Browse Articles

This manuscript explores the performance of five different machine learning models in classifying brain tumors from a dataset of MRI scans. The authors find that several of the models showed >90% accuracy. Thus, the authors suggest that machine learning models demonstrate potential for effective implementation in clinical settings, including as a diagnostic tool that can be used to complement the expertise of neuroradiologists.

The authors looked at using computer vision to evaluate the degree of exotropia in individuals with strabismus.

The authors test symbiotic relationships among cyanobacteria species to generate more robust cultures for potential biofuel production.

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.

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.

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.

Detecting cervical spondylosis using deep learning