Search

• Identifies factors affecting the workers' bargaining power. • Builds a composite index for the United States using the principal component analysis. • Analyses the relationship between this index and the wage share in the years 1960–2018. • Discusses the link between the workers' bargaining power and inflation. • Estimates the Phillips curve and explains why it has flattened over the last decades. This paper aims to construct a synthetic index of workers' bargaining power and investigate the relationship between it and inflation in the U.S. economy. As a first step, we identify the factors affecting the bargaining power of workers, referring to different groups of variables: labour market indicators; institutional indicators (e.g., collective bargaining coverage, union density); characteristics of the economy (e.g., degree of freedom for capital mobility, share of employment by sector). We then implement Principal Component Analysis (PCA) to assess the adequacy of the indicators and calculate the weights to aggregate the single indicators into a composite index. As a second step, we estimate the impact of our Bargaining Index on inflation by estimating an equation of the determinants of inflation. The composite index thus has a twofold use: it sheds light on the extent to which changes in the labour market in recent decades have weakened workers' bargaining power, and it can be used to test how the evolution of the wage bargaining system affects inflation. [ABSTRACT FROM AUTHOR]

Warehouses represent key links in domestic and international commodity flows. The increasing shortage of workers and increasing costs on the one hand, and the increasing number and stricter demands of users on the other hand lead warehouse managers to realize their operations as efficiently as possible. A proposed model has an objective of enabling companies to monitor warehouse performance in an authoritative, reliable, and simple way and define appropriate corrective measures accordingly. The proposed empirical research consists of three stages, where in the first stage a combination of Principal Component Analysis-Data Envelopment Analysis methods was applied in order to determine efficient warehouses based on 90 decision making units. In the second phase, a completely new method called Interval Fuzzy Rough Pivot Pair-wise Relative Criteria Importance Assessment method used for determining criteria weights was developed and applied, which is one of the most important novelties of this study. In the last phase, the Interval Fuzzy Rough Measurement of Alternatives and Ranking according to the Compromise Solution method was applied to rank the alternatives. Twelve criteria were observed to evaluate 21 alternatives. Based on the results, it was concluded that salary stood out as the most important criterion, while amortization stood out as the least significant criterion. On the other hand, alternatives A9 and A10 stood out as the best-ranked alternatives while A1, A2, and A3 stood out as the least efficient ones. The paper provides clear scientific contributions that are reflected in the reduction of the gap that was observed after reviewing the literature where there is a lack of papers dealing with this task. Also, the combination of methods applied in the paper has not been used so far, so it can be said that this paper represents an excellent basis for further research. The model has practical contributions as it allows decision-makers to make quality decisions regarding the operation of their warehouses in different time periods or observation periods, as well as it represents a decision support tool that can be used for better warehouse management. • New model for warehouse performance evaluation has been proposed. • An integrated PCA-DEA-IFR PIPRECIA-IFR MARCOS Model was developed. • New approach IFR PIPRECIA was developed and presented in literature for first time. • The model enables more accurate and precise decision-making in logistics. [ABSTRACT FROM AUTHOR]

The aims of this study were to examine the relationship between lamb and ewe behaviors in postnatal 3-hour and lamb survival using machine learning (ML) algorithms and to determine the best ML classifier to predict lamb survival. The research data consisted of postnatal 3-hour behavior records of 43 Kivircik ewes and their 65 lambs, along with preweaning survival information of lambs. The prediction of lamb survival was performed on three datasets containing different features using decision tree, support vector machine (SVM), multilayer perceptron, logistic regression, random forest (RF), K-nearest neighbors, and boosting (B) ML algorithms. The accuracy, precision, recall, and F1 score values of the RF algorithm were 0.931, and the area under curve value was 0.966 for dataset 1, which included parity of dam, birth type and sex of lamb, and birth weight predictors, as well as postnatal lamb and ewe behaviors as features. In dataset 2, which includes principal component scores instead of lamb and ewe behaviors, the RF approach made classification with an accuracy of 0.909. In dataset 3, which includes the maternal behavior score as a feature, the RF and SVM algorithms showed similar performance (0.909 accuracy). These results indicate that, by using lamb and ewe behaviors in the postnatal 3-hour with ML methods, it is possible to classify lambs as either surviving or dying before weaning with high accuracy. In addition, it was determined that the ML algorithm that best adapted to the current study data was the RF classifier. • Relationship between lamb and ewe behaviors in postnatal 3-hour and lamb survival. • Using machine learning to classify lambs as either surviving or dying before weaning. • The best performance was obtained using random forest with an accuracy of 0.931. • Sucking durations during 150 and 180 minutes were the most crucial features of survival. [ABSTRACT FROM AUTHOR]

[Display omitted] • Stocking density of Eisenia fetida could affect the green waste (GW) vermicomposting. • The optimum earthworm stocking density is 30 worms/kg (T3) for GW vermicomposting. • 30 worms/kg stocking increases the growth of earthworms and the NPK content. • T3 increased the OM degradation rate by 35 % relative to control (no earthworm). • PCA showed that earthworm growth was negatively correlated with lignocellulose. Appropriate stocking density plays an important role in ensuring the stability and improving the overall efficiency of the vermicomposting system. Although some studies have shown that earthworms can degrade lignocellulosic materials, relatively few studies have been conducted on the effect of earthworm stocking density on the degradation of a single green waste (GW) with high lignocellulosic content. Therefore, this study investigated the degradation effect of earthworms on GW at different stocking densities, and assessed the stability and maturity of the whole vermicomposting by comprehensively analysing the changes in physicochemical and biological properties of earthworms during vermicomposting, and by combining the growth of earthworms with a multi-dimensional assessment of the stability and maturity of the whole vermicomposting. In this study, six stocking densities (CK-T5) were set up, namely, no earthworms, 10, 20, 30, 40, and 50 worms/kg. The results showed that compared with the CK (without earthworms), when there were 30 earthworms per kg of GW (i.e. T3), the total nitrogen, total phosphorus, total potassium, organic matter decomposition, bacterial and fungal numbers, and germination index of earthworm compost products increased by 14 %, 29 %, 32 %, 35 %, 42 %, 94 %, and 125 %, respectively. T3 also enhanced the activities of cellulase and alkaline phosphatase. The results were further supported by principal component analysis. Finally, we conclude that when the stocking density of earthworms is appropriate (T3), it not only favours the growth of earthworms, but also positively affects the physicochemical properties of the vermicomposting process, which in turn significantly improves the biodegradation efficiency of GW. [ABSTRACT FROM AUTHOR]

• The principal component analysis was suitable for sludge properties analysis. • The variance contribution of the extracted two principal components was 92.5 %. • Principal component scores visualized characteristics of sludge solids parameters. • The maximum drying rate was positively correlated with the initial moisture content. Convective drying is an effective method for reducing the moisture content of the sludge. Fewer studies have discussed the effect of sludge physicochemical properties on drying compared to air parameters. Eleven types of sludge were collected, and ultimate analysis, proximate analysis, and heat value analysis were performed. Meanwhile, the maximum drying rate (u max) of sludge convection drying at 70 °C was determined. The results showed that the cumulative variance contribution of the two extracted principal components (PCs) was 92.5 %. Then, a regression model of u max was developed based on the extracted PCs. The coefficient of determination of this model was 0.788, and the difference was statistically significant, with a negative correlation between u max and PC2. Further, the principal component score plot enabled the traceability of the integrated sludge, and based on this classification results, the drying characteristics of various types of sludge were discussed, and a high correlation (R2 = 0.9590) between the initial moisture content of sludge and u max was found. Mathematical models between sludge physicochemical properties and drying characteristics can be effectively developed from both sludge composition and type scales. This exploration deepened the knowledge of sludge drying and facilitates the prediction of drying rate. [ABSTRACT FROM AUTHOR]

This study investigates the combustion characteristics of nonpremixed bluff-body stabilized H 2 /N 2 -air flames, with a specific focus on a fully cracked ammonia case. The motivation behind this exploration lies in the potential of such flames to contribute to low-carbon combustion technologies, serving as both a reference and a first step towards understanding the role of the recirculation zone on the in-situ cracking of ammonia bluff-body stabilized flames. Simultaneous Raman/Rayleigh measurements of temperature and major species are utilized to validate the numerical model, offering a detailed characterization of the flame structure. To achieve computational efficiency at high fidelity, the simulation algorithm employs a data-driven approach that combines principal component analysis (PCA) with deep neural networks (DNNs). The model incorporates differential diffusion and subgrid-scale effects. The proposed PC-DNN approach includes differential diffusion based on a rotation technique, utilizing the mixture-averaged (MA) transport model for the training dataset. To show the potential of the PC-DNN approach in modeling fully cracked ammonia flames, the study compares large eddy simulation (LES) results with recent Raman/Rayleigh scattering measurements obtained at KAUST. The findings reveal that the PC-DNN method accurately captures key flame features with just two principal components. Incorporating differential diffusion and subgrid-scale effects enhances predictions, despite some inconsistencies in fuel-rich areas, and in the far field of the burner exit where mixing is predominant, suggesting further room for improvement in the model. This research sheds light on the complex dynamics of fully cracked ammonia flames, providing valuable insights for advancing low-carbon combustion technologies. • H 2 /N 2 -air bluff-body stabilized flames are studied. • Differential diffusion in PCA-based models with subgrid closure is considered. • Accounting for differential diffusion and subgrid-scale effects enhances predictions. • Flame structure in fully cracked ammonia is revealed, showing double layers of OH. [ABSTRACT FROM AUTHOR]

