Multivariate Statistical Analysis Techniques Research Articles

VAE-Based Interpretable Latent Variable Model for Process Monitoring.

Latent variable-based process monitoring (PM) models have been generously developed by shallow learning approaches, such as multivariate statistical analysis and kernel techniques. Owing to their explicit projection objectives, the extracted latent variables are usually meaningful and easily interpretable in mathematical terms. Recently, deep learning (DL) has been introduced to PM and has exhibited excellent performance because of its powerful presentation capability. However, its complex nonlinearity prevents it from being interpreted as human-friendly. It is a mystery how to design a proper network structure to achieve satisfactory PM performance for DL-based latent variable models (LVMs). In this article, a variational autoencoder-based interpretable LVM (VAE-ILVM) is developed for PM. Based on Taylor expansions, two propositions are proposed to guide the design of appropriate activation functions for VAE-ILVM, allowing nondisappearing fault impact terms contained in the generated monitoring metrics (MMs). During threshold learning, the sequence of counting that test statistics exceed the threshold is considered a martingale, a representative of weakly dependent stochastic processes. A de la Peña inequality is then adopted to learn a suitable threshold. Finally, two chemical examples verify the effectiveness of the proposed method. The use of de la Peña inequality significantly reduces the minimum required sample size for modeling.

Mandarin Variety Significantly Affects the Metabolites Present in the Leaves

Late-season varieties of mandarin (Citrus reticulata Blanco) have a high economic value, so their study, characterization, and comparison among different commercial varieties is of great interest for agriculture. Detailed metabolomic analysis of mandarin leaves can provide valuable information on agronomic characteristics, vegetative development, and tree response to abiotic and biotic stresses. In this study, an analysis of the main metabolites presents in the leaves of three late-season mandarin orange varieties (‘Afourer’, ‘Orri’ and ‘Tango’), cultivated under homogeneous conditions, was carried out using nuclear magnetic resonance (1H NMR) and multivariate statistical analysis techniques. The results show that organic acids and sugars are the metabolites with the highest presence in mandarin leaves, especially malate and sucrose. Ten amino acids and other metabolites such as choline and trigonelline were also detected. Metabolites such as asparagine and isoleucine were widely implicated in the metabolic pathways of the detected compounds. The ‘Orri’ variety showed significantly more differences in metabolite concentrations compared to the other two varieties studied. Malate and sucrose were shown to be the metabolites with the greatest significant differences between the varieties compared. From an agronomic point of view, the ‘Orri’ variety differs from the other two varieties because it has concentrations of metabolites that provide good resistance to abiotic and biotic stresses and fruits of higher quality and sweetness.

Study of Correlated Motions to Detect the Conformational Transitions of the Intrinsically Disordered Sheep Prion Peptide.

Intrinsically disordered proteins (IDPs) are known for their random structural changes throughout their sequence based on the environment. The mechanism underlying these structural changes is difficult to explain. All biological processes are known to follow the direction through which they act. A study of the correlated motion can help to understand the direction of the change. Herein, we introduced the multivariate statistical analysis (MSA) technique to study the correlated motion of the peptide. The correlated motion of the sheep prion peptide was studied with the change in the temperature and solvent. These techniques helped to identify the contributing residual motions that helped to form the different secondary structures of the protein and also the triggering factors that drive these sorts of residual motions. The structural details match the experimentally reported data. It was found that the direction of the change of the secondary structure for this peptide shifted from the C-terminal to the N-terminal with an increase in the temperature. It was found that the involvement of the hydrophobic residues present at the C-terminal and the middle residues (residues 12-17) is responsible for forming a β-sheet at the normal temperature. Hydration water was found to play an important role in this change. Insights gained from this study can be used to design strategies for desirable structural changes in the IDPs.

