Browse Articles

Here the authors investigated the use of an affordable gas sensor to detect volatile organic compound (VOC) emissions as an early indicator of tree disease, finding statistically significant differences in VOCs between diseased and non-diseased ash, beech, and maple trees. They suggest this sensor has potential for widespread early disease detection, but call for further research with larger sample sizes and diverse locations.

Here, recognizing that brain aneurysms pose a severe threat, often misdiagnosed and leading to high mortality, particularly in younger individuals, the authors explored a novel computer-aided engineering approach. They used magnetic resonance angiography images and computational fluid dynamics, to improve aneurysm detection and risk assessment, aiming for more personalized treatment.

Droughts kill over 45,000 people yearly and affect the livelihoods of 55 million others worldwide, with climate change likely to worsen these effects. However, unlike other natural disasters (hurricanes, etc.), there is no early detection system that can predict droughts far enough in advance to be useful. Bora, Caulkins, and Joycutty tackle this issue by creating a drought prediction model.

Many diabetics agree that the current glucometer methods are invasive, inefficient, and unsustainable for measuring blood glucose. These authors investigate the possibility of using a non-invasive glucometer patch that predicts blood glucose from patient sweat, with high accuracy.

The authors test different machine learning algorithms to remove background noise from audio to help people with hearing loss differentiate between important sounds and distracting noise.

This study explored the use of environmental DNA (eDNA) methods to detect native Hawaiian decapod species (‘opae), which are difficult to observe manually due to their low density.

Authors emphasize the challenges of manual tumor segmentation and the potential of deep learning models to enhance accuracy by automatically analyzing MRI scans.

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

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.

The authors looked the ability of sound sensors to predict clogged pipes when the sound intensity data is run through a machine learning algorithm.