检索结果-内蒙古大学图书馆

28th International electrical Power Distribution Conference, EPDC 2024

作者： Miri, Seyed Alireza Azimi, Zahra Bagheri, Amir University of Zanjan Master's Student of Electrical Engineering Department of Electrical Engineering Zanjan Iran University of Zanjan Department of Electrical Engineering Zanjan Iran

ISBN: (纸本)9798350385502

Considering the technical, economic, and environmental benefits of renewable distributed generators (DGs), today we are witnessing penetration of these DGs in active distribution networks. In this way, one of the concerns of the network operators is the changes in the output power of wind and photovoltaic (PV) units and the mismatch of their generation pattern with the network load curve, which leads to voltage and congestion problems in the network. This issue may cause these units not be dispatched with their maximum capacity such that some part of the available power is curtailed. In this paper, in order to improve the operation of distribution network and increase the utilization of renewable units, an optimization model based on the dynamic reconfiguration in the presence of voltage-dependent loads is presented. The mentioned problem is modeled as a mixed-integer non-linear programming (MINLP) and implemented in the GAMS environment. The effectiveness of the proposed method is investigated by applying it on the IEEE 33-bus network through various experiments. The results show the improvement of the desired indicator of the network operator. © 2024 IEEE.

关键词： Electric power distribution

来源：评论

学校读者我要写书评

暂无评论

RUL Estimation for Power Electronic Devices Using RNNs

RUL Estimation for Power Electronic Devices Using RNNs

引用

2024 Prognostics and System Health Management Conference, PHM 2024

作者： Cai, Congrui Lu, Zhonghai School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Embedded Systems Master Program Sweden School of Electrical Engineering and Computer Science Department of Electrical Engineering KTH Royal Institute of Technology Sweden

ISBN: (纸本)9798350360585

Recurrent Neural Networks (RNNs) are commonly used in data-driven approaches to estimate the Remaining Useful Lifetime (RUL) of power electronic devices. RNNs are preferred because their intrinsic feedback mechanisms are better suited to model time-series data. However, the impact of RNN complexity on estimation accuracy is rarely discussed in the literature. This issue is important because choosing a lower-complexity model that delivers the same or similar performance as a higher-complexity model can increase implementation efficiency. In the paper, we use three RNN models, namely, the vanilla version, LSTM (Long Short Term Memory) and GRU (Gated Recurrent Unit) to conduct RUL estimation for power electronic devices. We use two accelerated aging datasets, one dataset targeting the package failure of MOSFETs, and the other dataset targeting package failure of power diodes. Our study shows that a lower-complexity RNN does not necessarily deliver a lower performance. Similarly, a higher-complexity model does not assure a higher performance. As such, our work highlights the importance of selecting a proper neural network for RUL estimation not biased towards complex models. This is especially useful and important for implementing such RUL estimation techniques in embedded resource-constrained and speed-limited computins platforms. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

A ShuffleNet Architecture-Based Multi-Layer Feature Scaling and Fusion Approach for Underwater Net Cage Damage Detection in Aquaculture

A ShuffleNet Architecture-Based Multi-Layer Feature Scaling ...

引用

2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Huang, Xiang-Rui Chen, Yi-Cheng Chen, Liang-Bi Hu, Wu-Chih National Penghu University of Science and Technology Master Program in Electrical Engineering and Computer Science Department of Electrical Engineering Penghu Taiwan National Penghu University of Science and Technology Department of Computer Science and Information Engineering Penghu Taiwan

ISBN: (纸本)9798331530839

In offshore aquaculture operations, personnel equipped with diving gear are often necessary to inspect the underwater net cages for damage, particularly on the sea floor. This manual inspection process is time-consuming and complex. To overcome this problem, this paper proposes a computer vision solution for identifying damage in underwater net cages to address the inefficiencies and challenges of traditional manual inspections. The proposed scheme utilizes a high-performance multi-branch computational architecture designed based on ShuffleNet architecture to detect net cage damage more efficiently. Experimental results demonstrate that this work performs well on the ImageNet ILSVRC-2010 dataset and achieves an accuracy of 88.54% in underwater net damage detection. © 2024 IEEE.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Location Estimation of Moving Targets by Passive Sonobuoy and Recurrent Deep Neural Network

Location Estimation of Moving Targets by Passive Sonobuoy an...