Selection of chemical marker for Cnidii Rhizoma by Gyeongbuk production area and harvest time using UPLC-QTOF/MS and multivariate statistical analysis techniques

Selection of chemical marker for <i>Cnidii Rhizoma</i> by Gyeongbuk production area and harvest time using UPLC-QTOF/MS and multivariate statistical analysis techniques

The Effect off Leadership Style and Work Environment on Online Team Performance Using SEM-PLS

&lt;p&gt;&lt;em&gt;The problem that occurs in the online group of Gen-Q Educational Product Distribution (EPD-R), namely the lack of qualified EPC which causes organizational performance in the EPD-R online group is less than optimal. The purpose of this study is to know whether the style of leadership and work environment affects the performance of the team in the EPD-R online group. The method used is SEM with the Tools Partial Least Square (pls). Partial Least Square (pls) is a multivariate statistical analysis technique by predicting the effect of variables X to Y variables and explaining theoretical relationships between the two variables. The results showed that the influence of leadership style variables on team performance was proven significant with a value of p-value 0.05 and the working environment variable on the team's performance did not have a significant effect because of the value of p-value 0.05. The coefficiency value of the leadership style variable on the performance of the team has a positive value. Where, when leadership style increases, team performance will also increase. While the coefficient value of the work environment variable on the performance of the team has a positive value.&lt;/em&gt;&lt;em&gt;&lt;/em&gt;&lt;/p&gt;

Risk assessment and strontium isotopic tracing of potentially toxic metals in creek sediments around a uranium mine, China

The contamination of creek sediments near industrially nuclear dominated site presents significant environmental challenges, particularly in identifying and quantifying potentially toxic metal (loid)s (PTMs). This study aims to measure the extent of contamination and apportion related sources for nine PTMs in alpine creek sediments near a typical uranium tailing dam from China, including strontium (Sr), rubidium (Rb), manganese (Mn), lithium (Li), nickel (Ni), copper (Cu), vanadium (V), cadmium (Cd), zinc (Zn), using multivariate statistical approach and Sr isotopic compositions. The results show varying degrees of contamination in the sediments for some PTMs, i.e., Sr (16.1–39.6 mg/kg), Rb (171–675 mg/kg), Mn (224–2520 mg/kg), Li (11.6–78.8 mg/kg), Cd (0.31–1.38 mg/kg), and Zn (37.1–176 mg/kg). Multivariate statistical analyses indicate that Sr, Rb, Li, and Mn originated from the uranium tailing dam, while Cd and Zn were associated with abandoned agricultural activities, and Ni, Cu, and V were primarily linked to natural bedrock weathering. The Sr isotope fingerprint technique further suggests that 48.22–73.84% of Sr and associated PTMs in the sediments potentially derived from the uranium tailing dam. The combined use of multivariate statistical analysis and Sr isotopic fingerprint technique in alpine creek sediments enables more reliable insights into PTMs-induced pollution scenarios. The findings also offer unique perspectives for understanding and managing aqueous environments impacted by nuclear activities.

Unlocking solutions for cleaner waters: The Industrial Wastewater Quality Index in Egypt and beyond

AbstractThis research study conducted in Egypt focuses on addressing the issue of industrial water pollution and promoting sustainable water and environmental management practices. The study introduces a novel tool called the Industrial Wastewater Quality Index (IWQI) and utilizes two assessment methods to evaluate the extent of water pollution caused by industrial effluents. The IWQI takes into consideration both the environmental limits specified by Egyptian legislation and industry‐specific parameters, effectively condensing extensive water quality data into simplified categories. The IWQI model proves to be a dependable instrument for assessing the overall quality of groundwater intended for industrial use. It incorporates multiple water quality indices and employs multivariate statistical analysis techniques to determine the contribution of each parameter to industrial water quality. This comprehensive analysis enhances the reliability of the model, making it a valuable point of reference for similar locations worldwide, particularly those sharing similar climatic conditions. The outcomes of this study provide valuable insights for policymakers and stakeholders involved in regulating and mitigating industrial water pollution in Egypt. The findings also have relevance to other countries facing similar challenges, highlighting the importance of developing effective techniques for investigating pollution sources, monitoring water quality, and forecasting future trends. The study underscores the necessity of implementing proactive measures to address industrial water pollution and protect water resources and ecosystems. By emphasizing these aspects, the study emphasizes the importance of promoting sustainable water and environmental management practices. Overall, the IWQI and the study's findings contribute to the development of strategies to manage and control industrial water pollution and can guide policymakers and stakeholders in Egypt and other countries facing similar challenges.

