检索结果-内蒙古大学图书馆

IEEE Transactions on Signal and Power Integrity 2025年 4卷 88-95页

作者： Chen, Yen-Hao Tseng, Chun-I Lin, Ding-Bing National Taiwan University of Science and Technology Department of Electronic and Computer Engineering Taipei106335 Taiwan Inventec Corporation Taoyuan330417 Taiwan

With the increasing data rate of high-speed digital systems, equalization techniques have been widely applied to counteract intersymbol interference and maximize eye opening in today's high-speed serial links. Channel simulations with optimal equalization settings allow engineers to explore design tradeoffs, reduce the need for costly prototypes, and ensure robust performance before manufacturing. Existing equalization optimization methods require either iterative interaction with commercial channel simulators during the optimization process, developing models with extensive training data before optimization, or separately optimizing linear equalizers in the frequency domain. In this article, the method to jointly optimize feedforward equalization, continuous-time linear equalization, and decision feedback equalization at the transmitter, receiver, or both is proposed. The optimization is achieved through the analysis of a nonequalized pulse response, eliminating the computational cost of channel simulations during optimization. Practical examples using non-return-to-zero (NRZ) and pulse amplitude modulation four-level (PAM4) signaling schemes demonstrate the effectiveness of the proposed method. A comparison with the Bayesian optimization approach, a widely discussed method for equalization optimization, shows that while both methods achieve nearly identical optimal eye openings, the proposed method offers significantly higher optimization efficiency. © 2022 IEEE.

关键词： Intersymbol interference

来源：评论

学校读者我要写书评

暂无评论

Multi-Fault Classification Method for Wind Turbine with Class Imbalance Data 14th

Multi-Fault Classification Method for Wind Turbine with Clas...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Chatterjee, Subhajit Gil, Joon-Min Byun, Yung-Cheol Department of Computer Engineering Jeju National University Jeju63243 Korea Republic of Department of Computer Engineering Major of Electronic Engineering Institute of Information Science and Technology Jeju National University Jeju63243 Korea Republic of

ISBN: (纸本)9789819623945

Data-driven fault classification is critical for wind turbine condition monitoring systems. However, imbalanced class distributions, where certain fault types are significantly less frequent than others, pose a challenge for traditional classifiers. This work addresses this issue by investigating the combined effect of oversampling with Synthetic Minority Oversampling Technique (SMOTE) and undersampling with Tomek Links for data cleaning, followed by a stacking ensemble learning approach. We evaluate the proposed method on a multiclass wind turbine fault dataset and demonstrate its effectiveness in improving classification performance compared to baseline methods. Our findings highlight the potential of the proposed approach for enhancing fault classification accuracy in wind turbine systems plagued by imbalanced data. The classification performance is evaluated using metrics like confusion matrix, precision, recall, and F1-score, demonstrating significant improvements compared to baseline methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Wind turbines

来源：评论

学校读者我要写书评

暂无评论

An Intelligent SCADA System for Power Distribution Network Cable Fault Detection with Real-Time Monitoring and Autonomous Maintenance 4

An Intelligent SCADA System for Power Distribution Network C...

引用

4th International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2025

作者： Nahidul Islam, S.M. Ahmad, Shameem Prodhan, Md. Mahbub-E-Elahi Khan Chowdhury, Md. Shoaib Bin Mizan, Sakib Ahmed, Abir Jahan, Effat Hazari, Md. Rifat Hossain, Chowdhury Akram American International University-Bangladesh Faculty of Engineering Department of Electrical and Electronic Engineering Dhaka1229 Bangladesh American International University-Bangladesh Faculty of Engineering Department of Computer Engineering Dhaka1229 Bangladesh

