检索结果-内蒙古大学图书馆

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Juan Pereira Silva Jefferson Rafael Pereira De Assis Darlan Alexandria Fernandes Nady Rocha Alfeu J. Sguarezi Filho Graduate Program in Electrical Engineering (PPGEE) Federal University of Paraíba Joäo Pessoa / SENAI Amapá Brazil Department of Electrical Engineering Federal University of Campina Grande Campina Grande Brazil Department of Electrical Engineering Federal University of Paraíba João Pessoa Brazil Center for Eng. Model. and Appl. Soc. Sciences Federal University of ABC Santo André SP Brazil

This work presents different techniques for calculating predictors for the application of predictive control as a regulator system of an active power filter (APF), which supplies distorted current grid. From that, some performance criteria are analyzed for each presented method. Four discretization techniques were used: Euler's Backward, Trapezoidal, Centered Form, and TSA (two-step ahead). The APF has the function of eliminating the current harmonic components present in the electrical grid by injecting currents, thus mitigating distortions in the grid and improving the power factor of the installation. The mathematical modeling, discretization, and the development of predictive control algorithm are discussed and presented in simulation using the Simulink/MATLAB platform. The validation of the system was presented and carried out through real-time simulations in the OP5700 simulator from OPAL-RT Technologies.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effective Loss Function for Unbalanced Breast Thermal Image Segmentation

Effective Loss Function for Unbalanced Breast Thermal Image ...

引用

2021 International Conference on Computer System, Information Technology, and electrical engineering, COSITE 2021

作者： Roslidar, Roslidar Saddami, Khairun Irhamsyah, Muhammad Arnia, Fitri Syukri, Maimun Munadi, Khairul Universitas Syiah Kuala Doctoral Program Post Graduate Program School of Engineering Banda Aceh23111 Indonesia Universitas Syiah Kuala Department of Electrical and Computer Engineering Banda Aceh23111 Indonesia Universitas Syiah Kuala Medical Faculty Banda Aceh23111 Indonesia

ISBN: (纸本)9781665425094

The convolutional neural network's ability to learn images has reigned in computer vision tasks of object detection, classification, and segmentation. In segmentation, the CNN architectures of U-Net and SegNet have shown a good performance;thus, we implemented these networks to take the region of interest (ROI) of the breast thermal images from database for mastology research (DMR). We fine-tuned the networks to find the optimal hyperparameter that can result in the best learning performance. The networks were trained using the stochastic gradient descent optimization algorithm, and weights were updated using the error backpropagation of the algorithm. To minimize the error, the loss function is applied to evaluate a candidate solution of the weights. Thus, we conducted a preliminary study on finding the optimal loss function for breast thermal image segmentation. We applied loss functions of cross-entropy, dice, and focal and figured out the one that provides the highest segmentation accuracy. Then, to evaluate the segmentation result, we calculated the pixel accuracy rate and the dice coefficient to obtain the overlapping index measuring the overlay area between ground truth and predicted output. The result shows that the SegNet model with cross-entropy loss function can take the ROI of breast thermal images at the highest pixel accuracy and optimum dice coefficient of 0.8845 and 0.7928, respectively. © 2021 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Single-Phase Current Source Rectifier With Power Decoupling Using The X - Type CSC Topology

Single-Phase Current Source Rectifier With Power Decoupling ...

引用

Brazilian Power Electronics Conference, COBEP

作者： Montiê Alves Vitorino Lucas Vinícius de Araújo Gomes Graduate Program in Electrical Engineering (PPgEE-COPELE) Industrial Electronics and Machine Drive Laboratory (LEIAM) Federal University of Campina Grande (UFCG)

ISBN: (纸本)9781665421300

This work proposes a topology of X-Type Current Source Rectifier (X-type CSR) that helps to mitigate the effect of the double-the-line-frequency power ripple (low frequency) in the output of a single-phase rectifier. The low frequency ripple reduction allows to increase the converter power density by reducing the volume of the DC-bus inductor, without lack of stiffness at the DC-bus. The low frequency reduction is achieved by using a different single-phase CSR topology that uses the well known X-type CSC approach which allows reduction in conducting losses and independent control for two CSCs which share the same DC-bus and the middle switches of the leg. Details of topology, control strategy and modulation are presented. Simulation and experimental results for a 500W prototype are provided to validate the theoretical approach.

关键词： Legged locomotion Power system measurements Simulation Rectifiers Prototypes Power electronics Topology

来源：评论

学校读者我要写书评

暂无评论

Assessing uncertainty in wind turbine electrical power production using Monte-Carlo simulation: A case study on Sidrap wind turbine, Sulawesi - Indonesia

引用

AIP Conference Proceedings 2024年第1期3039卷

作者： Leonard Lisapaly Post Graduate Program Electrical Engineering Department Universitas Kristen Indonesia (UKI) Jakarta Indonesia

