检索结果-内蒙古大学图书馆

Hierarchical Control for Cyber-Physical Systems via General Approximate Alternating Simulation Relations ⁎

IFAC-PapersOnLine 2024年第11期58卷 13-18页

作者： Bingzhuo Zhong Murat Arcak Majid Zamani Department of Computer Science University of Colorado Boulder USA Department of Electrical Engineering and Computer Sciences University of California Berkeley USA

Traditional hierarchical control methodologies refine controllers from an abstract to a concrete system using a simulation relation established over the state sets of both systems. However, such a relation may yield a large error between the abstract and concrete systems, thus constraining the efficacy of hierarchical control architectures. To address this limitation, we introduce a more versatile simulation relation, namely general approximate alternating simulation relation, which also makes use of the input set of the abstract system. We demonstrate that our novel simulation relation effectively captures the similarity between the abstract and concrete system outperforming conventional simulation relations. Furthermore, it strengthens the hierarchical control architecture by reducing the error between the outputs of a concrete and its abstract system. We provide methods for establishing this new relation in linear control systems alongside their continuous abstractions. The practicality and effectiveness of our approach are underscored through its application in an illustrative example.

关键词： Simulation Relation Hierarchical Control Abstract System

来源：评论

学校读者我要写书评

暂无评论

Graph-based deep learning models in the prediction of early-stage Alzheimers 46

Graph-based deep learning models in the prediction of early-...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Thapaliya, Bishal Wu, Zundong Sapkota, Ram Ray, Bhaskar Suresh, Pranav Ghimire, Santosh Calhoun, Vince Liu, Jingyu Georgia State University Department of Computer Science Atlanta United States Tri-Institutional Center for Translational Research in Neuroimaging and Data Science United States Georgia Institute of Technology School of Electrical and Computer Engineering Atlanta United States Tribhuvan University Department of Applied Sciences and Chemical Engineering Nepal

ISBN: (纸本)9798350371499

Alzheimer's disease is the most common age-related problem and progresses in different stages, from cognitively normal to early mild cognitive impairment, and severe dementia. This study investigates the predictive potential of resting-state functional magnetic resonance imaging (rs-fMRI) and its derived functional connectivity (FC) in understanding Alzheimer's progression. Leveraging deep learning and graph-based models, we introduce two key contributions: 1) a comparative analysis of rs-fMRI time points and FC for Alzheimer's prediction. 2) an innovative graph transformer variant incorporating self-clustering for enhanced prediction accuracy. Experiments on the Alzheimer's Disease Neuroimaging Initiative dataset with 830 subjects reveal two notable conclusions. Firstly, rs-fMRI time points offer limited utility compared to functional network connectivity for transformer-based models, even when considering temporal information. Secondly, a clustering-based attention module proves effective for classifying brain networks in predicting Alzheimer's disease progression, providing valuable insights for future research and clinical applications. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection Using K-Nearest Neighbors (KNN) and Recurrent Neural Networks (RNN)

Network Intrusion Detection Using K-Nearest Neighbors (KNN) ...

引用

2024 International Conference on science, engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Adebiyi, Marion O. Atanda, Oladayo G. Okeke, Chidinma Adebiyi, Ayodele A. Adebiyi, Abayomi A. Landmark University SDG 3: Good Health and Well-Being Department of Computer Science Omu-Aran Nigeria Landmark University SDG 11: Sustainable Cities and Community Department of Computer Science Omu-Aran Nigeria Landmark University Department of Computer Science Omu-Aran Nigeria Durban University of Technology Department of Electrical Power Engineering South Africa

ISBN: (纸本)9798350358155

In today's interconnected world, the security of computer networks is of utmost importance due to the prevalence of cyber threats. To tackle this challenge, a machine learning-based methodology for detecting network intrusions was adopted. The approach leverages two powerful algorithms: K-Nearest Neighbors (KNN) and Recurrent Neural Network (RNN). The proposed methodology involves several steps: data collection, preprocessing, feature extraction, training KNN and RNN models concurrently to capture temporal dependencies, merging model outputs to enhance accuracy, and testing the integrated model on various data types to reduce false alarms. For evaluation, a dataset simulating intrusions in a military network environment was employed. The dataset includes normal and attack instances, and preprocessing techniques were applied to prepare the data for model training. KNN's architecture involves identifying K nearest neighbors based on distance measures, while RNN captures temporal dependencies in sequential data. Confusion metrics, including true positives, true negatives, false positives, and false negatives, along with performance metrics such as accuracy, precision, sensitivity, and F1 score, were utilized to assess model performance. In conclusion, the adopted methodology utilizing KNN and RNN demonstrates strong performance in network intrusion detection. Both algorithms exhibit high accuracy, precision, and sensitivity, making them effective tools for combating cyber threats in real-world network environments. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Smart Auto Image Captioning Using LSTM and Densenet Network 6

Smart Auto Image Captioning Using LSTM and Densenet Network

引用

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： Arumugam, M. Vijayakumar, P. Siddharrth, G.M. Rohini, J. Karthikeyan, A. Rohith Bhat, C. Kongu Engineering College Department of Computer Technology - PG Perundurai India Kongu Engineering College Department of Master of Computer Applications Tamil Nadu Perundurai638060 India Erode Sengunthar Engineering College Department of Computer Science and Engineering Thuduppathi638057 India PSNA College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul624622 India Saveetha School of Engineering Department of Computer Science and Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (纸本)9798350304480

