Browse Articles

In this study, the authors test whether providing a larger dataset of glass transition temperatures (T_g) to train the machine-learning platform Polymer Genome would improve its accuracy. Polymer Genome is a machine learning based data-driven informatics platform for polymer property prediction and T_g is one property needed to design new polymers in silico. They found that training the model with their larger, curated dataset improved the algorithm's T_g, providing valuable improvements to this useful platform.

This study examined how social determinants of health (SDH) relate to vision loss by analyzing publicly available data from 18 northern and southern U.S. states and using Bayesian correlation analysis.

This study analyzes genetic alterations and expression patterns of protein kinases involved in phagocytosis across multiple cancers using TCGA data.

The authors looked the ability of sound sensors to predict clogged pipes when the sound intensity data is run through a machine learning algorithm.

The authors were interested in whether they could observe the effects of climate change by analyzing historical temperature data of two U.S. cities. They predicted that they should observe a warming trend in both cities. Their results showed that despite yearly variations, warming trends can be observed both in Rochester, NY and Seattle, WA which fit the predictions of climate change forecasts.

A significant percentage of cancer survivors develop a second primary cancer. Using data of deceased patients provided by the Peninsula Regional Medical Center, Li and Holdai conducted a retrospective statistical analysis to investigate whether the type of the first cancer affects the occurrence time and type of the second primary cancer.

Here the authors investigated the relationship between offensive play-calling styles and scoring success within the NFL's red zone by analyzing play-by-play data and expected points metrics. Their findings suggest that a conservative approach to play design and execution is more strongly associated with maximizing efficiency and point-value gains than aggressive strategies.

Here the authors investigated a combination therapy to target the Kirsten rat sarcoma viral oncogene homolog mutation in lung cancer, by analyzing publicly available data. Their findings indicate that the combination therapy of CA170 and Kvax enhances helper T cell function and improves cytotoxic T lymphocyte infiltration, while Kvax alone drives plasma and memory B cell proliferation.

This study investigates how the hyperparameters epochs and batch size affect the classification accuracy of a convolutional neural network (CNN) trained on pulsar candidate data. Our results reveal that accuracy improves with increasing number of epochs and smaller batch sizes, suggesting that with optimized hyperparameters, high accuracy may be achievable with minimal training. These findings offer insights that could help create more efficient machine learning classification models for pulsar signal detection, with the potential of accelerating pulsar discovery and advancing astrophysical research.

This study investigates PFAS contamination in Santa Clarita groundwater, focusing on potential sources. The study employs statistical analysis to assess data quality and trends which allowed them to identified domestic waste, fire extinguisher materials, and food packaging as the most likely sources of contamination.