Use Of Principle Component Analysis Research Articles

Revisiting the financial development and economic growth nexus: empirical evidence from SAARC countries

PurposeThis study aims to examine the effect of economic growth and the moderating impact of inflation on financial development (FD) for six South Asian Association of Regional Countries (SAARC)es during the period of 1990–2020. Besides, the inflation threshold level and FD index are also estimated.Design/methodology/approachThis study uses several cross-sectional dependency tests, pooled mean group and panel fully modified least squares method. This study also makes use of principle component analysis in index construction.FindingsThe results indicate that economic growth positively impacts regions’ FD. The mediating term has a negative impact on FD when the inflation rate rises. The finding indicates after the 3.5% threshold limit, inflation changes its positive effect on FD. The constructed index is a superior measurement of FD because it controls measurement sensitivity and offers significant results.Originality/valueTo the best of the authors’ knowledge, this is the first empirical study in the context of SAARC to analyse the interaction effect of inflation on the growth–finance relationship. This study’s novelty is further ensured by estimating the threshold level of inflation and construction index.

From big data to smart data: a sample gradient descent approach for machine learning

This research paper presents an innovative approach to gradient descent known as ‘‘Sample Gradient Descent’’. This method is a modification of the conventional batch gradient descent algorithm, which is often associated with space and time complexity issues. The proposed approach involves the selection of a representative sample of data, which is subsequently subjected to batch gradient descent. The selection of this sample is a crucial task, as it must accurately represent the entire dataset. To achieve this, the study employs the use of Principle Component Analysis (PCA), which is applied to the training data, with a condition that only those rows and columns of data that explain 90% of the overall variance are retained. This approach results in a convex loss function, where a global minimum can be readily attained. Our results indicate that the proposed method offers faster convergence rates, with reduced computation times, when compared to the conventional batch gradient descent algorithm. These findings demonstrate the potential utility of the ‘‘Sample Gradient Descent’’ technique in various domains, ranging from machine learning to optimization problems. In our experiments, both approaches were run for 30 epochs, with each epoch taking approximately 3.41 s. Notably, our ‘‘Sample Gradient Descent’’ approach exhibited remarkable performance, converging in just 8 epochs, while the conventional batch gradient descent algorithm required 20 epochs to achieve convergence. This substantial difference in convergence rates, along with reduced computation times, highlights the superior efficiency of our proposed method. These findings underscore the potential utility of the ‘‘Sample Gradient Descent’’ technique across diverse domains, ranging from machine learning to optimization problems. The significant improvements in convergence rates and computation times make our algorithm particularly appealing to practitioners and researchers seeking enhanced efficiency in gradient descent optimization.

The use of principle component analysis and MALDI-TOF MS for the differentiation of mineral forming Virgibacillus and Bacillus species isolated from sabkhas.

Occurrence of mineral forming and other bacteria in mats is well demonstrated. However, their high diversity shown by ribotyping has not been explained, although it could explain the diversity of formed minerals. Common biomarkers as well as phylogenic relationships are useful tools for clustering the isolates and the prediction of their potential role in the natural niche. In this study, a combination of MALDI-TOF MS with PCA was shown to be a powerful tool to categorize 35 mineral forming bacterial isolates isolated from Dohat Faishakh sabkha, northwest of Qatar (23 from decaying mats and 12 from living ones). The 23 strains from decaying mats belong to the Virgibacillus genus as identified by ribotyping and are shown to be highly involved in the formation of protodolomite and a diversity of minerals. They were used as internal references for the categorization of sabkha bacteria. Combination of the isolation of bacteria on selective mineral forming media, their MALDI TOF MS protein profiling and PCA analysis established their relationship in a phylloproteomic dendrogram based on protein biomarkers including m/z 4905, 3265, 5240, 6430, 7765, and 9815. PCA analysis clustered the studied isolates into 3 major clusters, showing strong correspondence to the 3 phylloproteomic groups that were established by the dendrogram. Both clustering analysis means have evidently demonstrated a relationship between known Virgibacillus strains and other related bacteria based on profiling of their synthesized proteins. Thus, larger populations of bacteria in mats can be easily screened for their potential to exhibit certain activities, which is of ecological, environmental and biotechnological significance.

