检索结果-内蒙古大学图书馆

Black Start and Grid Synchronization Effect Study on GFM IBR-based Power system

Transactions of the Korean Institute of Electrical Engineers 2023年第3期72卷 349-355页

作者： Kim, Dong-Hwi Jang, Jung-Soo Hur, Jin Jung, Seungmin Yoon, Minhan Dept. of Electrical Engineering Kwangwoon University Korea Republic of Dept. of Energy System Engineering Ewha Womans University Korea Republic of Dept. of Electrical Engineering Hanbat National University Korea Republic of

The increasing use of inverter-based resources, while reducing synchronous generators, decreases the system's inertia, leading to an increased risk of power outages. The shift from a centralized power generation structure to a decentralized structure can be effective for stable operation of inverter-based power generation sources and to mitigate the risks of power outages. The grid forming inverter can perform the same role as a synchronous generator and can contribute to energizing primary restorative transmission systems. Grid-forming inverters must meet several requirements to replace synchronous generators in power systems. One of the most important requirements is the ability to operate as AC voltage sources. This means that the grid-forming inverter must be able to provide a stable AC voltage to the grid, just like a synchronous generator. To address this, a black start study using inverter resources was conducted, and a pumping generator-IBR cooperative black start was simulated through cooperation with an existing black start resource. The paper proposed the grid-synchronization method of grid-forming inverter and emphasizes the need for independent and quick recovery of inverter resources, which must operate as AC voltage sources to replace synchronous generators and contribute the primary power system restoration. The effectiveness of the proposed method to increase the input capacity and speed by stably inputting through synchronization has been studied and were verified through PSCAD/EMTDC simulation. Copyright © The Korean Institute of Electrical Engineers.

关键词： Outages

来源：评论

学校读者我要写书评

暂无评论

Controlled Dropout for Uncertainty Estimation

Controlled Dropout for Uncertainty Estimation

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Hasan, Mehedi Hossain, Ibrahim Rahman, Ashikur Nahavandi, Saeid Institute for Intelligent Systems Research and Innovation Deakin University GeelongVIC3220 Australia Bangladesh University of Engineering and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350337020

Uncertainty quantification in a neural network is one of the most discussed topics for safety-critical applications. Though Neural Networks (NNs) have achieved state-of-the-art performance for many applications, they still provide unreliable point predictions, which lack information about uncertainty estimates. Among various methods to enable neural networks to estimate uncertainty, Monte Carlo (MC) dropout has gained much popularity in a short period due to its simplicity. In this study, we present a new version of the traditional dropout layer where we are able to fix the number of dropout configurations. As such, each layer can take and apply the new dropout layer in the MC method to quantify the uncertainty associated with NN predictions. We conduct experiments on both toy and realistic datasets and compare the results with the MC method using the traditional dropout layer. Performance analysis utilizing uncertainty evaluation metrics corroborates that our dropout layer offers better performance in most cases. © 2023 IEEE.

关键词： dropout Monte Carlo dropout neural network Uncertainty estimation

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to ESS Safety Monitoring Using a Low-Power UV Camera

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第11期72卷 1498-1501页

作者： Lee, Hunseo Kang, Hyunil Park, Young Dept. of Electrical System Engineering Hanbat National University Korea Republic of

A low-power UV camera and software for ESS safety monitoring are proposed. The UV camera can detect UV in the wavelength range of 285 to 375 nm and has a power consumption of less than 4.4 W. The software is developed using LabVIEW in Windows environment and provides real-time image display, storage, exposure control, and filtering functions. The proposed UV camera is expected to be able to detect corona discharge in the interior of ESS, which is often not directly exposed due to the complex structure including the housing and various devices. This paper proposes a software for ESS safety monitoring using a low-power UV camera developed by combining a 1/2.3-inch CMOS sensor that can detect UV in the wavelength range of 285 to 375 nm and a 25mm f/2.8 lens. The software was developed using LabVIEW in Windows environment. Copyright © The Korean Institute of Electrical Engineers.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Smart IoT system for Automatic Detection and Protection from Indoor Hazards: An Experimental Study 10

Smart IoT System for Automatic Detection and Protection from...

