Anais do XVI Congresso Brasileiro de Inteligência Computacional最新文献

Predição de Corrosão Atmosférica em Materiais Metálicos Utilizando Aprendizado de Máquina 利用机器学习预测金属材料的大气腐蚀性

Anais do XVI Congresso Brasileiro de Inteligência Computacional Pub Date : 2024-01-29 DOI: 10.21528/cbic2023-101

Vinicius Michelon Geremias, Thiago Brandenburg, Gustavo A. A. Fischer, F. Miranda, José Francisco Silva Filho, Rafael Parpinelli

引用次数: 0

Adaptive Radiation as an Autotuning Strategy for Genetic Algorithms on Dynamic Problems 自适应辐射作为动态问题遗传算法的自动调整策略

Anais do XVI Congresso Brasileiro de Inteligência Computacional Pub Date : 2024-01-25 DOI: 10.21528/cbic2023-050

H. Costa, Roberto Oliveira

{"title":"Adaptive Radiation as an Autotuning Strategy for Genetic Algorithms on Dynamic Problems","authors":"H. Costa, Roberto Oliveira","doi":"10.21528/cbic2023-050","DOIUrl":"https://doi.org/10.21528/cbic2023-050","url":null,"abstract":"As optimization processes have become more complex for embracing problems of different characteristics, it is necessary to have multiple adequate algorithms to tackle each of such problems. Bio-inspired evolutionary algorithms are suitable solutions for these situations, but they require re-tuning when working with different systems. Autotuning is a popular strategy to increase the adaptability of optimization algorithms. Adaptive Radiation (AR) is a phenomenon in nature that optimizes a population by diversity increase and niche specialization through intense mutation. This research aimed to insert this effect into the Genetic Algorithm (GA) workflow as a biological-inspired autotuning method, creating a new model called Genetic Algorithm with Adaptive Radiation (GAAR). The implementation of the AR component resulted in consistent and improved results on multiple benchmark functions from the CEC2019 challenge. The GAAR only changes the value of the AR component, which is enough to make this model achieve the best results in 57% of the tests and the worst results in 0% of the tests, while the Adaptive Particle Swarm Optimization (APSO) presented 39% and 12% of the best and worst results, respectively.","PeriodicalId":518335,"journal":{"name":"Anais do XVI Congresso Brasileiro de Inteligência Computacional","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530703","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Uma Função Objetivo para o Problema de Otimização do Projeto de Quantizadores Vetoriais Robustos 稳健矢量量化器设计优化问题的目标函数

Anais do XVI Congresso Brasileiro de Inteligência Computacional Pub Date : 2024-01-25 DOI: 10.21528/cbic2023-091

Wesley Santana, W. Lopes, Francisco Madeiro Bernardino Junior

引用次数: 0

Deep Learning and Satellite Images for Photovoltaic Power Forecasting: A Case Study 用于光伏发电预测的深度学习和卫星图像：案例研究

Anais do XVI Congresso Brasileiro de Inteligência Computacional Pub Date : 2024-01-24 DOI: 10.21528/cbic2023-120

Luiz Henrique Buzzi, Lucas Weihmann, Pablo Jaskowiak

{"title":"Deep Learning and Satellite Images for Photovoltaic Power Forecasting: A Case Study","authors":"Luiz Henrique Buzzi, Lucas Weihmann, Pablo Jaskowiak","doi":"10.21528/cbic2023-120","DOIUrl":"https://doi.org/10.21528/cbic2023-120","url":null,"abstract":"The growing demand for renewable energy resources presents a supply management challenge, as photovoltaic (PV) energy exhibits intermittent generation due to meteorological factors. The unpredictability of these variations leaves power grids vulnerable to instability, quality, and balance issues. In this context, accurate forecasting of PV power generation can improve management through generation planning, allowing for the balancing of different energy sources, which is crucial for achieving widespread PV energy adoption. The rapid development and significant advancements in deep learning present new possibilities for the use of satellite imagery in PV power forecasting. In this work we build and evaluate several deep learning models in the context of PV power forecasting, aiming at 30 and 60 minutes horizons. Our models are built for the prediction of the Global Horizontal Irradiance (GHI) component which, due to its strong correlation with PV power generation, can be employed not only to derive the actual PV plant output, but also as a measure generation potential, regardless of the actual PV plant. The models take as input images from the GOES-16 satellite and ground-based meteorological measurements, which are considered as desired outcomes. Several model configurations demonstrated the viability of GHI forecasting based on satellite imagery, with the best models achieving relative root mean squared errors (rRMSE) of 15.6% and 17.2% for 30-minute and 60-minute forecast horizons, respectively.","PeriodicalId":518335,"journal":{"name":"Anais do XVI Congresso Brasileiro de Inteligência Computacional","volume":"21 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530760","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Previsão de Geração de Energia Fotovoltaica Utilizando Transformação de Séries Temporais em Imagens e Redes Neurais Convolucionais 利用图像中的时间序列变换和卷积神经网络预测光伏发电量