ISBN: (纸本)9798331530938

Supervisory Control and Data Acquisition (SCADA) systems are significant for boosting industrial operations, but established systems often struggle with fault management and real-time monitoring. To address these issues, this paper proposes an advanced SCADA system that integrates IoT technologies, multi-agent systems, and predictive maintenance for seamless data collection, analysis, and decision-making. Machine learning enhances fault detection and cybersecurity, while a modular hardware design allows scalability and flexibility to various industrial environments. The system is highly sensitive to detecting faults, including open circuit faults, line-to-ground faults, line-to-line faults, double line to ground faults and three-phase faults. It improves operational safety and efficiency by accurately locating faults and notifying professionals in real time. Extensive simulations and hardware tests were conducted to validate its performance in different fault scenarios. The results show that the proposed SCADA system has successfully detected different types of faults, offering a unified approach for fault management, maintenance, and real-time monitoring. © 2025 IEEE.

关键词： SCADA systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Tomato Leaf Disease Classification with Augmentation Techniques in Deep Learning 14th

Enhancing Tomato Leaf Disease Classification with Augmentati...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Debnath, Anik Gil, Joon-Min Byun, Yung-Cheol Department of Computer Engineering Jeju National University Jeju63243 Korea Republic of Department of Computer Engineering Major of Electronic Engineering Inistitute of Information Science and Technology Jeju National University Jeju63243 Korea Republic of

ISBN: (纸本)9789819623945

Tomato leaf diseases pose a significant threat to crop yield and agricultural productivity. Addressing the challenge of automatic detection and classification of diseases found in tomato leaves through the utilization of Convolutional Neural Networks (CNNs), a subset of deep neural networks. Initially, the dataset is augmented to address the issue of limited labeled data, employing traditional data augmentation methods to balance and enlarge the dataset. Exploring the effectiveness of various fine-tuned pre-trained models, including VGG-16, VGG-19, InceptionV3, EfficientNetB7, and ResNet-50 for classifying tomato leaf diseases. Ten common diseases affecting tomato leaves are classified, with the dataset expanded fourfold through data augmentation. Experiments demonstrate that the ResNet-50 model achieves the highest accuracy of 96.15% in disease classification. Through a detailed analysis, evaluating the performance of each technique and providing insights into their effectiveness for enhancing disease classification in tomato plants. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

Review Rating Prediction Using BiLSTM 14th

Review Rating Prediction Using BiLSTM

引用

14th International Conference on Frontier Computing, FC 2024

作者： Kim, Yongjun Lee, Sang-Joon Byun, Yung-Cheol Department of Computer Engineering Jeju National University Jeju63243 Korea Republic of Department of Computer Engineering Major of Electronic Engineering Institute of Information Science and Technology Jeju National University Jeju63243 Korea Republic of

ISBN: (纸本)9789819623945

User review ratings are crucial for assessing the quality of restaurants, movies, products, and services online. Traditionally, predicting these ratings involved analyzing the content of user reviews using natural language processing techniques. While this approach allows for the consideration of diverse data by aggregating reviews from all users, it's hindered by the fact that users have unique tendencies and expressions, resulting in varying ratings for the same review. To address this challenge, a novel method is proposed in this paper: a BiLSTM model that incorporates the user's average rating alongside their review content. By doing so, this method aims to enhance prediction accuracy by accounting for individual user characteristics. This approach considers the textual content of reviews and integrates the user's typical rating behavior, resulting in more personalized and precise rating predictions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Short-Term Load Forecasting Using Deep Learning Algorithms with Hyperparameter Optimization 4

Short-Term Load Forecasting Using Deep Learning Algorithms w...

引用

4th International Conference on Robotics, Electrical and Signal Processing Techniques, ICREST 2025

作者： Uddin, Raihan Hazari, Md. Rifat Ahmad, Shameem Hossain, Chowdhury Akram Rahman Zishan, Md. Saniat Ahmed, Abir American International University-Bangladesh Faculty of Engineering Department of Electrical and Electronic Engineering Dhaka1229 Bangladesh American International University-Bangladesh Faculty of Engineering Department of Computer Engineering Dhaka1229 Bangladesh