As the number of populations worldwide, including Indonesia, increases annually, the need for electrical energy also increases. With fossil-based energy starting to decrease in some places, and the global need to achieve net zero-emission, renewable energy is gaining popularity as the source of electrical power generation, for example, wind energy. electrical power generated from wind turbines is one of the popular choices in many countries; among them is the Sidrap wind turbine plant in Sulawesi, Indonesia. electrical power generated by a wind turbine relies on the wind speed, which varies from time to time and season to season. Therefore, building wind turbines plant should not be based on a deterministic wind speed but should bring the wind speed uncertainty into account. Taking the Sidrap wind turbine plant in Sulawesi, Indonesia, as the case study, this work aims to predict the plant’s average power and uncertainty. This calculation is done by implementing the Monte-Carlo simulation to calculate the production uncertainty. The data used for simulation is public data set between 2004 and 2015, obtained from the EMD International website. The simulation result is then compared to the actual production in 2018 and 2019 for analysis. The result indicates that the product is still in the range estimated using the Monte Carlo simulation. This method can also estimate other electrical power potential and uncertainty in an area before a wind turbine plant is built, given enough data sets containing wind speed variation for years. It is expected that by correctly understanding the uncertainty in electrical power production, the decision-making process to build the plant can be accurately determined.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Power Quality Evaluation in a Microgrid Implementation

Power Quality Evaluation in a Microgrid Implementation

引用

IEEE Annual Southern Power Electronics Conference (SPEC)

作者： Mariana N. Cunha e Silva Sidelmo Magalhaes Silva Igor Amariz Pires Graduate Program in Electrical Engineering (PPGEE) Federal University of Minas Gerais Belo Horizonte Brazil Federal University of Minas Gerais Belo Horizonte Brazil

ISBN: (纸本)9781665436243

The implementation of microgrids including distributed energy resources is an efficient energy solution with regard to saving financial and environmental resources and assisting in the stability and reliability of the power system. However, some unwanted effects such as voltage fluctuations, unbalance, frequency changes and harmonic distortions due to the Distributed Renewable Generations (DRGs) and non-linear loads operations may affect the power quality within the microgrid, making necessary studies and analyzes, to maintain the quality indicators at satisfactory levels. The power quality in systems with distributed generation (DG) is discussed in papers mostly through mathematical and computational modeling and these do not allow the consideration of equipment operation characteristics. It is therefore necessary to complement the theoretical studies with experimental results [1]. This study aims to evaluate the power quality at the connection point where a microgrid was installed on a university campus to characterize the energy scenario to which the microgrid will be submitted. It was found that the system had a monthly average of22.9 voltage sag events, 1.8 interruptions per month, 2.37% of total voltage harmonic distortion, 0.283% of voltage fluctuation, and unbalance below 0.5%.

关键词： Total harmonic distortion Voltage fluctuations Fluctuations Power quality Microgrids Power system stability Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Applied to a Sparse-Reward Trading Environment with Intraday Data

SSRN

引用

SSRN 2023年

作者： Takara, Lucas de Azevedo Alves Portela Santos, André Mariani, Viviana Cocco dos Santos Coelho, Leandro Department of Electrical Engineering PPGEE Federal University of Parana UFPR Avenida Coronel Francisco Herácito dos Santos Parana Curitiba81530–000 Brazil CUNEF Universidad Calle Almansa 101 Madrid28040 Spain Mechanical Engineering Graduate Program PPGEM Pontifical Catholic University of Parana PUCPR Imaculada Conceição Parana Curitiba80215–901 Brazil Industrial and Systems Engineering Graduate Program PPGEPS Pontifical Catholic University of Parana PUCPR Imaculada Conceição Parana Curitiba80215–901 Brazil

Deep reinforcement learning (DRL) achieved significant progress in several areas enabling computers to perform complex decision-making tasks. Applied to quantitative trading, DRL trading agents can optimize their decisions during distinct market scenarios to reach a profitable strategy by learning from previous experiences. This work proposes a trading system containing a variant of the Deep Q-Network (DQN) algorithm as its main component called Extended Trading DQN (ETDQN). It can adapt its learning to trade across numerous market-behavior moments, receiving feedback only when a trade is liquidaded, differently from recent approaches that provide constant feedback. Based on distributional learning and other independent extensions suggested by the DRL community, the algorithm optimizes its decision-making process by replaying prioritized experiences containing different sub-goals, assisting the agent in collecting the maximum value of profits and removing the need for fine-tuning rewards. ETDQN learned to trade on three distinct financial time series signals, identifying trading opportunities during volatile price moments. The algorithm showed more aggressive behavior regarding the volatility of its annual returns than the Trading DQN benchmark, achieving a 1.46 and 7.13 better performance with respect to average daily cumulative returns in Western Digital Corporation and Cosmos cryptocurrency historical market data. © 2023, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

ADHD Diagnosis through Resting-State EEG Frequency Analysis with Random Forest

ADHD Diagnosis through Resting-State EEG Frequency Analysis ...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Guilherme R. Pedrollo Leia B. Bagesteiro Alexandre R. Franco Alexandre Balbinot Post-Graduate Program in Electrical Engineering Universidade Federal do Rio Grande do Sul Porto Alegre Brazil Department of Kinesiology San Francisco State University San Francisco USA Child Mind Institute The Nathan Kline Institute for Psychiatric Research NYU Grossman School of Medicine New York USA

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Attention-deficit hyperactivity disorder (ADHD) affects about 5% of the population. In order to minimize ADHD effects, it is important to identify its biomarkers. We analyzed electroencephalographic (EEG) signals using a random forest (RF) classifier optimized with a genetic algorithm (GA) to find differences between control and ADHD groups. Data from 856 participants were analyzed with a preprocessing procedure that included artifact subspace reconstruction (ASR) and independent component analysis (ICA). After preprocessing and GA optimization, the RF classifier achieved 88.6% total average accuracy considering the theta frequency band. This outcome suggests that this approach has great potential as a biomarker analyzer for ADHD diagnosis.