The aim of this study was to evaluate the physiology of 13 yeast strains by assessing their kinetic parameters under anaerobic conditions. They included Saccharomyces cerevisiae CAT-1 and 12 isolated yeasts from different regions in Brazil. The study aimed to enhance understanding of the metabolism of these strains for more effective applications. Measurements included quantification of sugars, ethanol, glycerol, and organic acids. Various kinetic parameters were analyzed, such as specific substrate utilization rate (q S), maximum specific growth rate (μ max), doubling time, biomass yield, product yield, maximum cell concentration, ethanol productivity (P Eth), biomass productivity, and CO 2 concentration. S. cerevisiae CAT-1 exhibited the highest values in glucose for μ max (0.35 h−1), q S (3.06 h−1), and P Eth (0.69 gEth L−1 h−1). Candida parapsilosis Recol 37 did not fully consume the substrate. In fructose, S. cerevisiae CAT-1 stood out with higher values for μ max (0.25 h−1), q S (2.24 h−1), and P Eth (0.60 gEth L−1 h−1). Meyerozyma guilliermondii Recol 09 and C. parapsilosis Recol 37 had prolonged fermentation times and residual substrate. In sucrose, only S. cerevisiae CAT-1, S. cerevisiae BB9, and Pichia kudriavzevii Recol 39 consumed all the substrate, displaying higher P Eth (0.72, 0.51, and 0.44 gEth L−1 h−1, respectively) compared to other carbon sources. [Display omitted] • The physiology of 13 yeasts was investigated under anaerobic conditions using glucose, fructose, or sucrose. • Saccharomyces cerevisiae CAT-1 showed the higher fermentation capacity and rapid substrate consumption. • Candida glabrata Recol 43 also exhibited favourable metabolic traits and high ethanol productivity. • Only S. cerevisiae CAT-1, S. cerevisiae BB9, and Pichia kudriavzevii Recol 39 consumed all the sucrose. • All yeast strains exhibited higher ethanol yields when using fructose as a substrate. [ABSTRACT FROM AUTHOR]

Military development is increasingly related to strategic independence and technological advantages, representing an important factor in countries' scientific, technological, and economic development. In this context, the present work proposes a methodology for evaluating the world's military power based on the integration between Multi-Criteria Decision-Making (MCDM) and Machine Learning. To this end, data from the military, economic, and strategic spheres of 140 countries were analyzed and evaluated considering 12 quantitative variables. Considering the large volume of data to be analyzed and establishing a ranking of countries, the Principal Component Analysis (PCA), an unsupervised Machine Learning technique, was used. PCA allowed the analysis of 140 countries, identifying three factors representing the collective behavior of the 12 original variables, providing a world ranking of military power. The results were compared with specialized rankings on the subject and proved robust and reliable. As a contribution to the academy and society, the authors highlighted that this work fills the gap regarding the application of PCA in military problems to classify the observations, emphasized that the proposed methodology can be replicated in the most diverse problems and serve as input in other MCDM and data science techniques. In addition, the multidisciplinary of PCA allows the technique to support the decision-making process in the most diverse areas of knowledge that involve data analysis in tactical, operational, and strategic problems. [ABSTRACT FROM AUTHOR]

This study is devoted to the analysis of the statistical relationship between the efficiency of an insurance company and a number of factors characterizing the structures of its assets. Efficiency in the study is considered as a metric that evaluates the quality of an organization's management, which is the one of the most important characteristic of its financial stability. The empirical analysis was carried out using data from the financial statements of insurance companies for the period from 2017 to 2020 of the group of leaders in terms of insurance premiums of the Expert RA rating agency based on the results of 2020. Life insurance companies, reinsurance companies and mutual insurance companies were excluded from this list due to the specifics of their business and financial statements. For the companies included in the final sample, an assessment of overall efficiency was built. The methodology of its calculation is formulated and developed in [3, 14, 15]. It is based on Data Envelopment Analysis (DEA). The partial efficiency indicators obtained for a certain set of DEA model specifications are aggregated into several indicators using the principal component analysis method (PCA). It is important that there is a positive correlation between the overall efficiency indicator and the partial efficiency indicators. The first principal component acts as an indicator of overall efficiency, the others allow one to identify its sources. This makes it possible to compare companies that have the same overall efficiency. Further, for all representatives of the final sample, a regression model of the statistical relationship of overall efficiency with the characteristics of the asset structure was built. The model specification was performed based on the MFP (Multivariable Model-Building with Fractional Polynomials) algorithm [16, 17], which allows to adapt the specification of the regression model to the properties of the data and identify nonlinear statistical relationships. The results of the evaluation of the model allow us to assert that the general and, accordingly, all partial performance indicators have a statistical relationship with the selected characteristics of the asset structure. The nature of the relationship is predominantly nonlinear. The results obtained in the work can be useful in forming a strategy for managing the financial stability of an insurance company, as well as for potential partners and investors in solving the task of benchmarking. [ABSTRACT FROM AUTHOR]

This research aims to analyze the importance of inventory control and management, especially regarding the components used in industrial machinery maintenance. The methodology used was based on a quantitative approach, descriptive scope, and non-experimental cross-sectional design. Principal Component Analysis (PCA) and Clustering techniques were employed to evaluate both the quantities consumed and the frequency of usage, to efficiently categorize the components according to their distinctive attributes. This approach is proposed as an objective guidance that will significantly contribute to improving effectiveness and sustainability in the overall management of spare parts inventories. The developed methodology allowed for a detailed description of spare parts behavior; 1,753 references of spare parts used in the maintenance of industrial equipment in a food factory during the period from the second half of 2021 to the first half of 2022. The highest production peaks were recorded during this time, highlighting consumed quantities and usage frequencies, guiding the material management teams in making decisions about spare parts storage. [ABSTRACT FROM AUTHOR]

• This study aims to develop a rational model of the intention to risky behaviour based on behavioural characteristics, demographic information, and the amount of exposure and comparing aggregate and disaggregate models of input variables. • In this study, the self-reported data of Tehran taxi drivers was collected in the form of a questionnaire based on the theory of planned behaviour, and then the amount of intention to commit violations was predicted and modeled using stepwise regression and decision tree regression. • The variables were compared and refined in two stages of exploratory factor analysis and stepwise regression before being entered into the tree regression model. • The results obtained from different modelling cases showed that the presence or absence of the exposure variable did not have much effect on the models. The inclusion of attitude, subjective norm, perceived behavioural control and descriptive norm increased the explained variance of intention to violate. The need to predict and understand drivers' intention to violate emphasizes the importance of developing a model based on the motives behind the action. This study aims to develop a model to predict a taxi driveŕs intention to speed in an urban area using variables including psychological factors, demographic information, and exposure. Aggregate (factor-based) and disaggregate (item-based) models of input variables will also be compared. In this study, the self-reported data on Tehran taxi drivers was collected in the form of a scenario-based questionnaire which is inspired by the Theory of Planned Behaviour (TPB). The intention to commit violations was predicted and modelled using stepwise regression and decision tree regression models. The results, based on the stepwise regression model showed a higher value of fitting score for an item-based linear model (R2 = 0.695), but the final model using the tree-based regression presented a better fit for the factored model (R2 = 0.746) considering the cross-validated model with the lowest deviation criteria (RMSD = 0.26). Furthermore, in this model attitude made the greatest contribution to the prediction of intention. The results obtained from the two different modelling approaches showed that exposure and age did not have much effect on the models. A main advantage of the current study is that the variables were compared and refined in two stages of exploratory factor analysis and stepwise regression before being entered into the tree regression model. In addition, the results of the factor-based model were compared with the item-based model. [ABSTRACT FROM AUTHOR]

• Developed a framework combining PCA and logistic regression to predict fall risks in older adults. • Selected hospitalization due to falls as outcome measure for model development. • PCA with full variables showed best prediction performance (AUC=0.78, sensitivity=74 %). • Provided practical suggestions for community health promotion and fall prevention. • Compared feature selection between traditional statistics and machine learning. Falls require comprehensive assessment in older adults due to their diverse risk factors. This study aimed to develop an effective fall risk prediction model for community-dwelling older adults by integrating principal component analysis (PCA) with machine learning. Data were collected for 45 fall-related variables from 1630 older adults in Taiwan, and models were developed using PCA and logistic regression. The optimal model, PCA with stepwise logistic regression, had an area under the receiver operating characteristic curve of 0.78, sensitivity of 74 %, specificity of 70 %, and accuracy of 71 %. While dimensionality reduction via PCA is not essential, it aids practicality. Our framework combines PCA and logistic regression, providing a reliable method for fall risk prediction to support consistent screening and targeted health promotion. The key innovation is using PCA prior to logistic regression, overcoming conventional limitations. This offers an effective community-based fall screening tool for older adults. [ABSTRACT FROM AUTHOR]

Older people with sensory impairment are more likely to have smaller and weaker social network due to their reduced ability, which lowers their quality of life. However, there is little research on the social network in older people with sensory impairment, especially the related factors. The aim of the study was to explore the related factors of social network and to provide evidence for the improvement of social network to promote successful aging in older people with sensory impairment. A cross-sectional study was conducted among 374 participants for hearing and vision assessment and questionnaire survey in a community, Beijing. Data were collected and analyzed by principal component analysis (PCA) and multiple logistic regression using IBM SPSS 25.0 software. PCA showed that there were six risk factors whose eigenvalues >1 were extracted, with a total variance of 56.555%. Multiple logistic regression analysis of principal component indicated that five factors including physical health factor, social interaction factor, psychological status factor, lifestyle factor, and family condition factor, were statistically significant (p < 0.05). The social network of older people with sensory impairment is relatively poor. Physical health factor, social interaction factor, psychological status factor, lifestyle factor, and family condition factor may be related factors. Medical staff should pay attention to physical, psychological and social characteristics of older people, especially with sensory impairment, to carry out necessary measures to improve social network and avoid social isolation. [ABSTRACT FROM AUTHOR]

