Search

The first year of the COVID-19 pandemic constituted a major life stress event for many adolescents, associated with disrupted school, behaviors, social networks, and health concerns. However, pandemic-related stress was not equivalent for everyone and could have been influenced by pre-pandemic factors including brain structure and sleep, which both undergo substantial development during adolescence. Here, we analyzed clusters of perceived stress levels across the pandemic and determined developmentally relevant pre-pandemic risk factors in brain structure and sleep of persistently high stress during the first year of the COVID-19 pandemic. We investigated longitudinal changes in perceived stress at six timepoints across the first year of the pandemic (May 2020–March 2021) in 5559 adolescents (50 % female; age range: 11–14 years) in the United States (U.S.) participating in the Adolescent Brain Cognitive Development (ABCD) study. In 3141 of these adolescents, we fitted machine learning models to identify the most important pre-pandemic predictors from structural MRI brain measures and self-reported sleep data that were associated with persistently high stress across the first year of the pandemic. Patterns of perceived stress levels varied across the pandemic, with 5 % reporting persistently high stress. Our classifiers accurately detected persistently high stress (AUC > 0.7). Pre-pandemic brain structure, specifically cortical volume in temporal regions, and cortical thickness in multiple parietal and occipital regions, predicted persistent stress. Pre-pandemic sleep difficulties and short sleep duration were also strong predictors of persistent stress, along with more advanced pubertal stage. Adolescents showed variable stress responses during the first year of the COVID-19 pandemic, and some reported persistently high stress across the whole first year. Vulnerability to persistent stress was evident in several brain structural and self-reported sleep measures, collected before the pandemic, suggesting the relevance of other pre-existing individual factors beyond pandemic-related factors, for persistently high stress responses. • The paper reports findings from the ABCD study® on U.S. youth across the first COVID-19 pandemic year: May 2020 – March 2021. • 5% of adolescents reported persistently high stress levels during the first year of the pandemic. • Persistent stress was linked to pre pandemic brain structure, sleep difficulties, and more advanced puberty stages. • The findings inform preventive and treatment approaches for persistent stress during major life stress events like pandemics. [ABSTRACT FROM AUTHOR]

This paper investigates the future U.S. demand for streamlined space tourism by showing the missions and factors impacting traveler choices with machine learning. Space tourism is growing and is expected to become available to the masses soon. While private companies need to better understand the demand for space tourism to customize their services, transportation agencies require guidance to support fund management related to commercial space exploration. This work analyzes the three most prominent missions for streamlined space tourism (i.e., suborbital, orbital, and space tourism around the moon) and their selection determinants (i.e., price, safety, training, number of passengers, take-off locations, among other decision-maker factors). A stated preference experiment is constructed to collect data that is analyzed using machine learning. Results provide valuable insights into the mixed opinions of Americans with respect to space tourism, their mission preferences, and risk considerations. • Space tourism serves a niche of high-income travelers. • We investigate the future U.S. demand if space tourism is available to the masses. • A stated preference experiment is constructed to collect data from Americans. • The collected dataset is analyzed using machine learning paradigms. • Results unveil the mission and traveler factors impacting space tourism choices. [ABSTRACT FROM AUTHOR]

In literature, many studies try to analyze healthcare usage and generated decision support systems. In this paper, the aim is to generate a decision support system for insurance companies in the United States according to the federal dataset. The data set contains variables from the United States Healthcare Administration formal data group and they are; group of age, group of healthcare insurance, group of nationality, Corporate Social Responsibility (CSR) usage, and Advance Premium Tax Credit (APTC) usage. The best model for each state in the United States is determined with the dataset from 2014 November to 2015 February. In this study, various statistical models are attempted to generate independent and optimal models for each state. In the model selection process, three different metrics are used. Accuracy rate, f1score and precision score are used in the model selection process and models are compared to each other according to these three metrics for each state uniquely. Consequently, the proposed model is used with a decision support scheme to support customer service workers in healthcare insurance companies. The decision support system under consideration can facilitate a substantial decrease in the duration of interactions between customer service representatives and clients. Additionally, this system can generate more logically sound and efficient customer offers. [ABSTRACT FROM AUTHOR]