关键词： Filters Quality control Independent component analysis Forestry Biomarkers Feature extraction Electroencephalography Optimization Genetic algorithms Classification tree analysis

来源：评论

学校读者我要写书评

暂无评论

Grid-Forming MMC: A Comparison between Single- and Dual-Loop Control Approaches 16

Grid-Forming MMC: A Comparison between Single- and Dual-Loop...

引用

16th Brazilian Power Electronics Conference, COBEP 2021

作者： Freitas, Cleiton M. Watanabe, Edson H. Monteiro, Luis F. C. Rio de Janeiro State University Dept. of Electrical Engineering Rio de Janeiro Brazil Federal University of Rio de Janeiro Electrical Engineering Program - COPPE Rio de Janeiro Brazil Rio de Janeiro State University Post-Graduate Prog. of Electronic Eng. Rio de Janeiro Brazil

ISBN: (纸本)9781665421294

This work presents an analysis of the grid-forming Modular Multilevel Converter (MMC), in the frequency domain, when it is controlled through single or dual-loop implementation. The dual-loop approach presents an inner current-loop control gathered with the external voltage-loop control, whereas the single-loop only presents a voltage-loop control for the grid-forming capability. In both cases, the control algorithms were implanted in a natural reference frame, including resonant controllers. The paper follows an impedance-modeling approach for introducing the analytical representation of the MMC in the frequency domain. These representations are, in fact, the linearized Teéenin-equivalent models of the single- and dual-loop grid-forming MMC. The results showed that the inner current-loop control is a feasible approach for damping specific resonant peaks of the Thevenin-equivalent impedance. In other words, the current-control loop adds a resistive parcel in MMC impedance in the frequency range in which the resonant peaks appear. As a consequence, the LC resonance between this impedance and the capacitor bank in the main bus is damped. The article also contains some switching-level EMTDC/PSCAD simulations to validate the work. © 2021 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Three-Phase Integrated PFC AC-AC Half-Bridge Boost Rectifier and Class D Resonant Inverter with Weak Coupled Coils for IH Application

Three-Phase Integrated PFC AC-AC Half-Bridge Boost Rectifier...

引用

Annual IEEE Conference on Applied Power Electronics Conference and Exposition (APEC)

作者： Ruan C. M. Gomes Montiê A. Vitorino Maurício B. R. Corrêa Post-Graduate Program in Electrical Engineering (PPgEE–COPELE) Federal University of Campina Grande (UFCG) Campina Grande PB Brazil

ISBN: (数字)9781728148298

ISBN: (纸本)9781728148304

This paper presents a three-phase integrated PFC AC-AC resonant inverter with boost effect for Induction Heating (IH) Application. This converter is composed by three independent half-bridge boost rectifier and class D resonant inverters with non-smoothed DC link that achieve high power factor operation. The magnetic coupling of the three coils was measured for characterizing the resonant behavior of the arrangement. Experimental results validate the modes of operation with ZVS and the converter performance in the entire power input range (PF and THD).

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of potential telemarketing customers predictions with a data mining approach using the MLPNN and RBFNN methods 2

Comparison of potential telemarketing customers predictions ...

引用

2nd International Conference on Information and Communications Technology, ICOIACT 2019

作者： Puteri, Annisa Nurul Dewiani Tahir, Zulkifli Post-graduate Program of Electrical Engineering Hasanuddin University Makassar Indonesia Dept. Electrical Engineering Hasanuddin University Makassar Indonesia Dept. Informatics Engineering Hasanuddin University Makassar Indonesia

ISBN: (纸本)9781728116556

Bank as a company that has many customers who conduct transactions every day, of course, has data that is increased continuously. In this paper, customer transaction data has been predicted to find potential customers in deposit offer. Data mining approach has been performed to classify potential customers for marketing through telemarketing. This data analysis can be used as a consideration in determining marketing strategy decisions for marketing managers. 15,713 data with 13 class attributes and 1 target class were obtained from UCI Machine Learning repository. The data was divided into 70% training data and 30% test data. Feedforward method of Artificial Neural Network was used to classify customer data. Multilayer Perceptron Neural Network and Radial Basis Function Neural Network were used to obtain optimal classification results. The result of this classification predicted potential customers to subscribe deposits. The result of this study indicated that the Radial Basis Function Neural Network method with 95.3% accuracy and 96.4% sensitivity was a better method compared to the Multilayer Perceptron Neural Network method with 88.0% accuracy and 99.4% sensitivity. © 2019 IEEE

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：