Browse Articles

Semantic segmentation - labelling each pixel in an image to a specific class- models require large amounts of manually labeled and collected data to train.

In this study, the authors use existing mathematical models to how high school athletes pace 800 m, 1600 m, and 3200 m distance track events compared to elite athletes.

Here in an effort to better understand how our brains process and remember different categories of information, the authors assessed working memory capacity using an operation span task. They found that individuals with higher working memory capacity had higher overall higher task accuracy regardless of the type of category or the type of visual distractors they had to process. They suggest this may play a role in how some students may be less affected by distracting stimuli compared to others.

In this study, the authors conduct a series of experiments within an elevator traveling on an angle to determine if Einstein's Equivalency Principle and motion vector decomposition can be used to calculate the angle of inclination.

In this study, the authors address the current climate concern of high CO₂ levels by testing solid forms of hydroxide for CO₂ reduction and designing a drone to fly it in ambient air!

This paper develops a gelatin-based hydrogel dressing infused with bromothymol blue dye that visibly changes from yellow to blue as wound pH rises from 5.0 to 8.0, signaling possible infection. The color shift was visually detectable and statistically significant across all six Fitzpatrick skin tones, suggesting a low-cost ($0.40/dressing) tool for early infection monitoring in settings with limited access to care.

Physics‑Informed Neural Networks (PINNs) offer a promising way to estimate blood‑flow behavior in arteries, especially near the vessel wall where traditional methods struggle. In this study, students tested how sensor density and placement affect PINN accuracy in modeling carotid artery flow and found that accuracy improves up to a moderate sensor density and depends strongly on how close sensors are placed to the arterial wall. Applying the optimized configuration to a patient‑specific carotid model produced velocity predictions closely matching computational fluid dynamics results, highlighting PINNs’ potential for future personalized cardiovascular assessment.

This study strongly illustrates that optimizing 3D printing parameters would enhance a triboelectric nanogenerator's performance. The design improvements substantiate the potential of optimized, 3D-printed TENGs for developing scalable, cost-effective solutions for powering low-energy electronics, particularly in applications such as structural health monitoring.

This study investigates skin tone bias in artificial intelligence models used for dermatological disease classification and evaluates a CycleGAN-based data augmentation approach to improve diagnostic performance on darker skin types. We generated synthetic dark-skinned images to enhance dataset diversity and compared model performance before and after augmentation. The results demonstrate that augmentation with synthetic dermatological images can help reduce disparities in diagnostic performance across skin tones, highlighting a practical strategy for improving fairness in dermatology AI systems.

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.