The construction industry in the United States consumes more than 50% of the global energy supply per year, suggesting that significant efforts may be needed to reduce building energy demand and its carbon footprint. During their lifespans, buildings consume embodied energy (EE) and operational energy (OE). Building professionals, therefore, conduct life cycle energy assessments (LCEA) to quantify and understand the paradox and interconnectedness between EE and OE. Traditionally, simulation-based optimization techniques were used for design space exploration to identify a building design with the fewest energy implications. However, literature shows these data-driven approaches are often error-prone, time-consuming, and computationally expensive, and they fail to provide real-time feedback to the user. Moreover, EE and OE assessment tools are disjointed and suffer from interoperability issues. These limitations restrict design space exploration, which eventually hinders the design decision-making process. Over the last few years, the increased availability of building data has made machine learning (ML) techniques a popular choice for building performance assessments. Several articles have developed prediction models to assess or optimize OE. While this work is significant, studies utilizing ML techniques for building LCEA are lacking, mainly due to the unavailability of a large-scale LCEA database. In this paper, we propose a methodology to (1) generate a simulation-based building energy dataset for different building typologies using a parametric framework, (2) utilize the synthetically generated database to develop an ML-based prediction model to predict EE and OE, and (3) test the model using a case study. The case study results show that the model achieves high prediction performance using minimal inputs available during the early design phase. The results further indicate that ML techniques can be used by building designers with no or limited LCE expertise to instantaneously estimate building LCE performance and help them select design options with minimal LCE consumption. [ABSTRACT FROM AUTHOR]

Track geometry is highly important for ensuring railroad safety. Predicting track geometry degradation can support preventive maintenance by identifying and prioritizing track segments that are more prone to potential track geometry defects. This paper develops a novel machine learning approach that can simultaneously geospatially align track geometry data from multiple inspections accounting for positional errors, and also predict foot-by-foot track geometry change over time. The proposed position correction method considers multiple geometry parameters to provide highly accurate positional information for geometry measurements, which is a prerequisite for foot-by-foot track geometry prediction. A hybrid CNN (convolutional neural network)-LSTM (long short-term memory neural network) machine learning model is developed to account for spatial–temporal dependence with respect to foot-by-foot track geometry change. Specifically, CNN is used to incorporate spatial dependence of track geometry on adjacent segments. LSTM is applied to learn dynamic changes in track geometry data over time to consider the temporal dependence. The hybrid CNN-LSTM model is validated using track inspection data provided by one major freight railroad in the United States. The results show that our positional error correction method can reduce the relative positional error to less than 1 foot with a 99% confidence interval. Our proposed CNN-LSTM model outperforms four other models, including a naïve model (using the last observation), multi-layer perceptron (MLP), plain CNN, and plain LSTM, for both short-term and long-term prediction periods. The proposed hybrid machine learning methodology can be adapted to various other freight and passenger rail lines. The predictive track geometry change information can be used by the industry to plan and prioritize resources for preventative maintenance, yielding benefits in safety and operational efficiency. [ABSTRACT FROM AUTHOR]

This paper proposes a novel methodology for recovering missing time series data, a crucial task for subsequent Machine Learning (ML) analyses. The methodology is specifically applied to Significant Wave Height (SWH) time series in the field of marine engineering. The proposed approach involves two phases. Firstly, the SWH time series for each buoy is independently reconstructed using three transfer function models: regression-based, correlation-based, and distance-based. The distance-based transfer function exhibits the best overall performance. Secondly, Evolutionary Artificial Neural Networks (EANNs) are utilised for the final recovery of each time series, using as inputs highly correlated buoys that have been intermediately recovered. The EANNs are evolved considering two metrics, the novel squared error relevance area, which balances the importance of extreme and around-mean values, and the well-known mean squared error. The study considers SWH time series data from 15 buoys in two coastal zones in the United States. The results demonstrate that the distance-based transfer function is generally the best transfer function, and that EANNs outperform a range of state-of-the-art ML techniques in 12 out of the 15 buoys, with a number of connections comparable to linear models. Furthermore, the proposed methodology outperforms the two most popular approaches for time series reconstruction, BRITS and SAITS, for all buoys except one. Therefore, the proposed methodology provides a promising approach, which may be applied to time series from other fields, such as wind or solar energy farms in the field of green energy. • Massive time series reconstruction is carried out by a novel two-phased approach. • Three transfer functions are used in the 1st phase: the distance-based stands out. • Evolutionary Artificial Neural Networks obtain the best performance in the 2nd phase. • New SERA metric optimises 2nd phase models to pay more attention to extreme values. • This method is applied to accurately recover time series of renewable energy sources. [ABSTRACT FROM AUTHOR]

