Learning and Nonlinear Models最新文献_第3页

A Scalable Analytics Pipeline for COVID-19 Face Mask Surveillance COVID-19口罩监测的可扩展分析管道

Learning and Nonlinear Models Pub Date : 2022-10-13 DOI: 10.21528/lnlm-vol20-no1-art5

Clayton Kossoski, Gustavo Schaefer, Gianlucca Fiori Oliveira, Heitor Silvério Lopes

{"title":"A Scalable Analytics Pipeline for COVID-19 Face Mask Surveillance","authors":"Clayton Kossoski, Gustavo Schaefer, Gianlucca Fiori Oliveira, Heitor Silvério Lopes","doi":"10.21528/lnlm-vol20-no1-art5","DOIUrl":"https://doi.org/10.21528/lnlm-vol20-no1-art5","url":null,"abstract":"The COVID-19 coronavirus pandemic still causes a global health crisis. An effective protection method is using a face mask in public areas, according to the World Health Organization (WHO). Computer vision systems can be allies in monitoring public areas where the face mask is mandatory. However, face mask detection is challenging due to many factors, including diversity of people, facial features, head accessories, mask design, image position, and lighting changes. To tackle these issues, we present the following contributions: a new balanced face mask dataset named UTFPR-FMD1, consisting of 61,430 images splitted into “face” and “mask” classes; a transfer learning classification model for computer vision tasks, trained with our dataset; a new processing pipeline that allows face mask detection in video streams. Unlike available public datasets with imbalanced class distributions, the UTFPR-FMD1 contains images from different people, gender, and ages to minimize the training difficulty of deep learning models. We introduced a new measure to select valid images to perform inferences. Experimental results show the effectiveness of our model, outperforming the state-of-art methods for face mask detection tasks. Additionally, and different from other authors, we also present qualitative results. The system can detect heads with up to 60 degrees of rotation and process up to 10 FPS. In future work, we will deploy the current framework into production, perform tests in a near real-time environment, and extend it to process multiple video streams.","PeriodicalId":386768,"journal":{"name":"Learning and Nonlinear Models","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128073072","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

Linear Models Applied to Monthly Seasonal Streamflow Series Prediction 线性模型在月度季节流量序列预测中的应用

Learning and Nonlinear Models Pub Date : 2022-10-13 DOI: 10.21528/lnlm-vol20-no1-art4

J. Belotti, I. Luna, J. J. A. Mendes Junior, P. T. Asano, S. Stevan Jr., F. Trojan, H. Siqueira

{"title":"Linear Models Applied to Monthly Seasonal Streamflow Series Prediction","authors":"J. Belotti, I. Luna, J. J. A. Mendes Junior, P. T. Asano, S. Stevan Jr., F. Trojan, H. Siqueira","doi":"10.21528/lnlm-vol20-no1-art4","DOIUrl":"https://doi.org/10.21528/lnlm-vol20-no1-art4","url":null,"abstract":"Linear models are widely used to perform time series forecasting. The Autoregressive models stand out, due to their simplicity in the parameters adjustment based on close-form solution. The Autoregressive and Moving Average models (ARMA) and Infinite Impulse Response filters (IIR) are also good alternatives, since they are recurrent structures. However, their adjustment is more complex, since the problem has no analytical solution. This investigation performs linear models to predict monthly seasonal streamflow series, from to Brazilian hydroelectric plants. The goal is to reach the best achievable performance addressing linear approaches. We propose the application of recurrent models, estimating their parameters via an immune algorithm. To compare the optimization performance, the Least Mean Square (LMS) and Recursive Prediction Error (RPE) algorithms are utilized. Also, the AR model and the Holt-Winters method were performed. The results showed that the insertion of feedback loops increases the quality of the responses. The ARMA models optimized by the immune algorithms achieved the best overall performance.","PeriodicalId":386768,"journal":{"name":"Learning and Nonlinear Models","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123265332","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

A Nonlinear Optimized Hybrid System For Energy Consumption Forecasting From Smart Meters 智能电表能耗预测的非线性优化混合系统

Learning and Nonlinear Models Pub Date : 2022-10-13 DOI: 10.21528/lnlm-vol20-no1-art2