Advancement of Individualized Head-Related Transfer Functions (HRTFs) in Perceiving the Spatialization Cues: Case Study for an Integrated HRTF Individualization Method

Head-related transfer function (HRTF), which varies across individuals at the same direction, has grabbed widespread attention in the field of acoustics and been used in many scenarios. In order to in-depth investigate the performance of individualized HRTFs on perceiving the spatialization cues, this study presents an integrated algorithm to obtain individualized HRTFs, and explores the advancement of such individualized HRTFs in perceiving the spatialization cues through two different binaural experiments. An integrated method for HRTF individualization on the use of Principle Component Analysis (PCA), Multiple Linear Regression (MLR) and Partial Least Square Regression (PLSR) was presented first. The objective evaluation was then made to verify the algorithmic effectiveness of that method. Next, two subjective experiments were conducted to explore the advancement of individualized HRTFs in perceiving the spatialization cues. One was auditory directional discrimination degree based on semantic differential method, in which the azimuth information of sound sources was told to the listeners before listening. The other was auditory localization, in which the azimuth information was not told to the listeners before listening. The corresponding statistical analyses for the subjective experimental results were made. All the experimental results support that individualized HRTFs obtained from the presented method achieve a preferable performance in perceiving the spatialization cues.

Process monitoring and troubleshooting of a local refinery's hydrogen plant using multivariate methods

Modern refineries are equipped with distributed control systems (DCS) for monitoring and regulation. These systems generate large amount of process measurements which are acquired and stored in data historian. These measurements are characterised by being cross-correlated, with low signal to noise ratio and many missing observations in almost all variables. Multivariate-based monitoring and troubleshooting techniques provides an appropriate tool to address the aforementioned challenges. This paper demonstrates the use of principle component analysis (PCA) as an analytics tool for process monitoring and troubleshooting. A real case study from a local refinery in Bahrain was used to prove the proficiency of PCA. To demonstrate the ease and flexibility of the proposed scheme, all model buildings and testing were done using specialised commercial software, namely Aspen ProMV™ (AspenTech, 2018). The aim is to assist operators and engineers in refineries and petrochemical plants to realise the advantages of multivariate methods for troubleshooting plant and equipment upsets. The latter is necessary to assure safe, reliable and profitable operation. [Received: November 9, 2017; Accepted: May 9, 2018]

Clustering of frequency spectrums from different bearing fault using principle component analysis

In this paper, the application of principle component analysis (PCA) as a pre-processing method for hierarchical clustering analysis on the frequency spectrum of the vibration signal was proposed. To achieve the aim, the vibration signal was acquired from the operating bearings with different condition and speed. In the next stage, the principle component analysis was applied to the frequency spectrums of the acquired signals for pattern recognition purpose. Meanwhile the mahalanobis distance model was used to cluster the result from PCA. According to the results, it was found that the amplitude of vibration at Ball Passing Frequency Outer Race and Ball Passing Frequency Inner Race will increase in align with the presence of outer race defect and inner race defect respectively. Moreover, the overall amplitude of vibration spectrum was found to be uniformly increased for the case of corroded bearing due to the widespread uniform corrosion on the entire bearing. By applying principle component analysis, the change in amplitude at any of these fundamental frequencies can be detected. Meanwhile, the application of mahalanobis distance was found to be suitable for clustering the results from principle component analysis. Uniquely, it was discovered that the spectrums from healthy and inner race defect bearing can be clearly distinguished from each other even though the change in amplitude pattern for inner race defect frequency spectrum was too small compared to the healthy one. In this work, it was demonstrated that the use of principle component analysis could sensitively detect the change in the pattern of the frequency spectrums. Likewise, the implementation of mahalanobis distance model for clustering purpose was found to be significant for bearing defect identification.

The Use of Principle Component Analysis in Type Classification of Air-dry Peat

The use of principle component analysis (PCA) in the variant of projection on latent values with discriminant analysis (PLS-DA) in type classification of Siberian region air-dry peat by a set of properties is presented. A statistical analysis in principle component space by PCA of different physico-chemical properties of peat such as component composition, concentration of paramagnetic centers and IR-spectra is presented and shows a developed PLS- DA classification model allows estimating peat type by a set of physico-chemical properties with minimum prediction errors.

