Artificial Intelligence: Methodology, Systems, and Applications

This book constitutes the refereed proceedings of the 19th International Conference on Artificial Intelligence: Methodology, Systems, and Applications, AIMSA 2024, held in Varna, Bulgaria, during September 1820, 2024.

The 18 revised full papers presented in this book were carefully reviewed and selected from 23 submissions. They cover a wide range of topics in AI and its applications: natural language processing, sentiment analyses, image processing, optimization, reinforcement learning, from deep ANNs to spike timing NNs, applications in economics, medicine and process control.

Inhalt

1 Multimodal Sentiment Analysis: Recognizing Sentiment in Memes.- Remote Sensing Data for Predicting Crop Growth.- Cross-lingual Style Transfer TTS for High-quality Machine Dubbing.- An Approach to Discovering, Tracking over Time, and Summarizing Publicly Available Information on a Given Topic.- Reinforcement Learning Control of Cart Pole System with Spike Timing Neural Network Actor-critic Architecture.- Predictive and Explainable Modelling in Economics on the Case Study of Remittance Prediction Using the NeuDen AI Computational Architecture.- Deep Learning for Multi-class Diagnosis of Thyroid Disorders using Selective Features.- Medical Ultrasound Image Quality Assessment using Deep Learning.- Testing the NEAT Algorithm on a PSPACE-Complete Problem.- Investigating the Regularization of Deep Neural Networks for Affect Recognition with Relevance-Guided Local Explanations.- Layered Data-Centric AI to Streamline Data Quality Practices for Enhanced Automation.- Combining Graph NN and LLM for Improved Text-based Emotion Recognition.- A Novel Study on Modelling and Adaptive Optimal Control of a Tubular Reactor Based on Gaussian Processes.- Converging Dimensions: Information Extraction and Summarization through Multisource, Multimodal, and Multilingual Fusion.- Enhancing Question Answering in Lecture Videos with a Multimodal Retrieval Augmented Generation Framework.- Agent-based Simulation Leveraging Declarative Modeling for Efficient Resource Allocation in Emergency Scenarios.- Enhancing Security in Federated Learning: Detection of Synchronized Data Poisoning Attacks.- 3 Clinical and Acquisition Data for Optimizing MGMT Methylation Status Prediction: A Comprehensive Ensemble Strategy Emphasizing Non-Invasive Approaches.