Principal Component Analysis Regression Research Articles

Chemometric Assessment of Soil Pollution and Pollution Source Apportionment for an Industrially Impacted Region around a Non-Ferrous Metal Smelter in Bulgaria.

The present study deals with the assessment of pollution caused by a large industrial facility using multivariate statistical methods. The primary goal is to classify specific pollution sources and to apportion their involvement in the formation of the total concentration of the chemical parameters being monitored. This aim is accomplished by intelligent data analysis based on cluster analysis, principal component analysis and principal component regression analysis. Five latent factors are found to explain over 80% of the total variance of the system being conditionally named “organic”, “non-ferrous smelter”, “acidic”, “secondary anthropogenic contribution” and “natural” factor. The apportionment models designate the contribution of the identified sources quantitatively and help in the interpretation of risk assessment and management actions. Since the study takes into account pollution uptake from soil to a cabbage plant, the data interpretation could help in introducing biomonitoring aspects of the assessment. The chemometric expertise helps in revealing hidden relationships between the objects and the variables involved to achieve a better understanding of specific pollution events in the soil of a severely industrially impacted region.

Analysis of key factors and prediction of gas production pressure of coalbed methane well: Combining grey relational with principal component regression analysis

The critical desorption pressure is different from the gas production pressure of coalbed methane. Gas production pressure is affected by many factors, but their relationships are not obvious. Ther...

Production environment effect on agronomic performance of okra breeding lines and their F2 populations

ABSTRACTThe type of production environment can affect agronomic performance of West African okra [Abelmoschus caillei (A.Chev) Stevels] breeding lines and their progenies. The study was conducted to (1) compare agronomic performance of West African okra lines and F2 populations under upland and bottomland environments, (2) identify sources of genes with potential to improve pod yield, (3) estimate genetic and phenotypic correlations for evaluated traits, and (4) estimate expected response to selection for pod yield and other agronomic traits through intergeneration correlation and regression. Twenty-three genotypes (9 F2 populations and their corresponding 14 parents) were grown in two production environments at the research farms of the Federal University of Agriculture, Abeokuta, Nigeria. Results were analyzed using principal component analysis, correlation and regression analyses. Unique trait profiles in genotypes responses to production environments occurred. Most genotypes indicated adaptation to the bottomland environment by reducing days to physiological maturity. Hybrid AGA97/066/5780 × NGAE-96–-0062-2, which combines early maturity with superior expression of pod yield between production environments, may be used to improve earliness in West African okra. Principal component analysis revealed three major factors that explained more than 66% and 69% of interrelation among traits in upland and bottomland, respectively. Changes of genotypic correlations between pod yield and other agronomic traits occurred between environments indicating the influence of environmental factors to trait correlation. A significant, positive correlation, and regression coefficients, between parents and the F2 generation for pod yield occurred between production environments, indicating the effectiveness of selection for pod yield in the early segregating generation. Generally, bottomland production environment offered a higher potential for agronomic trait expression in breeding lines and F2 population of West African okra.

Development of statistical predictive models for estimating the methane yield of Italian municipal sludges from chemical composition: a preliminary study.

The biochemical methane potential (BMP) of primary and biological sludge varies in a wide range, mostly depending on location, sewer characteristics, wastewater treatment plant design and operating conditions. BMP tests are useful to verify the performance of a full scale digester, but they are not yet a common procedure in the operation of most Italian facilities because of cost and test duration. Changes in the composition of sewage sludge can lead to a high variation of biogas production. Aimed at developing BMP predictive models based on low cost and fast analyses, this study investigated the chemical composition of 20 sludge samples by means of principal component and multiple linear regression analyses. Three preliminary predictive models were developed based on soluble organic nitrogen, volatile solids, carbohydrates, proteins, lipids and an operational parameter, the sludge retention time: the explained variance and the standard errors of prediction of BMP are in the range 77-81% and 21-34 NmLCH4·gVS -1, respectively. Models were evaluated on five additional samples: errors ranged 2-15% for four samples and about 54% for one sample, collected from a peculiar facility. Further data and variables describing the operation mode of the waterline would certainly improve the reliability and robustness of the models.

