Browse Articles

The authors develop and test a machine learning algorithm for predicting diabetes diagnoses.

Spinal degeneration has been linked to critical conditions such as osteoarthritis in adults aged 40+; while this condition is considered to be irreversible, we took interest in magnetic resonance imaging (MRI) for early detection of the condition. Ultimately, our purpose was to determine the effectiveness of a relatively novel T1rho method in the early detection of spinal degeneration, and we hypothesized that the early to mild progression of spinal degeneration would affect T1rho values following an MRI scan.

The authors use pictures of candy wrappers and neural networks to improve nutritional accuracy of diet-tracking apps.

This article describes the relationship between socioeconomic factors and the extent of how the COVID-19 Pandemic affected communities. Factors such as infection rate, vaccination rate, and economic status were all evaluated within the context of this article.

Several studies have applied different machine learning (ML) techniques to the area of forecasting solar photovoltaic power production. Most of these studies use weather data as inputs to predict power production; however, there are numerous practical issues with the procurement of this data. This study proposes models that do not use weather data as inputs, but rather use past power production data as a more practical substitute to weather-based models. Our proposed models demonstrate a better, cheaper, and more reliable alternatives to current weather models.

Food spoilage happens when food is not kept in a good storage condition. Qualitatively estimating the shortened shelf life of food could reduce food waste. In this study, we tested the impact of heat on milk shelf life. Our results showed that an exposure at room temperature (25°C) for 3.2 hours will decrease the shelf life of milk by one day.

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

In this study, the authors developed and assessed the accuracy of a machine learning algorithm to identify skin cancers using images of biopsies.

Here, seeking to better understand the roles of glycans in the receptors of active sites of neuronal cells, the authors used molecular dynamics simulations to to uncover the dynamic nature of N-glycans on membrane proteins. The authors suggest the study of theinteractions of these membrane poreins could provide future potential therapeutic targets to treat mental diseases.

Using a convolution neural network, these authors show machine learning can clinically diagnose breast cancer with high accuracy.