Browse Articles

The authors combine fine needle aspiration biopsy and machine learning algorithms to develop a breast cancer detection method suitable for resource-constrained regions that lack access to mammograms.

The authors created a 1D model to diagnose hepatomegaly and cirrhosis via ultrasound of the liver.

The escalating crisis of climate change, driven by the accumulation of greenhouse gases from human activities, demands urgent and innovative solutions to curb rising global temperatures. Plasma-based methane (CH₄) and carbon dioxide (CO₂) reforming offers a promising pathway for carbon capture and the sustainable production of hydrogen fuel and syngas components. To advance this technology, particularly in terms of energy efficiency and selectivity, it is essential to enhance the conversion efficiencies of CO₂ and CH₄.

Here the authors provided greater coverage of adolescent stances by investigating the political perspectives and trends of high school journalists, utilizing web scraping methods and artificial intelligence (ChatGPT-4o) to analyze over 153,000 articles. They found that high school publications exhibit lower levels of political polarization compared to mainstream media and that journalists' views, while tending to lean moderately liberal, showed no significant correlation with local voting patterns.

The authors looked at different ways to build computational resources that would analyze shooting form for basketball players.

The authors developed and tested machine learning methods to diagnose tuberculosis from pulmonary X-ray scans.

The authors looked at soil quality of former military sites where chemical disposal was known to have occurred. Along with testing for heavy metals, the authors also looked for the presence (and number) of earthworms present in topsoil samples as a marker of soil health.

The authors analyze differences in sports commentary between men's matches and women's matches during the 2023 US Open.

This article describes the classification of medical text data using vector databases and text embedding. Various large language models were used to generate this medical data for the classification task.

The authors develop a method for detecting fake AI-generated images from real images.