A data-driven approach to establishing microstructure–property relationships in porous transport layers of polymer electrolyte fuel cells

The diffusion media (DM) has been shown to be a vital component for performance of polymer electrolyte fuel cells (PEFCs). The DM has a dual-layer structure composed of a macro-substrate referred to as the gas diffusion layer (GDL) coated with a micro-porous layer (MPL). Efficient prediction of the effective transport properties of the DM from its internal structure is essential to optimizing the multifunctional characteristics of this critical component. In this work, a unique data-driven approach to establishing structure–property correlations is introduced and applied to the case of gas diffusion in the GDL and MPL. This new approach provides an automated process to produce unbiased estimators to microstructural variance, in contrast to many process-related (hence biased) parameters employed by prominent correlations in the field. The present approach starts with a rigorous quantification of microstructure in the form of n-point statistics. It is followed by the identification of the key aspects of the internal structure through the use of principle component analysis. A data-driven correlation is established when the principal components are related to effective diffusivity by multivariate linear regression. This data-driven approach is compared to the conventional correlations and shown to achieve a very high accuracy for capturing the diffusive transport in the tested PEFC components.

Seismic facies analyses as aid in regional gas hydrate assessments. Part-I: Classification analyses

The identification of areas of natural gas hydrate occurrence, defining its concentration and regional distribution, as well as understanding the processes that control gas hydrate formation is a crucial component of regional gas hydrate assessments. In this study, we incorporate an additional element into a regional assessment strategy by including the depositional environment defined through seismic facies classes. The seismic facies classification is attempted using regional 2D seismic data and a 3D seismic volume, as well as core and log-data from two gas hydrate drilling expeditions carried out in the Ulleung Basin, East Sea, to conduct a fully integrated gas hydrate assessment. The facies classification described in this study is part of a procedure to conduct an assessment including: (1) Lithologic description of the recovered core and describe the deposition character of the sediment facies identified; (2) seismic facies classification using 2D and 3D seismic data and their derived various seismic attributes; (3) Linking seismic facies classes to core-derived sedimentological descriptions to define the host-strata most favourable for gas hydrate occurrences; (4) Defining reservoir physical properties and linking these to seismic facies classes for reservoir property description; (5) Calculating regional elements of the gas hydrate petroleum system (top of gas hydrate occurrence and base of gas hydrate stability); (6) Merging seismic facies and reservoir properties, definition of the top and base of the gas hydrate stability zone, to calculate gas hydrate saturations in each seismic facies and the total volume of gas hydrate present in the study area; (7) Defining probabilistic elements of the predicted volume of gas hydrate by combining statistical information of the individual input parameters through exhaustive Monte Carlo simulations. The seismic facies classification algorithm used in this study is based on identifying clusters (classes) that show similar properties in the seismic data and derived attribute characteristics. Our classification scheme uses seven seismic attributes (amplitude, instantaneous frequency and amplitude (also referred to as envelope), sweetness, acoustic impedance, thin-bed- and parallel-bedding indicator) and incorporates the use of principle component analysis for data reduction. The achieved classifications are overall robust and yield identical facies classes for the co-located 2D and 3D data. Linking the seismic facies classes to the recovered core and sedimentological descriptions results in a sedimentological interpretation of the seismic facies. Cross-plots of individual components as well as analysing the Eigen-vectors and -values from the principle component analysis (PCA) helps understand the physical meaning of these seismic facies classes and their seismic character. The five facies classes assigned to the 3D volume and 2D seismic line after PCA represent the mass transport deposit (MTD) units (class #1), hemipelagic mud with some sandy turbidite (class #2), hemipelagic mud with many sandy turbidites (class #3), as well as water-bearing mud with few sand layers and occurring mostly at shallow depth near the seafloor or beneath the base of the gas hydrate stability zone (classes #4 and #5). Within the study area and seismic data sets used, gas hydrate occurrences are only linked to facies classes #2 and #3.

Vision based Robot Navigation for Disaster Scenarios

This paper aims at providing real time vision based robotnavigation for disaster management scenarios. The task is to navigate a robot in unstructured environment by using gestures. Navigation is an important task that is to be performed while traversing a particular path in disaster management scenario. There are various methodologies like autonomous mapping and SLAM techniques in which the robot is trained itself to create the path by making a map, but training the robot and creating a map itself requires a lot of time and is a tedious process. Meanwhile in this approach a real time video streaming is done by the robot itself that is being transmitted to user who in turn controls the robot using gestures. Apart from streaming the video we also find the closest obstacle distance using IR sensors. For the purpose of performing a particular task for a detected gesture, the robot needs to have intelligence. This intelligence is the algorithm that is loaded into the robot to make it perform the task assigned to it. Here we make use of principle component analysis along with image moments for identifying the gestures and thereby controlling the robot. Real-time implementation is done on iRobot platform.