引用

2023 International Symposium on Networks, computers and Communications, ISNCC 2023

作者： Abbaspour, Hooshang Najafi, Ghazal Master of Electrical and Communications Tehran Iran Shahre Rey Branch Electricl and Computer Engineering Department Tehran Iran

ISBN: (纸本)9798350335590

Today, one of the biggest challenges for military experts is to identifying and track submarines. concealment, is one of the most critical features of the Navy, which leads to limited active signal transmission. On the other hand, environmental factors such as salinity changes, temperature, the harsh and inhomogeneous environment of the sea etc. Affect the sound signals and their propagation. Currently, sonobuoys are an affordable and practical resource for tracking submarines. Passive sonobuoy is necessary for some operational conditions and special missions, especially the military. In this paper, the deep neural network is trained by a particle filter to the location estimation by passive sonobuoy in two dimensions. Also, simple dynamic equations without pre-processing are considered for sonobuoy and can be processed by a deep neural network, which has a high ability to estimate highly complex functions. The ratio of the average power of the primary signal to the noise of the sonobuoys is assumed in the SNR= [0,10]dB is assumed, and the simulation results demonstrate that the proposed method achieve high accuracy compared to the gradient descent training algorithms. Due to the use of a neural network, the computational load is significantly reduced and real-time calculations. © 2023 IEEE.

关键词： Submarines

来源：评论

学校读者我要写书评

暂无评论

GPS and GSM-based Internet of Things based cable fault location detector 3

GPS and GSM-based Internet of Things based cable fault locat...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Kumar, Govind Shukla, Anand Vivekananda Global University Department of Electrical Engineering Jaipur India Chandigarh School of Business Department of Master of Computer Application India

ISBN: (纸本)9798350399264

To forestall over the top possibly destructive block, electrical lines frequently used to convey the energy are for the most part situated under the ground in metropolitan regions. Accordingly, diagnosing the specific site of any issues that arise turns out to be unquestionably difficult. A breakdown may at times happen for various driving variables like exhuming, cataclysmic events, and building, etc. On account of the line's unsure area, the maintenance system is intricate. This created system is expected to distinguish disappointments in underground organizations here Ohm's regulation is being utilized to exactly confine a base station to a distance of km utilizing an Arduino microcontroller gear. A blend of resistors addresses the link which detects the ongoing in the circuit and it is associated with Arduino microcontroller of this framework. Switch sets are responsible for setting up the shortcoming, and LCDs are connected to microcontrollers that display data;the switch sets are responsible for setting up the issue, and LCDs are connected to microcontrollers that display data;if a mistake occurs, GPS tracks will show on the LCD where the issuing district is located. It utilizes GSM to make an impression on the enrolled contact subtleties telling them of the link's area. © 2023 IEEE.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Predictive Model for Accident Severity

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2022年第1期49卷 110-124页

作者： Mostafa, Solwan M. Salem, Sameh A. Habashyis, Shahira M. Teaching Assistant and a Master Student of Computer and Systems Department Faculty of Engineering Helwan University Cairo11792 Egypt Professor of Computer and Systems Department Faculty of Engineering Helwan University Cairo11792 Egypt Associate Professor of Computer and Systems Department Faculty of Engineering Helwan University Cairo11792 Egypt

In the development of sustainable transportation, traffic safety is a significant matter, and predicting the severity of traffic accidents is still a critical problem in the traffic safety field. However, the utilized road traffic accidents (RTAs) datasets suffer from imbalance distribution. This problem leads to a decrease in classification performance, specifically in predicting the minority classes. This paper aims to treat the class imbalance problem through Synthetic Minority Over-sampling Technique (SMOTE), Support Vector Machine-SMOTE (SVM-SMOTE), Borderline-SMOTE(BL-SMOTE), and Adaptive Synthetic (ADASYN), along with proposing an accurate predictive model for accident severity. Different accident severity models are employed, namely Random Forest (RF), K-Nearest Neighbor (KNN), Naïve Bayes (NB) classifiers, Decision Tree (DT), and Extra Trees (ET). These models are tested using real-world datasets. Several evaluation metrics are used to evaluate the proposed model. Experimental results show that the proposed model significantly improves predicting both the minority and majority classes. These results indicate the robustness and reliability of the proposed predictive model in enhancing road traffic safety and management. © 2022. All Rights Reserved.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Anomalous Detection in Noisy Image Frames using Cooperative Median Filtering and KNN

