Linear Ridge Regression Research Articles

House Price Prediction Using Exploratory Data Analysis and Machine Learning with Feature Selection

In many real-world applications, it is more realistic to predict a price range than to forecast a single value. When the goal is to identify a range of prices, price prediction becomes a classification problem. The House Price Index is a typical instrument for estimating house price discrepancies. This repeat sale index analyzes the mean price variation in repeat sales or refinancing of the same assets. Since it depends on all transactions, the House Price Index is poor at projecting the price of a single house. To forecast house prices effectively, this study investigates the exploratory data analysis based on linear regression, ridge regression, Lasso regression, and Elastic Net regression, with the aid of machine learning with feature selection. The proposed prediction model for house prices was evaluated on a machine learning housing dataset, which covers 1,460 records and 81 features. By comparing the predicted and actual prices, it was learned that our model outputted an acceptable, expected values compared to the actual values. The error margin to actual values was very small. The comparison shows that our model is satisfactory in predicting house prices.

Persistent organic pollutant exposure contributes to Black/White differences in leukocyte telomere length in the National Health and Nutrition Examination Survey

Despite racial disparities in diseases of aging and premature mortality, non-Hispanic Black Americans tend to have longer leukocyte telomere length (LTL), a biomarker of cellular aging, than non-Hispanic White Americans. Previous findings suggest that exposure to certain persistent organic pollutants (POPs) is both racially-patterned and associated with longer LTL. We examine whether Black/White differences in LTL are explained by differences in exposure to 15 POPs by estimating the indirect effect (IE) of self-reported race on LTL that is mediated through nine polychlorinated biphenyls (PCBs), three furans, and three dioxins, as well as their mixtures. Our study population includes 1,251 adults from the 1999–2000 and 2001–2002 cycles of the cross-sectional National Health and Nutrition Examination Survey. We characterized single-pollutant mediation effects by constructing survey-weighted linear regression models. We also implemented various approaches to quantify a global mediation effect of all POPs, including unpenalized linear regression, ridge regression, and examination of three summary exposure scores. We found support for the hypothesis that exposure to PCBs partially mediates Black/White differences in LTL. In single-pollutant models, there were significant IEs of race on LTL through six individual PCBs (118, 138, 153, 170, 180, and 187). Ridge regression (0.013, CI 0.001, 0.023; 26.0% mediated) and models examining summative exposure scores with linear combinations derived from principal components analysis (0.019, CI 0.009, 0.029; 34.8% mediated) and Toxic Equivalency Quotient (TEQ) scores (0.016, CI 0.005, 0.026; 28.8% mediated) showed significant IEs when incorporating survey weights. Exposures to individual POPs and their mixtures, which may arise from residential and occupational segregation, may help explain why Black Americans have longer LTL than their White counterparts, providing an environmental explanation for counterintuitive race differences in cellular aging.

Coupling Process-Based Models and Machine Learning Algorithms for Predicting Yield and Evapotranspiration of Maize in Arid Environments

Crop yield prediction is critical for investigating the yield gap and potential adaptations to environmental and management factors in arid regions. Crop models (CMs) are powerful tools for predicting yield and water use, but they still have some limitations and uncertainties; therefore, combining them with machine learning algorithms (MLs) could improve predictions and reduce uncertainty. To that end, the DSSAT-CERES-maize model was calibrated in one location and validated in others across Egypt with varying agro-climatic zones. Following that, the dynamic model (CERES-Maize) was used for long-term simulation (1990–2020) of maize grain yield (GY) and evapotranspiration (ET) under a wide range of management and environmental factors. Detailed outputs from three growing seasons of field experiments in Egypt, as well as CERES-maize outputs, were used to train and test six machine learning algorithms (linear regression, ridge regression, lasso regression, K-nearest neighbors, random forest, and XGBoost), resulting in more than 1.5 million simulated yield and evapotranspiration scenarios. Seven warming years (i.e., 1991, 1998, 2002, 2005, 2010, 2013, and 2020) were chosen from a 31-year dataset to test MLs, while the remaining 23 years were used to train the models. The Ensemble model (super learner) and XGBoost outperform other models in predicting GY and ET for maize, as evidenced by R2 values greater than 0.82 and RRMSE less than 9%. The broad range of management practices, when averaged across all locations and 31 years of simulation, not only reduced the hazard impact of environmental factors but also increased GY and reduced ET. Moving beyond prediction and interpreting the outputs from Lasso and XGBoost, and using global and local SHAP values, we found that the most important features for predicting GY and ET are maximum temperatures, minimum temperature, available water content, soil organic carbon, irrigation, cultivars, soil texture, solar radiation, and planting date. Determining the most important features is critical for assisting farmers and agronomists in prioritizing such features over other factors in order to increase yield and resource efficiency values. The combination of CMs and ML algorithms is a powerful tool for predicting yield and water use in arid regions, which are particularly vulnerable to climate change and water scarcity.