Heart Failure (HF) is a clinical syndrome whose signs and symptoms gradually become incapacitating for the patient. Representing almost half of the HF incidence worldwide, Heart Failure with preserved Ejection Fraction (HFpEF) remains in constant growth, being associated with an increase in costs and the need for resources. Cardiac Rehabilitation Programs (CRPs), as a secondary prevention strategy, are multidisciplinary structured interventions that include the prescription of physical exercise, healthy habits, and nutritional counseling. The Physiopathology of HF includes the overactivation of the sympathetic nervous system, and access to this increased activity in the context of cardiovascular rehabilitation constitutes valuable information for exercise prescription. Accordingly, the main goal of this work is to propose a score of sympathetic activation in HFpEF patients, to be applied in the context of CRPs for exercise prescription. The methodology here proposed is based on a long-term Electrocardiogram (ECG) acquisition, followed by the extraction of autonomic attributes to conduct a Principal Component Analysis approach yielding a score of autonomic activation. Three cases were tested by using distinct sets of attributes, highlighting the contribution of using all attributes versus applying only the ones related to the specific part of the autonomic function, as is the case when the very low-frequency band is included to derive the activation score for the sympathetic system. The proposed methodology is a simple and easy-to-use method to compare, within a group with similar initial characteristics, the extent to which the intervention is changing the initial status of each individual when compared withing one group with similar phenotype. [ABSTRACT FROM AUTHOR]

Prediction of students' academic performance has garnered considerable interest, with many institutions seek to enhance students' performance and their quality of education. The integration of both unsupervised and supervised machine learning techniques has demonstrated significant efficacy in predicting student performance. This paper explores the application of different machine learning methods in predicting student academic performance. Initially, Principal Component Analysis (PCA) was utilised to reduce the dataset's dimensionality, thereby improving its visualisation. Subsequently, K-Means clustering was employed to segregate students into distinct groups, reflective of their learning behaviors. Afterwards, the observed clusters were utilised for training classification models to address each student cluster individually. This approach was implemented in a case study involving an undergraduate science course at a North American University (NAU) and the Open University Learning Analytics Dataset (OULAD). Empirical findings indicate that the combined use of Feedforward Dense Network (FDN), Random Forest (RF), and Decision Tree (DT), specifically in their clustered forms, outperforms other classifiers in predicting student academic performance effectively. [ABSTRACT FROM AUTHOR]

This article explores the effectiveness of applying auto encoders in the context of classical machine learning tasks, particularly classification tasks on tabular data. Significant emphasis is placed on a detailed comparison of this approach with other widely adopted methods in the field. As an applied task, the creation of a look-alike model for targeted advertising is pursued. Research into the requirements for this model reveals that conventional approaches to processing tabular data and model training cannot yield a solution that qualitatively meets all specified criteria. Evaluation is conducted on a closed dataset provided by a telecommunications operator. This de-identified dataset includes subscriber descriptions, their tariff plans, and mobile devices. The research goal is to assess non-traditional approaches from the domain of deep learning and neural networks in the context of classification tasks on tabular data and compare them with established methods in this context. The research findings demonstrate that the investigated approach yields a solution that surpasses traditional approaches across all specified criteria. Furthermore, the study provides insights into the universality of this approach, indicating its applicability in various domains for tabular data classification tasks. The ability to compress information into vector representations without significant loss and identify new hidden nonlinear dependencies in data enhances the practical value of the approach. Future research will address the formation of multiple autoencoders in different knowledge domains and their integration for specific tasks. Additionally, efforts will focus on identifying the most effective algorithm for finding similar subscribers based on the vector representations obtained from autoencoders. [ABSTRACT FROM AUTHOR]

[Display omitted] The reactivity of metal surfaces is a cornerstone concept in chemistry, as metals have long been used as catalysts to accelerate chemical reactions. Although fundamentally important, the reactivity of metal surfaces has hitherto not been explicitly defined. For example, in order to compare the activity of two metal surfaces, a particular probe adsorbate, such as O, H, or CO, has to be specified, as comparisons may vary from probe to probe. Here we report that the metal surfaces actually have their own intrinsic/eigen reactivity, independent of any probe adsorbate. By employing unsupervised machine learning algorithms, specifically, principal component analysis (PCA), two dominant eigenvectors emerged from the binding strength dataset formed by 10 commonly used probes on 48 typical metal surfaces. According to their chemical characteristics revealed by vector decomposition, these two eigenvectors can be defined as the covalent reactivity and the ionic reactivity, respectively. Whereas the ionic reactivity turns out to be related to the work function of the metal surface, the covalent reactivity cannot be indexed by simple physical properties, but appears to be roughly connected with the valence-electron number normalized density of states at the Fermi level. Our findings expose that the metal surface reactivity is essentially a two-dimensional vector rather than a scalar, opening new horizons for understanding interactions at the metal surface. [ABSTRACT FROM AUTHOR]

Clustering methods have become widely popular in the field of data analysis, as they enable the grouping of similar data points. However, the challenge of clustering high-dimensional data remains a significant obstacle due to the "curse of dimensionality." Traditional methods like Principal Component Analysis (PCA) and hierarchy-based feature agglomeration have been used to overcome this challenge by reducing the dimensionality of the dataset. However, there is currently no efficient method for clustering features of a high-dimensional dataset. To address this issue, we present a non-parametric clustering method in this paper, specifically designed for identifying features in a high-dimensional dataset. Our proposed feature clustering algorithm utilizes a partitioning algorithm that creates clusters of features. Through experimental results using publicly available datasets, we demonstrate the effectiveness of our method. Our approach offers a valuable tool for researchers and practitioners to better understand and analyze high-dimensional data. [ABSTRACT FROM AUTHOR]

Healthcare systems around the world have faced challenges due to the Coronavirus disease (COVID-19) epidemic, which has taken resources and attention away from long-term diseases like liver cancer. To identify the effect of COVID-19 on liver cancer, proposed an effective research work with Extreme Gradient Boosting (XGBoost) classifier. The identification of the most suitable feature is executed through the utilization of SelectKBest, Principal Component Analysis (PCA) and Singular Value Decomposition (SVD) techniques. A comparative analysis is carried out to ascertain the more precise feature selection, employing Decision Tree, K-Nearest Neighbors (KNN), CatBoost, LightGBM, and XGBoost algorithms. Further, the proposed work undertakes an analysis of the impact of COVID-19 on liver cancer, encompassing both the pandemic and pre-pandemic periods. In comparison to other feature selection techniques and models, SelectKBest feature selection with Xgboost classifier provided an accuracy of 0.92. The proposed research work provides valuable insights to healthcare professionals and policy makers, providing a better understanding of the challenges faced by liver cancer patients during the pandemic. By meticulously exploring feature selection techniques and employing advanced machine learning models, this study quantifiably demonstrates the effectiveness of the proposed methodology in addressing the impact of COVID-19 on liver cancer, contributing to a more comprehensive understanding of this critical issue. [ABSTRACT FROM AUTHOR]

One of the most frequent phenomena in the follow-up of glioblastoma is pseudoprogression, present in up to half of cases. The clinical usefulness of discriminating this phenomenon through magnetic resonance imaging and nuclear medicine has not yet been standardized; in this study, we used machine learning on multiparametric magnetic resonance imaging to explore discriminators of this phenomenon. For the study, 30 patients diagnosed with IDH wild-type glioblastoma operated on at both study centers in 2011–2020 were selected; 15 patients corresponded to early tumor progression and 15 patients to pseudoprogression. Using unsupervised learning, the number of clusters and tumor segmentation was recorded using gap-stat and k-means method, adjusting to voxel adjacency. In a second phase, a class prediction was carried out with a multinomial logistic regression supervised learning method; the outcome variables were the percentage of assignment, class overrepresentation, and degree of voxel adjacency. Unsupervised learning of the tumor in its diagnosis shows up to 14 well-differentiated tumor areas. In the supervised learning phase, there is a higher percentage of assigned classes (P < 0.01), less overrepresentation of classes (P < 0.01), and greater adjacency (55% vs. 33%) in cases of true tumor progression compared with pseudoprogression. True tumor progression preserves the multidimensional characteristics of the basal tumor at the voxel and region of interest level, resulting in a characteristic differential pattern when supervised learning is used. [ABSTRACT FROM AUTHOR]