A Data Driven Machine Learning Model for Fault Detection in Industrial Pipelines

Industry 4.0 has marked a paradigm shift in the way production and manufacturing operates. Process monitoring and fault diagnosis are important for the safety and reliability of industrial processes especially for smart manufacturing. As a data-driven process monitoring methodology, multivariate statistical analysis techniques, such machine learning based approaches have become extremely critical for automation. Pipelines carrying oil and gas are essential for a nation's economic sustainability. In order to maximise their function and prevent product losses during the transportation of petroleum products, they must be carefully inspected. However, they are susceptible to failure, which could have negative effects on the environment, financial loss, and safety. Therefore, evaluating the pipe's state and quality would be crucial. Despite being time-consuming and expensive, a number of inspection procedures are used to assure the safety of pipelines. However, due to the time consumption and error prone nature of manual inspection, data driven models are being explored for forecasting failure in oil and gas pipelines. The proposed work presents a Bayesian Regularized classifier for forecasting failure and the results show that the proposed approach outperforms the existing baseline techniques in terms of forecasting accuracy. Keywords:- Industry 4.0, oil pipelines; failure forecasting, Bayesian Regularization, Confusion Matrix, Classification Accuracy.

Assessment of heavy metals at mangrove ecosystem, applying multiple approaches using in-situ and remote sensing techniques, Red Sea, Egypt.

Mangrove areas are considered the most retention zone for heavy metal pollution as it work as an edge that aggregates land and sea sediments. This study aims to examine if the heavy metals' existence in the mangrove sediment is related to contamination or natural resources. In addition, it gives an interpretation of the origin of these metals along the Egyptian Red Sea coast. Twenty-two samples of mangrove sediments were collected and then, analyzed for metals (Mn, Ni, Cu, Fe, Cd, Ag, and Pb) using inductively coupled plasma mass spectroscopy (ICP-MS). Integration between the in-situ data, contamination indices, and remote sensing and geographical information science (GIS), and multivariate statistical analysis techniques (PCA) were analyzed to assess and clarify the spatial origin of heavy metals in sediment at a regional scale. The average concentration of heavy metals from mangrove sediments were shown to be substantially lower than the referenced value, ranging from moderate to significant except the levels of Ag were very high. The heavy metals concentrations were expected to be naturally origin rather than anthropogenic and that be confirmed by mapping of Red Sea alteration zones spots. These alteration zones are parallel to mangrove sites and rich by several mineralization types including heavy metals that are carried by flooding to the coastline. Remote sensing and GIS techniques successfully contributed to interpreting the pattern of the origin of heavy metals and discharging systems that control the heavy metals concentration along the Red Sea coast.

Multivariate Relationships Between Health Outcomes and Health System Performance Indicators: An Integrated Factor Analysis With Canonical Correlations

ObjectivesThis study aimed to investigate the relationships between sets of variables related to health system performance indicators and health outcomes. MethodsThe relationships between a set of health outcomes and a set of health system performance indicators of a developing country were examined using multivariate statistical analysis techniques. A combinative strategy of explanatory factor analysis and the canonical correlation coefficient was used to define linear structural relationships between study variables. Province-based data were gathered from2 official statistical records of the Turkish Statistical Institute for the year 2019. Life expectancy at birth, infant mortality rate, and crude death rate were accepted as health outcome indicators. ResultsThe explanatory factor analysis indicated 2 independent variable groups, namely (1) health-related human resources and capacity and (2) health service utilization characteristics. The results of the canonical correlation analysis illustrated good performance to define sparse linear combinations of the 2 groups of variables. There existed strong positive correlations between health outcomes and health-related human resources and capacity indicators (rc = 0.83; P < .001) and health service utilization indicators (rc = 0.59; P < .001). ConclusionsThe results of this study support the view that there is a linear and strong positive relationship between health outcomes and health-related human resources and capacity indicators. Further studies will combine big data analytics with multivariate statistical analysis techniques by studying large health system performance data sets.

