In this paper, we measured the privacy budgets and utilities of different differentially private mechanisms combined with different machine learning models that forecast traffic congestion at future timestamps. We expected the ANNs combined with the Staircase mechanism to perform the best with every value in the privacy budget range, especially with the medium high values of the privacy budget. In this study, we used the Autoregressive Integrated Moving Average (ARIMA) and neural network models to forecast and then added differentially private Laplacian, Gaussian, and Staircase noise to our datasets. We tested two real traffic congestion datasets, experimented with the different models, and examined their utility for different privacy budgets. We found that a favorable combination for this application was neural networks with the Staircase mechanism. Our findings identify the optimal models when dealing with tricky time series forecasting and can be used in non-traffic applications like disease tracking and population growth.

This study uses a fruit fly model of type 1 diabetes (T1D) to determine whether strengthening intestinal tight junctions to reduce intestinal permeability would improve T1D symptoms.

In this study, the authors test different infill patterns to determine which would be the strongest and most durable for 3D printing applications, which have become an integral part of many facets of life.

This study uses neuroimaging to investigate cognitive set-shifting, a type of executive function that involves shifting from one task to another. This study tested whether cortical gray-white matter contrast in subregions of the prefrontal cortex (PFC) was associated with set-shifting abilities in adults.

In this study, the authors present proposed cryptographic controls for election sites with the hypothesis that this will mitigate risk and remediate vulnerabilities.

The authors found that SARIMAX-GARCH is more accurate than SARIMAX for load forecasting with respect to energy consumption.

With molecular energy being an integral element to the study of molecules and molecular interactions, computational methods to determine molecular energy are used for the preservation of time and resources. However, these computational methods have high demand for computer resources, limiting their widespread feasibility. The authors of this study employed machine learning to address this disadvantage, utilizing neural networks trained on different representations of molecules to predict molecular properties without the requirement of computationally-intensive processing. In their findings, the authors determined the Feedforward Neural Network, trained by two separate models, as capable of predicting molecular energy with limited prediction error.

The authors investigated prophages present in Streptococcus bacteria that may increase their survival in different environments.

Did the COVID-19 pandemic and travel restrictions improve air quality? The authors investigate this question in New York City using existing pollution data and forecasting trends.

Environment affects the progression of life, especially at the cellular level. This study investigates multiple 3-dimensional growth environments, also known as scaffolds or hydrogels, and their effect on the growth of a type of cells called fibroblasts. These results suggest that a scaffold made of collagen and polyethylene glycol are favorable for cell growth. This research is useful for developing implantable devices to aid wound healing.