Ankle sprains are common and cause persistent ankle function reduction. To biomechanically evaluate the ankle function after ankle sprains, the ground reaction force (GRF) measurement during the single-legged landing had been used. However, previous studies focused on discrete features of vertical GRF (vGRF), which largely ignored vGRF waveform features that could better identify the ankle function. To identify how the history of ankle sprain affect the vGRF waveform during the single-legged landing with unsupervised machine learning considering the time-series information of vGRF. Eighty-seven currently healthy basketball athletes (12 athletes without ankle sprain, 49 athletes with bilateral, and 26 athletes with unilateral ankle sprain more than 6 months before the test day) performed single-legged landings from a 20 centimeters (cm) high box onto the force platform. Totally 518 trials vGRF data were collected from 87 athletes of 174 ankles, including 259 ankle sprain trials (from previous sprain ankles) and 259 non-ankle sprain trials (from without sprain ankles). The first 100 milliseconds (ms) vGRF waveforms after landing were extracted. Principal component analysis (PCA) was applied to the vGRF data, selecting 8 principal components (PCs) representing 96% of the information. Based on these 8 PCs, k-means method (k = 3) clustered the 518 trials into three clusters. Chi-square test assessed significant differences (p < 0.01) in the distribution of ankle sprain and non-ankle sprain trials among clusters. The ankle sprain trials accounted for a significantly larger percentage (63.9%) in Cluster 3, which exhibited rapidly increased impulse vGRF waveforms with larger peaks in a short time. PCA and k-means method for vGRF waveforms during single-legged landing identified that the history of previous ankle sprains caused a loss of ankle absorption ability lasting at least 6 months from an ankle sprain. • Data analysis was based on ungrouped data. • Combined PCA and k-means methods can cluster the features related to ankle sprain. • In Cluster 3, the vGRF impact phase may be affected by the ankle sprain history. [ABSTRACT FROM AUTHOR]

• Validation of promoted fracture healing via intramedullary Mg implantation. • Concurrent systemic and local bone modulation associated with retention of Mg implant. • Constructed radiological markers with improved differentiation of healing outcomes. • Preclinical evidence for comprehensive fracture research and developing Mg implants. The clinical application of magnesium (Mg) and its alloys for bone fractures has been well supported by in vitro and in vivo trials. However, there were studies indicating negative effects of high dose Mg intake and sustained local release of Mg ions on bone metabolism or repair, which should not be ignored when developing Mg-based implants. Thus, it remains necessary to assess the biological effects of Mg implants in animal models relevant to clinical treatment modalities. The primary purpose of this study was to validate the beneficial effects of intramedullary Mg implants on the healing outcome of femoral fractures in a modified rat model. In addition, the mineralization parameters at multiple anatomical sites were evaluated, to investigate their association with healing outcome and potential clinical applications. Compared to the control group without Mg implantation, postoperative imaging at week 12 demonstrated better healing outcomes in the Mg group, with more stable unions in 3D analysis and high-mineralized bridging in 2D evaluation. The bone tissue mineral density (TMD) was higher in the Mg group at the non-operated femur and lumbar vertebra, while no differences between groups were identified regarding the bone tissue volume (TV), TMD and bone mineral content (BMC) in humerus. In the surgical femur, the Mg group presented higher TMD, but lower TV and BMC in the distal metaphyseal region, as well as reduced BMC at the osteotomy site. Principal component analysis (PCA)-based machine learning revealed that by selecting clinically relevant parameters, radiological markers could be constructed for differentiation of healing outcomes, with better performance than 2D scoring. The study provides insights and preclinical evidence for the rational investigation of bioactive materials, the identification of potential adverse effects, and the promotion of diagnostic capabilities for fracture healing. [ABSTRACT FROM AUTHOR]

To examine the usefulness of carotid web (CW), carotid bifurcation and their combined angioarchitectural measurements in assessing stroke risk. Anatomic data on the internal carotid artery (ICA), common carotid artery (CCA), and the CW were gathered as part of a retrospective study from symptomatic (stroke) and asymptomatic (nonstroke) patients with CW. We built a model of stroke risk using principal-component analysis, Firth regression trained with 5-fold cross-validation, and heuristic binary cutoffs based on the Minimal Description Length principle. The study included 22 patients, with a mean age of 55.9 ± 12.8 years; 72.9% were female. Eleven patients experienced an ischemic stroke. The first 2 principal components distinguished between patients with stroke and patients without stroke. The model showed that ICA-pouch tip angle (P = 0.036), CCA-pouch tip angle (P = 0.036), ICA web-pouch angle (P = 0.036), and CCA web-pouch angle (P = 0.036) are the most important features associated with stroke risk. Conversely, CCA and ICA anatomy (diameter and angle) were not found to be risk factors. This pilot study shows that using data from computed tomography angiography, carotid bifurcation, and CW angioarchitecture may be used to assess stroke risk, allowing physicians to tailor care for each patient according to risk stratification. [ABSTRACT FROM AUTHOR]

Gait in people with lower limb amputation (LLA) is typically asymmetrical. Reducing this asymmetry is often attempted to minimise the impact of secondary health issues. However, temporal-spatial asymmetry in gait of people with LLA has also been shown to underpin dynamic stability. The current study aimed to identify the effects of acute attempts to achieve temporal-spatial symmetry on the dynamic stability of people with unilateral transtibial amputation (UTA). The secondary aim of this study was to identify the corresponding biomechanical adaptations during attempted symmetrical gait. Eleven people with UTA walked along a 15 m walkway in four different conditions: normal (NORM), attempted symmetrical step length and step frequency (SYM SL+SF) attempted symmetrical step length (SYM SL) and attempted symmetrical step frequency (SYM SF). Dynamic stability was measured using the backward (BW) and medio-lateral (ML) margins of stability (MoS). Results indicate that attempting SYM SF had a positive effect on gait stability in BW and ML directions, while attempting SYM SL had a potentially negative effect, although these results did not appear to be significant. The absence of clustering in principal component analysis, supported the lack of significant results, indicating no features differentiating between conditions of attempted symmetry. Conversely, there was clustering by limbs which were associated with differences in knee and ankle joint angles between the prosthetic and non-prosthetic limbs, and clustering by individuals highlighting the importance of patient-specific analysis. The data suggests that attempted symmetrical gait reduces asymmetry but also affects dynamic stability. • Asymmetry was preserved irrespective of attempted symmetry in amputee gait. • Non-prosthetic limb adjusted in attempt of symmetry rather than prosthetic limb. • Asymmetry has a functional role in maintaining stable amputee gait. • Clustering in principal component analysis was by limbs not condition. [ABSTRACT FROM AUTHOR]

[Display omitted] • The combination of PCA and ANN is an effective tool of data evalution. • PCA can be effectively used to reduce the number of water quality parameters. • Bootstrap method with ANN can effectively determine accurate indexes for model prediction Collecting and analyzing data on surface water across extensive areas is a challenging, time-consuming and expensive. Developing predictive models that offer high accuracy, reliability and require minimal parameters can potentially reduce the time and expense associated with water quality monitoring and management. While most existing studies have focused on estimating point prediction of water quality without approximating the predictive interval (PI) of the estimation, this study aimed to develop a prediction tool to estimate the PI of water quality indexes (WQIs) in the lower Mun river basin. This was achieved by employing principal component analysis (PCA), artificial neural networks (ANN), and bootstrap methods to enhance accuracy, robustness, and reliability with the minimum number of water quality parameters. PCA was initially used to select 4 parameters for the WQI. Subsequently, ANN regression was employed to develop a new WQI to enhance data evaluation efficiency. The testing results of the proposed model revealed its excellent performance compared to other models in terms of accuracy (root mean square error (RMSE) = 0.86, correlation coefficient (R) = 0.993, scatter index (SI) = 0.019, mean absolute error (MAE) = 0.709, and mean bias error (MBE) = −0.003). Additionally, the proposed model incorporated the bootstrap method to quantify uncertainty and create a PI, resulting in a high coverage rate exceeding 95%. By integrating statistical techniques with artificial intelligence and quantifying uncertainty, it is possible to effectively evaluate water quality, provide more accurate and reliable indexes. This study can be an effective tool for decision makers and planners seeking precise data on water quality to develop water resource management strategies. [ABSTRACT FROM AUTHOR]

Accurate prediction of remaining useful life (RUL) can ensure the safety and reliability of power batteries during operation, reduce the failure rate and operating costs, and enhance user experience. However, battery degradation is a complex, nonlinear dynamic process that is difficult to fully comprehend and predicting RUL remains a significant challenge. To address this issue, the hybrid data-driven prediction model PCA-CNN-BiLSTM was proposed in this paper, which combines principal component analysis (PCA), convolutional neural network (CNN), and bi-directional long short-term memory (Bi-LSTM) network. PCA was applied to downscale and whiten the health factor (HF) to maximize the extraction of important features of lifespan decay, while reducing the correlation between features. The convolution kernel of the CNN was used to explore the local region feature information of the input information and search for the common patterns among the neighboring data. Additionally, the model parameters and computational efforts were reduced through pooling. Finally, battery RUL prediction was achieved using Bi-LSTM, which has the advantages of effectively enhancing model accuracy and reducing the risk of over-fitting by taking into account both past and future data. The performance of the proposed model was evaluated utilizing NASA and CALCE's battery datasets, and the results suggest that it exhibits a high level of accuracy across various datasets. Compared to other methods, the PCA-CNN-BiLSTM method has the best performance indicators for predicting battery RUL, including RMSE, MAE, MAPE, RUL e and DOL. This indicates that the proposed model has better fitting performance, accuracy, robustness, and generalization ability. [Display omitted] • Propose a novel battery RUL prediction method based on hybrid data-driven model. • Nineteen health factors were extracted, including segmented discharge time and temperature. • The effectiveness of the PCA-CNN-BiLSTM was verified on multiple public datasets. [ABSTRACT FROM AUTHOR]