Combining mid infrared spectroscopy with stacked generalisation machine learning for prediction of key soil properties

AbstractAccurate assessment of key soil attributes such as soil organic carbon (OC), available phosphorus (P), and available potassium (K) using mid‐infrared spectroscopy (MIRS) is essential for better soil management in precision agriculture. However, the calibration of the portable version of MIRS is more challenging than the benchmark technologies, hence, demanding more efficient modelling methods to provide accurate outcomes. This research aims to use the stacked generalisation machine learning (SG–ML) framework, combining support vector machine (SVM), gradient boosted regression (GBR), and random forest (RF), using linear ridge regression as a meta learner, for predicting OC, P, and K using MIR spectra of 375 soil samples collected from four farms (Flanders, Belgium). The performance of the SG–ML models was compared with the multilayer perceptron (MLP) deep learning (DL) method. Results showed the superiority of the SG–ML method over the corresponding single ML and DL models. The predictive performance of SG–ML using the validation set was excellent for the three soil attributes, with coefficient of determination (R2) and root mean square error (RMSE) values of 0.88% and 0.10%, 0.85 and 4.53 mg 100 g−1, and 0.84 and 3.87 mg 100 g−1 for OC, K, and P, respectively. The performance of DL models were good for OC (R2 = 0.65, and RMSE = 0.17%), poor for K (R2 = 0.58 and RMSE = 7.59 mg 100 g−1), and very poor for P (R2 = 0.46, and RMSE = 6.57 mg 100 g−1). The SG–ML reduced the prediction RMSE by 10% to 31%, compared with the single ML (SVM, RF, and GBR) models. In summary, the proposed stacking method is a powerful modelling tool for the accurate prediction of key soil attributes using portable MIRS.Highlights Machine learning (ML) and deep learning (DL) models were developed based on mid‐infrared soil spectra. The stacked generalisation ML (SG–ML) was compared with ML and DL for predicting OC, P, and K. SG–ML models outperformed ML (GBR, RF, and SVM) and deep learning (DL) models. The SG–ML models significantly decreased RMSE by 10% to 31% compared with the single ML models.

Cost estimation models for seismic retrofit of masonry school buildings

Seismic retrofits can significantly reduce the vulnerability of masonry buildings. Multiple seismic retrofit alternatives are often available for a given building. Estimating the cost of each candidate action is essential to selecting and implementing the appropriate seismic retrofit initiatives. This research harnesses the capabilities of various regression models for cost estimation. A dataset from 167 retrofit projects for masonry school buildings was used to develop models. Three main retrofit actions were taken into consideration: shotcrete, steel belt and fiber-reinforced polymer. Various regression methods, including multiple linear regression, ridge regression, lasso regression, and elastic net regression, were applied to develop models that estimate the cost of each of the three retrofit actions based on a set of explanatory variables. Next, the models underwent a reduction process to simplify and increase their prediction precision. In most models, the reduction process eliminated multiple terms and enhanced the model prediction performance. This article identifies the height of the building as the most influential parameter governing retrofit costs. It examines the effect of proxy variables (e.g. lateral area of walls and added lateral strength) on the final retrofit cost by adding them as explanatory variables.

