Large Number Of Variables Research Articles

Optimal design of steel–concrete composite bridge based on a transfer function discrete swarm intelligence algorithm

Bridge optimization can be complex because of the large number of variables involved in the problem. In this paper, two box-girder steel–concrete composite bridge single objective optimizations have been carried out considering cost and CO_{2} emissions as objective functions. Taking CO_{2} emissions as an objective function allows to add sustainable criteria to compare the results with cost. SAMO2, SCA, and Jaya metaheuristics have been applied to reach this goal. Transfer functions have been implemented to fit SCA and Jaya to the discontinuous nature of the bridge optimization problem. Furthermore, a Design of Experiments has been carried out to tune the algorithm to set its parameters. Consequently, it has been observed that SCA shows similar values for objective cost function as SAMO2 but improves computational time by 18% while also getting lower values for the objective function result deviation. From a cost and CO_{2} optimization analysis, it has been observed that a reduction of 2.51 kg CO_{2} is obtained by each euro reduced using metaheuristic techniques. Moreover, for both optimization objectives, it is observed that adding cells to bridge cross-sections improves not only the section behavior but also the optimization results. Finally, it is observed that the proposed design of double composite action in the supports allows to remove continuous longitudinal stiffeners in the bottom flange in this study.

Predicting volatile fatty acid synthesis from palm oil mill effluent on an industrial scale

To determine the optimal conditions of anaerobic digestion of palm oil mill effluent (POME) for volatile fatty acid (VFA) synthesis on an industrial scale can be costly and time-consuming due to the large number of variables needed to be tested. In this study, variational autoencoder (VAE) was used to generate simulated data to expand the small size dataset. Then, machine learning models were developed to predict VFA synthesis. Using VAE, 250 simulated data were generated from 25 real data, and a total of 275 samples used for training/validation/testing of machine learning models. The dataset consists of features such as POME volume, COD loading, organic loading rate, temperature, pH. Random forest (RF) and artificial neural network (ANN) were trained and tested on predictions of VFA synthesis. Generally, ANN performed better than RF. To improve the performance, the 3 best performing ANN models were selected for ensemble neural network, where it has robust performances with RMSE of 55.80, R2 of 0.968 on test data. Features importance analysis indicated that temperature was the most important factor influencing VFA synthesis, suggesting that temperature control could improve VFA synthesis. Overall, ANN is robust to predict VFA synthesis while features importance analysis could provide the guidance for adjustment of optimal conditions, reducing the resources and workloads of experiments in real situations.

Exploration of Variables Predicting Sense of School Belonging Using the Machine Learning Method-Group Mnet.

The purpose of this study was to explore variables related to school belonging from a holistic perspective, including a large number of variables in one model, different to the traditional analytical method. Using 2015 data from the Program for International Student Assessment (PISA), we sought to identify variables related to school belonging by searching for hundreds of predictors in one model using the group Mnet machine learning technique. The study repeated 100 rounds of model building after random data splitting. After exploring 504 variables (384 student and 99 parent), 32 variables were finally selected after selection counts. Variables predicting a sense of school belonging were categorized as individual/parent variables (e.g. motivation to achieve, tendency to cooperative learning, parental support) and school-related variables (e.g. school satisfaction, peer/teacher relationship, learning/physical activities). The significance and implications of the study as well as future research topics were discussed.

Development of a Framework for Modeling Protection Mechanisms Provided By Multi-Layered Organic Coatings Applied to Aerospace Al Alloys Via Finite Element Analysis