Determinants of Social Entrepreneurial Intentions of University Students in South Africa

Entrepreneurial behaviour can be predicted by intentions. The study investigated the determinants of social entrepreneurial intentions (SEI) of university students in South Africa. The study adopted a quantitative research design that involved the use of a survey. The self-administered questionnaire method was used to collect data from the survey participants. The participants in the survey were final year undergraduate students of the Department of Business Management of two South African universities. Reliability was measured using the Cronbach’s alpha. The data analysis methods for the study were descriptive statistics, principal component analysis and regression analysis. The results indicated that empathy, moral obligation, entrepreneurial self-efficacy and perceived social support are predictors of social entrepreneurial intentions. The recommendations to improve the SEI of university students focus on passive and active entrepreneurship teaching methods.

Differential magnitude of rhizosphere effects on soil aggregation at three stages of subtropical secondary forest successions

Roots and their rhizosphere considerably influence soil structure by regulating soil aggregate formation and stabilization. This study aimed to examine the rhizosphere effects on soil aggregation and explore potential mechanisms along secondary forest successions. Effects of roots and their rhizosphere on soil aggregation in two subtropical secondary forest successions were examined by separating soils into rhizosphere and bulk soils. Soil aggregate mean weight diameter (MWD), soil organic carbon (SOC), soil nutrients, and fine-root traits were simultaneously measured. Soil aggregate MWD increased significantly in the bulk soils along secondary forest successions, but did not differ in the rhizosphere soils. Rhizosphere effects on soil aggregate MWD (i.e., root-induced differences between the rhizosphere and bulk soils) were thus significantly higher at the early-successional stage of subtropical forest with low soil fertility than those at the late stages with high fertility. Rhizosphere significantly increased SOC and soil total nitrogen (TN) throughout the entire secondary forest successions, which was nonlinearly correlated with soil aggregate MWD. Principal components regression analysis showed that SOC was the primary abiotic factor and positively correlated with soil aggregate MWD. As for biotic factors, fine-root length density and N concentration were two important root traits having significant effects on soil aggregate stability. An improved conceptual framework was developed to advance our understanding of soil aggregation and rhizosphere effects, highlighting the roles of soil fertility (i.e., SOC and available nutrients), root traits, and forest age in driving soil aggregation. Impacts of root-derived organic compounds inputs to rhizosphere on soil aggregation were stronger at the early-successional stage of subtropical forest than those at the late stages. This succession-specific pattern in rhizosphere effects largely resulted from the nonlinear relationships between soil aggregate MWD and SOC concentration with a plateau at high SOC. Incorporating the SOC-dependent rhizosphere effects on biogeochemical cycle into Earth system models might improve the prediction of forest soil C dynamics.

Where should China's thermal power industry prioritize its B&R investment? A study based on an environmental site selection analysis

The Belt and Road initiative (B&R) provided high-level opportunities for China's outward foreign direct investment. This study uses China's thermal power industry as an example for selecting optimum investment locations based on the host countries' environmental regulations. The study proposes an environmental site selection model based on a principal component and panel regression analysis. Considering the results of the principal component analysis, the main influencing factors affecting China's thermal power industry outward foreign direct investment (CTP-OFDI) and the comprehensive score of B&R countries were screened. In addition, the regression analysis provided a ranking of attractiveness scores for each country. Combining the analysis and results, the study draws the following conclusions. (1) The factors influencing investment are diverse and comprehensive, and the main influencing factors include three aspects, industrial development, the social and political situation, and the ecological environment. (2) Environment regulations are a significant factor and have a negative relationship with CTP-OFDI. (3) The B&R countries could be divided into the preferred, alternative, inferior, and avoidable investment locations. To conclude, the countermeasures and suggestions for improving investments are proposed based on the results of the environmental site selection model.

