Browse Articles

The purpose of this study was to determine the necessity of previous non-algorithmic attacks (Adversarial Training) in light of algorithmic defense methods (Gradient Masking and Defensive Distillation) against FGSM attacks. We found a significant increase in image classification accuracy from defense methods with the non-algorithmic defense method compared to ones without. By analyzing the significance with a McNemar test, we determined that the inclusion of non-algorithmic defense methods is still necessary in light of new algorithmic defense methods.

The authors investigated adoption rates of solar photovoltaic power at K-12 schools in California.

The main goal of this study is to determine what demographics are related to tuberculosis incidence in the United States populations, particularly if changing demographics are related to differences in tuberculosis risk over two discrete time periods. The major finding is that in the two studied time periods, tuberculosis risk factors were somewhat consistent and may be influenced by things such as immigration, healthcare access, and race or ethnicity, although the top predictor did change.

The authors looked at how vocabulary is impacted in Alzheimer's disease and whether it could be used a predictor of disease onset.

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.

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 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.

As AI becomes more integrated into healthcare, public trust in AI-developed treatment plans remains a concern, especially for emotionally charged health decisions. In a study of 81 community college students, AI-created treatment plans received lower trust ratings compared to physician-developed plans, supporting the hypothesis. The study found no significant differences in AI trust levels across demographic factors, suggesting overall skepticism toward AI-driven healthcare.

People with Type One diabetes often rely on Continuous Blood Glucose Monitors (CGMs) to track their blood glucose and manage their condition. Researchers are now working to help people with Type One diabetes more easily monitor their health by developing models that will future blood glucose levels based on CGM readings. Jalla and Ghanta tackle this issue by exploring the use of AI models to forecast blood glucose levels with CGM data.

Authors emphasize the challenges of manual tumor segmentation and the potential of deep learning models to enhance accuracy by automatically analyzing MRI scans.