• A highway-rail grade crossing consolidation model was created using XGBoost machine learning algorithm. The developed model contained 14 significant variables and the overall accuracy of 0.991% was obtained for it. • The significant variables included in the model were: in or near city, night thru train movement (6 pm to 6 am), day thru train movement (6 am to 6 pm), maximum timetable speed, typical minimum speed, typical maximum speed, crossbuck assemblies, total count of flashing light pair, crossing surface (main track), intersecting roadway within 500 ft., AADT, estimated percent trucks, total switching train, and average number of school buses passing over the crossing on a school day. • Based on this model, 62% of current highway-rail grade crossings in the USA should be either closed or improved. In the United States, there are approximately 212,000 highway-rail grade crossings, some of which experience vehicle-train incidents that often cause a massive financial burden, loss of life, and injury. In 2017, there were 2,108 highway-rail incidents resulting in 827 injuries and 307 fatalities nationwide. To eliminate collision risks, crossing grade separation and active alarm improvement are commonly used. Moreover, crossing closures are considered to be the most effective safety improvement program. While it may be very difficult, and in some cases impossible to close crossings, there are some incentive programs that facilitate the closure process. One of these programs is a working consolidation model that aims to determine crossing closure suitability. Using details of highway-rail grade crossings in the United States and applying an eXtreme Gradient Boosting (XGboost) algorithm, this paper proposes a data-driven consolidation model that takes into consideration a number of engineering variables. The results indicated an overall accuracy of 0.991 for the proposed model. In addition, the developed XGboost consolidation model reported the relative importance of the variables input to the model, offering an in-depth understanding of the model's behavior. Finally, for the practical implementation of the model, a simplified version containing fewer variables was developed. A sensitivity analysis was performed considering the aggregate gain and the different correlation threshold values between variables. This analysis developed a simplified model utilizing 14 variables, with aggregated gain values of 75% and a correlation threshold of 0.9 which would perform similarly to the full model. Based on this model, 62% of current highway-rail grade crossings should be closed. [ABSTRACT FROM AUTHOR]

Abstract Owing to its recent advance, machine learning has spawned a large collection of solar forecasting works. In particular, machine learning is currently one of the most popular approaches for hourly solar forecasting. Nevertheless, there is evidently a myth on forecast accuracy—virtually all research papers claim superiority over others. Apparently, the "best" model can only be selected with hindsight, i.e., after empirical evaluation. For any new forecasting project, it is irrational for solar forecasters to bet on a single model from the start. In this article, the hourly forecasting performance of 68 machine learning algorithms is evaluated for 3 sky conditions, 7 locations, and 5 climate zones in the continental United States. To ensure a fair comparison, no hybrid model is considered, and only off-the-shelf implementations of these algorithms are used. Moreover, all models are trained using the automatic tuning algorithm available in the R caret package. It is found that tree-based methods consistently perform well in terms of two-year overall results, however, they rarely stand out during daily evaluation. Although no universal model can be found, some preferred ones for each sky and climate condition are advised. Highlights • Hourly solar forecasting is performed using 68 machine learning models. • Models are evaluated at 7 locations in 5 climate zones for 2 years. • Tree-based methods consistently perform well in terms of 2-year average metrics. • Daily best model cannot be identified, regime-switching approach is advised. [ABSTRACT FROM AUTHOR]

Abstract Rainfall derivatives are in their infancy since starting trading on the Chicago Mercantile Exchange (CME) in 2011. Being a relatively new class of financial instruments there is no generally recognised pricing framework used within the literature. In this paper, we propose a novel Genetic Programming (GP) algorithm for pricing contracts. Our novel algorithm, which is called Stochastic Model GP (SMGP), is able to generate and evolve stochastic equations of rainfall, which allows us to probabilistically transform rainfall predictions from the risky world to the risk-neutral world. In order to achieve this, SMGP's representation allows its individuals to comprise of two weighted parts, namely a seasonal component and an autoregressive component. To create the stochastic nature of an equation for each SMGP individual, we estimate the weights by using a probabilistic approach. We evaluate the models produced by SMGP in terms of rainfall predictive accuracy and in terms of pricing performance on 42 cities from Europe and the USA. We compare SMGP to 8 methods: its predecessor DGP, 5 well-known machine learning methods (M5 Rules, M5 Model trees, k-Nearest Neighbors, Support Vector Regression, Radial Basis Function), and two statistical methods, namely AutoRegressive Integrated Moving Average (ARIMA) and Monte Carlo Rainfall Prediction (MCRP). Results show that the proposed algorithm is able to statistically outperform all other algorithms. [ABSTRACT FROM AUTHOR]

