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.

This study investigates PFAS contamination in Santa Clarita groundwater, focusing on potential sources. The study employs statistical analysis to assess data quality and trends which allowed them to identified domestic waste, fire extinguisher materials, and food packaging as the most likely sources of contamination.

Car emissions harm both the environment and human health, and current U.S. EV tax credits mainly benefit high-income households because EVs are expensive. This study evaluates U.S. vehicle emissions policies by analyzing 2022 national vehicle data to compare the fuel economy and greenhouse gas impacts of the current EV tax credit with a proposed policy that incentivizes hybrid vehicle purchases.

The authors looked at which measurements from the NFL combine were the most predictive of success for defensemen in the NFL.

Elevated acetylcholinesterase (AChE) activity contributes to cognitive decline and neurodegenerative diseases such as Alzheimer’s, motivating the search for more effective inhibitors with better bioavailability. This study used computational methods to design novel, non-toxic AChE inhibitors.

The authors survey high school students regarding preferences for taking notes by hand versus typing.

This study analyzes genetic alterations and expression patterns of protein kinases involved in phagocytosis across multiple cancers using TCGA data.

The authors looked at the effects of different treatments using flies with neurodevelopmental disorders.

The authors used a particle-in-cell simulation to determine the effects on extensive and intensive metrics. They found that preliminary simulations could be run quickly with much lower particle counts before more technically demanding and comprehensive simulations are performed.

This manuscript evaluates peak detection algorithms for feature extraction in EMG-based hand gesture recognition using a random forest classifier. The study demonstrates that wavelet-based peak detection features achieve the highest classification accuracy (96.5%), outperforming other methods. The results highlight the potential of peak features to improve EMG-based prosthetic control systems.