Combination Of Principal Component Analysis Research Articles

Quality prediction modeling for multistage manufacturing based on classification and association rule mining

For manufacturing enterprises, product quality is a key factor to assess production capability and increase their core competence. To reduce external failure cost, many research and methodology have been introduced in order to improve process yield rate, such as TQC/TQM, Shewhart CycleDeming's 14 Points, etc. Nowadays, impressive progress has been made in process monitoring and industrial data analysis because of the Industry 4.0 trend. Industries start to utilize quality control (QC) methodology to lower inspection overhead and internal failure cost. Currently, the focus of QC is mostly in the inspection of single workstation and final product, however, for multistage manufacturing, many factors (like equipment, operators, parameters, etc.) can have cumulative and interactive effects to the final quality. When failure occurs, it is difficult to resume the original settings for cause analysis. To address these problems, this research proposes a combination of principal components analysis (PCA) with classification and association rule mining algorithms to extract features representing relationship of multiple workstations, predict final product quality, and analyze the root-cause of product defect. The method is demonstrated on a semiconductor data set.

The Application of Advanced Design of Experiments for the Efficient Development of Chemical Processes

The combination of Principal Component Analysis (PCA) with Design of Experiments (DoE) is a powerful and very efficient tool for optimising chemical processes. This article explains how to apply PCA and DoE, and demonstrates the benefits with three case studies.

Inferring the core-collapse supernova explosion mechanism with gravitational waves

A detection of a core-collapse supernova (CCSN) gravitational-wave (GW) signal with an Advanced LIGO and Virgo detector network may allow us to measure astrophysical parameters of the dying massive star. GWs are emitted from deep inside the core, and, as such, they are direct probes of the CCSN explosion mechanism. In this study, we show how we can determine the CCSN explosion mechanism from a GW supernova detection using a combination of principal component analysis and Bayesian model selection. We use simulations of GW signals from CCSN exploding via neutrino-driven convection and rapidly rotating core collapse. Previous studies have shown that the explosion mechanism can be determined using one LIGO detector and simulated Gaussian noise. As real GW detector noise is both nonstationary and non-Gaussian, we use real detector noise from a network of detectors with a sensitivity altered to match the advanced detectors design sensitivity. For the first time, we carry out a careful selection of the number of principal components to enhance our model selection capabilities. We show that with an advanced detector network we can determine if the CCSN explosion mechanism is driven by neutrino convection for sources in our Galaxy and rapidly-rotating core collapse for sources out to the Large Magellanic Cloud.

A PCA-based bio-motion generator to synthesize new patterns of human running

Synthesizing human movement is useful for most applications where the use of avatars is required. These movements should be as realistic as possible and thus must take into account anthropometric characteristics (weight, height, etc.), gender, and the performance of the activity being developed. The aim of this study is to develop a new methodology based on the combination of principal component analysis and partial least squares regression model that can generate realistic motion from a set of data (gender, anthropometry and performance). A total of 18 volunteer runners have participated in the study. The joint angles of the main body joints were recorded in an experimental study using 3D motion tracking technology. A five-step methodology has been employed to develop a model capable of generating a realistic running motion. The described model has been validated for running motion, showing a highly realistic motion which fits properly with the real movements measured. The described methodology could be applied to synthesize any type of motion: walking, going up and down stairs, etc. In future work, we want to integrate the motion in realistic body shapes, generated with a similar methodology and from the same simple original data.

Forecasting of UV-Vis absorbance time series using artificial neural networks combined with principal component analysis.

