionally designed to bridge ecology and economy through economic language and logic (e.g., goods and services), this conceptual framework has developed into an effective tool for interdisciplinary work. The concept of ecosystem services is used to improve the management of ecosystems for human well-being. However, gaps in how to govern ecological benefits remain. Specifically, identifying which stakeholders benefit the most from the provision of ecosystem services remains largely unaddressed. This study examines the spatial discordance between ecosystem services and the residential stakeholders who may benefit. Using a landscape approach to quantify urban ecosystem services, an area-based composite index was developed for the City of Toronto, Canada, based on the three pillars of sustainability in order to identify potentially vulnerable populations. This method combines the use of principal component analysis (PCA) and spatial multicriteria decision analysis (GIS-MCDA) to combine and weight a select grouping of socioeconomic and ecological indicators. In addition, two sets of enumeration units (i.e., dissemination areas and census tracts) were evaluated to assess the potential impact of measurement scale on subsequent decision or policy outcomes. Results indicate the spatial interdependencies between ecological and socioeconomic processes in an urban setting, offering a unique framework for novel planning and policy intervention strategies. The influence of measurement scale was demonstrated, creating an opportunity to assess an appropriate policy scale by which to measure and evaluate trends over time and space. This approach seeks to provide a flexible and intuitive planning tool that can help to achieve goals relating to urban sustainability, resiliency and equity.

A robust methodology for predicting extreme structural responses of offshore wind turbines

ABSTRACT This paper proposes a robust methodology for predicting extreme structural responses of offshore wind turbines. This robust methodology starts with forecasting an improved IFORM (Inverse-First-Order Reliability Method) environmental contour line through the use of principal component analysis. It then performs stochastic time domain simulations of an offshore wind turbine based on the information of the highest sea state identified along the aforementioned environmental contour line. Next, an enhanced Peaks-Over-Threshold (POT) method is utilised for fitting an extreme value distribution based on which a long-term extreme structural response can finally be obtained. A specific example of predicting the 50-year extreme structural responses of a monopile-supported 5MW offshore wind turbine will be provided in this paper for demonstrating the robustness of our proposed methodology.