E. Alves, J. F. L. Oliveira, Francisco Madeiro Bernardino Junior, Manoel H. N. Marinho

{"title":"A Nonlinear Optimized Hybrid System For Energy Consumption Forecasting From Smart Meters","authors":"E. Alves, J. F. L. Oliveira, Francisco Madeiro Bernardino Junior, Manoel H. N. Marinho","doi":"10.21528/lnlm-vol20-no1-art2","DOIUrl":"https://doi.org/10.21528/lnlm-vol20-no1-art2","url":null,"abstract":"Smart grids are an alternative to minimize environmental impacts, such as CO2 emissions, and improve the efficiency of electricity consumption in buildings. Power grids enable adequate management and monitoring of consumption because of the periodic storage of measurements and easy access to them. In this scenario, an accurate prediction is a challenging task. Forecasting of consumption series is a defiant problem because data present linear and nonlinear patterns, and a dependence on external variables may be observed. Hybrid models are an alternative to mapping both patterns, which have been widely used to forecast load time series. Autoregressive Integrated Moving Average (ARIMA) and Support Vector Regression (SVR) models are used for this purpose, to map the linear and nonlinear patterns of the series, respectively. In this paper, a nonlinear optimized hybrid system based on ARIMA, SVR, and Particle Swarm Optimization (PSO) is proposed. The system can be divided into three steps. First, the linear patterns are predicted by the statistical model ARIMA. Then, the residual series is modeled using an optimized SVR, in which the parameters are selected from the PSO. One particularity from the proposal is to incorporate the choice of the topology and the inertia coefficient into the system. Lastly, the predictions are combined using the SVR. The simulations were conducted using a real database from smart meters of a building in Taiwan. To evaluate the performance of the proposed method, four related approaches were implemented and compared: a single ARIMA, two linear combination systems, and one non-linear combination system. The results show a superiority of the proposed method in terms of the metrics Mean Squared Error (MSE), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE).","PeriodicalId":386768,"journal":{"name":"Learning and Nonlinear Models","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121460441","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

Comparison Between Different Architectures of Multilayer Perceptron Networks for Blocking Rate Prediction in Mobile Phone Networks 手机网络阻塞率预测的多层感知器网络结构比较

Learning and Nonlinear Models Pub Date : 2022-10-13 DOI: 10.21528/lnlm-vol20-no1-art1

Gabriel da Silva Melo, B. A. Santos, R. M. Gomes

{"title":"Comparison Between Different Architectures of Multilayer Perceptron Networks for Blocking Rate Prediction in Mobile Phone Networks","authors":"Gabriel da Silva Melo, B. A. Santos, R. M. Gomes","doi":"10.21528/lnlm-vol20-no1-art1","DOIUrl":"https://doi.org/10.21528/lnlm-vol20-no1-art1","url":null,"abstract":"Blocking in mobile phone networks is a problem that consists of the refusal of the connection between a telephone device and a cell responsible for emitting the signal. The occurrence of blocking can indicate that a cell is close to congestion, leading to financial losses for telephone companies. This work developed three prediction systems using Multilayer Perceptron neural networks. Each system was modeled following different strategies: Direct, Recursive, and Direct Recursive, respectively. The training and test of the networks were carried out by using real data containing the history of blocking rates from a network of cells. The development stages consisted of analyzing the performance of each prediction system, varying the number of neurons in the hidden layers and the number of predicted steps from 1 (corresponding to 15 minutes ahead) to 20 (corresponding to 5 hours ahead). The system based on the Recursive strategy presented the lowest performance making predictions of short (15 minutes) and long (5 hours) terms with RMSE (Root Mean Squared Error) of approximately 13% and 40%, respectively, with a confidence interval between 27% and 29% considering all predictions. The systems based on the Direct and Direct Recursive strategies presented similar results, making predictions of short and long terms with RMSE of approximately 12% and 31%, respectively, with confidence intervals between 21% and 23% considering all predictions. Although the Direct and Direct Recursive systems obtained the lowest RMSE, the Direct Recursive is more advantageous as it requires fewer MLP networks. Consequently, it has simpler training and a lower computational cost.","PeriodicalId":386768,"journal":{"name":"Learning and Nonlinear Models","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131934331","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

Missing Data in Time Series: A Review of Imputation Methods and Case Study 时间序列中的缺失数据:归算方法综述与案例研究

Learning and Nonlinear Models Pub Date : 2022-10-13 DOI: 10.21528/lnlm-vol20-no1-art3

S. Ribeiro, C. Castro

引用次数: 0

Detection and Segmentation of Lungs Regions Using CNN Combined with Levelset 结合水平集的CNN肺区域检测与分割

Learning and Nonlinear Models Pub Date : 2021-12-31 DOI: 10.21528/lnlm-vol19-no1-art4

Pedro Cavalcante Sousa Júnior, L. F. D. F. Souza, J. C. Nascimento, Lucas de Oliveira Santos, A. G. Marques, Francisco Eduardo Sales Ribeiro, P. P. Rebouças Filho