This work proposes a methodology for the forecasting of online water quality data provided by UV-Vis spectrometry. Therefore, a combination of principal component analysis (PCA) to reduce the dimensionality of a data set and artificial neural networks (ANNs) for forecasting purposes was used. The results obtained were compared with those obtained by using discrete Fourier transform (DFT). The proposed methodology was applied to four absorbance time series data sets composed by a total number of 5705 UV-Vis spectra. Absolute percentage errors obtained by applying the proposed PCA/ANN methodology vary between 10% and 13% for all four study sites. In general terms, the results obtained were hardly generalizable, as they appeared to be highly dependent on specific dynamics of the water system; however, some trends can be outlined. PCA/ANN methodology gives better results than PCA/DFT forecasting procedure by using a specific spectra range for the following conditions: (i) for Salitre wastewater treatment plant (WWTP) (first hour) and Graz West R05 (first 18 min), from the last part of UV range to all visible range; (ii) for Gibraltar pumping station (first 6 min) for all UV-Vis absorbance spectra; and (iii) for San Fernando WWTP (first 24 min) for all of UV range to middle part of visible range.

Prediction of permeability and porosity from well log data using the nonparametric regression with multivariate analysis and neural network, Hassi R’Mel Field, Algeria

Most commonly, to estimate permeability, we can use values of porosity, pore size distribution, and water saturation from logging data and established correlations. One benefit of using wireline log data to estimate permeability is that it can provide a continuous permeability profile throughout a particular interval.This study will focus on the evaluation of formation permeability for a sandstone reservoir in the reservoir formations of Hassi R’Mel Field Southern from well log data using the multivariate methods. In order to improve the permeability estimation in these reservoirs, several statistical regression techniques have already been tested in previous work to correlate permeability with different well logs. It has been shown that statistical regression for data correlation is quite promising. We propose a two-step approach to permeability prediction that utilizes non-parametric regression in conjunction with multivariate statistical analysis. First we classify the well log data into electrofacies types. A combination of principal component analysis, model-based cluster analysis and discriminant analysis is used to characterize and identify electrofacies types. Second, we apply non-parametric regression techniques to predict permeability using well logs within each electrofacies. Three non-parametric approaches are examined via alternating conditional expectations (ACE), generalized additive model (GAM) and neural networks (NNET) and the relative advantages and disadvantages are explored. The results are compared with three other approaches to permeability predictions that utilize data partitioning based on reservoir layering, lithofacies information and hydraulic flow units. An examination of the error rates associated with discriminant analysis for uncored wells indicates that data classification based on electrofacies characterization is more robust compared to other approaches.These methods are tested and compared at the heterogeneous reservoirs in Triassic formations of Hassi R’Mel. The results show that permeability prediction is improved by applying variable selection to non-parametric regression ACE while tree regression is unable to predict permeability.In comparing the relative predictive performance of the three regression methods, the alternating conditional expectations with ACE method appears to outperform the other two methods.

The Influence of Research & Development Policy on Business-Sector Performance: The Baltic States in the EU

The success of business-sector research and development (R&D) activities and innovation performance is dependent on general development conditions (path dependency), but also on the efficiency of public R&D policy measures, which supports business-sector R&D activities directed towards innovation. In the current article we present a holistic approach based on macro-quantitative analysis for characterizing the role of the public sector in shaping business-sector R&D activities and innovation performance. The influence of R&D policy on business-sector R&D activities in EU member states (and countries closely associated with them) will be empirically analyzed with the combined methods of principal component analysis and multiple regression analysis. The goal of the article is to explore new possibilities of the macro-quantitative approach for policy-influence analysis and to assess on the basis of constructed models the situation in the Baltic States, which have, after the transformation from command to market economy, chosen different approaches to R&D policy. The article reports on the following research tasks: (1) an analysis of the role (needs and opportunities) of R&D policy for shaping business-sector R&D activities and innovation performance; (2) a presentation of the new opportunities to develop the macro-quantitative modelling of R&D policy influence through the combination of principal component analysis (PCA) and multiple regression analysis methods; and (3) an assessment of the results of R&D policy influence on business-sector R&D activities and innovation performance in the Baltic States, based on constructed statistical models. Data from 2004, 2006, 2008, and 2010 has been used. Large discrepancies can be found in both theoretical and empirical approaches to the formation of business-sector R&D activities and innovation performance. In the current study, available theoretical studies are systematized, the solution for some statistical modelling problems in available empirical studies is demonstrated, and finally, the assessment of the influence of R&D policy on the business sector in small Baltic States is provided in comparison to the sample of investigated countries.

