Browse Articles

Triggered largely by the warming and pollution of oceans, corals are experiencing bleaching and a variety of diseases caused by the spread of bacteria, fungi, and viruses. Identification of bleached/diseased corals enables implementation of measures to halt or retard disease. Benthic cover analysis, a standard metric used in large databases to assess live coral cover, as a standalone measure of reef health is insufficient for identification of coral bleaching/disease. Proposed herein is a solution that couples machine learning with crowd-sourced data – images from government archives, citizen science projects, and personal images collected by tourists – to build a model capable of identifying healthy, bleached, and/or diseased coral.

The authors looked at using machine learning to identify skills needed to apply for certain jobs, specifically looking at different techniques to parse apart the text. They found that Bidirectional Encoder Representation of Transforms (BERT) performed best.

Sequence accessibility is an important factor affecting gene expression. Sequence accessibility or openness impacts the likelihood that a gene is transcribed and translated into a protein and performs functions and manifests traits. There are many potential factors that affect the accessibility of a gene. In this study, our hypothesis was that the content of nucleotides in a genetic sequence predicts its accessibility. Using a machine learning linear regression model, we studied the relationship between nucleotide content and accessibility.

In this article the authors looked at different attributes of apps within the Google Play store to determine how those may impact the overall app rating out of five stars. They found that review count, amount of storage needed and when the app was last updated to be the most influential factors on an app's rating.

Auto-Regressive Integrated Moving Average (ARIMA) models are known for their influence and application on time series data. This statistical analysis model uses time series data to depict future trends or values: a key contributor to crime mapping algorithms. However, the models may not function to their true potential when analyzing data with many different patterns. In order to determine the potential of ARIMA models, our research will test the model on irregularities in the data. Our team hypothesizes that the ARIMA model will be able to adapt to the different irregularities in the data that do not correspond to a certain trend or pattern. Using crime theft data and an ARIMA model, we determined the results of the ARIMA model’s forecast and how the accuracy differed on different days with irregularities in crime.

Emissions from oil and natural gas (O&G) wells such as nitrogen dioxide (NO₂), volatile organic compounds (VOCs), and ozone (O₃) can severely impact the health of communities located near wells. In this study, we used O&G activity and wind-carried emissions to quantify the extent to which O&G wells affect the air quality of nearby communities, revealing that NO₂, NO_x, and NO are correlated to O&G activity. We then developed a novel land use regression (LUR) model using machine learning based on O&G prevalence to predict emissions.

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.

Additive manufacturing (AM) is transforming the production of complex metal parts, but challenges like internal cracking can arise, particularly in critical sectors such as aerospace and automotive. Traditional methods to assess cracking susceptibility are costly and time-consuming, prompting the use of machine learning (ML) for more efficient predictions. This study developed a multi-model ML pipeline that predicts solidification cracking susceptibility (SCS) more accurately by considering secondary alloy properties alongside composition, with Random Forest models showing the best performance, highlighting a promising direction for future research into SCS quantification.

The purpose of our study was to examine the correlation of glycosylated hemoglobin (HbA1c), blood pressure (BP) readings, and lipid levels with retinopathy. Our main hypothesis was that poor glycemic control, as evident by high HbA1c levels, high blood pressure, and abnormal lipid levels, causes an increased risk of retinopathy. We identified the top two features that were most important to the model as age and HbA1c. This indicates that older patients with poor glycemic control are more likely to show presence of retinopathy.

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.