Browse Articles

The authors looked at different factors, such as age, pre-existing conditions, and geographic region, and their ability to predict what an individual's health insurance premium would be.

The authors looked at the impact of calcium on iron absorption in mealworms, hypothesizing that calcium would inhibit iron absorption.

The authors evaluated the effect of concentration and variant of N-Acetylcysteine in hydrolyzing mucus.

The authors used machine learning to predict the presence of anxiety and burnout in students based on facial expressions and demographic information.

Using machine learning to predict the risk of algae bloom

This study investigated how well food labels from 280 different brands across multiple food and drink categories in India and the US adhered to recommended nutritional labeling standards as outlined by the Codex Alimentarius.

The authors looked at alternative production processes for PHB plastic in an effort to reduce environmental impact. They found that no alternative process was able to significantly decrease the environmental impact of PHB production, but that optimizing dewatering steps during production could lead to the largest improvement on environmental impact.

Here the authors aimed to understand factors influencing adolescent fentanyl exposure, hypothesizing a positive association between social media usage, socioeconomic factors, and fentanyl abuse among U.S. teens. Their analysis of the Monitoring the Future dataset revealed that a history of suspension and use of marijuana or alcohol were linked to higher fentanyl use, and while not statistically significant, a notable positive correlation between social media use and fentanyl frequency was observed.

In this study the authors looked at the ability to navigate planes in space between randomly placed planets. They used machine and reinforcement learning to run simulations and found that they were able to identify optimal paths for travel. In the future these techniques may allow for safer travel in unknown spaces.

The authors looked at the ability of different deep learning models to predict the presence of lung cancer from chest CT scans. They found that a pre-trained CNN model performed better than an autoencoder model.