Browse Articles

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.

Various methods exist to mitigate bias in AI models, including "Constitutional AI," a technique which guides the AI to behave according to a list of rules and principles. Lo, Poosarla, Singhal, Li, Fu, and Mui investigate whether constitutional AI can reduce bias in AI outputs on political topics.

The authors investigate how well AI-detection machine learning models can detect real versus AI-generated art across different art styles.

Advertising platforms like Google Ads use AI to drive the algorithms used to maximize advertisers benefits. This study shows that AI does not adjust it strategy based on auction type and highlights the limitations of AI running without explicit guidance.

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 studied the chemoreception of moon jellyfish in response to food, and developed an AI tool to identify track and quantify the pulsation of swimming jellyfish.

In this study, three models are used to test the hypothesis that data-centric artificial intelligence (AI) will improve the performance of machine learning.

This study evaluates the potential of natural language processing (NLP) models in an emotion-driven bibliotherapy framework to improve mental health challenges.

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.

AI analysis of brain scans offers promise for helping doctors diagnose brain tumors. Haider and Drosis explore this field by developing machine learning models that classify brain scans as "cancer" or "non-cancer" diagnoses.