ISBN: (纸本)9798331530938

The accurate forecasting of electrical load in short-term intervals is crucial for the efficient and secure operation of modern power systems. The dynamic nature of energy demand necessitates sophisticated forecasting techniques that can adapt to real-time changes, thereby optimizing power generation and distribution. This study proposes a Long Short-Term Memory (LSTM) model optimized using Hyperparameter Optimization (HPO) to address the inherent non-linearities in load data and enhance predictive performance. The LSTM with HPO achieved a Mean Absolute Percentage Error (MAPE) of 2.63%, substantially outperforming other models such as k-Nearest Neighbors (3.77%), Random Forest (3.46%), and Artificial Neural Networks (3.58%). It also recorded superior performance in Mean Squared Error (MSE) and Root Mean Squared Error (RMSE), with values of 1.1423 and 1.0688, and an R2 of 0.9442. Additionally, experiments were conducted combining LSTM with other models to form hybrid architectures without applying HPO. These LSTM-based hybrids, such as RF-LSTM, consistently outperformed non-LSTM models, achieving a MAPE as low as 2.81%. © 2025 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Early Parkinson's Disease Detection and Classification using Machine Learning and Neutrosophic Sets

引用

Neutrosophic Sets and Systems 2025年 82卷 873-886页

作者： Oudah, Hasan H. Metwaly, Ahmed A. Eassa, Mohamed Abdelhafeez, Ahmed Nagm, Ahmad M. Salama, Ahmed S. College of Arts Department of Journalism Ahl Al Bayt University Karbala Iraq Department of Computer Science Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Engineering and Electronics Cairo Higher Institute for Engineering Computer Science and Management New Cairo Egypt

Optimizing therapy and rehabilitation for Parkinson's disease (PD) requires early identification and precise evaluation of the illness's course. However, there is disagreement about the best way to use gait analysis to categorize the severity of motor symptoms and identify early-stage Parkinson's disease. The precision of machine learning (ML) models in identifying early and intermediate stages of Parkinson's disease was assessed in this study. Six ML models are used in this study for the prediction of PD. Different metrics are used to evaluate ML models such as accuracy, precision, recall, f1-score, and AUC score. Then we propose a multi-criteria decision-making methodology (MCDM) to evaluate the ML models and select the best one. Two MCDM methods are used such as CRITIC method to compute the criteria weights and the TOPSIS method to rank the alternatives. These methods are used under the bipolar neutrosophic sets (BNSs) to deal with uncertainty information. The results show the support vector machine is the best ML model for the prediction of PD. © 2025, University of New Mexico. All rights reserved.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Optimal control for unreliable manufacturing and remanufacturing system under environmental subsidy and overrun penalty mechanism

引用

IEEE Transactions on engineering Management 2025年 72卷 1983-2002页

作者： Turki, Sadok Jemmali, Mahdi Hidri, Lotfi University of Lorraine Department of Logistic and Maintenance UFR MIM at Metz Metz17 France University of Sharjah Computer Science Department College of Computing and Informatics Sharjah United Arab Emirates King Saud University Industrial Engineering Department College of Engineering Riyadh11421 Saudi Arabia

Because of environmental concerns, remanufacturing has become an integral process for many production companies. Most published papers dealing with manufacturing and remanufacturing systems (MRSs) overlook some industrial features. These include machine unreliability, the distinction between newly manufactured and remanufactured products, and uncertainty about the returned used products (RUPs). As a result, these models do not reflect the reality of industrial systems. This study aims to bridge the gap in research on MRSs by elaborating an optimal and dynamic control of manufacturing, remanufacturing, and recovery of RUPs. The goal is to develop a model based on manufacturing remanufacturing emissions hedging point control policy (MREHP) to adjust the production of new and remanufactured products, and recovery of RUPs according to economic and environmental thresholds. To reduce carbon emissions, a new method is proposed based on the environmental subsidy and overrun penalty mechanism (ESOPM), and that is combined with MREHP to control in parallel the MRS and generated emissions. A robust optimization algorithm is developed to determine the optimal economic and environmental thresholds in MREHP and ESOPM. A comparative study is provided to evaluate our proposed ESOPM in comparison with traditional reduction policies: carbon cap and trade (CCT) and carbon tax regulation (CTR). The obtained results reveal that machines' reliability, rate of RUPs, emissions subsidy, and carbon emissions limit have notable impacts on economic and environmental thresholds. Additionally, results show that the proposed ESOPM performs higher profit than CTR and CCT while reducing emissions when the carbon price is below a certain value. © 1988-2012 IEEE.