引用

10th IEEE Region 10 Humanitarian technology Conference, R10-HTC 2022

作者： Islam, R. Hossain, M.I. Rahman, M.S. Kabir, S. Sohan, M.S.R. Shufian, A. American International University-Bangladesh Dept. of Electrical and Electronic Engineering Dhaka Bangladesh Eastern University Dept. of Electrical and Electronic Engineering Dhaka Bangladesh Institute of Energy Technology Chittagong University of Engineering and Technology Chattogram Bangladesh

ISBN: (数字)9781665401562

ISBN: (纸本)9781665401562

Electrical short circuits and gas leakages are responsible for most of the fire occurrences. Considering this problem, Internet of Things (IoT)-based smart sensors and relays have been proposed in this paper. Besides, an automated indoor safety mechanism has been introduced which consisted of various sensors, built up with Arduino with the monitoring mechanism of ThingSpeak via IoT. The purpose of this proposed model is to save living creatures and goods from fire incidents. Additionally, a comprehensive device has been built to avert this situation by disconnecting the power source promptly and hence, save lives and property within a short time period. The main feature of this model is-(i) the monitoring device can operate from a remote area, and (ii) it collects real-life data and for the purpose of storage, the collected data would be send to the cloud. However, collected data can be analyzed from various locations using smart devices e.g., smart phones, laptops, computers, and hence, real-time decisions can be taken as well as execute. This experimental study ensures power safety as a result of fire or gas hazards and an IoT-based data monitoring system has been built which would continuously monitor the leakage of flammable gases e.g., Liquefied petroleum gas (LPG), Carbon dioxide (CO2), Ammonia (NH3) from the surroundings. The proposed system has been planned for online monitoring of indoor safety measurement, and the parameters can give important as well as helpful information about the atmospheric record and security issues of that place. The application of the developed model has been widely used in various settings, including-(i) residence, (ii) industries, (iii) gas stations, (iv) automobiles, (v) power plants, (vi) research centers, (vii) commercial areas (e.g., shopping malls), and (viii) hospitals. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Epileptic Seizure Detection from EEG Signal: Bangladesh Perspective 6

Machine Learning based Epileptic Seizure Detection from EEG ...

引用

6th International Conference on Electrical Information and Communication technology, EICT 2023

作者： Das, Shupta Mumu, Suraiya Akter Salam, Abdus Akhand, M.A.H. Khulna University of Engineering & Technology Dept. of Computer Science and Engineering Khulna9203 Bangladesh Shaheed Sheikh Abu Naser Specialized Hospital & Prince Hospital Khulna Bangladesh

ISBN: (纸本)9798350370836

Epileptic seizures (ES) pose significant challenges to individuals' well-being and quality of life, with a global impact affecting millions of people. Detecting and classifying ES is essential for proper medical intervention and management. This study addresses ES detection using EEG analysis, focusing specifically on the context of Bangladesh. This study presents a EEG-based method for detecting epileptic seizures differentiating between seizure and non-seizure signals. Utilizing empirical mode decomposition, essential subcomponents are extracted from EEG signals, from which three distinct features were derived. Neural Network (NN), the well-known machine learning model, is employed for ES classification from the extracted features. The significance of this research lies in the utilization of real-life EEG data from a hospital in Khulna, Bangladesh, rather than relying solely on publicly available benchmark datasets. Processing real-life EEG data presents unique challenges, including data preprocessing and variability in EEG signals due to different devices and channel configurations. The proposed model achieved remarkable average accuracies, with 91.05% using 50 hidden neurons in the NN. To validate the effectiveness of the proposed method, outcomes were also compared with publicly available benchmark dataset. The proposed method offers a reliable and efficient approach for ES detection, particularly relevant for real-life healthcare settings in Bangladesh, contributing to improved epilepsy management. © 2023 IEEE.