Assessment of Water Quality in a Subtropical Alpine Lake Using Multivariate Statistical Techniques and Geostatistical Mapping: A Case Study

Concerns about the water quality in Yuan-Yang Lake (YYL), a shallow, subtropical alpine lake located in north-central Taiwan, has been rapidly increasing recently due to the natural and anthropogenic pollution. In order to understand the underlying physical and chemical processes as well as their associated spatial distribution in YYL, this study analyzes fourteen physico-chemical water quality parameters recorded at the eight sampling stations during 2008–2010 by using multivariate statistical techniques and a geostatistical method. Hierarchical clustering analysis (CA) is first applied to distinguish the three general water quality patterns among the stations, followed by the use of principle component analysis (PCA) and factor analysis (FA) to extract and recognize the major underlying factors contributing to the variations among the water quality measures. The spatial distribution of the identified major contributing factors is obtained by using a kriging method. Results show that four principal components i.e., nitrogen nutrients, meteorological factor, turbidity and nitrate factors, account for 65.52% of the total variance among the water quality parameters. The spatial distribution of principal components further confirms that nitrogen sources constitute an important pollutant contribution in the YYL.

Application of principal component analysis enables to effectively find important physical variables for optimization of fluid bed granulator conditions

Principal component analysis was applied to effectively optimize the operational conditions of a fluidized bed granulator for preparing granules with excellent compaction and tablet physical properties. The crucial variables that affect the properties of the granules, their compactability and the resulting tablet properties were determined through analysis of a series of granulation and tabletting experiments. Granulation was performed while the flow rate and concentration of the binder were changed as independent operational variables, according to a two-factor central composite design. Thirteen physicochemical properties of granules and tablets were examined: powder properties (particle size, size distribution width, Carr's index, Hausner ratio and aspect ratio), compactability properties (pressure transmission ratio, die wall force and ejection force) and tablet properties (tensile strength, friability, disintegration time, weight variation and drug content uniformity). Principal component analysis showed that the pressure transmission ratio, die wall force and Carr's index were the most important variables in granule preparation. Multiple regression analysis also confirmed these results. Furthermore, optimized operational conditions obtained from the multiple regression analysis enabled the production of granules with desirable properties for tabletting. This study presents the first use of principle component analysis for identifying and successfully predicting the most important variables in the process of granulation and tabletting.

Rapid determination of Paeoniae Radix using near infrared spectroscopy

A rapid and nondestructive near infrared spectroscopy (NIRS) was used to differentiate different geographical Paeoniae Radix and quantitatively predict the content of main active components. Paeoniflorin, albiflorin and benzoylalbiflorin were analyzed simultaneously with an Agilent Zorbax SB-C 18 column by gradient elution under high-performance liquid chromatography-UV detection (HPLC-UV). Multiplicative scatter correction (MSC), first derivative and Savitsky–Golay were utilized together to correct the scattering effect and eliminate the baseline shift in all near infrared diffuse reflectance spectra in order to give a better correlation with the results obtained by HPLC-UV. Multiplicative regression methods were discussed. The spectra calibration equations produced highest correlation coefficient values ( R 2) and lowest root mean square error of prediction (RMSEP) were used for the determination of paeoniflorin, albiflorin and benzoylalbiflorin. The RMSEP of paeoniflorin, albiflorin and benzoylabiflorin were 0.866 mg/g, 0.369 mg/g and 0.084 mg/g, respectively, and the R 2 of cross validation were 0.986, 0.939 and 0.971, respectively. Furthermore with the use of principle component analysis (PCA), Paeoniae Radix was clustered according to different cultivation area. The results indicated that the NIRS method could be used for the quality control of Chinese herbal medicine.

Tumor motion and deformation during external radiotherapy of bladder cancer

First, to quantify bladder-tumor motion in 3 dimensions during a 4-week to 5-week course of external radiotherapy. Second, to relate the motion to the tumor location on the bladder wall. Third, to extensively evaluate gross tumor volume (GTV) shape and volume changes during the course of the treatment. Multiple repeat computed tomography (CT) images were obtained for 21 bladder cancer patients. These scans were matched to the rigid bony anatomy. For each patient, the main direction and magnitude of the tumor movement was determined by use of principle-component analysis. To study GTV shape changes, all GTVs were registered to the GTV in the planning CT scan, and the residual shape errors were determined by measurement of edge variations perpendicular to the median surface. Gross tumor volume translations were largest in cranial-caudal and anterior-posterior direction (SD, 0.1 to approximately 0.9 cm). The translations were strongly correlated with the tumor location on the bladder wall. The average value of the local standard deviations of the GTV shape ranged from 0.1 to approximately 0.35 cm. Despite large differences in bladder filling, variations in GTV shape were small compared with variations in GTV position. Geometric uncertainties in the GTV position depended strongly on the tumor location on the bladder wall.

