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.

The authors demonstrate computationally that two types of nanoplastics can bind to estrogen receptor beta and potentially disrupt endocrine systems.

The authors looked at how pharmacokinetics changed depending on the use of an in vitro or an in vivo model.

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.

The authors looked at the ability to use graphite from pencils in anodes of lithium-anode batteries.

Lung cancer is highly fatal, largely due to late diagnoses, but early detection can greatly improve survival. This study developed three models to enhance early diagnosis: an MLP for clinical data, a CNN for imaging data, and a hybrid model combining both.

Here the authors aimed to understand factors influencing adolescent fentanyl exposure, hypothesizing a positive association between social media usage, socioeconomic factors, and fentanyl abuse among U.S. teens. Their analysis of the Monitoring the Future dataset revealed that a history of suspension and use of marijuana or alcohol were linked to higher fentanyl use, and while not statistically significant, a notable positive correlation between social media use and fentanyl frequency was observed.

This study compares the performance of two deep learning models, U-Net and DeconvNet, for segmenting gliomas from MRI scans.

The authors looked at different ways to build computational resources that would analyze shooting form for basketball players.