Search

Mobile games can contribute to learning at greater success. In this paper, the authors have developed and evaluated a novel educational game, named FoodCalorie, to learn food calorie intake standard. The game is aimed to learn calorie values of various traditional foods of Bangladesh and the calorie intake standard that varies with age and gender. They are the first in this field to perform an empirical study on women in Bangladesh to see how game-based learning can contribute to learn food calories. They further analyze and report the impact of participants' age, professions, and smartphone proficiency levels on their learning experience and progression. The study also conforms the finding of existing studies that game-based learning can enhance the learning experience.

Prenatal alcohol exposure (PAE) refers to the exposure of the developing fetus due to alcohol consumption during pregnancy and can have life-long consequences for learning, behavior, and health. Understanding the impact of PAE on the developing brain manifests challenges due to its complex structural and functional attributes, which can be addressed by leveraging machine learning (ML) and deep learning (DL) approaches. While most ML and DL models have been tailored for adult-centric problems, this work focuses on applying DL to detect PAE in the pediatric population. This study integrates the pre-trained simple fully convolutional network (SFCN) as a transfer learning approach for extracting features and a newly trained classifier to distinguish between unexposed and PAE participants based on Tl-weighted structural brain magnetic resonance (MR) scans of individuals aged 2-8 years. Among several varying dataset sizes and augmentation strategy during training, the classifier secured the highest sensitivity of 88.47% with 85.04% average accuracy on testing data when considering a balanced dataset with augmentation for both classes. Moreover, we also preliminarily performed explainability analysis using the Grad-CAM method, highlighting various brain regions such as corpus callosum, cerebellum, pons, and white matter as the most important features in the model's decision-making process. Despite the challenges of constructing DL models for pediatric populations due to the brain's rapid development, motion artifacts, and insufficient data, this work highlights the potential of transfer learning in situations where data is limited. Furthermore, this study underscores the importance of preserving a balanced dataset for fair classification and clarifying the rationale behind the model's prediction using explainability analysis. [ABSTRACT FROM AUTHOR]

The Southern Ocean (SO) provides a unique natural laboratory for studying cloud formation and cloud-aerosol interactions with minimal anthropogenic influence. The Southern Ocean Clouds, Radiation, Aerosol Transport Experimental Study (SOCRATES), was an aircraft-based campaign conducted from January 15 to February 28, 2018, off the coast of Hobart, Tasmania. During SOCRATES, the NSF/NCAR GV research aircraft, equipped with in-situ probes and remote sensors, observed aerosol, cloud, and precipitation properties, and provided detailed vertical structure of clouds over the SO, particularly for the low-level clouds (below 3 km). The HIAPER Cloud Radar (HCR) and in-situ cloud and drizzle probes (CDP and 2DS) measurements were used to provide comprehensive statistical and phase-relevant macrophysical properties for the low-level clouds sampled by the 15 research flights during SOCRATES. A new method based on HCR reflectivity and spectrum width gradient was developed to estimate cloud boundaries (cloud-base and -top heights) and classify cloud types based on their top and base heights. Low-level clouds were found to be the most prevalent, with an almost 90 % occurrence frequency. A new phase determination method was also developed to identify the single-layered low-level clouds as liquid, ice, and mixed phases, with occurrence frequencies of 45.4 %, 32.5 %, and 22.2 %, respectively. Low-level clouds over the SO have significantly higher SLW concentrations, with liquid being most prevalent at higher temperatures, ice phase dominating at lower temperatures, and mixed-phase being least common due to its thermodynamic instability. Regarding their vertical distributions, the liquid phase occurs most frequently in the lower mid-cloud range (from 500 m to 1 km), the mixed phase dominates at cloud bases lower than 1 km but is well distributed along the vertical cloud layer, while the ice phase is prevalent from the middle to upper cloud levels (1–3 km). The higher occurrence of the mixed phase at the cloud base could be attributed to large drizzle-sized drops and/or ice particles. [ABSTRACT FROM AUTHOR]

