Browse Articles

Many of us take our vision for granted, but rarely do we measure how well we can see. In this study, the authors investigate the ability of people of different ages to read progressively fainter letters in dark light. They find that the ability to see in dim light drops drastically after age 30. The ability to read fainter letters worsens after age 30 as well. These findings should help inform lighting decisions everywhere from restaurants to road signs.

Recent advances in generative AI have made it increasingly hard to distinguish real images from AI-generated ones. Traditional detection models using CNNs or U-net architectures lack precision because they overlook key spatial and frequency domain details. This study introduced a hybrid model combining Convolutional Neural Networks (CNN) with Fast Fourier Transform (FFT) to better capture subtle edge and texture patterns.

The author looked at how dance styles can vary by individuals, even between a student and their teacher.

The authors looked at different algorithms and their ability to encrypt and decrypt text of various lengths.

The authors looked at public knowledge regarding suggested daily limits for sugar intake and then looked at how sugar levels vary in the same drink obtained from different sources and across different days.

The authors looked at the ability to use graphite from pencils in anodes of lithium-anode batteries.

Here the authors aimed to find the best preservative combinations to stop bacterial growth in food, using data modeling and biochemical experiments. They discovered that single preservatives are often not enough, with varying effectiveness against different bacteria, and suggest future research into combining preservatives for better results.

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

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

Additive manufacturing (AM) is transforming the production of complex metal parts, but challenges like internal cracking can arise, particularly in critical sectors such as aerospace and automotive. Traditional methods to assess cracking susceptibility are costly and time-consuming, prompting the use of machine learning (ML) for more efficient predictions. This study developed a multi-model ML pipeline that predicts solidification cracking susceptibility (SCS) more accurately by considering secondary alloy properties alongside composition, with Random Forest models showing the best performance, highlighting a promising direction for future research into SCS quantification.