Comparison of Classical and Robust Factor Analyses Methods

Factor analysis is a multivariate statistical analysis technique that has become very popular in recent years. In the factor analysis model, the error covariance matrix is assumed to be the multivariate normal distribution, and outliers are likely to be accounted for. Various estimation methods were compared with Monte Carlo simulation for the factor analysis model. The performances of the estimation methods were evaluated based on the ratio of the total variance explained and the criterion fit values. Considering the MLE, PCA, WLS, and GLS methods for classical factor analysis and the MCD, M, and S methods for robust factor analysis, the ratio of total variance explained, and fit values decreased as the sample size increased. When the number of variables increases, the ratio of total variance explained, and fit values increase at different sample sizes. It can be said that the WLS and GLS methods are better than others for classical factor analysis and the MCD and M methods are better than others for robust factor analysis.

Classification of Vietnamese Cashew Nut (Anacardium occidentale L.) Products Using Statistical Algorithms Based on ICP/MS Data: A Study of Food Categorization

Fingerprinting techniques, which utilize the unique chemical and physical properties of food samples, have emerged as a promising approach for food authentication and traceability. Recent studies have demonstrated significant advancements in food authentication through the use of fingerprinting methods, such as multivariate statistical analysis techniques applied to trace elements and isotope ratios. However, further research is required to optimize these methods and ensure their validity and reliability in real-world applications. In this study, the inductively coupled plasma mass spectrometry (ICP-MS) analytical method was employed to determine the content of 21 elements in 300 cashew nut (Anacardium occidentale L.) samples from 5 brands. Multivariate statistical methods, such as principal components analysis (PCA), were employed to analyze the data obtained and establish the provenance of the cashew nuts. While cashew nuts are widely marketed in many countries, no universal method has been utilized to differentiate the origin of these nuts. Our study represents the initial step in identifying the geographical origin of commercial cashew nuts marketed in Vietnam. The analysis showed significant differences in the means of 21 of the 40 analyzed elements among the cashew nut samples from the 5 brands, including 7Li, 11B, 24Mg, 27Al, 44Ca, 48Ti, 51V, 52Cr, 55Mn, 57Fe, 60Ni, 63Cu, 66Zn, 93Nb, 98Mo, 111Cd, 115In, 121Sb, 138Ba, 208Pb, and 209Bi. The PCA analysis indicated that the cashew nut samples can be accurately classified according to their original locations. This research serves as a prerequisite for future studies involving the combination of elemental composition analysis with statistical classification methods for the accurate establishment of cashew nut provenance, which involves the identification of key markers for the original discrimination of cashew nuts.

Assessment academic performance in online courses: a multivariate model

Grades and other student academic indicators are the most evaluated parameters in studies about teaching and learning. However, several authors point out that these indexes, alone, are not enough to explain the students' performance. To understand the predictors that facilitate or compromise learning in higher education, it is neces-sary to consider other variables related to students, teachers, and the teaching con-text. Thus, this paper presents a multivariate model for assessing student performance in online courses. The model was tested in the context of the COVID-19 pandemic with undergraduate students in Engineering. The course was Calculus 2. Data were analyzed using multivariate statistical analysis techniques. Among the 10 variables tested in the model. Three variables were significant and showed that the students' performance in Calculus 2 was impacted by: family income, cognitive and self-regulatory learning strategies, and teachers' instructional events. The main con-tribution of the study is the construction of a multivariate model that can be replicate in other contexts. In practices, professors and managers will have inputs to better plan the disciplines and avoid increasing retention and dropout rates.

Connecting Obsidian Artifacts with Their Sources Using Multivariate Statistical Analysis of LIBS Spectral Signatures

With the recent introduction of handheld instruments for field use, laser-induced breakdown spectroscopy (LIBS) is emerging as a practical technology for real-time in situ geochemical analysis in the field. LIBS is a form of optical emission spectroscopy that is simultaneously sensitive to all elements with a single laser shot so that a broadband LIBS spectrum can be considered a diagnostic geochemical fingerprint. Sets of LIBS spectra were collected for seven obsidian centers across north-central California, with data processed using multivariate statistical analysis and pattern recognition techniques. Although all obsidians exhibit similar bulk compositions, different regional obsidian sources were effectively discriminated via partial least squares discriminant analysis. Obsidian artifacts from seven archaeological sites were matched to their putative sources with a high degree of confidence.

