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.

Detecting cervical spondylosis using deep learning

This paper looks at using spent coffee grounds as a partial substitute for titanium dioxide (TiO₂) as a catalyst for chemical reactions. Using UV-Vis spectrophotometry, they found that adding the coffee grounds to TiO₂ in a 3:1 ratio, there is still meaningful catalytic activity. This offers a cheaper solution than just using pure TiO₂.

The authors developed a quantum inspired model for stock market fluctuations.

The authors looked at how the length of an audio clip used of a song impacted the ability to properly classify it by musical genre.

The authors combine fine needle aspiration biopsy and machine learning algorithms to develop a breast cancer detection method suitable for resource-constrained regions that lack access to mammograms.

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 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.