Browse Articles

This study investigates how the hyperparameters epochs and batch size affect the classification accuracy of a convolutional neural network (CNN) trained on pulsar candidate data. Our results reveal that accuracy improves with increasing number of epochs and smaller batch sizes, suggesting that with optimized hyperparameters, high accuracy may be achievable with minimal training. These findings offer insights that could help create more efficient machine learning classification models for pulsar signal detection, with the potential of accelerating pulsar discovery and advancing astrophysical research.

Analysis of the Sloan green and red photometry of the Type Ia supernova 2024neh

The authors looked at the ability to detect heart disease before the onset of severe clinical symptoms.

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.

This study analyzed patient demographics in the ophthalmology department at Indira Gandhi Medical College and Hospital (IGMCH) to assess relationships between age, sex, and eye conditions. While the overall sex distribution was equal, individual conditions varied, with cataracts and retinal disorders more common in males and conjunctival conditions slightly more prevalent in females, though none were statistically significant (p > 0.05) except for cataract patients aged 50–89 (p < 0.001). Understanding these trends can help medical facilities allocate resources more effectively for improved patient care.

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.

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.

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.

Coronary heart disease (CHD) is the leading cause of death in the U.S., responsible for nearly 700,000 deaths in 2021, and is marked by artery clogging that can lead to heart attacks. Traditional prediction methods require expensive clinical tests, but a new study explores using machine learning on demographic, clinical, and behavioral survey data to predict CHD.

The authors looked at hydrogen gas production and how reaction temperature, concentration and alkaline solution used impacted the overall reaction with silicon. They found that all alkaline solutions tested would be viable options for using silicon waste to produce hydrogen gas to be used a renewable energy source.