Browse Articles

Improving the classifier of the difficulty level of Sudoku.

Depression affects millions globally, yet identifying symptoms remains challenging. This study explored detecting depression-related patterns in social media texts using natural language processing and machine learning algorithms, including decision trees and random forests. Our findings suggest that analyzing online text activity can serve as a viable method for screening mental disorders, potentially improving diagnosis accuracy by incorporating both physical and psychological indicators.

Authors examine the effectiveness of Large Language Models (LLMs) like BERT, MathBERT, and OpenAI GPT-3.5 in assisting middle school students with math word problems, particularly following the decline in math performance post-COVID-19.

Utilization of neural network to analyze Free Word Association to predict accurately age, gender, first language, and current country.

AI analysis of brain scans offers promise for helping doctors diagnose brain tumors. Haider and Drosis explore this field by developing machine learning models that classify brain scans as "cancer" or "non-cancer" diagnoses.

Dust accumulation on solar panels can reduce electricity output by 20–50%, posing a major challenge for solar energy collection. Instead of altering panel design, we explored a simpler approach by modifying surface energy through nanotexturing, predicting that hydrophobic surfaces would repel both water and dust. This study found that treating glass and silicone surfaces with potassium hydroxide (KOH) for 13 and 10 minutes, respectively, created optimal nanotextures (445 nm for glass, 205 nm for silicone), significantly reducing dirt accumulation and improving solar energy capture.

As atmospheric carbon dioxide (CO₂) levels rise, ocean acidification poses a growing threat to marine ecosystems. To better understand these changes, this study investigates how varying CO₂ levels influence the growth of brine shrimp. The findings offer important insights into the resilience of aquatic life and the broader implications of environmental change.

This article describes the classification of medical text data using vector databases and text embedding. Various large language models were used to generate this medical data for the classification task.

Here the authors investigated the effects of natural coagulants on reducing the turbidity of water samples from the Tennessee River Watershed. They found that turbidity reduction was higher at lower temperatures for eggshells. They then projected and mapped turbidity reactions under two climate change scenarios and three future time spans for eggshells. They found site-specific and time-vary turbidity reactions using natural coagulants could be useful for optimal water treatment plans.

The authors looked at different models of semantic segmentation to determine which may be best used in the future for segmentation of CT scans to help diagnose certain conditions.