Quality and Sensory Characteristics of Volutharpa ampullacea perryi (False Abalone) Meat during the Boiling Cooking

ABSTRACT Volutharpa ampullacea perryi (false abalone) meats were water cooked at 75–100°C for 5–60 min, and the changes in weight loss, pH, color, in vitro digestibility, texture, microstructure, and sensory characteristics were investigated. The weight rapidly decreased in the initial cooking and decreased slightly with the extension of both heating temperature and time. Obvious differences in color were found compared between the raw and cooked meats with respect to ΔL*, Δa*, and Δb* values. Digestibility was significantly improved with the thermal treatments. Textual properties, such as hardness, springiness, chewiness, and resilience, improved with the increasing of thermal intensity, but reduced with overcooking, and the variations were further confirmed by the scanning electron microscopy analysis. The samples boiled at 90–95°C for 10–15 min and 100°C for 5–10 min acquired better acceptance in the sensory evaluation. The complex relationship among cooking conditions and physicochemical and histological characteristics of meat as well as the consumer perceptions was illuminated by the principal components regression analysis. These results could provide useful information for quality control in V. a. perryi meat cooking.

Visualization of Chlorophyll Content Distribution in Apple Leaves Based on Hyperspectral Imaging Technology

We took distribution visualization of chlorophyll content in apple leaves to estimate the nutrient content and growth levels of apple leaves. 130 mature and non-destructive apple leaves were collected, and imaging spectroscopy data were collected by SOC710VP hyperspectral imager. The chlorophyll content of the leaves was determined on the spectral information of the leaves. After pre-processing, we took linear wavelength stepwise regression method to choose the sensitive wavelength of chlorophyll content. And then we established partial least squares, principal component analysis and stepwise regression model. Finally, the chlorophyll content distribution visualization was realized. The results showed that the sensitive wavelengths of the chlorophyll content were 712.50 nm, 509.95 nm, 561.22 nm, 840.62 nm, 696.67 nm and 987.91 nm. The R2, RMSE, RE of the optical chlorophyll content estimation model, and the principal component analysis regression model, were 0.800, 0.319 and 26.4%. The chlorophyll content of each pixel on the hyperspectral image of apple leaves was calculated by the best estimation model and we completed the visualization distribution of chlorophyll content, which provided a technical support for the rapid detection of nutrient distribution.

Improved logistic regression model for diabetes prediction by integrating PCA and K-means techniques

Abstract Diabetes causes a large number of deaths each year and a large number of people living with the disease do not realize their health condition early enough. In this study, we propose a data mining based model for early diagnosis and prediction of diabetes using the Pima Indians Diabetes dataset. Although K-means is simple and can be used for a wide variety of data types, it is quite sensitive to initial positions of cluster centers which determine the final cluster result, which either provides a sufficient and efficiently clustered dataset for the logistic regression model, or gives a lesser amount of data as a result of incorrect clustering of the original dataset, thereby limiting the performance of the logistic regression model. Our main goal was to determine ways of improving the k-means clustering and logistic regression accuracy result. Our model comprises of PCA (principal component analysis), k-means and logistic regression algorithm. Experimental results show that PCA enhanced the k-means clustering algorithm and logistic regression classifier accuracy versus the result of other published studies, with a k-means output of 25 more correctly classified data, and a logistic regression accuracy of 1.98% higher. As such, the model is shown to be useful for automatically predicting diabetes using patient electronic health records data. A further experiment with a new dataset showed the applicability of our model for the predication of diabetes.

Associations between Vitamin D and β-Cell Function and Colorectal Cancer-Associated Tumor Markers in Chinese Type 2 Diabetic Patients with Albuminuria.