Characterization of Yeasts and Filamentous Fungi using MALDI Lipid Phenotyping

Matrix-assisted laser desorption/ionization mass spectrometry (MALDI-MS) becomes the method of choice for the rapid identification of microorganisms (i.e. protein biotyping). Although bacterial identification is already quite advanced, biotyping of other microbes including yeasts and fungi are still under development. In this context, lipids (e.g. membrane phospholipids) represent a very important group of molecules with essential functions for cell survival and adaptation to specific environments and habitats of the microorganisms. Therefore, lipids show the potential to serve as additional molecular parameters to be used for biotyping purposes. In this paper we present a molecular characterisation of yeasts and filamentous fungi based on the analysis of lipid composition by MALDI-MS (i.e. MALDI lipid phenotyping). Using a combination of Principal Component Analysis (PCA) and Hierarchical Clustering we could demonstrate that this approach allowed a classification and differentiation of several groups of yeasts (e.g. Saccharomyces) and filamentous fungi (e.g. Aspergillus, Penicillium, Trichoderma) at the species/strain level. By analysing the MALDI lipid profiles we were able to differentiate 26 closely related yeast strains, for which discrimination via genotypic methods like AFLP in this case are relatively more elaborate. Moreover, employing statistical analysis we could identify those lipid parameters (e.g. PCs and LPCs), which were responsible for the differentiation of the strains, thus providing insights into the molecular basis of our results. In summary, MALDI lipid phenotyping represents a suitable method for fungal characterization and shows the potential to be used as companion tool to genotyping and/or protein biotyping for the characterization and identification of yeasts and fungi in diverse areas (e.g. environmental, pharmaceutical, clinical applications, etc.).

Classification of EEG based-mental fatigue using principal component analysis and Bayesian neural network.

This paper presents an electroencephalography (EEG) based-classification of between pre- and post-mental load tasks for mental fatigue detection from 65 healthy participants. During the data collection, eye closed and eye open tasks were collected before and after conducting the mental load tasks. For the computational intelligence, the system uses the combination of principal component analysis (PCA) as the dimension reduction method of the original 26 channels of EEG data, power spectral density (PSD) as feature extractor and Bayesian neural network (BNN) as classifier. After applying the PCA, the dimension of the data is reduced from 26 EEG channels in 6 principal components (PCs) with above 90% of information retained. Based on this reduced dimension of 6 PCs of data, during eyes open, the classification pre-task (alert) vs. post-task (fatigue) using Bayesian neural network resulted in sensitivity of 76.8 %, specificity of 75.1% and accuracy of 76% Also based on data from the 6 PCs, during eye closed, the classification between pre- and post-task resulted in a sensitivity of 76.1%, specificity of 74.5% and accuracy of 75.3%. Further, the classification results of using only 6 PCs data are comparable to the result using the original 26 EEG channels. This finding will help in reducing the computational complexity of data analysis based on 26 channels of EEG for mental fatigue detection.

Combination of principal component analysis and time-frequency representations of multichannel vibration data for gearbox fault detection

A multichannel vibration data processing method in the context of local damage detection in gearboxes is presented in this paper. The purpose of the approach is to achieve more reliable information about local damage by using several channels in comparison to results obtained by single channel vibration analysis. The method is a combination of time-frequency representation and Principal Component Analysis (PCA) applied not to the raw time series but to each slice (along the time) from its spectrogram. Finally, we create a new time-frequency map which aggregated clearly indicates presence of the damage. Details and properties of this procedure are described in this paper, along with comparison to single-channel results. We refer to autocorrelation function of the new aggregated time frequency map (1D signal) or simple spectrum (that might be somehow linked to classical envelope analysis). The results are very convincing – cyclic impulses associated with local damage might be clearly detected. In order to validate our method, we used a model of vibration data from heavy duty gearbox exploited in mining industry.