Aluminum alloys, such as AA2024 and AA7050, are widely used in aerospace applications due to their high strength-to-weight ratio. However, because of the heterogeneous microstructure of these alloys, they are susceptible to microgalvanic corrosion and pitting in chloride-containing environments. The corrosion susceptibility is further increased when these alloys are in contact with more noble alloys, such as in locations near fasteners, where the galvanic interaction leads to accelerated corrosion attack of the less noble Al alloy. To protect these structures against corrosion attack, organic coatings are commonly used. Typical coating systems are usually composed of three layers: a conversion coating, a primer, and a topcoat. When the topcoat is breached, the primer can provide active corrosion protection by the release of inhibitors embedded in the primer. Depending on the type of inhibitor, it can provide chemical protection by the formation of a passive film on the surface of the exposed metallic area and/or provide cathodic protection by the preferential dissolution of sacrificial anodes.The efficacy of the corrosion protection provided by the multilayered coating system to Al alloys in aircraft components exposed to atmospheric corrosion is affected by a large number of variables. The dynamic environment in which the component is exposed to (e.g., relative humidity, temperature, salt loading density), the geometry of the component, the chemistry of the primer, and the type of alloy are examples of important parameters that impact the corrosion and protection mechanisms. To unravel the impact of each one of these variables and/or the synergistic effects between them, a large volume of experimental work is needed, making the prediction of coating failure, corrosion damage, and, ultimately, component lifetime, remarkably challenging. In this context, the development of computational models that can simulate corrosion and corrosion protection mechanisms is attractive, as they can be used as tool to effectively assess the large parameter space and increase efficiency of experimental work.This work focuses on developing a framework for modeling the protection mechanisms offered by chromate-based and Mg-rich primers via finite element analysis. Chemical and electrochemical protection mechanisms were modeled taking into consideration leaching of inhibitor from the primer, mass transport and the impact of the inhibitors in the electrochemistry of the Al alloys. The impact of environmental, geometric, and coating parameters on the effectiveness of the protection mechanisms was assessed. Ultimately, the framework developed will provide a better understanding of protection mechanisms of the organic coating systems and serve as a framework to study new coating systems.

Predicting defects in laser powder bed fusion using in-situ thermal imaging data and machine learning

Variation in the local thermal history during the Laser Powder Bed Fusion (LPBF) process in Additive Manufacturing (AM) can cause micropore defects, which add to the uncertainty of the mechanical properties ( e.g. , fatigue life, tensile strength) of the built materials. In-situ sensing has been proposed for monitoring the AM process to minimize defects, but successful minimization requires establishing a quantitative relationship between the sensing data and the porosity, which is particularly challenging with a large number of variables ( e.g. , laser speed, power, scan path, powder property). Physics-based modeling can simulate such an in-situ sensing-porosity relationship, but it is computationally costly. In this work, we develop Machine Learning (ML) models that can use in-situ thermographic data to predict the micropore of LPBF stainless steel materials. This work considers two identified key features from the thermal histories: the time above the apparent melting threshold ( τ ) and the maximum radiance ( T max ). These features are computed, stored for each voxel in the built material, and then used as inputs. The binary state of each voxel, either defective or normal, is the output. Different ML models are trained and tested for the binary classification task. In addition to using the thermal features of each voxel to predict its own state, the thermal features of neighboring voxels are also included as inputs. This is shown to improve the prediction accuracy, which is consistent with thermal transport physics around each voxel contributing to its final state. Among the models trained, the F1 scores on test sets reach above 0.96 for Random Forests. Feature importance analysis based on the ML models shows that T max is more important to the voxel state than τ . The analysis also finds that the thermal history of the voxels above the present voxel is more influential than those beneath it. Our study significantly extends the capability of using in-situ thermographic data to predict porosity in LPBF materials. Since ML models are fast, they may play integral roles in the optimization and control of such AM technologies.

Data fusion using Multiple Factor Analysis coupled with non-linear pattern recognition (fuzzy k-means): application to Chenin blanc

Patterns in data obtained from wine chemical and sensory evaluations are difficult to decipher using classical statistics. Coupling data fusion with machine learning techniques could assist in solving these issues and lead to new hypotheses. The current study investigated the applicability of classical and machine learning pattern recognition approaches for oenological applications. A sample set of 23 Chenin blanc wines made from young (< 35 years) and old (> 35 years) vines were analysed (recently bottled (Year 1) and after two years of storage (Year 2)). Sensory (sorting) and chemical (NMR: nuclear magnetic resonance and HRMS: high-resolution mass spectrometry) data were collected. Multiple factor analysis (MFA) was used for the data fusion. Cluster analysis was performed by agglomerative hierarchical clustering (AHC) and fuzzy k-means. Optimal cluster conditions were found for both methods and the cophenetic coefficient was used to assess the confidence of fit. Given the large number of variables, the models were complex. Inconsistent clustering patterns were observed when varying clustering conditions, indicating high similarity between samples. Overall, fuzzy k-means resolved clustering patterns better than AHC and, coupled with data fusion, improved the interpretation of the complex oenological data.

