Full Description
The three-volume set LNAI 14195, 14196, and 14197 constitutes the refereed proceedings of the 12th Brazilian Conference on Intelligent Systems, BRACIS 2023, which took place in Belo Horizonte, Brazil, in September 2023.
The 90 full papers included in the proceedings were carefully reviewed and selected from 242 submissions. They have been organized in topical sections as follows:
Part I: Best papers; resource allocation and planning; rules and feature extraction; AI and education; agent systems; explainability; AI models;
Part II: Transformer applications; convolutional neural networks; deep learning applications; reinforcement learning and GAN; classification; machine learning analysis;
Part III: Evolutionary algorithms; optimization strategies; computer vision; language and models; graph neural networks; pattern recognition; AI applications.
Contents
Embracing data irregularities in multivariate time series with Recurrent and Graph Neural Networks.- Regulation and Ethics of Facial Recognition Systems: an analysis of cases in the Court of Appeal in the State of São Paulo.- A combinatorial optimization model and polynomial time heuristic for a problem of finding specific structural patterns in networks.- Efficient Density-Based Models for Multiple Machine Learning Solutions over Large Datasets.- Exploring Text Decoding Methods for Portuguese Legal Text Generation.- Community Detection for Multi-Label Classification.- A Monte Carlo Algorithm for Time-Constrained General Game Playing.- Alpha-MCMP: trade-offs between probability and cost in SSPs with the MCMP criterion.- Specifying Preferences over Policies using Branching Time Temporal Logic.- Logic-based Explanations for Linear Support Vector Classifiers with Reject Option.- The Multi-Attribute Fairer Cover Problem.- A Custom Bio-Inspired Algorithm for the Molecular Distance Geometry Problem.- Allocating Dynamic and Finite Resources to a Set of Known Tasks.- A Multi-algorithm approach to the optimization of thermal power plants operation.- An incremental MaxSAT-based model to learn interpretable and balanced classification rules.- d-CC Integrals: generalizing CC-integrals by restricted dissimilarity functions with applications to fuzzy-rule based systems.- FeatGeNN: Improving Model Performance for Tabular Data with Correlation-based Feature Extraction.- Hierarchical Time-aware Approach for Video Summarization.- Analyzing college student dropout risk prediction in real data using walk-forward validation.- The artificial intelligence as a technological resource in the application of tasks for the development of joint attention in children with autism.- Machine teaching: an explainable machine learning model for individualized education.- BLUEX: a benchmark based on Brazilian Leading Universities Entrance eXams.- Towards Generating P-Contrastive Explanations for Goal Selection in extended-BDI Agents.- Applying Theory of Mind to Multi-Agent Systems: A Systematic Literature Review.- A Spin-off Version of Jason for IoT and Embedded Multiagent Systems.- Hybrid Multilevel Explanation: A new approach for explaining regression models.- Explainability of COVID-19 Classification Models using Dimensionality Reduction of SHAP values.- An explainable model to support the decision about the appropriate therapy protocol for AML.- Bayes and Laplace versus the world: A new label attack approach in federated environments based on Bayesian Neural Networks.- MAT-Tree: A Tree-based Method for Multiple Aspect Trajectory Clustering.