Principal component analysis vs. self-organizing maps combined with hierarchical clustering for pattern recognition in volcano seismic spectra

Variations in the spectral content of volcano seismicity related to changes in volcanic activity are commonly identified manually in spectrograms. However, long time series of monitoring data at volcano observatories require tools to facilitate automated and rapid processing. Techniques such as self-organizing maps (SOM) and principal component analysis (PCA) can help to quickly and automatically identify important patterns related to impending eruptions. For the first time, we evaluate the performance of SOM and PCA on synthetic volcano seismic spectra constructed from observations during two well-studied eruptions at Klauea Volcano, Hawai'i, that include features observed in many volcanic settings. In particular, our objective is to test which of the techniques can best retrieve a set of three spectral patterns that we used to compose a synthetic spectrogram. We find that, without a priori knowledge of the given set of patterns, neither SOM nor PCA can directly recover the spectra. We thus test hierarchical clustering, a commonly used method, to investigate whether clustering in the space of the principal components and on the SOM, respectively, can retrieve the known patterns. Our clustering method applied to the SOM fails to detect the correct number and shape of the known input spectra. In contrast, clustering of the data reconstructed by the first three PCA modes reproduces these patterns and their occurrence in time more consistently. This result suggests that PCA in combination with hierarchical clustering is a powerful practical tool for automated identification of characteristic patterns in volcano seismic spectra. Our results indicate that, in contrast to PCA, common clustering algorithms may not be ideal to group patterns on the SOM and that it is crucial to evaluate the performance of these tools on a control dataset prior to their application to real data.

A Comparison of Classification Methods for Telediagnosis of Parkinson’s Disease

Parkinson’s disease (PD) is a progressive and chronic nervous system disease that impairs the ability of speech, gait, and complex muscle-and-nerve actions. Early diagnosis of PD is quite important for alleviating the symptoms. Cost effective and convenient telemedicine technology helps to distinguish the patients with PD from healthy people using variations of dysphonia, gait or motor skills. In this study, a novel telemedicine technology was developed to detect PD remotely using dysphonia features. Feature transformation and several machine learning (ML) methods with 2-, 5- and 10-fold cross-validations were implemented on the vocal features. It was observed that the combination of principal component analysis (PCA) as a feature transformation (FT) and k-nearest neighbor (k-NN) as a classifier with 10-fold cross-validation has the best accuracy as 99.1%. All ML processes were applied to the prerecorded PD dataset using a newly created program named ParkDet 2.0. Additionally, the blind test interface was created on the ParkDet so that users could detect new patients with PD in future. Clinicians or medical technicians, without any knowledge of ML, will be able to use the blind test interface to detect PD at a clinic or remote location utilizing internet as a telemedicine application.

Quantitative proteomics reveals protein profiles underlying major transitions in aspen wood development.