This paper proposes a collection of novel deliverability prediction models for underground natural gas storage (UNGS) in salt caverns based on machine learning algorithms. Considering that the natural gas supply chain is characterized by imbalances between demand and supply on a timely basis, effective and fast models for predicting the deliverability of UNGS would not only be a valuable tool to various stakeholders but also, of great benefit in competitive natural gas marketplace. In this paper, a first step in applying machine learning algorithms to predict the deliverability of UNGS in salt caverns is proposed. To achieve this, the capability of three machine learning algorithms namely, artificial neural network (ANN), support vector machine (SVM), and Random Forest (RF) are examined. The predictive capabilities of these methods were investigated using different monthly field storage data samples for different years with varied data samples of 36 active UNGS in salt caverns in the United States. Experimental results reveal that the machine learning models developed in this study can serve as suitable tools for predicting the deliverability of UNGS in salt caverns with different performances. Overall result shows that RF model exhibits better prediction performance with varied data partitions over ANN and SVM models. • Deliverability prediction for underground natural gas storage in salt caverns. • Artificial Neural Network, Random Forest, and Support Vector Machines are examined. • Random Forest exhibits better prediction performance on different data samples. • Results can facilitate decisions for narrowing the gap between demand and supply. • Results can guide decisions for future design specification of gas storage. [ABSTRACT FROM AUTHOR]

Building energy consumption makes up 40% of the total energy consumption in the United States. Given that energy consumption in buildings is influenced by aspects of urban form such as density and floor-area-ratios (FAR), understanding the distribution of energy intensities is critical for city planners. This paper presents a novel technique for estimating commercial building energy consumption from a small number of building features by training machine learning models on national data from the Commercial Buildings Energy Consumption Survey (CBECS). Our results show that gradient boosting regression models perform the best at predicting commercial building energy consumption, and can make predictions that are on average within a factor of 2 from the true energy consumption values (with an r 2 score of 0.82). We validate our models using the New York City Local Law 84 energy consumption dataset, then apply them to the city of Atlanta to create aggregate energy consumption estimates. In general, the models developed only depend on five commonly accessible building and climate features, and can therefore be applied to diverse metropolitan areas in the United States and to other countries through replication of our methodology. [ABSTRACT FROM AUTHOR]

The war on terrorism, radicalism and violent extremism is no longer confined to the battlefield; it has become omnipresent in the recent years with militant, terrorists and insurgent groups actively recruiting new technologies as platform to impel their ideologies worldwide. Nonetheless, one thing remains constant in the fight against radicalism equation, that is, the information about radical individuals, whether personal, demographical, social or economic information. The ability to identify, classify and profile potential radicals based on such information has an appealing trait for security agencies around the world. The Intelligence and Security Informatics research field emphasizes the importance of engaging multidiscipline technologies to provide security-related applications that serve as aiding tools in combating terrorism and other forms of violent extremism. In this paper, the authors focus on radical Islamism and hypothesize that Islamist radicals have identifiable information and behavioral traits that could be utilized to identify their ideological motive uniquely amongst other radicals. Four different supervised machine learning algorithms are applied to validate this hypothesis using the “profiles of individual radicalization in the United States” dataset and their performance is compared and discussed. The evaluation results support the authors’ hypothesis and show that profiling religious extremists can be achieved with high recall and precision using machine learning models. [ABSTRACT FROM AUTHOR]

• More accurate and explanatory model is proposed for natural gas storage deliverability. • A hybrid Sparse Autoencoder and Random Forest model shows on average of 5.7% increase in prediction accuracy. • The first use of machine learning and explanatory methods (XAI) in deliverability prediction for natural gas storage. Numerous subsurface factors, including geology and fluid properties, can affect the connectivity of the storage spaces in depleted reservoirs; hence, fluid flow simulations become more complicated, and predicting their deliverability remains challenging. This paper applies Machine Learning (ML) techniques to predict the deliverability of underground natural gas storage (UNGS) in depleted reservoirs. First, three baseline models were developed based on Support Vector Regression (SVR), Artificial Neural Network (ANN), and Random Forest (RF) algorithms. To improve the accuracy of the RF model as the best-performing baseline model, a unified framework, referred to as SARF, was developed. SARF combines the capabilities of Sparse Autoencoder (SA) and that of Random Forest (RF). To achieve this, the internal representations of the SA, which constitute extracted features of the input variables, are used in RF to develop the proposed SARF framework. The predictive capabilities of the baseline models and the proposed SARF model were validated using 3744 real-world storage data samples of 52 active storage reservoirs in the United States. The experimental result of this study shows that the proposed SARF model achieved an average 5.7% increase in accuracy on four separate data partitions over the baseline RF model. Furthermore, a set of eXplainable Artificial Intelligence (XAI) methods were developed to provide an intuitive explanation of which factors influence the deliverability of reservoir storage. The visualizations developed using the XAI method provide an easy-to-understand interpretation of how the SARF model predicted the deliverability values for separate reservoirs. [ABSTRACT FROM AUTHOR]