This study is to investigate the protective effects of vitamin D in T2DM, as well as the associations between serum calcifediol level and β-cell function, and risk of CRC, in Chinese type 2 diabetes mellitus (T2DM) patients with albuminuria. Serum calcifediol levels were analyzed and compared among healthy individuals and T2DM patients stratified by albumin/creatinine ratio (ACR). Relative correlation analyses were performed with β-cell function (BCF) and risk of CRC. Patients' ACR was positively associated with fasting plasma glucose and insulin, homeostasis model assessment (HOMA) of insulin resistance (IR), alpha-fetoprotein (AFP), carcinoembryonic antigen (CEA), carbohydrate antigen (CA)199, CA125, and Septin9 methylation, but inversely associated with HOMA-BCF and insulin secretion. Serum calcifediol level in the healthy controls was significantly higher than T2DM patients. In T2DM patients, calcifediol level was inversely associated with ACR, HOMA-IR, AFP, CEA, and Septin9 methylation, but positively associated with HOMA-BCF and insulin secretion. Multivariate stepwise principal component regression analysis indicated that calcifediol, hemoglobin A1c, and serum creatinine were independent risk factors for elevated CEA in T2DM. Higher serum calcifediol level is correlated with better β-cell function, lower insulin resistance, and decreased risk of CRC. Vitamin D may have suppressive effects on T2DM-associated complications and therefore represents a potential prophylactic treatment against β-cell dysfunction and cancer development in T2DM patients with albuminuria.

Effects of stand-level and landscape factors on understorey plant community traits in broad-leaved forest of the boreo-nemoral zone in Latvia

Knowledge of the limiting processes shaping the composition of plant communities of woodland is important in conservation of biological diversity. The aim of our study was to examine the effect of stand-level factors (soil and canopy composition, age and area) and landscape factors (fragmentation of broad-leaved forest, distance to a historical manor house, and past history) on plant community trait composition in broad-leaved forest. We hypothesized that the plant functional community is shaped by both dispersal filtering due to landscape factors and by environmental characteristics. We recorded all vascular plants, described canopy composition and estimated soil characteristics in 44 randomly chosen broad-leaved stands in Latvia. Relationships between plant community traits and potential factors were assessed using PCA and multivariate regression analysis. Interrelationship of richer topsoil fertility and admixture of broad-leaved tree species other than Q. robur was associated with greater abundance of nemoral species and hemicryptophytes. The invasion of Picea abies into the canopy was associated with poor topsoil fertility and acidified soil, likely due to poor litter quality, and with greater number of boreal species and geophytes in the herb layer. The results suggested a weak and contradictory effect of landscape structure and history on the forest plant community traits, maybe because the long-term history of afforestation around manors and spatio-temporal connectivity to ancient forests had resolved these effects.

The ratio of chelate-soluble fraction to alcohol insoluble residue is a major influencing factor on the texture of lotus rhizomes after cooking

The differences in cell wall polysaccharides are considered as a major influencing factor on the texture of plant-based food after cooking. Here, 18 varieties of lotus rhizomes were collected from different regions of China and subjected to analysis, with the aim to identify the key factors that affect the texture of lotus rhizomes after cooking. The texture (hardness) of fresh samples and the samples after thermal treatment for different time periods was examined. The cell wall polysaccharides present in alcohol insoluble residue (AIR) were further subdivided into different fractions, and the composition of monosaccharides in each fraction was analyzed by gas chromatography. We then calculated the sugar ratios to examine the discrepancies in molecular structure among the fractions. Principal component analysis and regression analysis showed that the ratio of chelate-soluble fraction (CSF) to AIR is the major factor affecting the texture of lotus rhizomes after cooking.

QSAR, Docking and Molecular Dynamics Studies on the Piperidone-grafted Mono- and Bis-spiro-oxindole-hexahydropyrrolizines as Potent Butyrylcholinesterase Inhibitors

ABSTRACT: Quantitative structure-activity relationship (QSAR) study on the piperidone-grafted mono- and bis-spirooxindole-hexahydropyrrolizines as potent butyrylcholinestrase (BuChE) inhibitors were carried out using statistical methods, molecular dynamics and molecular docking simulation. QSAR methodologies, including classification and regression tree (CART), multiple linear regression (MLR), principal component analysis (PCA) and principal component regression analysis (PCRA). Three descriptors in three classes: 3D-Morse, WHIM and GETAWAY descriptors were selected by SPSS software and then applied in the final tree structure to describe the inhibitory activities. Docking simulations were carried out using AutoDock Vina softwares for all inhibitors. Docking results showed that the studied BuChE inhibitors have two commons binding modes. Molecular dynamics results obtained by Gromacs showed that the more potent inhibitor has more interaction with the enzyme and higher effect on the enzyme structure.