Although concrete framed structures are widely used with masonry infills, the contribution of masonry infills in structural design is limited to their dead loads only. Therefore, the full-fledged stiffness characteristics of masonry infill are not often considered. However, recent earthquakes showed the impact of masonry infill on the lateral behavior of surrounding RC frames. Moreover, sometimes existing masonry infills are strengthened using Ferrocement (FC), Textile Reinforced Mortar (TRM), Carbon Fiber Reinforced Polymer (CFRP), etc., which might also have a similar impact on surrounding RC frames. The impact includes enhanced shear demand, damage, etc. However, the effect of the enhanced shear demand on RC columns is a relatively less investigated issue. In this context, an experimental program was designed to compare the effect of non-strengthened and FC strengthened masonry infill on the behavior of the surrounding RC frame in terms of lateral strength, hinge formation, shear demand enhancement, and damage to columns. The test specimens, including a bare RC frame, a masonry infilled RC frame, and a FC strengthened masonry infilled RC frame, were subjected to a quasi-static cyclic lateral loads. The experimental result showed that the masonry infill and FC strengthened masonry infill increased lateral strength, on average, by 81% and 244%, respectively, when compared to that of the bare RC frame. Meanwhile, FC strengthening of masonry infill improved the lateral strength, on average, by 90% when compared with the masonry infilled RC frame’s lateral strength. In this study, low-strength masonry infill caused the formation of a short column on the tension column of the RC frame. The application of ferrocement to low-strength masonry altered the position of the plastic hinge formed on the tension column of the RC frame when compared to that of the masonry infilled RC frame. Therefore, ferrocement strengthening of masonry eliminated the short column phenomenon in this particular study. Nevertheless, the shear demand (in terms of strain on the column tie) enhancement of the tension column was not substantial due to the ferrocement strengthening of the masonry infill when compared to that of the masonry infilled RC frame. Moreover, the damage concentration on RC columns (i.e., residual crack width) after insertion of masonry infill and ferrocement strengthened masonry infill changed to a smaller extent when compared to the bare RC frame damages, where the residual crack widths were within 1.0 ~ 2.0 mm. [ABSTRACT FROM AUTHOR]

Crashes involving heavy trucks on rural mountainous freeways are known to result in severe injuries and fatalities, particularly under challenging driving conditions. This study aims to develop a robust model to accurately predict fatal and injury crashes involving heavy trucks on rural mountainous freeways. The crash database of Interstate-80 in Wyoming was used to extract a wide range of variables related to environmental, roadway, crash, occupant, and vehicle characteristics. This study employed a state-of-the-art deep neural network architecture named ResNet-50 using transfer learning to develop crash severity prediction models. The numeric crash data were converted to images utilizing DeepInsight to facilitate the application of the proposed deep learning model. Due to the imbalanced nature of the crash severity data, this study employed random undersampling (RUS) and synthetic minority oversampling technique (SMOTE) data balancing techniques and investigated several data sampling ratios. A ratio of 1:2:2 (Fatal: Injury: PDO) combined with both RUS and SMOTE produced the best performance with recall values of 99.7%, 79.7%, and 79.3% for fatal, injury, and PDO crashes, respectively. This study also employed Boruta and extreme gradient boosting (XGBoost) to examine the significance of variables on crash severity. The findings revealed that the deployment of airbags, use of seatbelts, driver distraction, and driver conditions such as inattentiveness and fatigue, vehicle type, vertical grades, weather, and road surface conditions were the most critical variables contributing to the severity of crashes involving heavy trucks. Furthermore, this study developed several reduced truck-involved crash severity prediction models without significantly compromising the prediction performance. The proposed deep neural network model can provide accurate and timely prediction of fatal and injury crashes involving heavy trucks, which is beneficial for ensuring efficient collision management, avoiding secondary pile-up crashes, and facilitating prompt medical assistance. [ABSTRACT FROM AUTHOR]

This study presented an extensive assessment of risky driving behavior through Structural Equation Modeling (SEM) technique and explored the applicability of this method in identifying contributing factors influencing drivers' risk-taking behavior in clear and adverse weather. Drivers' questionnaire responses as well as vehicle trajectories of their completed trips in clear and adverse weather were utilized from the SHRP2 Naturalistic Driving Study (NDS). Factor analyses were conducted to identify the number of unobserved "latent" variables. Subsequently, two SEM models in clear and adverse weather were developed to attain the relationships between the observed and the latent variables. "Human Factors" and "Driving Skills" were determined as exogenous latent variables in both models to investigate their impacts on an endogenous latent variable (i.e., risky driving). The results suggested that "Human Factors" was the most significant latent variable affecting drivers' risk-taking behavior in clear and adverse weather conditions. Moreover, speeding was found to have a significant impact on risky behavior in adverse weather conditions. The findings could help safety practitioners with better understanding of the influencing factors affecting risky driving to improve safety through proper enforcement and necessary training programs, particularly targeting young and inexperienced drivers. [ABSTRACT FROM AUTHOR]