Wave energy flux is a critical index of available wave energy in a region. The short-term wave energy flux prediction is conducive to implementing marine energy generation management. Due to the high degree of nonlinearity in the time series, it is challenging to achieve the accurate prediction of the short-term wave energy flux. The existing prediction models usually only focus on the prediction accuracy without considering the prediction stability. This paper presents hybrid support vector models combining a multi-objective optimizer and data denoising for short-term wave energy flux prediction. The proposed models are tested on the hourly wave energy flux data from November 2014 to January 2015 at the South Energy Test Site in the United States. The results indicate that: (1) The model combining ensemble empirical mode decomposition with multi-objective grey wolf optimizer and support vector machine has the highest prediction accuracy and stability in the case study. The mean absolute percentage error and standard deviation of the percent error are 1.95% and 2.46%, respectively; (2) The data decomposition method improves the radial basis function neural network's prediction accuracy and stability, but has a negative impact on some predictors, such as extreme gradient boosting and random forest; (3) The optimizer does not necessarily have a positive effect on the accuracy and stability of the predictor; (4) The prediction accuracy and stability of the multi-objective optimization hybrid model are higher than that of the single-objective optimization model. • This work conducts forecasting tests of the wave energy flux using machine learning models. • Twenty artificial intelligence methods are compared. • The most accurate forecasts are achieved using a support vector machine with a multi-objective grey wolf optimizer. • The effects of optimizers and data denoising methods on predictions are investigated. [ABSTRACT FROM AUTHOR]

The past two decades have witnessed an increase in ethnicity-related peer aggression, driven by the intensification of the migration phenomenon and rise of information and communication technologies. The goal of the current study is to extend the scope of previous reviews on peer aggression to examine the emerging evidence on the role of technological tools in the prevention, detection, and handling of ethnicity-related peer aggression among young people. We have identified 14 relevant papers published between 2005 and 2020 that help us answer the following research questions: What forms of aggression among young ethnic minorities do these technological interventions try to address? What types of technological interventions are being used? The results indicate that the technological tools are being used to tackle both intergroup as well as intragroup peer aggression, in which ethnic minorities youth is involved (as a victim, perpetrator or bystander). Most studies have focused on adolescents and young adults in the US or in Europe. The technological tools reported on, include: online games, videos, social media, and chat-based programmes, or machine learning algorithms aimed at tackling online and offline peer aggression. They can be used either as stand - alone tools, or as part of intervention programmes (at the school, family or community level). These findings can be useful to improve and elaborate future digital technologies developed to address ethnicity-related peer aggression. • The review maps the existing literature on the role of technological tools in tackling ethnicity-related peer aggression. • All forms of peer aggression are considered in which ethnic minorities youth was involved. • Three groups of technological interventions are identified and categorized into intra- or intergroup ethnicity-related peer aggression. • The digital tools presented include: online games, video, social media, chat-based programmes, and machine learning algorithms. • Our study reveals some follow-up research questions needed to expand current knowledge on digital technologies. [ABSTRACT FROM AUTHOR]

This paper investigated whether the commonly observed immigrant health advantage persists among undocumented immigrants in the U.S. and provides nationally representative evidence on the health of this vulnerable population. Data were derived from pooled cross-sections of the National Health Interview Survey (NHIS, 2000–2018). The legal status of foreign-born NHIS respondents is imputed using a non-parametric machine learning model built based on information from the 2004, 2008 and 2014 cohorts of the Survey of Income and Program Participation (SIPP). Multivariate logistic regression analysis indicated that, despite exposure to numerous additional risk factors, the undocumented population experienced a more pronounced Healthy Migrant Effect, with lower odds of reporting fair or poor self-rated health, any physician-diagnosed chronic conditions or being obese. The observed patterns in undocumented health outcomes may be related to the additional challenges and exclusionary policies associated with undocumented migration that could in turn lead to a more pronounced selection of healthy and resilient individuals. • Undocumented immigrants had 26% lower odds of reporting poor or fair health. • Undocumented immigrants had 23% lower odds of having been diagnosed with a chronic condition. • Undocumented immigrants had 8% lower odds of being obese. • Differences in health behaviors do not explain the health advantage of undocumented immigrants. • Residence in the US 5+ years is positively associated with worse health outcomes. [ABSTRACT FROM AUTHOR]