Precision Medicine Approaches with Metabolomics and Artificial Intelligence.

Recent technological innovations in the field of mass spectrometry have supported the use of metabolomics analysis for precision medicine. This growth has been allowed also by the application of algorithms to data analysis, including multivariate and machine learning methods, which are fundamental to managing large number of variables and samples. In the present review, we reported and discussed the application of artificial intelligence (AI) strategies for metabolomics data analysis. Particularly, we focused on widely used non-linear machine learning classifiers, such as ANN, random forest, and support vector machine (SVM) algorithms. A discussion of recent studies and research focused on disease classification, biomarker identification and early diagnosis is presented. Challenges in the implementation of metabolomics–AI systems, limitations thereof and recent tools were also discussed.

A Symmetry Evaluation Method, Using Elevation Angle, for Lower Limb Movement Patterns during Sitting-to-Standing

In this paper, we propose a method that uses the femoral and tibial elevation angles to quantitatively evaluate the symmetry of lower limb movement during the transition from a sitting position to a standing position. In kinematic analysis of the transition from sitting to standing, the angles of the three joints of the lower limb are often measured. However, due to the large number of variables, it is difficult to evaluate the symmetry of the lower limb movement by comparing data from the six joints of the left and right lower limbs. In this study, therefore, we measured the femoral and tibial elevation angles of healthy participants and rehabilitation patients and visually and numerically evaluated the symmetry and asymmetry of the movement of the left and right lower limbs. We were able to identify the kinematically major lower limbs in the transition from sitting to standing and quantify the symmetry of the movement patterns of the left and right lower limbs. Furthermore, we examined the possibility that the method could be effectively used in the rehabilitation field to evaluate the motor co-ordination that constitutes the lower limb movement pattern in the transition from the sitting to standing position, such as the gait plane rule.

Approaches to identify the contribution of understudied toxicants in complex metal mixtures

Background and Aim. Exposures to complex mixtures are increasingly acknowledged to contribute to adverse health outcomes through complex joint or interactive effects. Emerging advanced statistical approaches facilitate appropriate analyses of complex mixtures by incorporating high correlations, nonlinearities, and interactions among individual exposures. Selection of appropriate analytical approaches for complex mixture analysis, and the interpretation of results, is dependent on the specific scientific goals. This presentation discusses and compares the use of complementary and combined approaches in analyses of metal mixture exposures in the Navajo Birth Cohort Study (NBCS). Methods. We compare results and interpretation from 1) Clustering methods that assess the study participant’s co-occurring exposure patterns; 2) Regression methods with shrinkage and variable selection that identify a subset of exposure mixtures associated with the outcome of interest; 3) Kernel machine regression approaches that model mixture effects by incorporating interaction and nonlinear relationships; 4) Ensemble learning methods that provide outcome prediction by ranking each variable’s predictive power, thereby handling a large number of variables; and 5) Causal analysis methods that provide inference that mimics interventional effects to control for confounders, reducing biased estimates that may limit generalizability. Results. Different approaches used have helped to identify not only the patterns of exposures in the population, but also understudied metals that, in mixtures, are significant contributors to birth outcomes and developmental delays in NBCS. The results obtained from different approaches have affected the interpretation and opened new avenues of investigation for understudied toxicants. Conclusions. Using complex analytic strategies to parse effects of complex exposures supports both understanding of population-specific exposure-response relationships, and also the specific contributors to those responses and associated mechanisms that are generalizable to populations where metal-mixture mineralogic composition, chemistry, doses, and patterns of exposure will vary. Keywords clustering, penalized regression, kernel machine regression, ensemble learning, causal analysis, mixtures, metals

Prediction and optimization of thermal comfort, IAQ and energy consumption of typical air-conditioned rooms based on a hybrid prediction model

