Full Description
The 3-volume set LNAI 14967, 14968, and 14969 constitutes the proceedings of the 23rd EPIA Conference on Artificial Intelligence, EPIA 2024, held in Viana do Castelo, Portugal, during September 3-6, 2024.
The 94 full papers presented in these proceedings were carefully reviewed and selected from 187 submissions. The papers are organized in the following topical sections:
Volume I:
AI and Creativity (AIC); Ambient Intelligence and Affective Environments (AmIA); Artificial Intelligence and IoT in Agriculture (AIoTA); Artificial Intelligence and Law (AIL); and Artificial Intelligence for Industry and Societies (AI4IS).
Volume II:
Artificial Intelligence in Medicine (AIM); Artificial Intelligence in Power and Energy Systems (AIPES); Artificial Intelligence in Transportation Systems (AITS); Ethics and Responsibility in AI (ERAI); and General AI (GAI).
Volume III:
Generative AI - Foundations and Applications (GenAI); Intelligent Robotics (IROBOT); Knowledge Discovery and Business Intelligence (KDBI); Natural Language Processing, Text Mining and Applications (TeMA); and Data-Centric AI - Solutions and Emerging Technologies (DCenAI).
Contents
Generative AI - Foundations and Applications (GenAI).- Large Language Model for Querying Databases in Portuguese.- A Novel Integration of Federated Learning and LSTM for Synthetic Time Series Generation.- Assessment on the Effectiveness of GitHub Copilot as a Code Assistance Tool: An Empirical Study.- AICIS: A System for Identifying AI Contribution in Textual Content.- Intelligent Robotics (IROBOT).- AIMSM - A Mechanism to Optimize Systems with Multiple AI Models: A Case Study in Computer Vision for Autonomous Mobile Robots.- Defect Detection in the Painting of Combustion Device Covers using the Deflectometry Method and YOLOv8.- Information-Oriented and Energy-Aware Path Planning for Small Unmanned Aerial Vehicles.- Pollinationbots - A Swarm Robotic System for Tree Pollination.- Knowledge Discovery and Business Intelligence (KDBI).- Extensible Data Ingestion System for Industry 4.0.- Next Location Prediction with Time-Evolving Markov Models over Data Streams.- Improving Fraud Detection with 1D-Convolutional Spiking Neural Networks through Bayesian Optimization.- A Benchmark of Automated Multivariate Time Series Forecasting Tools for Smart Cities.- A Data Drift Approach to Update Deployed Energy Prediction Machine Learning Models.- Optimising Dialogue Flow Discovery.- BI-Enabled Web Visualization of In-Place Inclinometer Data for Geotechnical Applications.- An Empirical Evaluation of DeepAR for Univariate Time Series Forecasting.- Natural Language Processing, Text Mining and Applications (TeMA).- Meta-prompting Optimized Retrieval-augmented Generation.- Pseudo-Semantic Graphs for Generating Paraphrases.- Compositionality and Ambiguity in Multiword Expressions: A Dataset for the Evaluation of Language Models in Galician.- Bypassing the Nuances of Portuguese Covert Hate Speech through Contextual Analysis.- Sequence Labeling for Pun Location and Detection in Portuguese.- Open Sentence Embeddings for Portuguese with the Serafim PT* Encoders Family.- WordNet Expansion with Bilingual Word Embeddings and Neural Machine Translation.- A Galician-Portuguese Generative Model.-Assessing the Trustworthiness of Large Language Models on Domain-specific Questions.- Data-Centric AI - Solutions and Emerging Technologies (DCenAI).- Lag Selection for Univariate Time Series Forecasting using Deep Learning: An Empirical Study.-Chatbot Decision Support with Intent-Rich Structures in the Hospitality Industry.- Meta TadGAN: Time Series Anomaly Detection Using TADGAN with Meta-Features.- Context-aware Deep Forecasting: Principles for the Nation-wide Management of Blood Products.