Comparison of individualized behavioral predictions across anatomical, diffusion and functional connectivity MRI

A fundamental goal across the neurosciences is the characterization of relationships linking brain anatomy, functioning, and behavior. Although various MRI modalities have been developed to probe these relationships, direct comparisons of their ability to predict behavior have been lacking. Here, we compared the ability of anatomical T1, diffusion and functional MRI (fMRI) to predict behavior at an individual level. Cortical thickness, area and volume were extracted from anatomical T1 images. Diffusion Tensor Imaging (DTI) and approximate Neurite Orientation Dispersion and Density Imaging (NODDI) models were fitted to the diffusion images. The resulting metrics were projected to the Tract-Based Spatial Statistics (TBSS) skeleton. We also ran probabilistic tractography for the diffusion images, from which we extracted the stream count, average stream length, and the average of each DTI and NODDI metric across tracts connecting each pair of brain regions. Functional connectivity (FC) was extracted from both task and resting-state fMRI. Individualized prediction of a wide range of behavioral measures were performed using kernel ridge regression, linear ridge regression and elastic net regression. Consistency of the results were investigated with the Human Connectome Project (HCP) and Adolescent Brain Cognitive Development (ABCD) datasets. In both datasets, FC-based models gave the best prediction performance, regardless of regression model or behavioral measure. This was especially true for the cognitive component. Furthermore, all modalities were able to predict cognition better than other behavioral components. Combining all modalities improved prediction of cognition, but not other behavioral components. Finally, across all behaviors, combining resting and task FC yielded prediction performance similar to combining all modalities. Overall, our study suggests that in the case of healthy children and young adults, behaviorally-relevant information in T1 and diffusion features might reflect a subset of the variance captured by FC.

Spatial Prediction Models for Soil Stoichiometry in Complex Terrains: A Case Study of Schrenk’s Spruce Forest in the Tianshan Mountains

Spatial patterns of soil carbon (C), nitrogen (N) and phosphorus (P) and their stoichiometric characteristics (C:N:P) play an important role in nutrient limitations, community dynamics, nutrient use efficiency and biogeochemical cycles, etc. To date, the spatial distributions of soil organic C at various spatial scales have been extensively studied, whereas little is known about the spatial patterns of N and P and C:N:P ratios in various landscapes, especially across complex terrains. To fill this gap, we estimated the spatial patterns of concentrations of soil C, N and P and C:N:P ratios in Schrenk’s spruce (Picea schrenkiana Fisch. & C. A. Mey.) forest in the Tianshan Mountains based on data from soil cores collected from 2012 to 2017, and using the following four regression models: multiple linear regression, stepwise regression, ridge regression and lasso regression. We found the following: (1) elevation and climatic variables jointly contributed to concentrations of C, N and P and C:N:P ratios, (2) soil C, N and P concentrations, and their stoichiometric ratios, demonstrated continual spatial patterns in Schrenk’s spruce forest, (3) Multiple linear regression could be reliably used to estimate the spatial patterns of soil elemental concentrations and stoichiometric ratios in mountainous terrain. We suggest that more independent variables (including biotic, abiotic and anthropogenic factors) should be considered in future works. Additionally, adjustment of multiple linear regression and other models should be used for a better delineation of spatial patterns in the concentrations of soil elements and stoichiometric ratios.

The relationship between job-hopping motives and congruence

Orientation: Many organisational turnover and vocational counselling studies have investigated the outcomes associated with person–environment fit. However, few studies have investigated the potential individual difference variables that might lead to person–environment fit.Research purpose: This study set out to investigate the relationship between job-hopping motives and interest–environment fit (i.e. congruence).Motivation for the study: Job-hopping motives reflect individual difference motives that are thought to lead to voluntary turnover behaviour over and above environmental factors. We investigated the hypothesis that these motives might lead to people entering jobs that are congruent with their interests.Research approach/design and method: A cross-sectional survey research design was used. The Job-Hopping Motives Scale was administered to 197 adults. Multiple linear regression and ridge regression were used to investigate the proposed relationships.Main findings: Job-hopping motives were related to congruence, with the escape motive showing a negative partial linear relationship with congruence and the advance motive showing no partial linear relationship with congruence.Practical/managerial implications: Our results suggest that people who have a propensity to frequently change jobs might tend to enter a job that does not necessarily match their interests. This in turn might lead to some of the negative outcomes associated with working in so-called incongruent environments, or alternatively, potentially lead to a cycle of entering and leaving jobs throughout a person’s career.Contribution/value-add: We provide evidence that job-hopping motives might be an organisational-relevant individual difference variable that might lead to working in a congruent or incongruent environment.