HVAC systems provide satisfactory indoor environments, but they usually consume large amounts of energy in order to achieve an acceptable thermal comfort level and indoor air quality (IAQ). Balancing thermal comfort, IAQ, and energy consumption is thus a challenging task. However, the main problem faced in such research is that it is inefficient to conduct traditional experiments or numerical simulation to obtain the optimal air supply parameters from a large number of variables. Therefore, the aim of this study is to develop a rapid prediction and optimization framework of IAQ, occupant comfort, and energy consumption. Firstly, Building Information Modeling (BIM) technology and Computational Fluid Dynamics (CFD) simulations are used to create the database containing indoor velocity, temperature and CO2 concentration for different distributions of occupants and ventilation parameters. Next, the extreme learning machine (ELM) model optimized by the grey wolf optimizer (GWO) algorithm is developed to predict the thermal comfort level and CO2 concentration, and the input parameters of the prediction models are interpolated to generate more cases. Finally, the satisfied air supply parameters for various optimization objectives are determined by combining the predicted PMV value and CO2 concentration with the energy consumption analysis. The results of the comprehensive analysis showed that the average concentration of CO2 after optimization is reduced and the |PMV|avg is reduced to less than 0.5, which is within acceptable limits. In addition, 14.34% energy saving is achieved in the illustrative example.

A mechanobiological computer optimization framework to design scaffolds to enhance bone regeneration.

The treatment of large bone defects is a clinical challenge. 3D printed scaffolds are a promising treatment option for such critical-size defects. However, the design of scaffolds to treat such defects is challenging due to the large number of variables impacting bone regeneration; material stiffness, architecture or equivalent scaffold stiffness—due it specific architecture—have all been demonstrated to impact cell behavior and regeneration outcome. Computer design optimization is a powerful tool to find optimal design solutions within a large parameter space for given anatomical constraints. Following this approach, scaffold structures have been optimized to avoid mechanical failure while providing beneficial mechanical stimulation for bone formation within the scaffold pores immediately after implantation. However, due to the dynamics of the bone regeneration process, the mechanical conditions do change from immediately after surgery throughout healing, thus influencing the regeneration process. Therefore, we propose a computer framework to optimize scaffold designs that allows to promote the final bone regeneration outcome. The framework combines a previously developed and validated mechanobiological bone regeneration computer model, a surrogate model for bone healing outcome and an optimization algorithm to optimize scaffold design based on the level of regenerated bone volume. The capability of the framework is verified by optimization of a cylindrical scaffold for the treatment of a critical-size tibia defect, using a clinically relevant large animal model. The combined framework allowed to predict the long-term healing outcome. Such novel approach opens up new opportunities for sustainable strategies in scaffold designs of bone regeneration.

A Review of Simplified Numerical Beam-like Models of Multi-Storey Framed Buildings

Modern computational techniques have greatly influenced the numerical analyses of structures, not only in terms of calculation speed, but also in terms of procedural approach. In particular, great importance has been given to structural modelling, that is, the process by which a structure and the actions to which it is subjected are reduced to a simplified scheme. The use of a simplified calculation scheme is necessary since the structures are, in general, considerably complex physical systems whose behaviour is influenced by a large number of variables. The definition of a structural scheme that is at the same time simple enough to be easily computable as well as sufficiently reliable in reproducing the main characteristics of the behaviour of the analysed structure is, therefore, a crucial task. In particular, with reference to multi-storey framed buildings, the extensive use of three-dimensional finite element models (FEM) has been made in recent decades by researchers and structural engineers. However, an interesting and alternative research field concerns the possibility of studying multi-storey buildings through the use of equivalent beam-like models in which the number of degrees of freedom and the required computational effort are reduced with respect to more demanding FEM models. Several researchers have proposed single or coupled continuous beams to simulate either the static or dynamic response of multi-storey buildings assuming elastic or inelastic behaviour of the constitutive material. In this paper, a review of several scientific papers proposing elastic or inelastic beam-like models for the structural analyses of framed multi-storey buildings is presented. Considerations about limits and potentialities of these models are also included.

Maximizing mRNA vaccine production with Bayesian optimization.