关键词： Empirical mode decomposition

来源：评论

学校读者我要写书评

暂无评论

Temporal-Spatial Power Spectrum and Sensitivity Measure for Visual Perception Considering Video Dynamics

Temporal-Spatial Power Spectrum and Sensitivity Measure for ...

引用

2023 International Conference on Integrated Intelligence and Communication systems, ICIICS 2023

作者： Thulajanaik, Aruna Kumar Bananaik Manjanaik, Naganaik Gowdara Mallikarjunappa Institute of Technology Affiliated to Visvesvaraya Technological University Dept. of Computer Science and Engineering Davangere Belagavi India University B. D. T. College of Engineering Affiliated to Visvesvaraya Technological University Dept. Electronics and Communication Engineering Davangere Belagavi India

ISBN: (纸本)9798350315455

Multiple difficulties arise for video transmission in a wide-area millimeter wave (mm-wave) network due to the combined effects of network transmission link shortcomings and real-time limits of video data. The difficulties are compounded, especially in crowded environments, by users' rising standards for video quality. This work proposes a Perceptual Quality Aware Video Encoding (PQAVE) to address these issues: in stage one, an efficient perceptual quality encoding method is implemented, making use of low-rank approximation to reduce overall video size;in stage two, a novel bitstream optimization method is utilized to enhance perceptual quality. The proposed PQAVE model outperforms the state-of-the-art perceptual video encoding technique in terms of bitrate percentage reduction (? R), and Peak Signal-to-Noise Ratio (PSNR), as demonstrated by experiments conducted on a standard video dataset. The PQAVE achieved an average ? R of 58.012 and an average PSNR of 41.071 which is better when compared with BL-JUNIPER existing work. © 2023 IEEE.

关键词： Bitrate Perception PSNR Transmission Video Transmission

来源：评论

学校读者我要写书评

暂无评论

Advancements in Hybrid Inverter technology: Design and Emerging Trends 10

Advancements in Hybrid Inverter Technology: Design and Emerg...

引用

10th International Conference on Electrical Energy systems, ICEES 2024

作者： Kandaswamy, Vijay Anand Jeeva, S. Mohan Raj, S. Vishnupriyan, J. Suganyadevi, M.V. Pugazhendhi, S. R.M.K. Engineering College Dept. of ECE Chennai India Chennai Institute of Technology EEE Dept Chennai India Chennai Institute of Technology Centre for Energy Research Chennai India Saranathan College of Engg. Dept. of EEE Trichy India

ISBN: (纸本)9798350353778

Hybrid inverters, now pivotal in contemporary power systems, especially in the integration of renewable energy and microgrid applications, are thoroughly examined in this paper. It begins with an extensive overview of hybrid inverter design, control strategies, and their manifold applications. The paper elucidates the fundamental operational principles of hybrid inverters, emphasizing their efficacy in integrating diverse energy sources like solar photovoltaic (PV), battery storage, and conventional sources into a power system. Subsequently, various design considerations including topology selection, sizing, and interfacing with energy storage systems are discussed in detail. Furthermore, emerging trends in hybrid inverter technology are outlined, highlighting opportunities for further advancements in performance, flexibility, and integration with emerging energy systems. © 2024 IEEE.

关键词： Hybrid power

来源：评论

学校读者我要写书评

暂无评论

User Specific Real-Time Noise Cancellation using Deep Learning

User Specific Real-Time Noise Cancellation using Deep Learni...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Anil Kadu Advay Argade Aditya Deore Asit Anand Atharva Nehete Arya Alurkar Dept. of Instrumentation Engineering Vishwakarma Institute of Technology Pune Maharashtra Dept. of Computer Engineering Vishwakarma Institute of Technology Pune Maharashtra

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

Noise cancellation is a critical concern in various domains, from personal audio experiences to professional settings. This paper presents a novel approach utilizing machine learning, specifically Convolutional Neural Networks (CNNs) trained on urban sound datasets and Yet Another Multilayered Network (YAMNet), to identify and cancel real-time noise. Note that the system is designed as an anti-mechanism for rather repetitive sounds and not for those which vary unpredictably. The methodology involves converting sound inputs into 2D arrays and extracting Mel-Frequency Cepstral Coefficients (MFCC) features, conducting pattern recognition, and employing inversion techniques for noise cancellation. The results exhibit promising noise reduction, showcased through visual representations of input and output sound waves. The potential implications and prospects of this approach are also discussed.