Statistically based nomograms for the minimal needle length required to achieve intra-articular fluoroscopic-guided injections of the shoulder, hip, and knee.

Image-guided intra-articular injections are commonly performed to reduce pain in patients with arthritis or other joint-related pathology. Utilizing a needle length that is too short could lead to increased patient discomfort, increased procedural time, and extra-articular injections. To predict the minimum needle length required for fluoroscopic-guided intra-articular injections of the hips, knees, and shoulders based on patient age, gender, height and weight, or body mass index (BMI) and to evaluate whether this varies by gender. Cross-sectional study. Tertiary care academic center. 600 consecutive patients with available magnetic resonance imaging (MRI) of the hips, knees, and shoulders (100 males and 100 females for each joint). The distance from the skin to the joint (glenohumeral, hip and knee) and the thickness of the subcutaneous fat pad (distance from the skin to the muscle) along the injection path were measured. Multivariable linear ridge regression with 10-fold cross-validation was used to predict the distance from the skin to the hip, knee, and glenohumeral joints using age, gender, weight, and height or using age, gender, and BMI. The data show that the subcutaneous fat thickness and the distance from the skin to all joints increase with weight (p < .001) and BMI (p < .001). Subcutaneous fat pads around the anterior shoulder (p < .02) and knee (<.001) are thicker in women than in men. Patient habitus, in particular weight and BMI, are strong predictors of the thickness of the subcutaneous fat pads and consequently strong predictors of the distance from the skin to the joint. Subcutaneous fat pad thickness around the shoulders and knees varies by gender. Nomograms showing the minimal needle length required to achieve intra-articular injections of the hip, knee and glenohumeral joints are presented.

Machine learning in scientific grant review: algorithmically predicting project efficiency in high energy physics

As more objections have been raised against grant peer-review for being costly and time-consuming, the legitimate question arises whether machine learning algorithms could help assess the epistemic efficiency of the proposed projects. As a case study, we investigated whether project efficiency in high energy physics (HEP) can be algorithmically predicted based on the data from the proposal. To analyze the potential of algorithmic prediction in HEP, we conducted a study on data about the structure (project duration, team number, and team size) and outcomes (citations per paper) of HEP experiments with the goal of predicting their efficiency. In the first step, we assessed the project efficiency using Data Envelopment Analysis (DEA) of 67 experiments conducted in the HEP laboratory Fermilab. In the second step, we employed predictive algorithms to detect which team structures maximize the epistemic performance of an expert group. For this purpose, we used the efficiency scores obtained by DEA and applied predictive algorithms – lasso and ridge linear regression, neural network, and gradient boosted trees – on them. The results of the predictive analyses show moderately high accuracy (mean absolute error equal to 0.123), indicating that they can be beneficial as one of the steps in grant review. Still, their applicability in practice should be approached with caution. Some of the limitations of the algorithmic approach are the unreliability of citation patterns, unobservable variables that influence scientific success, and the potential predictability of the model.

Local wavelet packet decomposition of soil hyperspectral for SOM estimation

It is a critical work to accurate extraction of spectral characteristics of soil organic matter (SOM), which will help to improve the model performance for SOM estimation. In this paper, we propose a new SOM prediction model using local wavelet characteristics of soil spectrum. Specifically, six level local wavelet packets decomposition are considered with different moving window sizes and sliding lengths, and thus formulate two new spectral indicators, namely, local wavelet packet energy spectrum (LWE) and local logarithmic wavelet packet energy spectrum (LLWE). The LWE and LLWE are then viewed as model inputs, which are respectively used to forecast SOM content. We test the prediction performance of the LWE and LLWE based on the two prediction models, that is, multiple linear regression (MLR) and ridge regression with cross-validation (RCV). The result shows that the two new spectral indicators help to enhance the spectral response information of SOM. Among the four prediction models, the LLWE-MLR is the most outstanding. Compared to the original hyperspectral and energy features vectors, the LWE and LLWE bring the better model performance. Since both the high and low-frequency components of local information of soil hyperspectral are fully extracted, the two new spectral indicators significantly improve the prediction accuracy and reliability of SOM.