To increase leakage diagnosis (LD) efficiency of heating-networks and overcome the lack of actual leakage data, a LD method is proposed based on system simulation and principal component analysis (PCA)_back propagation (BP) neural network that treats the LD problem as a pattern recognition one. In this method, a hydraulic working-condition (HWC) simulation model is constructed to obtain model datasets (MD) of heating-network operation and HWC experiments are conducted to obtain experimental datasets (ED), then cross datasets (CD) is constructed by mixing MD and ED with different ratio. These three datasets are handled through the PCA to unify data feature distribution and realize feature transfer learning in neural network. Then two BP neural networks are trained by ED and CD respectively and both tested with ED. Finally, four kinds of experimental heating-networks, including a branch network with single heat source (B-SHS), a branch network with double heat sources (B-DHS), a single-ring network with single heat source (SR-SHS) and a double-ring network with double heat sources (DR-DHS), are researched. The results indicate that the LD prediction accuracy of BP neural network trained by CD is higher than that one trained by ED. The LD prediction accuracy varies with the cross-data ratio: from 97.52% to 92.21% for B-SHS, from 97.23% to 92.02% for B-DHS, from 97.85% to 89.74% for SR-SHS, and from 95.89% to 92.50% for DR-DHS. Furthermore, the proposed LD method based on BP neural network has better transfer learning performance than that based on random forest or support vector machine. [ABSTRACT FROM AUTHOR]

• The optimal features are screened by the importance and correlation analysis to construct the fault detection model. • Anomaly detection has great influence on the efficiency of PCA and KPCA fault detection. • The KPCA method can significantly improve the fault detection efficiency of PCA at each fault magnitude with the improved efficiency from 1.7% to 28.29%. • For this study, 8 features-IF-KPCA is the most appropriate combination method when considering computational cost and efficiency. With the widespread use of building automation systems (BAS), a large amount of chiller operating data is often readily available, which provides a good basis for optimizing the control of unit sensors. However, these data are highly coupled and contain a large number of outliers which would significantly affect sensor fault detection. Compared with the traditional PCA method, the improved kernel PCA can effectively handle nonlinear data. Meanwhile, anomaly detection has shown excellent ability in rejecting outliers, so an anomaly detection step before fault detection is also necessary. Therefore, to address the problem of data presence coupling and outliers, this study attempts to investigate the impact of different anomaly detection methods on PCA and KPCA based chiller sensor fault detection. Based on the optimal combination of features screened by importance and correlation analysis to construct a fault detection model, the impact of two anomaly detection methods (Isolation Forest and K-means) on KPCA fault detection was analyzed and compared. To obtain general results, an experimental dataset of RP-1043 is used to validate the study. The results show that both anomaly detection methods can improve the overall quality of the original training data. Compared with the traditional PCA method, KPCA improves the detection efficiency by 1.7%–28.29% at all fault magnitudes. The IF-KPCA and Kmeans-KPCA improve the fault detection efficiency by 3.66%–14.63% and 3.17%-20% on top of KPCA. This study would provide reference for the optimal feature combination selection and anomaly detection method selection for practical engineering. [ABSTRACT FROM AUTHOR]

Lifestyle behaviours associated with the incidence of type 2 diabetes mellitus (T2DM) need further clarification using health insurance data. This is a cohort study. In 2015, 193,246 participants aged 40–74 years attended the specific health checkups and were observed up to 2020 in Fukushima, Japan. Using the principal component analysis, we identified two patterns from ten lifestyle behaviour questions, namely, the "diet–smoking" pattern (including smoking, alcohol drinking, skipping breakfast, eating fast, late dinner, and snacking) and the "physical activity–sleep" pattern (including physical exercise, walking equivalent activity, walking fast, and sufficient sleep). Then, individual pattern scores were calculated; the higher the scores, the healthier the behaviours. The accumulative incidence rate of T2DM was 630.5 in men and 391.9 in women per 100,000 person-years in an average of 4 years of follow-up. Adjusted for the demographic and cardiometabolic factors at the baseline, the hazard ratio (95% confidence interval) of the highest versus lowest quartile scores of the "diet–smoking" pattern for T2DM risk was 0.82 (0.72, 0.92; P for trend = 0.002) in men and 0.87 (0.76, 1·00; P for trend = 0.034) in women; that of the "physical activity–sleep" pattern was 0.92 (0.82, 1·04; P for trend = 0.0996) in men and 0.92 (0.80, 1·06; P for trend = 0.372) in women. The "physical activity–sleep" pattern showed a significant inverse association in non-overweight men. Lifestyle behaviour associated with a healthy diet and lack of smoking may significantly lower the risk of T2DM in middle-aged Japanese adults. [ABSTRACT FROM AUTHOR]

At the moment, there is a growing interest in composite materials with matrices based on thermoplastic polymers; these materials are superior to traditional carbon fiber plastics due to higher fracture toughness and impact strength, low smoke generation during combustion, and high thermal and chemical resistance. The deformation behavior of such composite materials due to the high plastic deformation of the matrix differs from the behavior of traditional composites, which must be considered when performing calculations. In our study, as a model object, the features of the microstructure of single carbon thread impregnated with polysulfone were studied in order to evaluate the distribution of misorientation angles of elementary fibers, the degree of their damage, the thickness of the polymer matrix interlayers between elementary fibers in threads impregnated with more viscous thermoplastic binders. Statistical analysis of a large array of micrographs was carried out using specially developed algorithms for computer processing of electron microscopic images of a composite material. Algorithms for processing arrays of images using machine vision algorithms are proposed. Based on the analysis of the data array, the distributions of carbon fibers impregnated with polysulfone were plotted over the misorientation angle of the filaments and over the interfilament distance in the longitudinal and cross sections of the fiber. Using the machine learning method, an algorithm for detecting violations of the filament structure was implemented. The data obtained can be used to refine the calculations of the strength and deformation characteristics of composite materials with thermoplastic matrices. [ABSTRACT FROM AUTHOR]

Previous studies employed varying methods, predictors, and endpoints to determine how to best predict student success. This study examined current admission criteria in predicting nursing students' success during two first semester courses. Grade point averages and Health Education Systems Incorporated entrance exam scores were extracted from student files while pre-nursing pathophysiology grades from electronic gradebooks were used as independent variables. A principal component analysis confirmed three components: Academic performance, logical/mathematical intelligence, and verbal/linguistic intelligence. Multiple regressions were performed using first semester nursing course grades as dependent variables. A multiple regression using Pharmacology course grades as the dependent variable (R 2 = 0.268, p ≤0.001) was more predictive than a regression using Concepts course grades as the dependent variable (R 2 = 0.177, p ≤0.001). Bivariate analyses revealed that each independent variable significantly predicted Concepts course grades and all except math and reading scores predicted Pharmacology course grades. Pathophysiology was a better predictor of both dependent variables. A high degree of shared variance necessitated bivariate analyses to elucidate the importance of each independent variable. Pharmacology course grades proved better predictors of success by the independent variables than Concepts course grades. • Diverse analyses showed groupings, importance, and overlap among variables. • PCA confirmed GPAs and two of Gardner's intelligences as constructs. • Multiple and bivariate regressions distinguished shared from unique variances. • Pathophysiology grades predicted performance better then GPAs or entrance exam scores. [ABSTRACT FROM AUTHOR]

Understanding detailed foot morphology as well as regional plantar forces could provide insight into foot function and provide recommendation for footwear design for chronic ankle instability (CAI) people. This study presented 3-dimensional statistical shape models of feet from three different populations including CAI, copers and healthy individuals, with regional plantar forces also acquired. Sixty-six males (22 participants per group) were included in this study to capture 3-dimensional foot shapes under a standing condition and regional plantar forces during a cutting maneuver. Principal component analysis was performed to generate a mean foot shape of each group as well as modes of variations. A generalized procrustes analysis was used to achieve rapid registration of mean shapes. Besides, regional plantar forces and contact duration among these three populations were compared. For 3-dimensional foot shapes, although no significant differences of the average distance between each mode and mean shape were found among three populations, there were subtle variations in mean shapes. The CAI population presented a more bulging of the lateral malleolus; copers were characterized by the flexion of the lesser toes, a more bulging of the medial foot in the sagittal plane; and healthy individuals showed a greater heel width and a more bulging of the heel in the sagittal plane. In terms of plantar forces, healthy individuals had significantly greater summated plantar forces and greater plantar forces in the lateral heel area during the early contact phase compared to copers and CAI participants. Overall, this study suggested that repetitive ankle sprains may lead to the bulging of the lateral malleolus. Further, CAI and copers seem to stabilize the ankle joint by medially shifting the center of pressure compared to healthy individuals under the static and less challenging dynamic conditions. • Statistical shape models of foot for different populations were established. • Foot characteristics in CAI group presented a more bulging of lateral malleolus. • Copers were characterized by the flexion of lesser toes and medial bulging. • CAI and copers stabilize the ankle joint by medially shifting COP. [ABSTRACT FROM AUTHOR]

• The evidence-based practice and evidence-informed practice questionnaire is a self-assessment tool, which measures the outcomes of evidence-based practice and evidence-informed practice education, including knowledge, attitudes, understanding, behavior, and an individual's self-perceived application and use. • The evidence-based practice and evidence-informed practice questionnaire was developed and pilot-tested using experts, students and academics across a range of professions. • The evidence-based practice and evidence-informed practice questionnaire is a valid and reliable tool designed to be used across a range of nursing and allied health disciplines. Good-quality questionnaires are needed to assess the effectiveness of educational programs on undergraduate healthcare students' knowledge, attitudes, understanding and behavior regarding evidence-based practice and evidence-informed practice. However, there is currently no available questionnaires designed to evaluate the outcomes of evidence-based practice and evidence-informed practice education. Based on the methods proposed by Streiner et al., this study developed and validated a questionnaire for assessing evidence-informed practice and evidence-based practice knowledge, attitudes, understanding, self-perceived application and use, and behavior among undergraduate preregistration students in the nursing and allied health disciplines. Seventy-three questionnaire items were developed and administered to varied groups of people, including students and academics. Principal component analysis was conducted to reduce dimensions and establish construct validity and internal consistency of the developed questionnaire. Following pilot-testing and expert review, the final validated questionnaire consists of 53 items (8 demographic items, 25 evidence-based practice items, and 20 evidence-informed practice items). The evidence-based practice and evidence-informed practice questionnaire is a valid and reliable tool to measure the outcomes of evidence-based practice and evidence-informed practice education. [ABSTRACT FROM AUTHOR]