This paper explores the utility of machine learning methods for understanding bullying, a significant social-psychological issue in the United States, through social media data. Machine learning methods were applied to all public mentions of bullying on Twitter between September 1, 2011 and August 31, 2013 to extract the posts that referred to discrete bullying episodes ( N = 9,764,583) to address five key questions. Most posts were authored by victims and reporters and referred to general forms of bullying. Posts frequently reflected self-disclosure about personal involvement in bullying. The number of posts that originated from a state was positively associated with the state population size; the timing of the posts reveal that more posts were made on weekdays than on Saturdays and more posts were made during the evening compared to daytime hours. Potential benefits of merging social science and computer science methods to enhance the study of bullying are discussed. [ABSTRACT FROM AUTHOR]

Tornado outbreaks in the United States have caused large numbers of human and economic losses. The analysis of gridded climate data to find spatial patterns of meteorological variables that produce tornadoes is often a time consuming and manual process requiring visual inspection. Therefore, the ability to train convolutional neural networks (CNNs) to recognize patterns in climate data that produce tornado outbreaks would be a huge benefit to climatologists. In this paper, three CNNs of increasing complexity, including LeNet-5, VGG-16, and Resnet-50 were trained to predict days with tornado outbreaks of varying size based on gridded values of convective available potential energy (CAPE), convective inhibition (CIN), storm relative helicity (HLCY), and geopotential height. All three models showed promising results in predicting large tornado outbreaks with greater than 20 tornadoes with VGG-16 using the variable CAPE having a slightly better performance, highlighting the importance of CAPE in the analysis of tornado environments. • CNN models and climate grids were used to predict tornado outbreaks in the US. • A feature engineering pipeline was developed to enhance image features. • Models were trained on individual climate variables and all variables combined. • The combination of all variables with VGG-16 produced the best overall result. • VGG-16 with CAPE was best at predicting days with 20 or greater tornadoes. [ABSTRACT FROM AUTHOR]

U 10Zr based metallic nuclear fuel is the leading candidate for next-generation sodium-cooled fast reactors in the United States. US research reactors have used and tested this fuel type since the 1960s and accumulated considerable experience and knowledge about the fuel performance. Most of the knowledge, however, remains empirical. The lack of mechanistic understanding of fuel performance puts a large burden on proof through experimental verification for the qualification of U 10Zr fuel for commercial use. This paper proposes an image data-driven machine learning approach, coupled with domain knowledge provided by advanced post irradiation examination, to provide unprecedented quantified insights into the morphology, size, density and the connectivity of fission gas bubbles and their effects on the fission product transportation and thermal conductivity. Specifically, we developed a method to automatically detect, extract statistics, and classify ~19,000 fission gas bubbles into different categories, and quantitatively link the data to lanthanide transportation through connected bubbles and degradation of thermal conductivity along the radial temperature gradient in a neutron irradiated U 10Zr annular fuel. Results indicate the approach can be modified to study other irradiation effects, such as secondary phase redistribution and gaseous fuel swelling in other irradiated nuclear fuels. • This study showcases a novel method utilizing an image data-driven machine learning approach for advanced post irradiation examination. • The features and statistics of 19,000 fission gas bubbles are derived by the decision tree algorithm. • The bubble statistics provide quantified insights into microstructural features of irradiated fuel and how they relate to fuel performance. [ABSTRACT FROM AUTHOR]

Abstract: The increasing prevalence of multimedia and research data generated by scientific work affords an opportunity to reformulate the idea of a scientific article from the traditional static document, or even one with links to supplemental material in remote databases, to a self-contained, multimedia-rich interactive publication. This paper describes our concept of such a document, and the design of tools for authoring (Forge) and visualization/analysis (Panorama). They are platform-independent applications written in Java, and developed in Eclipse 1 [1] http://www.eclipse.org. using its Rich Client Platform (RCP) framework. Both applications operate on PDF files with links to XML files that define the media type, location, and action to be performed. We also briefly cite the challenges posed by the potentially large size of interactive publications, the need for evaluating their value to improved comprehension and learning, and the need for their long-term preservation by the National Library of Medicine and other libraries. [Copyright &y& Elsevier]

• Proposing an interpretable utility-based framework for dynamic activity pattern estimation. • Mapping from individual trip chains to aggregated activity location types. • Estimating traveler behavior with the support of multiple data sources. • Integrating machine learning tools, nested logit model and transportation domain knowledge. • Testing the proposed framework using 2017 national household survey and Google mobility dataset. During the coronavirus disease 2019 pandemic, the activity engagement and travel behavior of city residents have been impacted by government restrictions, such as temporary city-wide lockdowns, the closure of public areas and public transport suspension. Based on multiple heterogeneous data sources, which include aggregated mobility change reports and household survey data, this paper proposes a machine learning approach for dynamic activity chain pattern estimation with improved interpretability for examining behavioral pattern adjustments. Based on historical household survey samples, we first establish a computational graph-based discrete choice model to estimate the baseline travel tour parameters before the pandemic. To further capture structural deviations of activity chain patterns from day-by-day time series, we define the activity-oriented deviation parameters within an interpretable utility-based nested logit model framework, which are further estimated through a constrained optimization problem. By incorporating the long short-term memory method as the explainable module to capture the complex periodic and trend information before and after interventions, we predict day-to-day activity chain patterns with more accuracy. The performance of our model is examined based on publicly available datasets such as the 2017 National Household Travel Survey in the United States and the Google Global Mobility Dataset throughout the epidemic period. Our model could shed more light on transportation planning, policy adaptation and management decisions during the pandemic and post-pandemic phases. [ABSTRACT FROM AUTHOR]