BackgroundWood development is of outstanding interest both to basic research and industry due to the associated cellulose and lignin biomass production. Efforts to elucidate wood formation (which is essential for numerous aspects of both pure and applied plant science) have been made using transcriptomic analyses and/or low-resolution sampling. However, transcriptomic data do not correlate perfectly with levels of expressed proteins due to effects of post-translational modifications and variations in turnover rates. In addition, high-resolution analysis is needed to characterize key transitions. In order to identify protein profiles across the developmental region of wood formation, an in-depth and tissue specific sampling was performed.ResultsWe examined protein profiles, using an ultra-performance liquid chromatography/quadrupole time of flight mass spectrometry system, in high-resolution tangential sections spanning all wood development zones in Populus tremula from undifferentiated cambium to mature phloem and xylem, including cell expansion and cell death zones. In total, we analyzed 482 sections, 20–160 μm thick, from four 47-year-old trees growing wild in Sweden. We obtained high quality expression profiles for 3,082 proteins exhibiting consistency across the replicates, considering that the trees were growing in an uncontrolled environment. A combination of Principal Component Analysis (PCA), Orthogonal Projections to Latent Structures (OPLS) modeling and an enhanced stepwise linear modeling approach identified several major transitions in global protein expression profiles, pinpointing (for example) locations of the cambial division leading to phloem and xylem cells, and secondary cell wall formation zones. We also identified key proteins and associated pathways underlying these developmental landmarks. For example, many of the lignocellulosic related proteins were upregulated in the expansion to the early developmental xylem zone, and for laccases with a rapid decrease in early xylem zones. We observed upregulation of two forms of xylem cysteine protease (Potri.002G005700.1 and Potri.005G256000.2; Pt-XCP2.1) in early xylem and their downregulation in late maturing xylem. Our data also show that Pt-KOR1.3 (Potri.003G151700.2) exhibits an expression pattern that supports the hypothesis put forward in previous studies that this is a key xyloglucanase involved in cellulose biosynthesis in primary cell walls and reduction of cellulose crystallinity in secondary walls.ConclusionOur novel multivariate approach highlights important processes and provides confirmatory insights into the molecular foundations of wood development.Electronic supplementary materialThe online version of this article (doi:10.1186/s12864-016-2458-z) contains supplementary material, which is available to authorized users.

Metabolomic study of the bone trabecula of osteonecrosis femoral head patients based on UPLC–MS/MS

The severity and/or progression of osteonecrosis of the femoral head (ONFH) are commonly assessed by radiography, nuclear magnetic resonance image which aren’t invariably correlated to severity of disease and may be disturbed by other factors. Consequently, exploring the novel biochemical signatures of ONFH may be beneficial for diagnosing and understanding this disease. In this work, a bone trabecula metabolomics was undertaken to determine the expression pattern of low molecular mass metabolites in patients of femoral head necrosis based on the ultra-performance liquid chromatography/time-of-flight tandem mass spectrometry (UPLC/TOF MS/MS). Histological study showed that necrotic bone was characterized by necrosis, fibrosis and lacuna, but adjacent “normal” bone was pathologically normal. Principal component analysis in combination with orthogonal partial least-squares discrimination analysis was used to find out changed metabolites. MS/MS was used to speculate the corresponding molecule. Both osteonecrotic bone trabecula (ONBT) and adjacent “normal” bone trabecula (ANBT) showed higher levels of amino acids, such as proline, arginine, glutamine, dipeptides and lower levels of antioxidants. Most disrupted lipids, such as fatty acid esters, glycerophospholipids, sphingolipids, were found in osteonecrotic zone. The area under the receiver operating characteristic curve of combinational biomarkers (d-arginine, l-proline, l-carnitine, inosine) in ONBT and ANBT was 0.996 and 0.950, respectively. Our findings might provide a significant insight to understand the metabolic mechanism and diagnosis biomarkers of ONFH in the future.

Prediction of column ozone concentrations using multiple regression analysis and principal component analysis techniques: A case study in peninsular Malaysia

The aim of this study is to develop new algorithms of the column ozone (O3) in Peninsular Malaysia using statistical methods. Four regression equations, denoted as O3 NEM, O3 SWM, (PCA1) O3 NEM season, and (PCA2) O3 SWM season, were developed. Multiple regression analysis (MRA) and principal component analysis (PCA) methods were utilized to achieve the objectives of the study. MRA was used to generate regression equations for O3 NEM and O3 SWM, whereas a combination of the MRA and PCA methods were used to generate regression equations for PCA1 and PCA2. The results of the best regression equations for the column O3 through MRA by using four of the independent variables were highly correlated (R = 0.811 for SWM, R = 0.803 for NEM) for the six-year (2003–2008) data. However, the result of fitting the best equations for the O3 data using four of the independent variables gave approximately the same R values (≈0.83) for both the NEM and SWM seasons using the combined MRA and PCA methods. The common variables that appeared in both regression equations were H2O vapor and NO2. This result was expected because NO2 is a precursor of O3. The correlation coefficients (R) of the validation for the NEM and SWM seasons were 0.877–0.888 and 0.837–0.896, respectively. These statistical values indicated a very good agreement between the monthly predicted and observed O3 for Peninsular Malaysia.