The long-term assessment of air quality on an island in Malaysia

This study aims to evaluate the air quality on Langkawi Island, a famous tourist destination in Malaysia, using 13 years of data (1999–2011) recorded by the Malaysian Department of Environment. Variations of seven air pollutants (O3, CO, NO, NO2, NOx, SO2 and PM10) and three meteorological factors (temperature, humidity and wind speed) were analysed. Statistical methods used to analyse the data included principal component regression (PCR) and sensitivity analysis. The results showed PM10 was the dominant air pollutant in Langkawi and values ranged between 5.0 μg m−3 and 183.2 μg m−3. The patterns of monthly values showed that the concentrations of measured air pollutants on Langkawi were higher during the south-west monsoon (June–September) due to seasonal biomass burning activities. High CO/NOx ratio values (between 28.3 and 43.6), low SO2/NOx ratio values (between 0.04 and 0.12) and NO/NO2 ratio values exceeding 2.2 indicate the source of air pollutants in this area was motor vehicles. PCR analysis grouped the seven variables into two factor components: the F1 component consisted of SO2, NO and NOx and the F2 component consisted of PM10. The F1 component (R2 = 0.931) indicated a stronger standardized coefficient value for meteorological variables compared to the F2 component (R2 = 0.059). The meteorological variables were statistically significant (p < 0.05) in influencing the distribution of the air pollutants. The status of air quality on the island could be improved through control on motor vehicle emissions as well as collaborative efforts to reduce regional air pollution, especially from biomass burning.

Social and anxiety-like behaviors contribute to nicotine self-administration in adolescent outbred rats

Both emotional and social traits interact with genetic factors to influence smoking behavior. We previously established a socially acquired nicotine intravenous self-administration model where social learning of a nicotine-associated odor cue reversed conditioned flavor aversion and promoted nicotine intake. In this study, we first phenotyped ~800 adolescent heterogeneous stock rats in open field, novel object interaction, social interaction, elevated plus maze, and marble burying behaviors. These rats were then phenotyped on socially acquired nicotine self-administration. We found 243 significant correlations between different behavioral tests. Principal component regression analysis found that ~10–20% of the variance in nicotine-related measures, such as intake during the first or the last three fixed-ratio sessions, the progressive ratio session, and reinstatement behavior, can be explained by variations in behavioral traits. Factors corresponding to social behavior and anxiety were among the strongest predictors of nicotine intake and reinstatement of nicotine-seeking behavior. We also found many sex differences in behavioral measures. These data indicated that the genetic diversity of this population, in combination with social behaviour and anxiety, are significant contributors to the divergent nicotine self-administration behavior and indicated a high probability of discovering sex-specific genetic mechanisms for nicotine intake in future genome-wide association studies.

Quantitative prediction of the aged state of Ni-base superalloys using PCA and tensor regression

The microstructure of Ni-base superalloy components evolves and degrades during the operation of gas turbines. Since the remaining life depends on the degradation, it is highly desirable to have a quantitative descriptor of the aged state of the microstructure that can be linked to the operating conditions. In this paper, data analytics algorithms are used to develop such relationships. High-throughput aging experiments were performed to generate a dataset comprising multiple aged microstructure images. The digital images of the γ/γ′ phase are used as an indicator of the aged state and statistically evaluated using 2-point spatial correlation functions. To reduce the high-dimensional structural information so that a quantitative linkage can be made between aging conditions and the aged state, two algorithms were considered. The first algorithm involves two steps, first using conventional principal component analysis (PCA) to provide a lower dimension descriptor of the microstructure and then regression analysis to generate the linkage. The second algorithm, called tensor regression (TR), is a novel algorithm that merges the dimensionality reduction and model construction step into a single step. The output of the TR model is directly the statistical descriptors of the microstructure rather than the PC scores, thereby reducing the amount of information loss. Even though PCA provides an effective tool for visualization and classification of data, the model built based on the TR algorithm is shown to have stronger prediction capability.

Phylogenetic, ecological and biomechanical constraints on larval form: A comparative morphological analysis of barnacle nauplii.