Optimization of large combustion mechanisms means that a few dozen parameters (called active parameters) are optimized within their uncertainty limits to achieve a better reproduction of the experimental data, which is usually measured by a mean square error function. In previous studies, the active parameters were selected based either on their local sensitivity coefficients (strategy S) or on the products of local sensitivity coefficient and a corresponding uncertainty parameter (strategy SU). This latter measure is known by various names: optimization potential, sensitivity-uncertainty index or uncertainty-weighted sensitivity coefficient. In this work, we proposed three novel active parameter selection strategies of increasing complexity (PCA-SU, PCA-SUE, PCALIN) and demonstrated their superior performance in the optimization of pre-exponential factors (A) in a methanol/NOx combustion mechanism (562 reaction steps of 70 species) against 2360 data measured in shock tube, JSR and flow reactor experiments. The novel methods are based on the principal component analysis (PCA) of sensitivity matrices scaled by the uncertainties of parameters (U) and the uncertainty of the experimental data (E). These PCA-based methods take into account parameter correlations and designate parameter groups and corresponding relevant subsets of experimental data, thereby a factor of 4–7 savings in optimization time was achieved over the S and SU methods. PCA-SUE method performed better than the PCA-SU as it also considered the uncertainty of the experimental data. The PCALIN strategy is similar to PCA-SUE, but it also considers the linear change (LIN) of the error function, which depends on the simulation error of experimental data, and thereby it could provide the most accurate models as a function of the number of active parameters. Based on the PCALIN strategy, fitting all three Arrhenius parameters resulted in further improvements, however, it provided moderate improvements over simple A -factor tuning and required significantly more computer time. [ABSTRACT FROM AUTHOR]

Principal Component Analysis can be used to reduce the cost of Computational Fluid Dynamics simulations of turbulent reacting flows by reducing the dimensionality of the transported variables through projection of the thermochemical state onto a lower-dimensional manifold. However, because of the nonlinearity of the principal component source terms, nonlinear regression techniques must be utilized for the source terms in terms of the principal components. Unfortunately, widely available and utilized nonlinear regression techniques can have prohibitive computational requirements and/or accuracy that is highly dependent on user experience in ad hoc tuning of model architecture and hyperparameters. In this work, a new nonlinear regression approach is proposed that is both computationally efficient and automated so does not require any user input. The approach is evaluated through a priori prediction of principal component source terms using data from a Direct Numerical Simulation of a turbulent nonpremixed n -heptane/air jet flame. In particular, the proposed framework consists of local regressions whose complexity is adapted according to the local nonlinearity of the data: local linear regression when accurate enough and local Artificial Neural Networks when nonlinear regression is required. The number of local clusters for local regression is determined automatically using the Davies-Bouldin index. In addition, Bayesian optimization is utilized for model training (i.e., to select the best architectures and hyperparameters of the nonlinear regressions in an unsupervised fashion), eliminating ad hoc hand-tuning and/or expensive grid searches. Overall, compared to a single, global neural network, the new local adaptive regression approach is shown to have comparable accuracy but 69% less training time due to the utilization of local linear regression and faster training of local neural networks. [ABSTRACT FROM AUTHOR]

The development of reduced-order combustion models able to accurately reproduce the physics of reactive systems has been a highly challenging aspect of numerical combustion research in the recent past. The complexity of the problem can be reduced by identifying and using low-dimensional manifolds able to account for turbulence-chemistry interactions. Recently, Principal Components Analysis (PCA) has shown its potential in reducing the dimensionality of a chemically reactive system while minimizing the reconstruction error. The present work demonstrates the application of the Manifold Generated by Local PCA (MG-L-PCA) approach in direct numerical simulation (DNS) of turbulent flames. The approach is enhanced with an unsupervised clustering based on Vector Quantization PCA (VQPCA) and an on-the-fly PCA-based classification technique. The reduced model is then applied on a three-dimensional (3D) turbulent premixed NH 3 /air flame by transporting only a subset of the original state-space variables on the computational grid and using the PCA basis to reconstruct the non-transported variables. Results are compared with both a detailed reaction mechanism and a Computational Singular Perturbation (CSP) reduced skeletal mechanism. A comparison between training the reduced model using one-dimensional (1D) and 3D data sets is also included. Overall, the MG-L-PCA allows not only for a reduction in the number of transport equations, but also a significant reduction in the stiffness of the system, while providing highly accurate results. [ABSTRACT FROM AUTHOR]

Reduced-order models (ROMs) for turbulent combustion rely on identifying a small number of parameters that can effectively describe the complexity of reacting flows. With the advent of data-driven approaches, ROMs can be trained on datasets representing the thermo-chemical state-space in simple reacting systems. For low-Mach flows, the full state vector that serves as a training dataset is typically composed of temperature and chemical composition. The dataset is projected onto a lower-dimensional basis and the evolution of the complex system is tracked on a lower-dimensional manifold. This approach allows for substantial reduction of the number of transport equations to solve in combustion simulations, but the quality of the manifold topology is a decisive aspect in successful modeling. To mitigate manifold challenges, several authors advocate reducing the state vector to only a subset of major variables when training ROMs. However, this reduction is often done ad hoc and without giving detailed insights into the effect of removing certain variables on the resulting low-dimensional data projection. In this work, we present a quantitative manifold-informed method for selecting the subset of state variables that minimizes unwanted behaviors in manifold topologies. While many authors in the past have focused on selecting major species, we show that a mixture of major and minor species can be beneficial to improving the quality of low-dimensional data representations. The desired effects include reducing non-uniqueness and spatial gradients in the dependent variable space. Finally, we demonstrate improvements in regressibility of manifolds built from the optimal state vector subset as opposed to the full state vector. [ABSTRACT FROM AUTHOR]

Salinity is a crucial problem affecting the productivity of crops across the globe and poses a serious threat to agricultural food production and food security. Salinity stress adversely affects the growth and development of plants by reducing growth attributes, chlorophyll content, and relative water content and further, led to nutritional toxicities and high osmotic stress. The present investigation was employed to assess the response of ten mustard [ Brassica juncea (L.) Czern. & Coss.] genotypes under different regimes of salt concentrations (0, 50, 100, 150, 200, 300 mM NaCl) for tolerance potential using principal component analysis (PCA). The PCA analysis of studied attributes found that Pusa Jai Kisan was salt-tolerant and Pusa Bold was susceptible under different salt conditions compared to the rest of the mustard genotypes. The reduction in morphological attributes, the maximum quantum yield of PSII (Fv/Fm), total chlorophyll, and relative water content was lower in Pusa Jai Kisan and higher in Pusa Bold with increasing concentrations of salinity. In addition, the accumulation of Na+ and Cl‒ ions was increased with increasing salinity stress. Based on growth performance, ten genotypes of mustard were ranked depending on their tolerance to salinity stress: Pusa Jai Kisan > Pusa Mustard 30 > Pusa Jagannath > Pusa Mustard 28 > Pusa Vijay > Pusa Tarak > Pusa Mustard 25 > Pusa Mustard 27 > Pusa Mahak > Pusa Bold, respectively. Thus, PCA analysis can be used as a powerful tool for the identification of tolerant and susceptible genotypes under salinity stress. The understanding of mustard responses towards salinity stress could help in the selection of tolerant genotypes and this selection may play a crucial role in further improving the effectiveness of breeding. [Display omitted] • Soil salinity impacts the global agriculture negatively and limits the crop production globally. • Differential response of ten Indian mustard genotypes under different regimes of salinity (0, 50, 100, 200, 300 mM NaCl) was noted. • Increasing concentration of salinity reduced the morphological traits, total chlorophyll and relative water content in all the ten genotypes studied. • Principal component analysis revealed Pusa Jai Kisan as promising candidate for developing salinity tolerant variety. [ABSTRACT FROM AUTHOR]

With the era of big data, data-driven models are increasingly vital to just-in-time decision support in pollution emission management and planning. This article aims to evaluate the usability of the proposed data-driven model to monitor NOx emission from a coal-fired boiler process using easily measured process variables. As the emission process is highly complex, process variables interact with each other, and they cannot guarantee that all the variables in the actual operation obey the Gaussian distributions. As conventional principal component analysis (PCA) can only extract variance information, a novel data-driven model is proposed, called survival information potential-based PCA (SIP-PCA) model, is proposed in this work. First, an improved PCA model is established based on the SIP performance index. SIP-PCA can extract more information in the latent space from the process variables following the non-Gaussian distributions. Then, the control limits for fault detection are determined based on the kernel density estimation method. Finally, the proposed algorithm is successfully applied to a real NOx emission process. By monitoring the operation of process variables, possible failures can be detected as soon as possible. Fault isolation and system reconstruction can be implemented in time, preventing NOx emissions from exceeding its standard. [Display omitted] • Survival information potential based PCA (SIP-PCA) for fault detection is proposed. • The SIP-PCA method does not have any distribution assumptions and it is robust. • The SIP-PCA algorithm is successfully applied to the real NOx emission detection. • The timeliness and effectiveness of the NOx emission fault are detected. • SIP-PCA outperforms conventional algorithms. [ABSTRACT FROM AUTHOR]