Messenger RNA (mRNA) vaccines are a new alternative to conventional vaccines with a prominent role in infectious disease control. These vaccines are produced in in vitro transcription (IVT) reactions, catalyzed by RNA polymerase in cascade reactions. To ensure an efficient and cost‐effective manufacturing process, essential for a large‐scale production and effective vaccine supply chain, the IVT reaction needs to be optimized. IVT is a complex reaction that contains a large number of variables that can affect its outcome. Traditional optimization methods rely on classic Design of Experiments methods, which are time‐consuming and can present human bias or based on simplified assumptions. In this contribution, we propose the use of Machine Learning approaches to perform a data‐driven optimization of an mRNA IVT reaction. A Bayesian optimization method and model interpretability techniques were used to automate experiment design, providing a feedback loop. IVT reaction conditions were found under 60 optimization runs that produced 12 g · L−1 in solely 2 h. The results obtained outperform published industry standards and data reported in literature in terms of both achievable reaction yield and reduction of production time. Furthermore, this shows the potential of Bayesian optimization as a cost‐effective optimization tool within (bio)chemical applications.

Mechanical and physical characterization of natural and synthetic consolidants

The mechanical behavior of adhesives is strongly influenced by a large number of variables, relating to a complex interaction of mechanical-physical-chemical factors, such as its loading direction (shear, peel), the temperature and the environmental relative humidity (RH). These variables can have a large influence on the durability of restored art objects where thermoplastic adhesives have been used as a consolidant. This study aims to characterise the mechanical and physical behavior of some adhesives commonly used polymers by conservators as consolidants to restore cultural objects such as canvas paintings or historic wooden furniture. Twelve commercially available natural and synthetic adhesive materials were tested. The influence of RH at room temperature on the mechanical and physical properties of the adhesives was investigated. Shear and peel experiments were performed on adhesively bonded wood and canvas coupon to establish mechanical characterisation. The physical properties of the adhesives were determined by performing moisture adsorption measurements and Differential Scanning Calorimetry (DSC). The results of this study demonstrate that synthetic adhesive products are able to resist higher shear and peel loads than natural types. Moreover, the influence of important changes in RH on the mechanical properties of the adhesives was demonstrated. Reflecting on the combined data derived from shear and peel tests with the adhesive's sensitivity to moisture will help conservators to select the most suitable adhesives for their applications to achieve optimal durability and the best mechanical performance in versatile environmental conditions.

Well control optimization in waterflooding using genetic algorithm coupled with Artificial Neural Networks

Optimum well controls to maximize net present value (NPV) in a waterflooding operation are often obtained from an iterative process of employing numerical reservoir simulation and optimization algorithms. It is often challenging to implement gradient-based optimization algorithms because of the large number of variables and the complexities to embed the optimization algorithm in the simulator solving workflow. Approaches based on repeated model evaluation are easier to implement but are often time-consuming and computationally expensive.

Affective valence of words differentially affects visual and auditory word recognition.

Recognizing written or spoken words involves a sequence of processing stages, transforming sensory features into lexical-semantic representations. Whereas the later processing stages are common across modalities, the initial stages are modality-specific. In the visual modality, previous studies have shown that words with positive valence are recognized faster than neutral words. Here, we examined whether the effects of valence on word recognition are specific to the visual modality or are common across visual and auditory modalities. To address this question, we analyzed multiple large databases of visual and auditory lexical decision tasks, relating the valence of words to lexical decision times while controlling for a large number of variables, including arousal and frequency. We found that valence differentially influenced visual and auditory word recognition. Valence had an asymmetric effect on visual lexical decision times, primarily speeding up recognition of positive words. By contrast, valence had a symmetric effect on auditory lexical decision times, with both negative and positive words speeding up word recognition relative to neutral words. The modality-specificity of valence effects were consistent across databases and were observed when the same sets of words were compared across modalities. We interpret these findings as indicating that valence influences word recognition partly at the sensory-perceptual stage. We relate these effects to the effects of positive (reward) and negative (punishment) reinforcers on perception. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

