Browse Articles

Using machine learning to predict the risk of algae bloom

In 2021, over 20 million people died from cardiovascular diseases, highlighting the need for a deeper understanding of factors influencing heart failure outcomes. This study examined multiple variables affecting mortality after heart failure, using random forest models to identify time, serum creatinine, and ejection fraction as key predictors. These findings could contribute to personalized medicine, improving survival rates by tailoring treatment strategies for heart failure patients.

Here, the authors sought to investigate the effects of water current on the growth of colonies of duckweed, a floating plant that forms colonies in silent ponds, marshes, lakes , and streams in North America. They found that current flow mediates the formation of colonies, disrupting and recreating the colonies which provides the opportunity for reorganizations that were identified as beneficial.

In this study, the authors developed a model named DNA Sequence Embedding Network (DNA-SEnet) to classify DNA-asthma associations using their genomic patterns.

The authors developed a quantum inspired model for stock market fluctuations.

This study uses interpretable machine learning models, lasso and ridge regression with Shapley analysis, to identify key sales drivers for Corporación Favorita, Ecuador’s largest grocery chain. The results show that macroeconomic factors, especially labor force size, have the greatest impact on sales, though geographic and seasonal variables like city altitude and holiday proximity also play important roles. These insights can help businesses focus on the most influential market conditions to enhance competitiveness and profitability.

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

In this study, the authors tested the ability and accuracy of a neural net to identify patterns in complex number matrices.

Using facial recognition as a use-case scenario, we attempt to identify sources of bias in a model developed using transfer learning. To achieve this task, we developed a model based on a pre-trained facial recognition model, and scrutinized the accuracy of the model’s image classification against factors such as age, gender, and race to observe whether or not the model performed better on some demographic groups than others. By identifying the bias and finding potential sources of bias, his work contributes a unique technical perspective from the view of a small scale developer to emerging discussions of accountability and transparency in AI.

The "Uncanny Valley" is a phenomenon in which humans feel discomfort in the presence of objects that are almost, but not quite, human-like. In this study, the authors tested whether this phenomenon could be overcome by sharing a stressful experience with a humanoid robot. They found that human subjects more readily accepted a robot partner that they had previously shared a stressful experience with, suggesting a potential method for increasing the effectiveness of beneficial human-robot interactions by reducing the Uncanny Valley effect.