Results 41 to 50 of about 59,683 (118)

Transformer-Based Ensemble Learning for Symptom-Level Classification and DSM-5-Oriented Depression Screening on Social Media

Information
Depression screening from social media has increasingly benefited from transformer-based architectures; however, integrating symptom-level analysis with clinically grounded diagnostic screening remains challenging. This study proposes a unified two-phase
Jandara Suksam, Piya Kaewbuadee, Chatklaw Jareanpon   +2 more
doaj   +1 more source

Probing Emergent World Representations in Go Life-and-Death Problems

AI
Large language models (LLMs) have demonstrated remarkable capabilities in learning complex tasks purely from sequential data. To explore whether such models can internalize strategic world representations, We investigate whether generative transformer ...
Zhikai Yang, Zhigang Meng, Zhiqiang Wen
doaj   +1 more source

An Empirical Study of Federated BERT for Decentralized Twitter Sentiment Analysis

Informatics
Twitter/x has become a key platform for analyzing public opinion on a large scale; however, traditional centralized approaches raise significant concerns regarding privacy and data governance. To address these challenges, this paper presents an empirical
Oumaima Louzar, Abdelaziz Elbaghdadi, Ahmed El Oualkadi, Ouafae Baida, Abdelouahid Lyhyaoui   +4 more
doaj   +1 more source

CROSS-LINGUAL TRANSFORMER-BASED SCREENING OF POST-TRAUMATIC STRESS DISORDER BASED ON COMPARATIVE ANALYSIS OF BERT AND XLM-ROBERTA WITH MACHINE TRANSLATION ADAPTATION FOR UKRAINIAN LANGUAGE

Компютерні системи та інформаційні технології
The paper presents a comprehensive study on automated screening of post-traumatic stress disorder (PTSD) using transformer-based natural language processing models in a cross-lingual setting.
Андрій ФЕДОРИЧКО, Вікторія ВИСОЦЬКА, Любомир ЧИРУН   +2 more
doaj   +1 more source

Temporal Windowed and Internal Feature (TWIF) Transformer for Attack Detection in Robotics

IEEE Access
Ensuring cybersecurity in robotic systems is critically important, as successful attacks can not only disrupt operations but also cause significant physical damage and safety risks, distinguishing robotics from traditional Information Technology ...
Esra Nergis Yolacan, Hande Cavsi Zaim
doaj   +1 more source

Leveraging Transfer Learning for Hate Speech Detection in Portuguese Social Media Posts

IEEE Access
The rapid rise of social media has brought about new ways of digital communication, along with a worrying increase in online hate speech (HS), which, in turn, has led researchers to develop several Natural Language Processing methods for its detection ...
Gil Ramos, Fernando Batista, Ricardo Ribeiro, Pedro Fialho, Sergio Moro, Antonio Fonseca, Rita Guerra, Paula Carvalho, Catarina Marques, Claudia Silva   +9 more
doaj   +1 more source

Improving attention mechanisms in transformer architecture in image restoration

Компьютерная оптика
We discuss a problem of improving the quality of images obtained under the influence of various kinds of noise and distortion. In this work we solve this problem using transformer neural network models, because they have recently shown high efficiency in
N.I. Berezhnov, A.A. Sirota
doaj   +1 more source

Advanced AI and Machine Learning Techniques for Time Series Analysis and Pattern Recognition

Applied Sciences
Time series analysis and pattern recognition are cornerstones for innovation across diverse domains. In finance, these techniques enable market prediction and risk assessment.
Antonio Pagliaro, Antonio Alessio Compagnino, Pierluca Sangiorgi   +2 more
doaj   +1 more source

RADAR#: An Ensemble Approach for Radicalization Detection in Arabic Social Media Using Hybrid Deep Learning and Transformer Models

Information
The recent increase in extremist material on social media platforms makes serious countermeasures to international cybersecurity and national security efforts more difficult.
Emad M. Al-Shawakfa, Anas M. R. Alsobeh, Sahar Omari, Amani Shatnawi   +3 more
doaj   +1 more source

Enhancing Text Classification Through Grammar-Based Feature Engineering and Learning Models

Information
Text classification remains a challenging task in natural language processing (NLP) due to linguistic complexity and data imbalance. This study proposes a hybrid approach that integrates grammar-based feature engineering with deep learning and ...
Alaa Mohasseb, Andreas Kanavos, Eslam Amer   +2 more
doaj   +1 more source