Anais do XVI Congresso Brasileiro de Inteligência Computacional Pub Date : 2024-01-24 DOI: 10.21528/cbic2023-014

Diego Monteiro, Adriana Castro

{"title":"Previsão de Geração de Energia Fotovoltaica Utilizando Transformação de Séries Temporais em Imagens e Redes Neurais Convolucionais","authors":"Diego Monteiro, Adriana Castro","doi":"10.21528/cbic2023-014","DOIUrl":"https://doi.org/10.21528/cbic2023-014","url":null,"abstract":"Este artigo apresenta uma nova abordagem baseada em Rede Neural Convolucional Bidimensional (Convolutional Neural Network CNN) e Gráfico de Recorrência (Recurrence Plot RP) para previsão em curto prazo da geração de energia elétrica de uma microusina fotovoltaica conectada à rede elétrica, localizada no Centro de Excelência em Eficiência Energética da Amazônia - CEAMAZON, da Universidade Federal do Pará (UFPA). O gráfico de recorrência foi utilizado para transformação das séries temporais em imagens para serem utilizadas como entrada para a CNN. A previsão de geração de energia elétrica com maior precisão possibilita ao usuário conhecer com maior grau de acerto quais os possíveis custos para implantação da rede e os prazos para retorno financeiro, além de avaliar com maior assertividade a disponibilidade de carga que poderá ser conectada ao sistema. Os resultados da previsão com a utilização da CNN 2D e RP foram comparados com resultados utilizando outros tipos de rede neurais já consolidadas na área, tendo obtido valores RMSE satisfatórios, da ordem de 1,85% menor que o erro obtido com a Perceptron Multicamadas e 3,03% menor que o RMSE da CNN 1D, mostrando assim a sua aplicabilidade para o problema.","PeriodicalId":518335,"journal":{"name":"Anais do XVI Congresso Brasileiro de Inteligência Computacional","volume":"17 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Deep Learning-Based Ovitrap Spatial Dynamics Analysis for Arbovirus Vector Monitoring 基于深度学习的虫媒空间动态分析用于虫媒病毒监测

Anais do XVI Congresso Brasileiro de Inteligência Computacional Pub Date : 2024-01-23 DOI: 10.21528/cbic2023-056

Ignacio Sánchez-Gendriz, Matheus Diniz, A. D. Dória Neto, Rodrigo Moreira Pedreira, Ion Andrade, R. Valentim

{"title":"Deep Learning-Based Ovitrap Spatial Dynamics Analysis for Arbovirus Vector Monitoring","authors":"Ignacio Sánchez-Gendriz, Matheus Diniz, A. D. Dória Neto, Rodrigo Moreira Pedreira, Ion Andrade, R. Valentim","doi":"10.21528/cbic2023-056","DOIUrl":"https://doi.org/10.21528/cbic2023-056","url":null,"abstract":"Dengue is a significant global health issue, affecting millions of people annually and imposing substantial socioeconomic burdens. Effective disease control relies on monitoring the population of Aedes aegypti mosquitoes, the primary vector of dengue. One surveillance method involves counting the eggs laid by these mosquitoes in spatially distributed ovitraps. This study focuses on the application of computational methods to forecast dengue vector populations. We analyze a four-year (2016- 2019) database from 397 ovitraps distributed across Natal, RN, Brazil, with a weekly sampling frequency. Our objective is to develop accurate machine learning (ML) models that can predict the egg density index (EDI) at a fine-grained spatial resolution, aligned with zoonosis interventions. To preprocess the dataset obtained from the ovitraps, we employ spatial smoothing techniques and aggregation. The preprocessed data is then used to train ML models, including recurrent deep learning (DL) models, enabling accurate forecasting of the EDI. This approach shows promise for monitoring and preventing arbovirus outbreaks. Our findings demonstrate the effectiveness of spatial smoothing and aggregation as preprocessing steps for reducing randomness and noise in the dataset. The recurrent DL models exhibit high forecasting accuracy, thereby validating their utility in arbovirus monitoring and prevention efforts.","PeriodicalId":518335,"journal":{"name":"Anais do XVI Congresso Brasileiro de Inteligência Computacional","volume":"28 3-4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Rede neural artificial para predição de brucelose bovina a partir de dados desbalanceados 从非平衡数据中预测牛布氏杆菌病的人工神经网络