Barnacle naupliar larvae are differentiated from other zooplankton by their unique pair of frontal lateral horns, frontal filaments, and a pear-shaped cephalic shield. Their morphology impose constraints on their ecological functions and reflect their evolutionary history. To explore the potential functional basis underlying the similarities and differences in barnacle larval form, we conducted a meta-analysis on the shape of the barnacle nauplii’s cephalic shield and examined its relation to larval size, trophic mode, pelagic larval duration and habitat. Nauplii cephalic shield morphology of 102 species were quantified with normalized elliptic Fourier analysis. Most of the species were distributed around the center of the morphospace but a few extreme groups occupied the periphery: nauplii that were large and lecithotrophic. Subsequent principal component regression analyses showed that larval size was a good predictor of the first shape variations axis (aspect ratio). After allometry adjustment, nauplii from different trophic modes differentiated along the second axis of the major shape variations (relative frontal horn length). Habitat was a poor predictor of variations in naupliar body form, but it could be used to differentiate extreme morphology groups from other nauplii. Our result suggests that size-related biomechanical or developmental constraints and feeding requirements are important in shaping the evolution of the naupliar body form. Within the limitations of these functional constraints, habitat drives the divergence of extreme morphology groups from the majority of species. Our comparative morphometrics analysis demonstrated how variations in larval body form can be quantitatively linked to the functional needs that constrain or drive their diversity, and inform further empirical experiments on larval functional morphology.

Chemometric Models for Quantification of Carbamazepine Anhydrous and Dihydrate Forms in the Formulation

Carbamazepine (CBZ) exists in anhydrous and dihydrate forms. These forms differ in their solubility, dissolution rate, and subsequently in their oral bioavailability. The objective of this study is to develop multivariate chemometric models for estimation of the low level of carbamazepine dihydrate (CBZ-DH) in the CBZ formulations containing excipients of the commercial formulation. The selected excipients were mixed in proportions to make sample matrices ranging from 0% to 50% CBZ-DH. Fourier transform infrared (FTIR), near infrared (NIR), and hyperspectral imaging data were mathematically pretreated before the development of partial least square and principal component analysis regression models. The developed partial least squares regression and principal component analysis models demonstrated predictability of CBZ and CBZ-DH by multiple scattering correction and standard normal variate processing methods. Among the spectroscopic techniques used the model performance parameters such as root-mean-square error, standard error, and bias were found to be low for NIR compared to FTIR. The treated data have shown better model fitting than without treatment, which was demonstrated by correlation coefficient of 0.9778, 0.9824, and 0.9852 for FTIR, NIR, and hyperspectral imaging, respectively. Furthermore, the predicted values were found to be very close to the selected low level of independent samples having 5% CBZ-DH in tablet formulation.

Effect of ultrasonic on deterioration of oil in microwave vacuum frying and prediction of frying oil quality based on low field nuclear magnetic resonance (LF-NMR)

The ultrasound assisted microwave vacuum frying system was investigated to achieve higher physicochemical and quality attributes of frying oil. In this study, the effect of ultrasonic on peroxide value, acid value, carbonyl value, polar component, fatty acid, color, viscosity, dielectric properties and low field nuclear magnetic resonance (LF-NMR) relaxation characteristics of frying oil under microwave vacuum frying were analyzed; the principal component regression (PCR) analysis was used to establish a correlation model for predicting physicochemical properties through LF-NMR relaxation characteristics. The results indicated that the acid value, carbonyl value, polar component, color, viscosity, dielectric constant and saturated fatty acids of the oil samples increased with the prolongation of frying time, and the peroxide value increased first and then decreased with the extension of frying time. Furthermore the relaxation time of peak T21, T22 and T23 decreased gradually of frying oil, and the peak area ratio of S21 gradually increased as the frying time goes on. Good correlations were found between the LF-NMR relaxation characteristics and the physicochemical properties using PCR, and the analysis results are credible. In conclusion, compared with the microwave vacuum frying, the ultrasonic combined with microwave vacuum frying can delay the deterioration of the frying oil and the physicochemical properties of frying oil could be well predicted by the LF-NMR T2 relaxation characteristics during the frying process.