Browse Articles

Autonomous drone imaging combined with machine learning offers a promising approach for early detection of invasive species. In this study, students built an autonomous drone and compared three models: CNN, SGDC, and XGBoost, to identify Brassica nigra from aerial footage. Their results show that CNNs most effectively recognize key visual features, demonstrating strong potential for supporting conservation and invasive plant management.

A bottleneck in deleting algal blooms is that current data section is manual and is reactionary to an existing algal bloom. These authors made a custom-designed Seek and Destroy Algal Mitigation System (SDAMS) that detects harmful algal blooms at earlier time points with astonishing accuracy, and can instantaneously suppress the pre-bloom algal population.

Despite the prevalence of PD, diagnosing PD is expensive, requires specialized testing, and is often inaccurate. Moreover, diagnosis is often made late in the disease course when treatments are less effective. Using existing voice data from patients with PD and healthy controls, the authors created and trained two different algorithms: one using logistic regression and another employing an artificial neural network (ANN).

The authors investigate how well AI-detection machine learning models can detect real versus AI-generated art across different art styles.

In this study, the authors study features of exoplanet 189733 b. This exoplanet, or planets that orbit stars other than the Sun, is found in the HD star system. Using a DSLR camera, they constructed a high caliber exoplanet transit detection tracker to study the orbital periods, radial velocity, and photometry of 189733 b. They then compared results from their system to data collected by other high precision studies. What they found was that their system produced results supporting previously published studies. These results are exciting results from the solar system demonstrating the importance of validating radial velocity and photometry data using high-precision studies.

Currently there is no early dehydration detection system using temperature and pH as indicators. A sensor could alert the wearer and others of low hydration levels, which would normally be difficult to catch prior to more serious complications resulting from dehydration. In this study, a protein fluorophore, green fluorescent protein (GFP), and a chemical fluorophore, fluorescein, were tested for a change in fluorescence in response to increased temperature or decreased pH. Reversing the pH change did not restore GFP fluorescence, but that of fluorescein was re-established. This finding suggests that fluorescein could be used as a reusable sensor for a dehydration-related pH change.

The authors combine fine needle aspiration biopsy and machine learning algorithms to develop a breast cancer detection method suitable for resource-constrained regions that lack access to mammograms.

The authors use machine learning to develop an evidence-based detection tool for identifying human trafficking.

Intelligent vehicles utilize a combination of video-enabled object detection and radar data to traverse safely through surrounding environments. However, since the most momentary missteps in these systems can cause devastating collisions, the margin of error in the software for these systems is small. In this paper, we hypothesized that a novel object detection system that improves detection accuracy and speed of detection during adverse weather conditions would outperform industry alternatives in an average comparison.

The authors compare neuroimaging datasets to identify potential new biomarkers for earlier detection of Alzheimer's disease.