Spectral neighbor representation for vector fields: Machine learning potentials including spin

We introduce a translational and rotational invariant local representation for vector fields, which can be employed in the construction of machine-learning energy models of solids and molecules. This allows us to describe, on the same footing, the energy fluctuations due to the atomic motion, the longitudinal and transverse excitations of the vector field, and their mutual interplay. The formalism can then be applied to physical systems where the total energy is determined by a vector density, as in the case of magnetism. Our representation is constructed over the power spectrum of the combined angular momentum describing the local atomic positions and the vector field, and can be used in conjunction with different machine-learning schemes and data taken from accurate ab initio electronic structure theories. We demonstrate the descriptive power of our representation for a range of classical spin Hamiltonian and machine-learning algorithms. In particular, we construct energy models based on both linear Ridge regression, as in conventional spectral neighbour analysis potentials, and gaussian approximation. These are both built to represent a Heisenberg-type Hamiltonian including a longitudinal energy term and spin-lattice coupling.

Predicting and interpreting cotton yield and its determinants under long-term conservation management practices using machine learning

Accurate predictions of crop yield are an integral part of effective agricultural tactical and strategic management decisions to sustain yield without adversely impacting the environment. Process-based simulation models are widely used to predict crop yields, but their application remains limited by the requirements of substantial expertise, intensive data, and extensive calibration. Therefore, greater attention is currently being devoted to machine learning (ML) methods that are more computationally expedient. We evaluated six ML algorithms (linear regression, ridge regression, lasso regression, random forest, XGboost, and artificial neural network (ANN)) to predict cotton (Gossypium spp.) yield and determine the yield response to critical determinants using long-term (1986–2018) data on management, climate, historical yield, and point measurement of soil organic carbon (SOC) from continuous no-till (NT) cotton cropping system in west Tennessee. Data from 1986 to 2015 were used for model training, hyper-parameterization and testing, while data from 2016 to 2018 were used for independent model validation. Results showed that tree-based models (random forest and XGboost) outperformed other models in predicting lint yield. The variable importance scores, predicted by random forest model, indicated that cotton yield was more responsive to management variables (nitrogen (N) fertilization rate, cover crop, and years since NT establishment) followed by soil (SOC) and climate variables at the study site. The model identified optimal N application at 60 kg ha-1N rate for cotton lint yield, and also highlighted that the benefits of NT in enhancing yield can be achieved after 15 years of practice. The model predicted that the long-term adoption of hairy vetch (Vicia villosa), a legume cover crop, has the potential to increase cotton yield. Among the climate variables, cotton lint yield was most impacted by average maximum temperature and precipitation during flowering to open boll period. While random forest and XGboost proved to be the most effective ML models in this study, multi-site data is needed to build a more robust model with greater generalization and interpretation capabilities under a wider prediction domain.

Battery life time prediction of electric vehicle using artificial intelligence

The widespread use of electric vehicles (EVs) is viewed as a turning point for lower emissions of co2 and much more advanced driver assistance systems. It is time-consuming to predict the battery capacity of the electric vehicle using the endurance and dependability of battery systems. Because battery deterioration is typically non-linear, predicting the capacity of the battery of charge estimation with significantly less deterioration is incredibly time-consuming. As a result of this complexity, real-time control of battery storage has proven difficult. Nevertheless, using the latest advancements in battery deterioration comprehension, simulation techniques, and testing, there is a potential to combine this expertise with new machine learning (ML) approaches to find a potential solution for this complexity. In this study, the battery life is predicted using three different regression models Linear Regression, Ridge Regression, and Ensemble Regression. The model's error analysis is conducted to improve the battery's performance characteristics. Finally, the three ML algorithms are compared using performance parameters. Out of the three regression models, the Ensemble regression model is found to be the best model which has an accuracy of 94.8%.