Anais do XVI Congresso Brasileiro de Inteligência Computacional Pub Date : 2024-01-23 DOI: 10.21528/cbic2023-108

Caio Donizetti Queiroz Alves, Danton Diego Ferreira, Danielle Fortunato, Christiane Rocha

{"title":"Rede neural artificial para predição de brucelose bovina a partir de dados desbalanceados","authors":"Caio Donizetti Queiroz Alves, Danton Diego Ferreira, Danielle Fortunato, Christiane Rocha","doi":"10.21528/cbic2023-108","DOIUrl":"https://doi.org/10.21528/cbic2023-108","url":null,"abstract":"The expressiveness of Brazilian livestock is unquestionable. According to data from the United States Department of Agriculture (USDA), in 2021 Brazil was the worlds largest exporter of beef. Bovine brucellosis is one of the most worrying diseases for the sector. In Brazil, bovine brucellosis causes annual losses of around 448 million dollars. Several factors threaten the establishment of actions of the current animal defense programs in Brazil, the main ones being: lack of distinct guidelines for the diagnosis of brucellosis cases, infected animals remain asymptomatic when infected, extensive Brazilian territory and large number of herds. The use of Artificial Neural Networks (ANNs) can be very useful in health and epidemiological surveillance services, helping to screen properties with different risks for the disease. The objective of this work is the development of ANN with class balancing techniques and selection of variables via genetic algorithm, for the classification and segregation of bovine herds, regarding seroprevalence for brucellosis. Five ANNs were designed combining different approaches of class balancing technique and variable selection, in order to compare which approach would perform better results. The results showed that ANN combined with the variable selection technique, via Genetic Algorithms, and class balancing, is a promising approach.","PeriodicalId":518335,"journal":{"name":"Anais do XVI Congresso Brasileiro de Inteligência Computacional","volume":"41 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140530884","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unsupervised Time Series Novelty Detection Using Clustering-based Local Autoencoders 使用基于聚类的本地自动编码器进行无监督时间序列新颖性检测

Anais do XVI Congresso Brasileiro de Inteligência Computacional Pub Date : 2024-01-22 DOI: 10.21528/cbic2023-172

Renan Albuquerque, G. Barreto

{"title":"Unsupervised Time Series Novelty Detection Using Clustering-based Local Autoencoders","authors":"Renan Albuquerque, G. Barreto","doi":"10.21528/cbic2023-172","DOIUrl":"https://doi.org/10.21528/cbic2023-172","url":null,"abstract":"Novelty detection, also known as anomaly detection, plays a crucial role in identifying new or abnormal instances within a dataset. Traditional autoencoder models have been effective in learning compact representations of data, but they often struggle with capturing fine-grained local variations in complex and high-dimensional datasets. To address this limitation, we propose a novel learning method called Local Autoencoders (LAEs) for novelty detection. LAEs incorporate local information into the encoding and decoding processes, enabling more precise and detailed reconstructions. In this paper, we present preliminary results on evaluation of LAEs considering benchmark datasets for time series novelty detection and compare their performance against traditional (i.e., global) autoencoder and nearest neighbor learning method. The results demonstrate LAEs competitive performance in detecting novel instances, surpassing (in several cases) traditional autoencoders. The proposed LAEs present a promising avenue for further exploration in the field of novelty detection, leading into new opportunities for research and practical applications.","PeriodicalId":518335,"journal":{"name":"Anais do XVI Congresso Brasileiro de Inteligência Computacional","volume":"319 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140531187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Análise de Desfechos de COVID-19 no RJ através de Técnicas de Aprendizado de Máquina 利用机器学习技术分析里约热内卢 COVID-19 结果

Anais do XVI Congresso Brasileiro de Inteligência Computacional Pub Date : 2024-01-22 DOI: 10.21528/cbic2023-072

J. Zavaleta, Robson Eduardo Silva, Fabiano Saldanha Oliveira, Luciane Velasque, Karla Figueiredo

引用次数: 0

Feature Extraction from EEG signals for detection of Parkinsons Disease 从脑电图信号中提取特征以检测帕金森病

Anais do XVI Congresso Brasileiro de Inteligência Computacional Pub Date : 2024-01-22 DOI: 10.21528/cbic2023-027

C. Souza, G. Viana, Bruno Coelho, Ana Beatriz Rodrigues Massaranduba, R. Ramos

引用次数: 0