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2022年第1期49卷 1-10页

作者： Esan, Dorcas. O. Owolawi, Pius. A. Tu, C. Master Student at Tshwane University of Technology Department of Computer Systems Engineering Soshanguve Campus South Africa Head of Department of Computer Systems Engineering Tshwane University of technology Soshanguve Campus South Africa Head of Research of Computer Systems Engineering Department and a Senior Lecturer in Computer Systems Engineering Department Tshwane University of Technology Soshanguve Campus South Africa

The widespread of surveillance cameras has consequently led to a significant increment in the global surveillance video market over the years. However, as the number of surveillance systems is increasing, the rate of crime threats is also increasing. Despite the advancements in surveillance systems, there are still challenges in the detection of anomalous behavioural patterns from noisy image frames, which significantly affect the accuracy of intelligent surveillance systems. This paper employs the median filtering technique and the k-nearest neighbor (KNN) classifier for the detection of behavioural patterns. Median filtering is used because of its ability to preserve the image edges while removing the noise;the statistical property of KNN is used to obtain vector distribution from images during the detection stage. Different analyses were conducted using the publicly available dataset repository that has been used by many researchers in the field of computer vision in the detection of anomalous behaviour. The results are compared with existing -state-of-anomalous detection models and the results obtained show that the proposed system outperforms the others mentioned by 85.15% and an F1-score of 0.54, equal error rate of 0.15, precision value of 0.90 and recall value of 0.40. © 2022. All Rights Reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Face Recognition using Opencv with LBPH Calcuation System for More Safety 3

Face Recognition using Opencv with LBPH Calcuation System fo...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Nivesh Goswami, Laxmi Chandigarh School of Business Department of Master of Computer Application Jhanjeri India Sanskriti University Department of Electrical Engineering Uttar Pradesh Mathura India

ISBN: (纸本)9798350399264

A continuing chin added layer for residences and places of business has been presented in this article. It was produced using a computation known as the Binarization Profile (LBPH). Face recognition has been effectively employed to support schemes that aim to increase home and minimize employee as well as criminal surveillance via ID through such espionage frameworks. The LBPH computation takes into consideration both of these variables. Differences in stance and features of human characteristics, like lighting, have been critical constraint among most face recognition algorithms. This article discusses the advantages of this analysis over competing ones and explains why VLC should be used to carry out the computation rather than FORTRAN. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Dynamically Reconfigurable Active Distribution Networks for Maximum Renewables Integration at the Presence of Voltage-Dependent Loads

Dynamically Reconfigurable Active Distribution Networks for ...

引用

Conference on electrical Power Distribution Networks (EPDC)

作者： Seyed Alireza Miri Zahra Azimi Amir Bagheri Department of Electrical Engineering Master’s Student of Electrical Engineering University of Zanjan Zanjan Iran Department of Electrical Engineering University of Zanjan Zanjan Iran

ISBN: (数字)9798350385502

ISBN: (纸本)9798350385519

关键词： Renewable energy sources Wind Energy loss Wind energy Voltage Distribution networks Wind power generation

来源：评论

学校读者我要写书评

暂无评论

An Edge AI-Powered Defect Coffee Detector Using Streamlit Web App

An Edge AI-Powered Defect Coffee Detector Using Streamlit We...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Rauzatul Jannah Akbar Maulana Putra Kahlil Muchtar Safrizal Razali Rika Sri Utami Department of Electrical and Computer Engineering Master of Electrical Engineering Universitas Syiah Kuala Indonesia Department of Electrical and Computer Engineering Universitas Syiah Kuala Indonesia

ISBN: (数字)9798350355079

ISBN: (纸本)9798350355086

Coffee is one of the most popular beverages today, necessitating a meticulous sorting process to ensure the quality of coffee beans. Manual sorting is time-consuming, prone to errors due to fatigue, and results in inconsistent quality. This paper highlights the novelty of deploying a deep learning model on edge devices using NVIDIA Jetson Orin Nano, with training on ResNet and deployment with Streamlit on low-cost hardware. The dataset is available at USK-Coffee Dataset.

关键词： Training Deep learning Image edge detection Manuals Detectors Fatigue Nanoscale devices Hardware Consumer electronics Sorting

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：