Hybrid Mahalanobis Taguchi System with Binary Whale Optimisation Feature Selection for the Wisconsin Breast Cancer Dataset

The Mahalanobis-Taguchi System (MTS) is a statistical approach used in breast cancer research to facilitate early detection and promote efficient treatment. The technique analyses mammogram images for significant features using a multivariate statistical analysis technique. It combines the Mahalanobis distance (MD) and Taguchi's method to determine the differences between benign and malignant samples. While orthogonal array (OA) has been widely used in MTS, it has been criticised for providing suboptimal results due to insufficient coverage of feature combinations during the feature optimisation process. To address this issue, the Binary Whale Optimisation Algorithm (BWOA) is proposed as an improved search algorithm for MTS. This paper aims to develop a novel hybrid method that enhances the efficiency of the Mahalanobis Taguchi System (MTS). The performance of feature selection ability due to different MTS hybrid algorithms were also compared. BWOA simulates the hunting behaviour of humpback whales and works by exploring new regions of the solution space, gradually narrowing the search space, and fine-tuning the solution. MTS-BWOA demonstrated its enhanced capability in feature optimisation compared to traditional MTS methods and has the potential to be applied in other medical imaging domains.

Correspondence Analysis to Visualize the Relationships between Alpha-S1 Casein and Beta-Lactoglobulin Gene Polymorphisms in Norduz Sheep

Correspondence analysis (CA) is one of the multivariate statistical analysis techniques which examines the relationships between different nominal variable categories in two-way or contingency tables. The aim of this study is to investigate the relationships between Alpha-S1 casein and Beta-lactoglobulin gene polymorphisms in Norduz sheep by the CA method. In this study, genotype frequencies of CSN1S1 and BLG genes in Norduz sheep (n=102) were used as categorical variables. As a statistical method, descriptive statistics of characteristics were presented as count and percent and the chi-square ( 𝜒 2 ) test and CA in this study were performed to explore the relationships among the genotype frequencies of Beta-lactoglobulin and Alpha-S1 casein genes. The results of this study indicated that CA can be contributed to a graphical display for categories of nominal variables. Animal breeders can utilize CA as an analytical technique and graphical representation for categorical data. According to the results of this study, the first and second dimensions jointly accounted for 52.25% of the total inertia and "AA" allele of CSN1S1 has the greatest significance in the first dimension, while "BB" allele of BLG has the greatest significant in the second dimension. Therefore, it would be useful to investigate the effects of βLactoglobulin and αS1-Casein genotypes on various yield traits in larger population of Norduz sheep.

Assessment of natural radionuclides in powder milk imported to Erbil Governorate, Kurdistan Region-Iraq

In this study, the activity concentrations of 40K, 232Th, and 226Ra radionuclides were estimated in imported milk powder samples from 40 brands available in local markets in Erbil Governorate, Iraq. The measurements were performed using High Purity Germanium (HPGe) detector. The results indicated that the average activity concentrations of 40K, 232Th, and 226Ra were 241, 0.476, and 1.23 Bq kg−1, respectively, and comparisons were made based on the typical consumption characteristics of powdered milk by Kurdistan residents. In all investigated age groups (2–17 years), the average annual effective doses were below the ICRP-recommended limit of 1 mSv y−1 for public exposure. Radiological hazard parameters were determined based on the measured radioactivity concentrations. The relation between all the determined activities of natural radionuclides and radiological parameters was examined using multivariate statistical analysis techniques such as histograms, descriptive statistics, and Pearson correlation analyses. The cancer risk in all samples was lower than the allowable value of (2.5 × 10−3), while the ingestion dose in two samples was higher than the worldwide acceptable value of (0.29) mSv y−1.

