Browse Articles

This study explored how green spaces, climate, traffic, and air quality (GCTA) collectively influence asthma-related emergency department visits in the U.S using machine learning models and explainable AI.

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.

Here, recognizing that brain aneurysms pose a severe threat, often misdiagnosed and leading to high mortality, particularly in younger individuals, the authors explored a novel computer-aided engineering approach. They used magnetic resonance angiography images and computational fluid dynamics, to improve aneurysm detection and risk assessment, aiming for more personalized treatment.

The authors looked at different models of semantic segmentation to determine which may be best used in the future for segmentation of CT scans to help diagnose certain conditions.

The authors looked at using machine learning to identify skills needed to apply for certain jobs, specifically looking at different techniques to parse apart the text. They found that Bidirectional Encoder Representation of Transforms (BERT) performed best.

Here the authors sought to use three machine learning models to predict poverty levels in Cambodia based on available household data. They found teat multilayer perceptron outperformed the other models, with an accuracy of 87 %. They suggest that data-driven approaches such as these could be used more effectively target and alleviate poverty.

Poor air quality is associated with negative effects on human health but can be difficult to measure in an accurate and cost-effective manner. The authors design and test a monitor for measuring indoor air quality using low-cost components.

Superabsorbent beads are remarkable, used throughout our daily lives for various practical applications. These beads, as suggested by their name, possess a unique ability to absorb and retain large quantities of liquids. This characteristic of absorbency makes them essential throughout the medical field, agriculture, and other critical industries as well as in everyday products. To create these beads, the process of photopolymerization is fast growing in favor with distinct advantages of cost efficiency, speed, energy efficiency, and mindfulness towards the environment. In this article, researchers explore the pairing of cheap monomers with accessible equipment for creation of superabsorbent beads via the photopolymerization process. This research substantially demonstrates the successful application of photopolymerization in producing highly absorbent beads in a low-cost context, thereby expanding the accessibility of this process for creating superabsorbent beads in both research and practical applications.

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.

With the advance of technology, artificial intelligence (AI) is now applied widely in society. In the study of AI, machine learning (ML) is a subfield in which a machine learns to be better at performing certain tasks through experience. This work focuses on the convolutional neural network (CNN), a framework of ML, applied to an image classification task. Specifically, we analyzed the performance of the CNN as the type of neural activation function changes.