引用次数: 1

Detection and Segmentation of Damaged Photovoltaic Panels Using Deep Learning and Fine-tuning in Images Captured by Drone 基于深度学习和微调的无人机图像损伤光伏板检测与分割

Learning and Nonlinear Models Pub Date : 2021-12-31 DOI: 10.21528/lnlm-vol19-no2-art1

L. F. D. F. Souza, T. M. Castro, L. D. O. Santos, A. G. Marques, J. C. Nascimento, Matheus Araujo dos Santos, G. F. B. Severiano, P. P. Rebouças Filho

{"title":"Detection and Segmentation of Damaged Photovoltaic Panels Using Deep Learning and Fine-tuning in Images Captured by Drone","authors":"L. F. D. F. Souza, T. M. Castro, L. D. O. Santos, A. G. Marques, J. C. Nascimento, Matheus Araujo dos Santos, G. F. B. Severiano, P. P. Rebouças Filho","doi":"10.21528/lnlm-vol19-no2-art1","DOIUrl":"https://doi.org/10.21528/lnlm-vol19-no2-art1","url":null,"abstract":"Energy consumption is a direct impact factor in various sectors of society. Different technologies for energy generation are based on renewable sources and used as alternatives to the consumption of finite resources. Among these technologies, photovoltaic panels represent an efficient solution for energy generation and an option for sustainable consumption. The problem of damaged panels brings numerous problems in energy generation, from the interruption of generation to losses through financial investments. The proposed study presents an efficient model based on deep learning for detection and different models based on fine-tuning for the segmentation of damaged photovoltaic panels. The use of the Detectron2 convolutional network obtained 78% of Accuracy for detection and 95% precision in the detectable panels, also obtaining 99.91% for the segmentation problem of photovoltaic panels in the best-generated model in this study. The proposed model showed great effectiveness for panel detection and segmentation, surpassing works found in the literature.","PeriodicalId":386768,"journal":{"name":"Learning and Nonlinear Models","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122274827","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

From MSE to Correntropy, a friendly survey 从MSE到Correntropy，一个友好的调查

Learning and Nonlinear Models Pub Date : 2021-12-31 DOI: 10.21528/lnlm-vol19-no1-art5

A. Martins

引用次数: 0

A Benchmark for Multi-Objective Routing in Vehicle Ad-Hoc Networks Using The Ant Colony Optimization Algorithm 基于蚁群优化算法的车辆自组织网络多目标路由基准

Learning and Nonlinear Models Pub Date : 2021-12-31 DOI: 10.21528/lnlm-vol19-no2-art2

Rodrigo Silva, H. S. Lopes

{"title":"A Benchmark for Multi-Objective Routing in Vehicle Ad-Hoc Networks Using The Ant Colony Optimization Algorithm","authors":"Rodrigo Silva, H. S. Lopes","doi":"10.21528/lnlm-vol19-no2-art2","DOIUrl":"https://doi.org/10.21528/lnlm-vol19-no2-art2","url":null,"abstract":"The growing number of vehicles in cities has a great impact on our quality of life, such as air and noise pollution, traffic jams and traffic accidents. Cooperative Intelligent Transportation System (C-ITS) relies on communication technologies to provide innovative services and applications for transportation and traffic management. In the C-ITS context, users, roadside infrastructure and vehicles need to be connected and, for this purpose, a wide variety of wireless technologies can be used (e.g, vehicular WiFi, cellular and visible light communication). In this work we consider a VANET (Vehicular Ad-hoc NETwork) using vehicular WiFi (based on 802.11p). The communications in VANET networks have been studied for years and several routing algorithms have been developed for such a kind of network. However, a benchmark to compare the performance of such algorithms is still lacking. To fill this gap, the present work proposes a benchmark composed by instances of data routing for different scenarios in the VANET. Moreover, we propose a multi-objective algorithm based on ACO (Ant Colony Optimization) to compare with such benchmark. The results of simulations show the impact of several factors in the VANET connectivity, such as vehicle density, geographical location, propagation and fading models. The results are promising and indicate the importance of choosing appropriated simulation models.","PeriodicalId":386768,"journal":{"name":"Learning and Nonlinear Models","volume":"166 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126277067","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

Sobre o Problema de Previsão da Covid-19 Utilizando Modelos Morfológico-Linear Profundos 关于使用深度形态线性模型预测Covid-19的问题

Learning and Nonlinear Models Pub Date : 2021-12-31 DOI: 10.21528/lnlm-vol19-no1-art3

R. D. A. Araújo

引用次数: 0