Patients with advanced cancer are burdened physically and psychologically, so there is an urgent need to pay more attention to their health-related quality of life (HRQOL). With an expected clinical endpoint prediction, over-treatment can be effectively eliminated by the means of palliative care at the right time. This paper develops a deep learning based approach for cancer clinical endpoint prediction based on patient's electronic health records (EHR). Due to the pervasive existence of categorical information in EHR, it brings unavoidably obstacles to the effective numerical learning algorithms. To address this issue, we propose a novel cross-field categorical attributes embedding (CCAE) model to learn a vectorized representation for cancer patients in attribute-level by orders, in which the strong semantic coupling among categorical variables are well exploited. By transforming the order-dependency modeling into a sequence learning task in an ingenious way, recurrent neural network is adopted to capture the semantic relevance among multi-order representations. Experimental results from the SEER-Medicare EHR dataset have illustrated that the proposed model can achieve competitive prediction performance compared with other baselines. [ABSTRACT FROM AUTHOR]

• Built-environment and socioeconomic variables are impactful to predict shipment statuses. • Sensitivity of bid is the highest for larger shipments, C2C market, and out-of-state requests. • Smartphone app gives senders realistic estimates. • Smartphone app empowers senders to influence the probability of delivery. This paper empirically studies the matching and delivery process in a major crowd-sourced delivery platform. The aim is to develop models to understand and predict crowd-shipping delivery performance and using the findings to design incentives to improve user experiences as well as system performance. We apply the random forest machine learning algorithm to predict the shipment status of 14,858 crowd-shipping requests recorded between January 2015 and December 2016 throughout the U.S. The models are used to predict three phases of the crowd-shipping performance, namely bidding, acceptance, and delivery, using shipping request, built-environment, and socioeconomic features as explanatory variables. The results demonstrate that the context of the shipment provides strong predictive performance even when shipping request and package information is unknown. Calculating the sensitivity of bid probability, we show that offering a higher reward and posting a shipping request in the morning has the largest effect on the probability to secure a bid. We also find that larger shipments, out-of-state destinations, and peer-to-peer shipments lead to higher sensitivity, likely reflecting the higher perceived risks of such transactions. In practice, the models presented in this study show promise in their ability to effectively predict shipment status in real time. We illustrate a valuable application of the sensitivity analysis derived from the random forest models to develop customer-tailored crowd-shipping smartphone applications. Based on the data mined from past deliveries, customers are given empirically based delivery forecasts for their specific package request and can modify delivery requests to increase their odds of delivery. We find that pricing is the variable with the highest potential to increase delivery probability followed by the timing of the request. [ABSTRACT FROM AUTHOR]

To effectively control and prevent air pollution, it is necessary to study the influential factors of air quality. A number of previous studies have explored the relationships between air pollution and related factors. However, the methods currently used either cannot well address the multicollinearity problem or fail to explain the importance of the influential factors. Moreover, most of the existing literature limited their studied area in a city or a small region and studied factors in one aspect. There is a lack of studies that analyze the influential factors from the perspective of a country or take into consideration multiple variables. To fill the research gap, this paper proposes a multivariate analysis in the national scale to investigate the most important factors of air quality. In order to study as much influential factors as possible, 171 features ranging from environmental, demographical, economic, meteorological, and energy, were collected and analyzed. To tackle such a "big data" problem, a non-linear machine learning algorithm namely Extreme Gradient Boosting (XGBoost) is utilized to model the relationship and measure the variable importance. Geographical Information System (GIS) is employed to preprocess the diversified variables and visualize the results. Performance of XGBoost is compared with other models and its parameters are tuned using Bayesian Optimization. Experimental results of a case study in the U.S. show that our methodology framework can effectively uncover the important factors of air quality. Six kinds of factors are found to have the largest impact on air quality. Practical suggestions are also proposed from the six aspects to control and prevent air pollution. • This study analyzed the impact factors on AQI of different counties in the U.S. • 171 variables were considered to study the most influential ones. • XGBoost outperforms other commonly seen algorithms in modeling. • Six kinds of factors are found to be most influential on AQI on a national scale. [ABSTRACT FROM AUTHOR]

