Full Description
The four-volume set LNAI 15412-15415 constitutes the refereed proceedings of the 34th Brazilian Conference on Intelligent Systems, BRACIS 2024, held in Belém do Pará, Brazil, during November 18-21, 2024.
The 116 full papers presented here were carefully reviewed and selected from 285 submissions. They were organized in three key tracks: 70 articles in the main track, showcasing cutting-edge AI methods and solid results; 10 articles in the AI for Social Good track, featuring innovative applications of AI for societal benefit using established methodologies; and 36 articles in other AI applications, presenting novel applications using established AI methods, naturally considering the ethical aspects of the application.
Contents
.- Main Track.
.- A Contrastive Objective for Training Continuous Generative Flow Networks.
.- A Data Distribution-based Ensemble Generation Applied to Wind Speed Forecasting.
.- A Large Dataset of Spontaneous Speech with the Accent Spoken in Sao Paulo for Automatic Speech Recognition Evaluation.
.- A Multi-Level Semantics Formalism for Multi-Agent Microservices.
.- A Novel Genetic Algorithm Approach for Discriminative Subspace Optimization.
.- A Performance Increment Strategy for Semantic Segmentation of Low-Resolution Images from Damaged Roads.
.- A Unified Framework for Average Reward Criterion and Risk.
.- Adaptive Client-Dropping in Federated Learning: Preserving Data Integrity in Medical Domains.
.- An Ensemble of LLMs finetuned with LoRA for NER in Portuguese legal documents.
.- An instance level analysis of classification difficulty for unlabeled data.
.- Analyzing the Impact of Coarsening on k-Partite Network Classification.
.- Applying Transformers for Anomaly Detection in Bus Trajectories.
.- Aroeira: A Curated Corpus for the Portuguese Language with a Large Number of Tokens.
.- Assessing Adversarial Effects of Noise in Missing Data Imputation.
.- Assessing European and Brazilian Portuguese LLMs for NER in specialized domains.
.- BASWE: Balanced Accuracy-based Sliding Window Ensemble for Classification in Imbalanced Data Streams with Concept Drift.
.- Beyond Audio Signals: Generative Model-Based Speaker Diarization in Portuguese.
.- Classification of Non-Alcoholic Hepatic Steatosis in Liver Thermal Imaging Using Siamese Neural Network.
.- Classifying graphs of elementary mathematical functions using Convolutional Neural Networks.
.- Comparing Neural Network Encodings for Logic-based Explainability.
.- Deep learning approach to temporal dimensionality reduction of volumetric computed tomography.
.- Deployment of IBM Federated Learning Platform and Aggregation Algorithm Comparison: A Case Study Using the MNIST Dataset.
.- Detection of Pathological Regions of the Gastrointestinal Tract in Capsule Images Using EfficientNetV2 and YOLOv8.
.- Dual-Bandwidth Spectrogram Analysis for Speaker Verification.
.- Dynamicity Analysis in the Selection of Classifier Ensembles Parameters.
.- Embedding Representations for AutoML Pipelines.
.- Enhancing Graph Data Quality by Leveraging Heterogeneous Node Features and Embeddings.
.- Ensemble of CNNs for Enhanced Leukocyte Classification in Acute Myeloid Leukemia Diagnosis.
.- ERASMO: Leveraging Large Language Models for Enhanced Clustering Segmentation.
.- Euclidean Alignment for Transfer Learning in Multi-band Common Spatial Pattern.
.- Evaluating CNN-Based Classification Models Combined with the Smoothed Pseudo Wigner-Ville Distribution to Identify Low Probability of Interception Radar Signals.
.- Evaluating Large Language Models for Tax Law Reasoning.
.- Explaining Biomarker Response to Anticoagulant Therapy in Atrial Fibrillation: A Study of Warfarin and Rivaroxaban with Machine Learning Models.