Relationship between sunlight and range use of commercial free-range hens in Australia

In Australia, summer brings intense, bright sunlight with high ultraviolet (UV) radiation and hot temperatures, which might impact free-range hens’ ranging outside. To determine how range use was correlated with different sunlight variables and weather factors, a study was carried out on three commercial free-range layer farms during the summer/autumn period (December-May) across diverse regions of Australia in Tasmania (TAS), Queensland (QLD), and Western Australia (WA). Hens’ range distribution was determined by counting the number of hens in the direct sunlight (‘sun’) or ‘cloud’ and shaded areas (‘sun-shade’ or ‘cloud-shade’, in sunny or cloudy conditions, respectively) using image snapshots taken at 30 min intervals from video recordings of a portion of one shed comprising 20,000–30,000 hens on each farm during the production phase of the laying cycle. The solar radiation spectrum [UV radiation (UVAB) (288–432 nm), photosynthetically active radiation (PAR; visible light) (400–700 nm), and total solar radiation (TSR) (285 nm-3000 nm)] and weather data (ambient temperature and relative humidity) were recorded through an on-site weather station. Data were analysed separately due to discrepancies between the farms’ layouts. The effects of time of day and months on range use were analysed using General Linear Models in JMP® 16.0 and the relationship of sunlight and weather variables with hens’ distribution in ‘sun’/’sun-shade’ and ‘cloud’/’cloud-shade’ in sunny and cloudy conditions respectively was determined by fitting linear ridge regression models using the ‘lmridge’ package in R. Overall, the time of day and month had significant effects on hens’ distribution on the range (all p < 0.0001). Hens’ range occupancy in the ‘sun’ decreased during the midday period with gradual increases in the late afternoon to evening, and the opposite pattern in the ‘sun-shade’. A linear increase in the number of hens on the range over the months indicated the seasonal effects on hen ranging patterns. Temperature, UVAB and PAR were the most important factors for discouraging hens’ range use in the ‘sun’ suggesting free-range systems in Australia should be designed to account for the extreme sunlight using adequate shade for optimum ranging across summer.

Used Car Price Prediction using Different Machine Learning Algorithms

Abstract: A car price prediction has been a high-interest research area, as it needed recognizable effort and knowledge of the field expert. This paper mainly focuses on working of three different kind regression algorithms which are used to predict price of a used car. In this project, We have Considered number of distinct attributes which are examined for the reliable and accurate prediction. To build a model for predicting the price of used cars we have used three different kinds of machine learning techniques which comes under supervised machine learning type of algorithm which are linear regression, lasso regression and ridge regression respectively. we have used Python libraries to design GUI for our project and some other machine learning related libraries like Numpy, Pandas, Sklearn etc. we have calculated and compared the accuracies of three machine learning algorithms. The accuracies for linear regression, lasso and Ridge regression were 83.65%, 87.09% and 84.00% respectively. The final main price is predicted according to lasso regression as it gives highest accuracy amongst three different algorithms. Keywords: car price prediction, machine learning, Regression techniques, linear regression, lasso regression, ridge regression

Credibility Analysis of User-Designed Content Using Machine Learning Techniques

Content is a user-designed form of information, for example, observation, perception, or review. This type of information is more relevant to users, as they can relate it to their experience. The research problem is to identify the credibility and the percentage of credibility as well. Assessment of such content is important to convey the right understanding of the information. Different techniques are used for content analysis, such as voting the content, Machine Learning Techniques, and manual assessment to evaluate the content and the quality of information. In this research article, content analysis is performed by collecting the Movie Review dataset from Kaggle. Features are extracted and the most relevant features are shortlisted for experimentation. The effect of these features is analyzed by using base regression algorithms, such as Linear Regression, Lasso Regression, Ridge Regression, and Decision Tree. The contribution of the research is designing a heterogeneous ensemble regression algorithm for content credibility score assessment, which combines the above baseline methods. Moreover, these factors are also toned down to obtain the values closer to Gradient Descent minimum. Different forms of Error Loss, such as Mean Absolute Error, Mean Squared Error, LogCosh, Huber, and Jacobian, and the performance is optimized by introducing the balancing bias. The accuracy of the algorithm is compared with induvial regression algorithms and ensemble regression separately; this accuracy is 96.29%.

