Browse Articles

The authors looked into eco-friendly alternatives for insulating material. They ultimately found that a polyurethane derived from eggshells was an effective insulator and further research into it is warranted.

The authors looked at ways to provide better forecasting on website traffic. They found that deep learning models performed better than statistical models.

In this study the authors looked at the ability to navigate planes in space between randomly placed planets. They used machine and reinforcement learning to run simulations and found that they were able to identify optimal paths for travel. In the future these techniques may allow for safer travel in unknown spaces.

The authors looked at different combinations of risk-adjusted return measures to determine which combination would provide an optimal return for investors. They found that different combinations performed better dependent on investment timeframe.

Predicting antibody structures and antibody-antigen complexes using AlphaFold

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.

Almost all urban areas face the challenge of urban heat islands, areas with substantially hotter land surface temperatures than the surrounding rural areas. These areas are associated with worse air and water
quality, increased power outages, and increased heat-related illnesses. To learn more about these areas, Ustin et al. analyze satellite images of Cleveland neighborhoods to find out if there is a correlation between surface area development and surface temperature.

The authors test various machine learning models to improve the accuracy and efficiency of pneumonia diagnosis from X-ray images.

The authors use machine learning and electroencephalogram data to propose a method for improving epilepsy diagnosis.

The challenge of accurately identifying shark species is crucial for biodiversity monitoring but is often hindered by time-consuming and labor-intensive manual methods. To address this, SharkNet, a CNN model based on AlexNet, achieved 93% accuracy in classifying shark species using a limited dataset of 1,400 images across 14 species. SharkNet offers a more efficient and reliable solution for marine biologists and conservationists in species identification and environmental monitoring.