Unraveling the hydrogeochemical evolution and pollution sources of shallow aquifer using multivariate statistical analysis and hydrogeochemical techniques: a case study of the Quaternary aquifer in Beni Suef area, Egypt

This study integrates multivariate statistical analysis and hydrogeochemical modeling to investigate the processes controlling the groundwater composition of a shallow aquifer where increased pumping rates and anthropogenic impacts were prevalent. Eighteen groundwater samples were collected and analyzed for major elements and selected heavy metals. The data were classified on the basis of multivariate statistical analysis into three clusters: C1 (Na-Cl facies), C2 (Ca-SO4 facies), and C3 (Ca-HCO3 facies). The application of factor analysis gave four factors affecting the groundwater chemistry, namely the salinization factor, anthropogenic/secondary enrichment factor, the secondary and the micro-nutrient fertilizers, and the aluminum fertilizer factor. The hydrogeochemical study of the groundwater revealed that the processes controlling the groundwater chemistry in the study area are mainly affected by the groundwater occurrence either to the east or to the west of Bahr Youssef Canal. Generally, the dominant hydrogeochemical processes affecting the groundwater are silicate weathering, ion exchange, irrigation return flow, gypsum applications in soil, and evaporation. The groundwater quality evaluation shows that water quality varies from fair to excellent for drinking purposes, where the best water is located in the northern and central parts of the study area. The suitability of groundwater for irrigation was evaluated using several indices indicating that groundwater is suitable for irrigation in the northwest and western parts of the study area. As some groundwater samples lie in high salinity classes on the US Salinity diagram, it is recommended to use this water for plants with good salt tolerance under good drainage conditions. The integration between the statistical and geochemical tools helps reveal the dominant processes through data reduction and classification.

Press media impact of the Cumbre Vieja volcano activity in the island of La Palma (Canary Islands): A machine learning and sentiment analysis of the news published during the volcanic eruption of 2021

In this work we have used as a source of information a large sample of the press articles published during 2021 about the eruption of the Cumbre Vieja volcano in the island of La Palma (Canary Islands). In contraposition, the scientific papers evaluating different facets of natural disasters have preferentially used social networks as a source of information. Herein we have shown how the emotions and sentiments expressed in press media can be efficiently analyzed via AI techniques to better assess the social impact of a disaster at the time it takes place. We have also gauged the usefulness of different classifiers combining sentiment analysis with multivariate statistical analysis and machine learning techniques. By applying this methodology, we were able to classify a newspaper article within a certain time frame of the eruption, and we observed significant differences between local news published in Spanish and those of foreign newspapers written in English. We also found different emotional trajectories of articles by applying the Fourier transform onto the inner “valence” progress along each article narrative time. In addition, there appeared a significant relationship between the surface area occupied by lava and the emotions and sentiments expressed in the articles—many other correlations and causalities could be explored too. The main findings of this research may constitute a helpful resource for a better understanding of the way press media react to volcanic activity, and may guide in public decision-making under different temporal horizons, including the design of improved strategies in the risk reduction domain.

Based on 1H NMR and LC-MS metabolomics reveals biomarkers with neuroprotective effects in multi-parts ginseng powder

In the absence of appearance features, it is becoming increasingly difficult to accurately distinguish botanical herbal powders from different families or parts of the plant. In this study, we explored the biomarkers with neuroprotective effects in multi-parts ginseng based on metabolite content changes and biological functions. First, using 1H NMR and LC-MS metabolomics techniques and multivariate statistical analysis techniques to analyze the differential metabolites (DMs) in ginseng main root (TR), lateral root (LR) and Rhizome (RZ). Also, the analysis of 14 differential metabolites (DMs) using network pharmacology yielded 23 core targets associated with neuroprotective diseases, the KEGG pathway was enriched for 117 signaling pathways and 184 enrichment processes were shown in the GO analysis. Combined with the correlation analysis of primary differential metabolites (PDMs) and secondary differential metabolites (SDMs) content and network activity, we finally identified three biomarkers in different parts of ginseng, namely sucrose, ginsenoside Rb1, and ginsenoside Rb3. Finally, the three biomarkers were validated by molecular docking and SH-SY5Y survival, and the results showed that sucrose, ginsenoside Rb1 and ginsenoside Rb3 exhibited favorable activity results in neuroprotective functions. The results of this study reveal the overall differences in the DMs of the three parts of ginseng, and three biomarkers can help identify different parts of ginseng powder, to avoid illegal substitution when ginseng is used in medicine. At the same time, it also provides a reference method for screening biomarkers that can distinguish different parts of traditional Chinese medicine.