The introduction of other combustible gases to methane could change accident consequences. This work aimed to experimentally compare the effects of blended fuels (C 2 H 6 , C 2 H 4 , CO, and H 2 mix in different proportions) on the explosion pressure behavior of methane and blended fuels in air. The explosion pressure properties of the mixtures were tested. Principal component analysis was employed, and multiple regression models were developed to predict the influences of principal components on the maximum explosion pressure of CH 4. In addition, the software was used to analyze and compare the sensitivity analysis. For the fuel-lean CH 4 -air mixture(φ = 0.72), the results demonstrated that the value of P max and (d P/ d t) max of the mixed gases increased, as the volume fraction of the blended fuels increased. The effects of other gases followed the order C 2 H 6 >C 2 H 4 >H 2 >CO. For stoichiometric concentrations (φ = 1), the order of the influence degree was H 2 >CO > C 2 H 6 >C 2 H 4 , and the value of P max and (d P/ d t) max of the mixed gases tended to decrease slightly. As the volume fraction of the blended fuels was increased to 2%, the P max and (d P/ d t) max of CH 4 showed a decreasing trend for the fuel-rich CH 4 -air mixture. The effects of blended fuels on the equivalence ratio of φ = 1.1 followed the order C 2 H 4 >H 2 >CO > C 2 H 6. The sensitivity variation analysis and normalized sensitivity variation analysis indicated that the chain branching reaction 2CH 3 (+M)<=>C 2 H6(+M) was the most sensitive reaction under various conditions. However, it was not very susceptible to changes in the blended fuel ratio. Most reactions were susceptible to changes in the blended fuel ratio. The 10 most sensitive reactions were generally much more susceptible to changes in the blended fuel ratio in the 2% blended fuels than they were in the 0.4% blended fuels. • Different ratios of blended fuels have significant effects on the explosion characteristics parameters of CH 4. • Multiple regression models were developed to obtain which gas plays the main role in the explosion of the gas mixture. • Insight was gained into the chemical mechanisms at different gas ratios and methane concentrations. • The effects were analyzed based on reaction characteristics. [ABSTRACT FROM AUTHOR]

Kānuka/rawirinui (Kunzea robusta de Lange & Toelken) is an endemic plant species in Aotearoa/New Zealand, which is still used today and traditionally by Māori. Chemical profiling of kānuka essential oils has been performed previously, although comprehensive studies are rare, as is the integration of multiple analytical platforms. In this study, we wished to compare the use of GCMS and NMR metabolomic methods for the analysis of eleven kānuka essential oils, and to apply statistical tools to evaluate how well the data sets corresponded. The main compounds detected were α-pinene (35 – 59%), p- cymene (0.1 – 19%), γ-terpinene (not detected – 12%), α-terpinolene (0.1 – 4%), linalool (1 – 5%), limonene (2 – 3%), eucalyptol (0.1 – 7%) and sesquiterpenoid viridiflorol (2 – 9%). Use of Procrustes analysis to compare the analytical data obtained from a pilot study using both GCMS and NMR metabolomic profiling indicated a high level of correlation between the data sets, suggesting either approach is suitable for analysis of kānuka essential oils in an unbiased fashion. In addition, we also report on the absolute configuration of the major component of the essential oil, (+)- D - α-pinene. [Display omitted] • Pilot study statistically comparing GCMS and NMR data of kānuka essential oils. • Both analytical platforms deliver statistically consistent results. • Either approach is suitable for chemometrics analysis of kānuka. • Determination of absolute configuration of α-pinene as (+)-enantiomer. [ABSTRACT FROM AUTHOR]

The increasing use of three-dimensional imaging calls for reference models representing large parts of the population. The aim of this prospective study was to create templates depicting facial maturation in the younger age groups. Healthy Dutch volunteers were captured, without selection of inclusions. Three-dimensional average faces were created using MATLAB, for both genders in four age groups (4–8 years, 8–12 years, 12–16 years, and ≥16 years). Variation within the groups was calculated and depicted on an average face with a green to red colour scale, corresponding to standard deviations between 0 and ≥ 3 mm, respectively. Measurements of the distances of eight peri-oral landmarks were provided as ratios. The statistical analysis was performed using ANOVA and Tukey's test. Three-dimensional reconstructions of the average face and their first principal component were created for each gender and age group. The first principal component comprised the facial width for each group, and the variation of landmarks was low. All ratios showed an increasing trend with increasing age, except for the ratio of philtrum width to mouth width. This study is novel in comparing facial morphology by means of ratios and in creating average faces for the different young age groups. These data provide useful insights into facial maturation, which might be beneficial for facial surgeons. [ABSTRACT FROM AUTHOR]

In the initial phase of this study, Principal Component Analysis (PCA) was employed to meticulously select noncollinear critical defects associated with construction quality from a comprehensive dataset comprising inspections conducted on 1,015 construction projects. The identified critical components were subsequently categorized into three distinct aspects: Inspection Records and Occupational Safety and Health (Aspect A), Concrete Quality (Aspect B), and Construction Team Quality Management (Aspect C). Subsequently, in the second stage of the study, a Multilayer Perceptron (MLP) network was meticulously trained, utilizing the 23 input variables corresponding to critical defects that had been identified through the PCA process. The training regimen persisted until convergence was achieved, resulting in a well-trained model capable of transforming input data into a probability value indicative of a project's quality level. The MLP model exhibited a remarkable performance, achieving an impressive accuracy rate of 91.3%. These robust evaluation metrics affirm the model's exceptional proficiency in predicting construction quality. The hybrid machine learning approach proposed in this study has proven to be highly effective in extracting valuable insights from inspection data and identifying defects intricately linked to construction quality. This model, with its capacity to accurately forecast construction quality, holds substantial potential for practical application in the construction industry. [ABSTRACT FROM AUTHOR]

Reinjection is of importance to ensure the sustainable utilization of geothermal resources. However, there are still challenges for achieving complete reinjection of pore-type sandstone reservoirs. Taking Neogene sandstone in Tianjin as an example, water-rock reaction experiments under four reinjection fluids at 60 °C and 15 MPa were designed and performed. From the point of view of inner pores and permeability, the variations of pH, TDS and mineral compositions were compared, and their influences on the reinjection were analyzed. Responses of hydrogen and oxygen isotopes to water-rock reactions were obtained. Further, the statistical method including principal component analysis, cluster analysis and Pearson relevance analysis revealed the intrinsic correlations among 9 major hydrochemical compositions, 41 trace elements and 6 mineral compositions during the water-rock reactions. Test results showed that nanofiltration treatment water had more advantages as an alternative reinjection fluid, and the municipal tap water was not recommended. It was found that specific trace elements (e.g. Cu, Pb, Ni, Co, Rb) can be used as potential indicators of dissolution or precipitation of sandstone minerals (e.g. quartz, calcite, ankerite, clay minerals). The present results can provide helpful references for optimal selection of reinjection fluids as well as monitoring and evaluation of geothermal reservoirs. [ABSTRACT FROM AUTHOR]

• The content and component information of essential oil from Cinnamomum parthenoxylo n (Jack) Meisner leaves in China were described. • The distribution pattern of C. parthenoxylo n essential oil in China was revealed. • The main influencing factors of C. parthenoxylo n essential oil were analyzed. The yield and chemical components of Cinnamomum parthenoxylo n (Jack) Meisner essential oil from 564 individual plants across 20 natural populations in five provinces in China were examined in this study. The leaf essential oil yield varied greatly among populations and individual plants (1.15–23.6 mg/g and 0.2–41.3 mg/g, respectively). A total of 117 chemical constituents, which included 51 types of monoterpenes, 46 types of sesquiterpenes, and 20 types of non-terpenoids, were detected from the essential oil of C. parthenoxylon leaves. A total of 14 chemotypes were identified, and eucalyptol chemotypes, camphor chemotypes, and linalool chemotypes were the most common. The 20 natural populations of C. parthenoxylon were divided into four categories based on their main chemical components, including eucalyptol, camphor, linalool, and elemol. The first category included Guangxi populations, which had a high essential oil yield and a high frequency of the eucalyptol chemotype. The second category included Yunnan populations, which had a high frequency of the camphor chemotype. The third category included Hunan and Jiangxi populations, which had a high frequency of the elemol chemotype. The fourth category included Guangdong and Jiangxi populations, which were characterized by a high diversity of chemotypes. The classification of populations was consistent with the geographical distance between them. The main environmental factors affecting variation in essential oil yield and components of C. parthenoxylon leaves were longitude, latitude, altitude, and annual average temperature. The yield of leaf essential oil showed a significant geographical gradient and was negatively correlated with longitude and latitude. The correlation coefficient between essential oil yield and latitude was -0.826, and the correlation coefficient between essential oil yield and longitude was -0.610. The linalool content was positively correlated with annual average temperature. The camphor content was negatively correlated with longitude and latitude and positively correlated with altitude. [ABSTRACT FROM AUTHOR]