关键词： Fabrication

来源：评论

学校读者我要写书评

暂无评论

A Systematic Three-Stage Safety Enhancement Approach for Motor Drive and Gimbal Systems in Unmanned Aerial Vehicles

引用

IEEE Transactions on Power electronics 2025年第7期40卷 9329-9342页

作者： Jie, Huamin Zhao, Zhenyu Li, Hong Gan, Theng Huat See, Kye Yak Nanyang Technological University School of Electrical and Electronic Engineering 639798 Singapore National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore Zhejiang University College of Electrical Engineering Hangzhou310058 China National University of Singapore Temasek Laboratories 117411 Singapore

Electromagnetic compatibility (EMC) is critical for ensuring the reliability and safety of power electronics-related assets, such as unmanned aerial vehicles (UAVs). EMC encompasses two key aspects: electromagnetic interference (EMI) and electromagnetic susceptibility (EMS). While EMI has been widely studied, EMS in power electronics systems, particularly with sensitive control and sensing modules, is gaining increasing attention due to rising threats from intentional or unintentional electromagnetic (EM) noises. Therefore, enhancing the EM safety of these systems is essential. This article proposes a systematic three-stage safety enhancement approach for power electronics-related systems in UAVs. In stage 1, a quantitative risk assessment strategy based on the EMS test results is introduced, identifying the motor drive and gimbal systems of the UAVs as the most vulnerable components. Stage 2 analyzes their failure mechanisms, offering valuable insights for further hardening. Stage 3 develops a comprehensive lightweight strategy to enhance the UAV safety. Using a DJI UAV as a case study, the proposed approach demonstrates the capability of the proposed EM hardening solutions against external EM noises with the electric field strength up to 200 V/m from 2 MHz to 18 GHz. The total weight increases by only 1.2% with a negligible addition to volume. © 2025 IEEE.

关键词： Antennas

来源：评论

学校读者我要写书评

暂无评论

Cardinality estimation for property graph queries with gated learning approach on the graph database

引用

Multimedia Tools and Applications 2025年第11期84卷 9159-9183页

作者： He, Zhenzhen Yu, Jiong Du, Xusheng Guo, Binglei Li, Ziyang Li, Zhe School of Information Science and Engineering Xinjiang University Urumqi China School of Computer Engineering Hubei University of Arts and Science Xiangyang China School of Software Xinjiang University Urumqi China Department of Electronic and Information Engineering The Hong Kong Polytechnic University Hong Kong

With the increasing complexity of graph query processing tasks, it is difficult for users to obtain the accurate cardinality before or during the execution of query tasks. Accurate estimate query cardinality is crucial for property graph data model, which usually involves entities, multiple joins, and various types of properties (key-value pairs). While learning-based approaches have been used in query optimization, estimating the cardinality of property graph queries is still particularly challenging. In this paper, we first formally represent each property graph query and then divide the estimation process into three phases: query execution, training data generation, and model training. Secondly, we construct a data pool to deal the updating query workloads in the training data generation phase. Thirdly, we utilize the gate mechanism to develop a cardinality estimation framework based on deep learning neural networks for property graph queries in the Neo4j database, and we propose a hybrid loss function to optimize the training process. Finally, we adopt a method of pre-aggregating the underlying data to speed up query execution in the first phase. The result of the experiment on two real-world datasets shows that our optimized methods can effectively improve the estimation accuracy of the deep learning model, and our query estimator outperforms other deep learning models compared in terms of estimation accuracy. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Query processing

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：