The recovery factor (RF) is one of the most fundamental parameters that define engineering and economical success of any operational phase in oil and gas production. Despite its importance, it is not easy to predict recovery factors as they are affected by many variables including the type of the recovery process, reservoir type, fluid properties, reservoir heterogeneity, depth, and thickness. The usual and most comprehensive method of estimating recovery factors is laboratory experiments or numerical reservoir simulation, or combination of both, each of which has their own limitations due to data requirements, boundary conditions and scale effects. In this work, a fuzzy inference system approach has been adopted to predict miscible CO 2 -EOR recovery factors of the major field applications in the United States using a more practical, multi-variable, inexpensive, quicker, and yet accurate alternative to conventional approaches. The fuzzy system was built using Mamdani-type fuzzy logic inference engine. Reservoir data compiled from different sources were used as model input parameters (9 of them) and associated recovery factors obtained from literature survey were used as control variable, i.e. output. Due to the limited number of field cases that could be used for this purpose, 24 sets of applications were included in the study. The model showed reasonable predictive capability for the field observations of recovery factor despite the complexity and dependence of this parameter on different inputs. In addition, the multidimensional fuzzy solution was used to demonstrate response of miscible CO 2 -EOR recovery factor to different inputs. The fuzzy system introduced in the paper can be used to predict RFs and also as a guidance tool for making decisions based on the sensitivity to different inputs. • A fuzzy inference system has been developed and used to predict miscible CO 2 -EOR recovery factors of the major field applications in the U.S. • Reservoir data and the associated recovery factors compiled from different sources were used for modeling. • Fuzzy system was used to demonstrate response of miscible CO 2 -EOR recovery factor to different inputs. • Results showed that the model had reasonable predictive capability for the field observations of recovery factors. [ABSTRACT FROM AUTHOR]

• Information from electronic health records can be used to help us understand what contributes to the onset of diseases including type 2 diabetes mellitus. • Machine learning, including deep learning, has been used to predict the onset of diseases using information from electronic health records. • Our work is the first to use wide and deep learning, a state-of-the-art deep learning architecture that achieves both memorisation and generalisation abilities, to predict the onset of type 2 diabetes mellitus using electronic health records. • Our algorithm is better at predicting the onset of type 2 diabetes mellitus than other state-of-the-art machine learning algorithms using the same dataset with similar experimental settings. • The synthetic minority over-sampling technique (SMOTE) was found to work better with the wide and deep learning framework than other machine learning algorithms in improving sensitivity for imbalanced electronic health record datasets. Diabetes is responsible for considerable morbidity, healthcare utilisation and mortality in both developed and developing countries. Currently, methods of treating diabetes are inadequate and costly so prevention becomes an important step in reducing the burden of diabetes and its complications. Electronic health records (EHRs) for each individual or a population have become important tools in understanding developing trends of diseases. Using EHRs to predict the onset of diabetes could improve the quality and efficiency of medical care. In this paper, we apply a wide and deep learning model that combines the strength of a generalised linear model with various features and a deep feed-forward neural network to improve the prediction of the onset of type 2 diabetes mellitus (T2DM). The proposed method was implemented by training various models into a logistic loss function using a stochastic gradient descent. We applied this model using public hospital record data provided by the Practice Fusion EHRs for the United States population. The dataset consists of de-identified electronic health records for 9948 patients, of which 1904 have been diagnosed with T2DM. Prediction of diabetes in 2012 was based on data obtained from previous years (2009–2011). The imbalance class of the model was handled by Synthetic Minority Oversampling Technique (SMOTE) for each cross-validation training fold to analyse the performance when synthetic examples for the minority class are created. We used SMOTE of 150 and 300 percent, in which 300 percent means that three new synthetic instances are created for each minority class instance. This results in the approximated diabetes:non-diabetes distributions in the training set of 1:2 and 1:1, respectively. Our final ensemble model not using SMOTE obtained an accuracy of 84.28%, area under the receiver operating characteristic curve (AUC) of 84.13%, sensitivity of 31.17% and specificity of 96.85%. Using SMOTE of 150 and 300 percent did not improve AUC (83.33% and 82.12%, respectively) but increased sensitivity (49.40% and 71.57%, respectively) with a moderate decrease in specificity (90.16% and 76.59%, respectively). Our algorithm has further optimised the prediction of diabetes onset using a novel state-of-the-art machine learning algorithm: the wide and deep learning neural network architecture. [ABSTRACT FROM AUTHOR]