Revealing the Mechanism for Conformational Changes from Structurally Rich Ensembles

Conformational changes in proteins are essential to their biological functions, from allosteric regulation to signal propagation. However, the transient nature of the intermediates along transition pathways hampers their experimental detection, making the mechanisms underlying these processes highly elusive. Here, applying an innovative combination of Principal Component Analysis (PCA) of experimental ensembles and coarse-grained simulations [1], we dissect the essential motions orchestrating biological functions for the highly studied ion channel GLIC. This prokaryotic protein, which has been solved in different functional states along the gating cycle, is a prototype for the Pentameric Ligand-Gated Ion Channels (PLGICs) that mediate synaptic communication. We show how the Principal Components (PCs) of the GLIC ensemble decode the core motions common to all the current structures, providing mathematical reaction coordinates to cluster them and reveal clearly the interconnecting pathways. Modeling GLIC as an elastic network in a Langevin simulation, we generate smooth trajectories between end-points that visit spontaneously multiple intermediate states along the transition, providing a realistic description of the mechanism. Finally, by direct analysis of the correlated motions along the dominant PCs we unveil an elegant mechanism to propagate information from the binding site throughout the protein [2]. Our approach provides a powerful and general theoretical framework to study conformational changes and synthetize the rich structural information deposited currently in the Protein Data Bank.1.Orellana L., Yoluk O., Orozco M., Lindahl E. Revealing conformational transition pathways by analysis of structurally rich X-ray ensembles and coarse-grained simulations (2015) (submitted)2.Fenwick R.B.∗, Orellana L.∗, Esteban-Martin S., Orozco M., Salvatella X. Correlated motions are a fundamental property of beta-sheets. Nature Communications (2014); 5: 4070. http://dx.doi.org/10.1038/ncomms5070 ∗ Shared First Authorship

Impacts of a flash flood on drinking water quality: case study of areas most affected by the 2012 Beijing flood.

In this study, we present a method for identifying sources of water pollution and their relative contributions in pollution disasters. The method uses a combination of principal component analysis and factor analysis. We carried out a case study in three rural villages close to Beijing after torrential rain on July 21, 2012. Nine water samples were analyzed for eight parameters, namely turbidity, total hardness, total dissolved solids, sulfates, chlorides, nitrates, total bacterial count, and total coliform groups. All of the samples showed different degrees of pollution, and most were unsuitable for drinking water as concentrations of various parameters exceeded recommended thresholds. Principal component analysis and factor analysis showed that two factors, the degree of mineralization and agricultural runoff, and flood entrainment, explained 82.50% of the total variance. The case study demonstrates that this method is useful for evaluating and interpreting large, complex water-quality data sets.

Toward food analytics: fast estimation of lycopene and β-carotene content in tomatoes based on surface enhanced Raman spectroscopy (SERS).

Carotenoids are molecules that play important roles in both plant development and in the well-being of mammalian organisms. Therefore, various studies have been performed to characterize carotenoids' properties, distribution in nature and their health benefits upon ingestion. Nevertheless, there is a gap regarding a fast detection of them at the plant phase. Within this contribution we report the results obtained regarding the application of surface enhanced Raman spectroscopy (SERS) toward the differentiation of two carotenoid molecules (namely, lycopene and β-carotene) in tomato samples. To this end, an e-beam lithography (EBL) SERS-active substrate and a 488 nm excitation source were employed, and a relevant simulated matrix was prepared (by mixing the two carotenoids in defined percentages) and measured. Next, carotenoids were extracted from tomato plants and measured as well. Finally, a combination of principal component analysis and partial least squares regression (PCA-PLSR) was applied to process the data, and the obtained results were compared with HPLC measurements of the same extracts. A good agreement was obtained between the HPLC and the SERS results for most of the tomato samples.