关键词： Deep learning Visualization Noise reduction Neural networks Noise cancellation Feature extraction Real-time systems Pattern recognition Convolutional neural networks Mel frequency cepstral coefficient

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Driven Knowledge Transfer for Automated Medical Image Segmentation

Deep Learning-Driven Knowledge Transfer for Automated Medica...

引用

Disruptive Technologies (ICDT), International Conference on

作者： Maninder Singh Vipin Kr. Kushwaha Shiva Gupta B. Sharan Dept. of CSE IEC College of Engineering & Technology Greater Noida India Dept. of CSE/IT IEC College of Engineering & Technology Greater Noida India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

This study presents a comprehensive review and comparative analysis of existing research on image segmentation techniques for MRI imaging. A detailed comparison is made between single-image and multispectral image segmentation, as well as between supervised and unsupervised segmentation approaches. Additional aspects such as image pre-processing, image registration, validation methods, and their classifications are also discussed. In medical image processing, segmentation is an essential step, especially for applications like brain MRI analysis, where segmentation results help in understanding brain anatomy, identifying structural changes, and aiding in clinical tasks such as surgical planning or image-guided treatments. Automated Knowledge Transfer (AKT) using deep learning, particularly through pre-trained convolutional neural networks enables efficient learning from large datasets, significantly reducing manual labeling efforts and enabling faster, more accurate image analysis. This study also discusses challenges and solutions within MRI segmentation, highlighting a case study on tumor volume measurement to illustrate practical applications.

关键词： Deep learning Image segmentation Accuracy Image analysis Magnetic resonance imaging Volume measurement Manuals Medical diagnostic imaging Knowledge transfer Tumors

来源：评论

学校读者我要写书评

暂无评论

Human Activity Recognition in Free Living Using a Wearable Sensor: A Two-Stage Approach 12

Human Activity Recognition in Free Living Using a Wearable S...

引用

12th International Conference on Awareness Science and technology, iCAST 2023

作者： Li, Tianhui Zhou, Xue Kokubun, Kota Chen, Wenxi Division of Information System The University of Aizu Aizu-Wakamatsu Japan Dept. of Computer and Information Systems The University of Aizu Aizu-Wakamatsu Japan Dept. of Computer Science and Engineering The University of Aizu Aizu-Wakamatsu Japan

ISBN: (纸本)9798350324693

A novel two-stage approach for human activity recognition (HAR) using a wearable sensor is proposed in this study. The goal is to achieve both coarse-level and fine-level recognition of activities. The study focuses on five common activities: desk-working, driving, walking, downstairs, and upstairs. Three-axis acceleration signals were collected using a wrist-worn accelerometer sensor, and the activities were annotated during the participant’s daily routines. The acceleration data were preprocessed through segmentation, feature extraction, and normalization. In the first s tage, a t raditional m achine learning model (decision tree) was used for coarse-level classification, distinguishing between activities with exercise and without exercise. In the second stage, deep learning models were employed for fine-level classification to recognize specific activities within the coarse classes. The performance of the models was evaluated using accuracy, sensitivity, and specificity. T he p roposed approach showed promising results with accuracies of 93.53%, 93.52%, 85.70%, 98.11%, and 85.91% respectively for desk-working, driving, walking, downstairs, and upstairs, demonstrating the effectiveness of the two-stage strategy for HAR. The proposed two-stage approach outperforms the one-stage method (decision tree classifier a nd d eep l earning m odel), p articularly i n imbalanced data, achieving a graceful equilibrium between sensitivity and specificity. T he s tudy h ighlights t he i mportance o f considering the complexity and variability of daily activities for accurate classification a nd r esource optimization. © 2023 IEEE.

关键词： Wearable sensors

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：