Browse Articles

Although there has been great progress in the field of Natural language processing (NLP) over the last few years, particularly with the development of attention-based models, less research has contributed towards modeling keystroke log data. State of the art methods handle textual data directly and while this has produced excellent results, the time complexity and resource usage are quite high for such methods. Additionally, these methods fail to incorporate the actual writing process when assessing text and instead solely focus on the content. Therefore, we proposed a framework for modeling textual data using keystroke-based features. Such methods pay attention to how a document or response was written, rather than the final text that was produced. These features are vastly different from the kind of features extracted from raw text but reveal information that is otherwise hidden. We hypothesized that pairing efficient machine learning techniques with keystroke log information should produce results comparable to transformer techniques, models which pay more or less attention to the different components of a text sequence in a far quicker time. Transformer-based methods dominate the field of NLP currently due to the strong understanding they display of natural language. We showed that models trained on keystroke log data are capable of effectively evaluating the quality of writing and do it in a significantly shorter amount of time compared to traditional methods. This is significant as it provides a necessary fast and cheap alternative to increasingly larger and slower LLMs.

Here the authors present an autonomous drone air filtration system that uses a novel algorithm, the gradient ascent ML particle filter (GA/MLPF), to efficiently locate and mitigate outdoor air pollution. They demonstrate that their GA/MLPF algorithm is significantly more efficient than the conventional gradient ascent algorithm, reducing both the time and number of waypoints needed to find the source of pollution.

Arrhythmias vary in type and treatment, and ECGs are used to detect them, though human interpretation can be inconsistent. The researchers tested four tree-based algorithms (gradient boosting, random forest, decision tree, and extra trees) on ECG data from over 10,000 patients.

Enzyme chemotaxis is a thermodynamic phenomenon in which enzymes move along a substrate concentration gradient towards regions with higher substrate concentrations and can be used to steer nanovehicles towards targets along natural substrate concentrations. In patients with Alzheimer’s disease, a gradient of tau protein forms in the bloodstream. Tau protein is a substrate of the enzyme CDK5, which catalyzes the phosphorylation of tau protein and can travel using chemotaxis along tau protein gradients to increasing concentrations of tau and amyloid-beta proteins. The authors hypothesized that CDK5 would be able to overcome these barriers of Brownian motion and developed a quantitative model using Michaelis-Menten kinetics to define the necessary parameters to confirm and characterize CDK5’s chemotactic behavior to establish its utility in drug delivery and other applications.

The purpose of this study was to determine the necessity of previous non-algorithmic attacks (Adversarial Training) in light of algorithmic defense methods (Gradient Masking and Defensive Distillation) against FGSM attacks. We found a significant increase in image classification accuracy from defense methods with the non-algorithmic defense method compared to ones without. By analyzing the significance with a McNemar test, we determined that the inclusion of non-algorithmic defense methods is still necessary in light of new algorithmic defense methods.

This study explores the factors that influence coffee quality ratings using data from the Coffee Quality Institute. Through a regression model based on gradient descent, the authors aimed to predict coffee ratings (total cup points) and hypothesized that sweetness and the coffee producer would be the most influential factors.

This study explores how to predict and minimize distortion in 3D printed parts, particularly when using affordable PLA filament. The researchers developed a model using a gradient boosting regressor trained on 3D printing data, aiming to predict the necessary CAD dimensions to counteract print distortion.

The authors develop and test a machine learning algorithm for predicting diabetes diagnoses.

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.

This study used machine learning models to examine which factors most influenced U.S. household energy consumption in 2020 using data from 18,496 households.