Cluster analysis in soft X-ray spectromicroscopy: Finding the patterns in complex specimens

Soft X-ray spectromicroscopy provides spectral data on the chemical speciation of light elements at sub-100 nanometer spatial resolution. If all chemical species in a specimen are known and separately characterized, existing approaches can be used to measure the concentration of each component at each pixel. In other situations such as in biology or environmental science, this approach may not be possible. We have previously described [M. Lerotic, C. Jacobsen, T. Schäfer, S. Vogt, Ultramicroscopy 100 (1–2) (2004) 35] the use of principle component analysis (PCA) to orthogonalize and noise-filter spectromicroscopy data, and cluster analysis (CA) to classify the analyzed data and obtain thickness maps of representative spectra. We describe here an extension of that work employing an angle distance measure; this measure provides better classification based on spectral signatures alone in specimens with significant thickness variations. The method is illustrated using simulated data, and also to examine sporulation in the bacterium Clostridium sp.

Cluster analysis of soft X-ray spectromicroscopy data

We describe the use of principle component analysis (PCA) to serve as a prefilter for cluster analysis or pattern recognition analysis of soft x-ray spectromicroscopy data. Cluster analysis provides a method to group regions with common spectral features even if no prior knowledge of their spectra is available, such as in biology or environmental science.

On the removal of random variables in data sets of meteorological observations

For some purposes it is not necessary to use a full data set of strongly spatially correlated parameters. In some situations, too much information may even be unwanted. We propose a procedure for finding a non-redundant choice of synoptic stations that is sufficient to capture the relevant physical patterns based on rule N. The technique makes use of principle component analysis and cluster analysis. The above-mentioned procedure can be applied to generic data sets. As an illustration, we apply it here to the strongly correlated two-meter temperature observed in the Belgian synoptic network during the winter period. We find that about three or four stations from this network are necessary. The method also suggests an intelligent choice of stations that are most suitable to be used.

Measuring airport quality from the airlines’ viewpoint: an application of data envelopment analysis

The main objective of this paper is to develop a model to determine the relative efficiency and quality of airports. This factor seems to have a strong effect on the airlines’ choice of hubs. Previous studies of airport quality have used subjective passenger data whereas in this study airport quality is defined from the airlines’ viewpoint. Accordingly, we have solicited airlines’ evaluations of a number of European and non-European airports by means of a detailed questionnaire. Statistical analysis of the median score has shown that these evaluations vary considerably relative to quality factors and airports. The key methodology used in this study to determine the relative quality level of the airports is Data Envelopment Analysis (DEA), which has been adapted through the use of principle component analysis. Of the set of West-European airports analyzed, Geneva, Milan and Munich received uniformly high, relative efficiency scores. In contrast, Charles de Gaulle, Athens and Manchester consistently appear low in the rankings.

Morphometric analysis of embryonic development in Alligator mississippiensis, Crocodylus johnstoni and Crocodylus porosus

The size of embryos at various stages of development was determined in three species of crocodilian (Alligator mississippiensis, Crocodylus johnstoni and C. porosus). Various morphometric measurements were taken of embryos throughout development and were described for each stage of development. Increase in size from stage to stage was faster in A. mississippiensis than in C. porosus and C. johnstoni. Hatchlings of A. mississippiensis were large in length but light in mass compared with the hatchlings of C. johnstoni and C. porosus which were heavier per unit length. These morphometric parameters can be used to determine the stage of embryonic development by size. The use of principle component analysis improves this technique further by dampening any anomalous data points.The rate of embryonic growth in A. mississippiensis appeared to be under greater genetic control than in the two species of Crocodylus. The evolutionary advantages of this phenomenon probably relate to the biology of A. mississippiensis. Due to the northerly range of this species it is advantageous for alligators to hatch as soon as possible, as large as possible, to maximize the period prior to winter hibernation and reduce predation. Tropical crocodiles have fewer selection pressures for rapid development and have slower rates of embryonic growth. Genetic aspects of crocodilian embryonic development have been largely ignored but may help explain some aspects of crocodilian growth under farming conditions.