Knee adduction and flexion moments do not reflect knee loading during stance phase of gait

s / Gait & Posture 42S (2015) S1–S90 S59 decreased IGFBP-3 concentrations compared to control in bothpreand post-training. http://dx.doi.org/10.1016/j.gaitpost.2015.03.103 Pattern recognition methods in clinical gait analysis – What do we gain? M. Bruderer-Hofstetter1,∗, F. Rast2, C. Bauer2, E. Graf2, A. Meichtry1 1 Institute of Physiotherapy, University of Applied Sciences Zurich, Winterthur, Switzerland 2 Laboratory for Motion Analysis, University of Applied Sciences Zurich, Winterthur, Switzerland Introduction and aim: Pattern recognition methods have been widely used in clinical gait analysis [1]. Although a combination of principal component analysis (PCA) and support vector machines (SVM) demonstrated a high sensitivity to visualize subtle differences inmovement patterns [2,3] the benefit of pattern recognition methods in clinical application remains uncertain. Therefore, the aim of our study was to compare the results of a discrete parameter analysis with a pattern recognition approach in order to detect differences in kinematics and kinetics between two different shod conditions. Patients/materials and methods: Five walking trials for each of the two conditions of 20 healthy subjects were captured using a 7-camera-motion-analysis-system (Vicon, 200Hz) and two forceplates (AMTI, 1000Hz). Discrete parameter analysis calculated a priori chosen kinematic and kinetic parameters. Pattern recognition approach (PCA) extracted gait features (PC) from an input matrix containing kinematic and kineticwaveforms. Subsequently, a SVM classifier with linear kernel function was applied to determine the optimal PC-subspace. Within the remaining PCs and all parameters paired sample t-testswere applied and Cohens’ d effect sizes were calculated. Results:Discrete parameter analysis revealed significant differences (p<0.01) for the second peak ankle flexion angle (d=0.60), the peak accelerating ground reaction force (GRF) (d=0.86) and the second peak vertical GRF (d=−0.47). Pattern recognition approach detected four condition dependent PCs. Significant differences (p<0.01) were found in PC2 and PC3 (effect sizes d=−1.21 and d=2.75, respectively). PC2 corresponded to angle differences at mid-stance at hip, knee and ankle joints and to anterior-posterior and vertical GRF differences at terminal-stance. PC3 represented knee angle difference at mid-stance, anterior-posterior GRF differenceat terminal-stanceandangledifferencesathipandankle joints and vertical GRF difference at pre-swing. Discussion and conclusions: With the pattern recognition approach a deeper insight into the data was achieved. Differences between the two shod conditions were detected in other sections of the gait cycle than a priori supposed. Although the pattern recognition approach detected condition dependent differences independently of prior knowledge the benefit for clinical gait analysis application hinges on the ability to interpret the extracted gait features.

An Efficient P-KCCA Algorithm for 2D-3D Face Recognition Using SVM

In this paper, a novel face recognition system for face recognition and identification based on a combination of Principal Component Analysis and Kernel Canonical Correlation Analysis (P-KCCA) using Support Vector Machine (SVM) is proposed. First, the P-KCCA method is utilized to detect and extract the important features from the input images. This method makes it possible to match the 2D face image with enrolled 3D face data. The resulting features are then classified using the SVM method. The proposed methods were tested on TEXAS database with 200 subjects. The experimental results in the TEXAS face database produce interesting results from the point of view of recognition success, rate, and robustness of the face recognition algorithm. We compare the performance of our proposed face recognition method to other commonly-used methods. The experimental results show that the combination of P-KCCA method using SVM achieves a higher performance compared to the alone PCA, CCA and KCCA algorithms.