Browse Articles

This study investigates skin tone bias in artificial intelligence models used for dermatological disease classification and evaluates a CycleGAN-based data augmentation approach to improve diagnostic performance on darker skin types. We generated synthetic dark-skinned images to enhance dataset diversity and compared model performance before and after augmentation. The results demonstrate that augmentation with synthetic dermatological images can help reduce disparities in diagnostic performance across skin tones, highlighting a practical strategy for improving fairness in dermatology AI systems.

The authors employ computational protein design to identify a mini-protein with the potential to enhance binding of the tight junction protein, claudin-5, at the blood-blood barrier with therapeutic potential for neurodegenerative diseases.

Here the authors present an autonomous drone air filtration system that uses a novel algorithm, the gradient ascent ML particle filter (GA/MLPF), to efficiently locate and mitigate outdoor air pollution. They demonstrate that their GA/MLPF algorithm is significantly more efficient than the conventional gradient ascent algorithm, reducing both the time and number of waypoints needed to find the source of pollution.

Toxic particulates in the atmosphere pose significant health risks, and while modern masks can help reduce inhalation of these pollutants, their availability may be limited during health crises. This study evaluated the effectiveness of household fabrics (cotton, fleece, wool, and rayon) as particulate filters, finding that cotton outperformed the others in filtration efficiency, while rayon was the least effective. The findings suggest that cotton is a preferable alternative for filtration purposes, while rayon should be avoided.

Here the authors investigated air quality forecasting in India, comparing traditional time series models like SARIMA with deep learning models like LSTM. The research found that SARIMA models, which capture seasonal variations, outperform LSTM models in predicting Air Quality Index (AQI) levels across multiple Indian cities, supporting the hypothesis that simpler models can be more effective for this specific task.

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.

In this study, the authors sample water at different points closer and closer to two different airports to determine if these airports may be contributing to water pollution, specifically by measuring metals, nitrates, and pH.

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 authors compare current machine learning algorithms with a new Explainable AI algorithm that produces a human-comprehensible decision tree alongside predictions.

The authors compare air quality in the presence and absence of a living wall in a high school hallway in Brooklyn, NY.