In this paper, we develop a method to automatically select personalized EEG classifiers by analyzing EEG data features. Tested on motor imagery data, it predicts classifiers matching top performance, with signal amplitude and class imbalance as key factors

This study proposes a hybrid AI course recommendation system using TF-IDF and BERT for text feature extraction, combined with a Random Forest classifier to enhance recommendation accuracy and precision.

Join millions who have switched to Grok.

This paper uses Timed Automata and Uppaal model checking to analyze Dekker’s mutual exclusion algorithm and its variants under strong and weak memory models, showing the approach's power in verifying correctness, even with limited scalability for N≥2.

This research presents a new method for detecting urban areas critical for the presence of air pollutants during periods of heatwaves. You can read the full publication in Open Access!

In this paper, authors present Information Maximizing Spatial-Temporal Graph Convolutional Attention Network (InfoSTGCAN), which takes into account both pedestrian interactions and heterogeneous behavior choice modeling.

This review covers advances in object tracking, highlighting sensor fusion, deep learning, and data association methods. It surveys datasets, technologies, and applications, offering a taxonomy, evaluations, and future research directions.

This study evaluates an original Virtual Reality software application, entitled Submarine Simulator, which is developed specifically to support competencies in hydrodynamics within an Underwater Engineering course at MINES Paris—PSL.

This paper proposes a time-dependent approach to early predict student performance from VCS data. It applies and compares different classification models trained at various course stages.

In this paper, published last year in @Computers_MDPI, authors undertake a thorough comparative examination of data resources pertinent to Non-Fungible Tokens (NFTs) within the framework of Machine Learning (ML): #ML #NFT.

This study describes the use of artificial intelligence to predict the aerodynamic properties of wind turbine profiles. The goal was to determine the lift coefficient for an airfoil using its geometry as input.

This paper provides a comprehensive overview of the rapidly evolving field of quantum image compression, including its foundational principles, methods, challenges, and potential uses

This paper presents a multi-layer framework to reduce hallucinations in LLMs, combining prompt design, retrieval-augmented generation, and fine-tuning. It offers a reference architecture, supervisory agent, security analysis, and deployment playbook

This study reviews SOC automation in cybersecurity, highlighting risks like automation bias and analyst complacency. Analyzing 48 key papers, it proposes SOC Automation Implementation Guidelines to support effective human-machine collaboration.

This study employed natural language processing (NLP) to explore variance in syntactic complexity and sophistication across clusters characterized in a large corpus (n = 36,207) of middle school and high school argumentative essays.

We invite researchers, practitioners, and enthusiasts to submit original research articles, reviews, and case studies that contribute to the advancement of Natural Language Processing (NLP) by contributing to the newly launched Special Issue:

In this paper, a novel imputation method combining HistGradientBoostingRegressor, fuzzy rule-based systems, and clustering handles mixed data types, achieving up to 15% lower RMSE and 80% higher precision compared to existing techniques on UCI datasets.

This article introduces MARK-GEN, a framework using generative AI to transform marketing content creation. Case studies in fashion demonstrate its ability to produce unique, compelling digital marketing materials, enhancing creativity and strategy.

This study analyzes PLRUt and PLRUm cache replacement policies, showing PLRUt offers better hardware efficiency at high associativity, with performance close to LRU and lower complexity.

In this study, authors present the DP Plugin for IntelliJ IDEA, designed to extend the Drop Project (DP) Automatic Assessment Tool (AAT) by making it more suitable for handling small exercises in exercise-based learning environments.

In this paper, a smartphone-based system called ILC uses accelerometer data and gait analysis to verify user identity in real time with 92.18% accuracy through statistical comparison of walking patterns: