In this report, Bhardwaj and Sharma tested whether placing specific plants indoors can reduce levels of indoor air pollution that can lead to lung-related illnesses. Using machine learning, they show that plants improved overall indoor air quality and reduced levels of particulate matter. They suggest that plant-based interventions coupled with sensors may be a useful long-term solution to reducing and maintaining indoor air pollution.

Coronary Artery Disease (CAD) is the leading cause of death in the United States, and 81% of Acute Kidney Injury (AKI) patients in the renal fibrosis stage later develop CAD. In this study, Mathew and Joykutty aimed to create a cost-effective strategy to treat AKI and thus prevent CAD using a model of the zebrafish, Danio rerio. They first tested whether AKI is induced in Danio rerio upon exposure to environmental toxins, then evaluated nitrotyrosine as an early biomarker for toxin-induced AKI. Finally, they evaluated 4 treatments of renal fibrosis, the last stage of AKI, and found that the compound SB431542 was the most effective treatment (reduced fibrosis by 99.97%). Their approach to treating AKI patients, and potentially prevent CAD, is economically feasible for translation into the clinic in both developing and developed countries.

In this study, the authors seek to improve a machine learning algorithm used for image classification: identifying male and female images. In addition to fine-tuning the classification model, they investigate how accuracy is affected by their changes (an important task when developing and updating algorithms). To determine accuracy, a set of images is used to train the model and then a separate set of images is used for validation. They found that the validation accuracy was close to the training accuracy. This study contributes to the expanding areas of machine learning and its applications to image identification.

Here the authors sought to use three machine learning models to predict poverty levels in Cambodia based on available household data. They found teat multilayer perceptron outperformed the other models, with an accuracy of 87 %. They suggest that data-driven approaches such as these could be used more effectively target and alleviate poverty.

Here, beginning from an initial interest in the possibility to use a computer to automatically solve a geometry diagram parser, the authors developed their own Fast Geometry Diagram Parser (FastGDP) that uses clustering and corner information. They compared their own methods to a more widely available, method, GeoSolver, finding their own to be an order of magnitude faster in most cases that they considered.

The death of George Floyd has shed light on the disproportionate level of policing affecting non-Whites in the United States of America. To explore whether non-Whites were disproportionately targetted by New York City's "Stop and Frisk" policy, the authors analyze publicly available data on the practice between 2003-2019. Their results suggest African Americans were indeed more likely to be stopped by the police until 2012, after which there was some improvement.

Reinforcement learning (RL) is a form of machine learning that can be harnessed to develop artificial intelligence by exposing the intelligence to multiple generations of data. The study demonstrates how reply buffer reward mechanics can inform the creation of new pruning methods to improve RL efficiency.

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.

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.

This study is centered around developing biofortification methods: the authors test whether the amount of calcium available to growing crops translates into more calcium present in the crops.