Full Description
The two-volume set LNAI 13653 and 13654 constitutes the refereed proceedings of the 11th Brazilian Conference on Intelligent Systems, BRACIS 2022, which took place in Campinas, Brazil, in November/December 2022.
The 89 papers presented in the proceedings were carefully reviewed and selected from 225 submissions. The conference deals with theoretical aspects and applications of artificial and computational intelligence.
Contents
A Sequential Recommender System with Embeddings Based on GraphSage Aggregators.- Least-Squares Linear Dilation-Erosion Regressor trained using a Convex-Concave Procedure.- Exploration Versus Exploitation in Model-Based Reinforcement Learning: An Empirical Study.- BoVW-CAM: Visual Explanation from Bag of Visual Words.- Using BERT to predict the Brazilian Stock Market.- Human Action Recognition Based in 2D Poses and Skeleton Joints.- Self-learning methodology based on degradation estimation for underwater image enhancement.- When Less May Be More: Exploring Similarity to Improve Experience Replay.- Human Identification Based on Gait and Soft Biometrics.- Training Aware Sigmoidal Optimization.- Combining Convolutional and Attention Networks and a Color Classifier for Fire Detection.- A Study of Emergency Siren Recognition on Resource-Constrained Devices.- A probabilistically-oriented analysis of theperformance of ASR systems for Brazilian radios and tvs.- A Reward Function using Image Processing for a Deep Reinforcement Learning Approach Applied to The Sonic The Hedgehog Game.- Predicting Failures in HDDs with Deep NN and Irregularly-Sampled Data.- Protein Molecular Function Annotation based on Transformer Embeddings.- Event detection in therapy sessions for children with Autism.- On Social Consensus Mechanisms for Federated Learning Aggregation.- MegaLite-PT: A Corpus of Literature in Portuguese for NLP.- A Survey of Recent Advances on Two-Step 3D Human Pose Estimation.- Exploring Advances in Transformers and CNN for Skin Lesion Diagnosis on Small Datasets.- A comparative study of federated versus centralized learning for time series prediction in IoT.- A Hybrid System with Nonlinear Combination for Wind Speed Forecasting.- Detecting malicious HTTP requests without Log Parser using RequestBERT-BiLSTM.- Aiding glaucoma diagnosis from the automated classification and segmentation of fundus images.- Offline and online neural network learning in the context of smart homes and fog computing.- Improved Alternative Average Support Value for Automatic Ingredient Substitute Recommendation in Cooking Recipes.- Augmenting a Physics-Informed Neural Network for the 2D Burgers equation by addition of solution data points.- Impact of Morphological Segmentation on Pre-trained Language Models.- Learning Global Optimization by Deep Reinforcement Learning.- A frequency learning approach based on the Hartley transform for texture classification.- How Resilient are Imitation Learning Methods to Sub-Optimal Experts?.- To Answer or not to Answer? Filtering Questions for QA Systems.- Deep Learning-Based Abstractive Summarization for Brazilian Portuguese Texts.- Interact2Vec: Neural item and user embedding for collaborative filtering.- Deep Learning-Based COVID-19 Screening using Photographs of Chest X-Rays Displayed in Computer Monitors.- Artificial neural networks to analyze energy consumption and temperature of uav on-board computers executing algorithms for object detection.- FastContext: handling out-of-vocabulary words using the word structure and context.- Wrapper Approach for Video Anomaly Detection applying Light Gradient Boosting Machine in a Multiple Instance Learning Setting.- PAN RAM Bootstrapping Regressor - A new RAM-based architecture for regression problems.- ConveXplainer for graph neural networks.- Extreme Learning Machine to Graph Convolutional Networks.- Sequence Labeling Algorithms for Punctuation Restoration in Brazilian Portuguese Texts.- Neural architecture search applied to hybrid morphological neural networks.- Extending the Universal Approximation Theorem for a Broad Class of Hypercomplex-ValuedNeural Networks.