PEMBENTUKAN PORTOFOLIO SAHAM OPTIMAL DENGAN MEAN ABSOLUTE DEVIATION PADA DATA SAHAM JAKARTA ISLAMIC INDEX

In 2017 to 2020 the Jakarta Islamic Index (JII) showed a positive trend and was quite stable compared to the LQ45 index. The selection of the JII stock index in this study is intended to obtain maximum profits. Investors are expected to create a series of portfolios to get maximum profit. One of the ways to identify stocks for portfolio formation is to use factor analysis. Factor analysis is used to summarize a large number of variables into new, smaller factors. This new factor is called the portfolio. The Mean Absolute Deviation (MAD) method is used for the formation of an optimal portfolio as well as an improvement on the Markowitz method in terms of non-linear (quadratic) mathematical models. The MAD method is the mean of the absolute value of the deviation between the realized return and the expected return. The optimization technique used in the MAD portfolio is the simplex method. Optimizing the objective function by constraining the set of constraints on the simplex method is done by forming a simplex table. Based on the processing using the simplex method, the investment weight for each of the stocks that make up the first portfolio is 30% CPIN shares; 29.23% of JPFA's shares; 10.77% shares of SMGR; and 30% shares in UNVR. Meanwhile, the investment weight of the constituent stocks for the second portfolio is 30% ACES shares; 10% of ERAA's shares; 30% of INCO's shares; 30% of PGAS shares; and 0% WIKA shares. The results of portfolio performance evaluation show that portfolio 2 is better than portfolio 1, by looking at the Sharpe Index for portfolio 2 of 0.0135629 and portfolio 1 of -0.0281177.

Harmful Drinking Phenotype in a Large Dutch Community Sample.

Harmful drinking patterns are shaped by a broad complex interaction of factors, societal and individual, psychological and behavioral. Although previous studies have focused on a few variables at a time, the current study simultaneously examines a large number of variables in order to create a comprehensive view (i.e. phenotype) of harmful drinking, and to rank the main predictors of harmful and non-harmful drinking by order of importance. We surveyed a large sample of Dutch adults about their habitual drinking characteristics and attitudes, perceptions and motives for drinking. We fed 45 variables into a random forest machine learning model to identify predictors for (1) drinking within and in excess of Dutch guideline recommendations and (2) harmful and non-harmful drinking. In both models, respondents' subjective perceptions of 'responsible drinking', both per occasion and per week, showed the strongest predictive potential for different drinking phenotypes. The next strongest factors were respondents' reason for drinking, motives for drinking and age. Other variables, such as drinking location, knowledge about alcohol-related health risks and consumption of different beverage types, were not strong predictors of drinking phenotypes. Although the direction of the relationship is unclear from the findings, they suggest that interventions and policy measures aimed at individuals and social norms around drinking may offer promise for reducing harmful drinking. Messaging and promotion of drinking guidelines should be tailored with this in mind.

Computing associators of endomorphism fusion categories

Many applications of fusion categories, particularly in physics, require the associators or FF-symbols to be known explicitly. Finding these matrices typically involves solving vast systems of coupled polynomial equations in large numbers of variables. In this work, we present an algorithm that allows associator data for some category with unknown associator to be computed from a Morita equivalent category with known data. Given a module category over the latter, we utilize the representation theory of a module tube category, built from the known data, to compute this unknown associator data. When the input category is unitary, we discuss how to ensure the obtained data is also unitary. We provide several worked examples to illustrate this algorithm. In addition, we include several Mathematica files showing how the algorithm can be used to compute the data for the Haagerup category \mathcal{H}_1ℋ1, whose data was previously unknown.

The Urban Development in Relation to the Occurrence of Diseases in the Casa-Settat Region of Morocco during the Emergence of SARS-CoV-2.

The Casa-Settat region is experiencing very worrying environmental and epidemiological problems and challenges, namely, population growth, the significant development of unsupervised industrial activities, road traffic, the significant weight of the spread of diseases with high epidemiological potential such as SARS-CoV-2, the increase in hospital activities, and the significant discharge of hospital effluents highly contaminated and untreated. To understand and analyze the factors influencing the high prevalence of deaths and the occurrence of diseases under surveillance, among others SARS-CoV-2, on the quantitative data recorded relating to ten regions of Morocco, and informing, on the one hand, on intrinsic data linked to the urban development, and on the other hand, on the evolution of diseases under epidemiological surveillance, a multidimensional analysis was made. The results reveal the typological framework highlighted by the factorial map F1 × F2 which showed the individualization of the region of Casablanca explained by a large number of variables and diseases that affect it. Finally, these results call for a diagnosis that will make it possible to model new approaches and implement new actions promoting the dynamics of environmental and epidemiological change in one of the most polluted and infected regions of Morocco.