The application of multivariate analysis is extremely useful when dealing with large datasets and can be applied also in provenance studies. In this work, Principal Component Analysis (PCA) was applied for the first time to the study of the provenance of lapis lazuli rocks used for glyptic art in ancient times, on a database including four different sources in Afghanistan, Tajikistan, Siberia and Myanmar. Results of the application of PCA on µ-PIXE data collected in mineralogical phases contained in lapis lazuli rocks, in particular diopside and pyrite, confirmed the role of some trace element contents as characteristics for different provenances, i.e. as provenance markers. As an additional important result, PCA seems to strengthen the role of previously found weaker markers (i.e. trace elements not sufficient alone to distinguish univocally among provenances) such as, for example, the coexistence of high Ti, V, Cr and Mn concentrations in diopside in Afghan lapis lazuli. This can be relevant when other discriminant phases like pyrite cannot be found in the sample or are not suitable for analysis. Moreover, for geological purposes and to try to distinguish among different quarries inside an extraction area, a study on intra-provenance variability was carried out on diopside data for Myanmar and Siberian samples. The separation into three groups for Myanmar samples, previously identified by means of minero-petrographic and elemental analysis, is confirmed and a partial differentiation was identified also for samples coming from the two Siberian areas of Sludyanka River and Malaya Bistraya River. [ABSTRACT FROM AUTHOR]

Frangipani flower (Plumeria rubra) plants are commonly found and grown in tropical and subtropical regions. The present study explored the antioxidant, α-glucosidase inhibitor, and antibacterial activities of Plumeria rubra flower extracts. P. rubra flower was extracted by maceration using hexane, ethyl acetate, methanol, and ethanol. The capability of P. rubra flower extract to scavenge radicals was evaluated using a β-carotene bleaching assay and DPPH (2,2-diphenyl-1-picryl-hydrazyl) assay. The total phenolic content (TPC) was assessed using the Folin-Ciocalteau method. Its antibacterial activity was assessed using the disc diffusion method against Salmonella typhimurium and Escherichia coli. The α-glucosidase inhibitor assay was conducted using α-glucosidase from Saccharomyces cerevisiae. The results revealed that the ethanolic 50 % extract of P. rubra flower showed the highest antioxidant activity of 66.49 % at 1000 µg/mL in the β-carotene bleaching assay, and the ethanolic 70 % extract had the highest antioxidant activity with an IC 50 of 93.2 µg/mL in DPPH assay. Meanwhile, for α-glucosidase inhibitory activity, the methanolic extract showed the highest activity of 94.05 % at 1000 µg/mL. These results were in accordance with the total phenolic content (TPC) of the extract, in which the highest TPC was obtained from 50 % ethanol extract (1405.33 mg gallic acid equivalent (GAE)/g). P. rubra extracts at 5 mg/mL showed good antibacterial activity against E. coli and moderate activity against S. typhimurium with inhibition zones of 8.14 mm and 6.88 mm, respectively. Moreover, the liquid chromatography-high-resolution mass spectrometry (LC-HRMS) analysis suggested that several phenolic compounds were presented in the P. rubra flower extracts. The constituents of the P. rubra flower were analyzed using principal component analysis (PCA). This study revealed that P. rubra flower extract could be used as a natural antidiabetic, antibacterial, and antioxidant agent in food additives, functional food industries, and pharmaceutical industries. [Display omitted] • P. rubra flower was utilized as source of natural antioxidant and antidiabetic. • The antioxidant of P. rubra was studied using DPPH and β-carotene assay. • The antidiabetic of P. rubra was studied using α-glucosidase inhibitor assay. • The antibacterial assay of P. rubra against E. coli and S. typhimurium was studied. • Characterization of P. rubra flower extract using FTIR and LC-HRMS. [ABSTRACT FROM AUTHOR]

Iron (Fe) toxicity, generated from excess reduced ferrous Fe (Fe2+) ion formation within the soil under submerged condition, is a potent environmental stress that limits lowland rice production. Total 11 diverse Thai rice genotypes, including a recognized tolerant genotype Azucena and a susceptible genotype IR64, were evaluated against 5 Fe2+ levels [0 (control), 150, 300, 600 and 900 mg/L] to screen the tested genotypes for their Fe-toxicity tolerance and to classify them as a sensitive/tolerant category. The evaluation was conducted by a germination study, followed by a polyhouse study on growth, yield and physiochemical performances. Results showed significant variations in Fe2+-tolerance across genotypes. Increasing Fe2+ level beyond 300 mg/L was detrimental for germination and growth of all the tested genotypes, although germination responses were negatively affected at Fe2+ ≥ 300 mg/L. Physiochemical responses in the form of leaf greenness, net photosynthetic rate, membrane stability index and Fe contents in leaf and root were the most representative of Fe2+-toxicity-mediated impairments on overall growth and yield. Difference in physiochemical responses was effectively correlated with the contrasting ability of the genotypes on lowering excess Fe2+ in tissues. Analysis of average tolerance and stress tolerance index unveiled that the genotypes RD85 and RD31 were the closest to the tolerant check Azucena and the sensitive check IR64, respectively. The unweighted pair group method with arithmetic means clustering revealed three major clusters, with cluster II (four genotypes) being Fe2+ tolerant and cluster I (four genotypes) being Fe2+ sensitive. Principal component (PC) analysis and genotype by trait-biplot analysis showed that the first two components explained 90.5% of the total variation, with PC1 accounting for 56.6% and PC2 for 33.9% of the total variation. The identified tolerant rice genotypes show potentials for cultivation in Fe2+-toxic lowlands for increased productivity. The findings contribute to the present understanding on Fe2+-toxicity response and provide a basis for future genotype selection or rice crop improvement programs against Fe2+-toxicity. [ABSTRACT FROM AUTHOR]

• 132 metabolites were identified and classified by LC-HRMS. • 27 compounds were revealed in the Ericaceae for the first time. • Metabolomic profiling confirms the pharmacological effects of Rhododendron adamsii. • R. lapponicum and R. burjaticum display high potential for pharmacological activity. • The PCA indicated relatedness between the samples of R. burjaticum and R. parvifolium. This study was aimed to compare three Rhododendron species (used as herbal medicines in East Siberia, Mongolia, and China) by a metabolomic assay based on liquid chromatography with high-resolution mass spectrometry and multivariate statistical analysis. The metabolomic profiling was carried out by liquid chromatography with high-resolution mass spectrometry (LC-HRMS). The mass-spectrometric analysis was performed in both positive and negative modes, and the data were processed in Xcalibur 4.0 and Compound Discoverer 3.1 software. In the leaves, 132 compounds identified as isoprenoids, phenolic compounds, nitrogen-containing compounds, prenylated phenols, fatty-acid derivatives, and other organic compounds were detected. Twenty-seven compounds were identified in the Ericaceae for the first time. These are mussaenosidic acid (compound 1), (1S,4R,4aS,8aS)-1,2-bis(hydroxymethyl)-5,5,8a-trimethyl-,4,4a,5,6,7,8,8a-octahydro-1,4-naphthalenediol (6), 2-(8-hydroxy-4a,8-dimethyldecahydro-2-naphthalenyl)acrylic acid (9), gibberellins A7 (11), A3 (13), and A4 (14), sericic acid (15), (3β,5ξ,9ξ)-3,23-dihydroxy-1-oxoolean-12-en-28-oic acid (16), 2-hydroxyestradiol (18), deoxycholic acid (19), 17α-hydroxyprogesterone (20), 3-(4-{[1,3-dihydroxy-1-(4-hydroxy-3-methoxyphenyl)-2-propanyl]oxy}-3-methoxyphenyl)propyl 6-deoxy-α-L-mannopyranoside (54), cis-4-hydroxymellein (58), diaporthin (59), 5,7-dihydroxy-4-methylcoumarin (60), scutellarein 6-methyl ether (65), xanthurenic acid (88), 2,5-dihydro-4-hydroxy-5-oxo-1-(phenylmethyl)-1H-pyrrole-3-carboxylic acid ethyl ester (90), indole-3-butyric acid (91), N6-(L-1,3-dicarboxypropyl)-L-lysine (97), cannabigerolic acid (100), 11-(2,3-dihydroxycyclopentyl)undecanoic acid (106), corchorifatty acid (109), prostaglandin B1 (121), sibiricose A3 (129), solanapyrone A (130), and herbarumin II (131). Principal component analysis confirmed species specificity of the metabolomic profile of each sample from the three Rhododendron species and close relatedness between the samples of R. burjaticum and R. lapponicum. The results indicate high therapeutic potential and low toxicity of the three analyzed species. [ABSTRACT FROM AUTHOR]

Principal component analysis (PCA) is a classic fault diagnosis method widely used in chemical process data modeling. However, the limitation of PCA to handle dynamic and time-variant data has been progressively exposed with the ever-increasing development of artificial intelligence technologies and applications of automation systems in the chemical industry. In this paper, an enhanced temporal algorithm-coupled optimized adaptive sparse PCA (ETA-OASPCA) methodology is proposed with the aim to improve the conventional PCA method by introducing temporal state computation and dynamic adaptive sparsity. The ETA is constructed to extract the state transitions of the time-variant process data by introducing the "Transition" and "Hold", acquire the region of interest by employing a Maximum Fuzzy c-means (MFCM) method, and then use the region time prediction automaton to label the possible abnormal states. The introduction of dynamic adaptive sparsity in PCA, achieved by presenting an iterative interior point optimization method to update the dynamic sparse penalty term, can impose sparsity constraints on dynamic data calculations, thus enhancing the interpretability of the PCA model. The effectiveness of the proposed method was validated through its application in the Eastman Tennessee process, showing that an average fault detection rate, false alarm rate, and latency of 99.4%, 0.37%, and 4.11 mins can be achieved, respectively. [ABSTRACT FROM AUTHOR]