Evaluation and application of machine learning principles to Zeolite LTA synthesis

A progressive machine learning methodology was utilised to not only identify the relationship between zeolite synthesis descriptors but also evaluate the potential for machine learning to predict the quantitative output of synthesis routes. The hypothesis was if statistics and machine learning principles are applied, then it may enable pre-evaluation and result in potential increases to zeolite yield and performance. Various machine learning algorithms were applied to zeolite LTA synthesis data; including linear regression, ridge regression, regression tree, random forest, XGBoost and artificial neural network models. Major findings included the use of input synthesis variables and the product yield for model training. Additionally, the use of both quantitative and qualitative X-ray diffraction (XRD) data was required to accurately determine product composition (“hybrid XRD” approach). Models, including linear regression, ridge regression and regression trees, returned R 2 values less than 0.5 indicating the complexity inherent with the problem. Embedded tree-based models, including random forest and XGBoost, resulted in testing accuracies equal to R 2 = 0.620 and R 2 = 0.700 , respectively. An ANN model achieved the highest accuracy among all machine learning algorithms of R 2 = 0.84. Notably, this model was the most accurate because it exploited non-linear and complex relationships within a multidimensional and intercorrelated dataset such as that obtained from zeolite synthesis. Despite reaching an accuracy greater than 80%, the ANN model accuracy continued to increase by increasing the network size, indicating that advanced deep learning models should be considered as part of future work. • Outlined strategy for evaluating machine learning optimization of material synthesis. • Data quality improved by using mixture of qualitative and quantitative XRD patterns. • Five Principal Components explained >90% of the data variance. • Complex Artificial Neural Network models were required to simulate synthesis data. • Deep Neural Networks and Generative Adversarial Networks may improve accuracy.

Effect of Bipolar Plate Material on Proton Exchange Membrane Fuel Cell Performance

Commercialization of proton exchange membrane fuel cells can only materials provided its performance is closely related to existing technologies useful in commercial application. Other critical parameters like the utilization of cheaper materials should be taken into account during the manufacturing of the cell. A key component in the cell that has direct correlation to the cell performance is the flow plate. The weight coupled with cost of the cell revolves around the flow plate used in the manufacturing of the cell. This study explores materials ideal for the manufacturing of fuel cells in order to improve the overall cell performance. The investigation highlights the critical impact of varying materials used in the manufacturing of flow plates for PEM fuel cells. Stainless steel (SS), aluminium (Al) and copper (Cu) were the materials considered. The flow plate designs considered were serpentine and open pore cellular foam channel. Machine learning using python for the validation of the results with Linear regression, Ridge regression and Polynomial regression algorithm was carried out. The performance of both flow field channels was compared using different bipolar plate materials. The results show that metal foam flow channels overall performance was better than serpentine flow channels with all the various bipolar plate material used and Al material outperformed Cu and SS material. There is a direct correlation in terms of the outcome of the study and literature based on the data generated experimentally. It can however be concluded that molecules of hydrogen are stable on aluminium plates compared to copper and stainless steel.

Using Machine Learning to Identify Patients at High Risk of Inappropriate Drug Dosing in Periods with Renal Dysfunction.

PurposeDosing of renally cleared drugs in patients with kidney failure often deviates from clinical guidelines, so we sought to elicit predictors of receiving inappropriate doses of renal risk drugs.Patients and methodsWe combined data from the Danish National Patient Register and in-hospital data on drug administrations and estimated glomerular filtration rates for admissions between 1 October 2009 and 1 June 2016, from a pool of about 2.6 million persons. We trained artificial neural network and linear logistic ridge regression models to predict the risk of five outcomes (>0, ≥1, ≥2, ≥3 and ≥5 inappropriate doses daily) with index set 24 hours after admission. We used time-series validation for evaluating discrimination, calibration, clinical utility and explanations.ResultsOf 52,451 admissions included, 42,250 (81%) were used for model development. The median age was 77 years; 50% of admissions were of women. ≥5 drugs were used between admission start and index in 23,124 admissions (44%); the most common drug classes were analgesics, systemic antibacterials, diuretics, antithrombotics, and antacids. The neural network models had better discriminative power (all AUROCs between 0.77 and 0.81) and were better calibrated than their linear counterparts. The main prediction drivers were use of anti-inflammatory, antidiabetic and anti-Parkinson's drugs as well as having a diagnosis of chronic kidney failure. Sex and age affected predictions but slightly.ConclusionOur models can flag patients at high risk of receiving at least one inappropriate dose daily in a controlled in-silico setting. A prospective clinical study may confirm that this holds in real-life settings and translates into benefits in hard endpoints.