The integration of semantic attention increase photo captioning ability. The premise underlying semantic attention-based techniques is that the model should prioritize words or qualities with high semantic value. Prior studies focused on the attribute detector and the captioning network as distinct entities. This hampers the best use of semantic data. Image captioning is the computational process of producing accurate written descriptions of an image's or video's visual content. Captioning images makes it easier to construct contextualized interpretations, allowing people to situate photographs within a larger context. Using photo captions can be useful in a variety of contexts, such as conducting research with an unlabeled image collection or attempting to identify. previously unknown patterns. Subtitles added to the photos using a Deep Learning Model. Recent advances in the fields of deep learning and natural language processing have made it much easier to generate captions for input photographs. This study will use neural networks to generate image captions on their own. The Long Short-Term Memory (LSTM) model, a type of recurrent neural network, used as an encoder, together with a pre-trained lexicon and visual attributes. This enables the extraction of image data and the generation of captions. © 2023 IEEE.

关键词： Deep Learning Model Densenet Network Long Short-Term Memory Remote Sensing

来源：评论

学校读者我要写书评

暂无评论

Numerical Study of Liquid Ammonia Flow Cooling of Power Electronics for Electric Aviation

Numerical Study of Liquid Ammonia Flow Cooling of Power Elec...

引用

AIAA science and Technology Forum and Exposition, AIAA SciTech Forum 2025

作者： Guo, Y. Kwon, J. Sumption, M.D. Collings, E.W. Cao, D. Meng, H. Marzang, V. Liu, X. Robert, R. Layhew, G. Schafer, D. The Ohio State University College of Engineering Department of Material Science and Engineering ColumbusOH43210 United States University of Dayton School of Engineering Department of Electrical and Computer Engineering DaytonOH45469 United States Tennessee Tech University School of Engineering Department of Electrical and Computer Engineering CookevilleTN38505 United States Tennessee Tech University College of Engineering Department of Mechanical Engineering CookevilleTN38505 United States

ISBN: (数字)9781624107238

ISBN: (纸本)9781624107238

The rapid development of electric aircraft technology drives the need for highly effective cooling systems to manage the significant heat generated by high-power electronic components. In this work, liquid ammonia, with its excellent thermophysical properties including a high specific heat, and volumetric energy density, is evaluated as a good coolant (especially relevant when it will also serve aviation fuel at the same time). This work focuses on designing fuel storage and cooling strategies to address thermal management challenges both globally and locally for the electric aircraft. Aluminum was chosen as the material for the heat exchanger/heat sink due to its excellent resistance to liquid ammonia corrosion, high thermal conductivity, and low density. Using computational fluid dynamics (CFD) simulations, we analyzed the heat transfer performance and liquid ammonia flow characteristics within the aluminum heat sink. Temperature distribution of aluminum heat sink and flowing liquid are simulated to determine the viability and effectiveness of this cooling strategy. In addition, various design configurations, including fluid storage methods (cold-temperature or high-pressure) and flow channel topology, are explored to optimize the cooling efficiency. The results shows that liquid ammonia cooling is feasible to maintain the power electronics within safe operating temperatures under the given flow rates and operating conditions, especially for the cold-temperature storage strategy. This research provides valuable insights into the design and implementation of advanced cooling systems for next generation electric aircraft, indicating the potential of liquid ammonia as an effective and innovative cooling media good cooling media, despite challenges related to environmental, safety, and corrosion concerns. © 2025, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： Aluminum corrosion

来源：评论

学校读者我要写书评

暂无评论

Modified TRFI Channel Estimation Scheme in OFDM-IM for 802.11p 23

Modified TRFI Channel Estimation Scheme in OFDM-IM for 802.1...

引用

23rd IEEE International Conference on Communication Technology, ICCT 2023

作者： Zhang, Si-Yu Dong, Qing-Shang Zheng, Hui Zhang, Yue-Xia Shahrrava, Behnam School of Information and Communication Engineering Beijing Information Science and Technology University Beijing China University of Windsor Department of Electrical and Computer Engineering ON Canada

ISBN: (纸本)9798350325959

IEEE 802.11p is developed to support cooperative intelligent transport systems. In such systems, channel estimation is a challenging problem due to the channel's double dispersive nature. In this paper, a modified time domain reliable test frequency domain interpolation (M-TRFI) scheme for 802.11p orthogonal frequency division multiplexing with index modulation (OFDM-IM) systems is proposed. Unlike OFDM, OFDM-IM can achieve better performance in vehicular communication environments. However, due to the in-active subcarriers, channel estimation for OFDM-IM is more difficult than OFDM. Inspired by the OFDM TRFI and the structure of OFDM-IM, the proposed M-TRFI utilizes preambles and least square (LS) methods to fill in the missing channel information on in-active subcarriers, reducing the serious performance degradation caused by the conventional TRFI used in OFDM-IM. Simulation results show that the proposed M-TRFI achieves a similar estimation performance as that of the OFDM TRFI. Moreover, the proposed M-TRFI significantly outperforms the existing channel estimation performance designed for OFDM-IM systems. © 2023 IEEE.

关键词： IEEE 802.11p standard index modulation (IM) least square (LS) Orthogonal frequency division multiplexing (OFDM) time domain reliable test frequency domain interpolation (TRFI) vehicular channels

来源：评论

学校读者我要写书评

暂无评论

Speech Enhancement Algorithm using Deep Learning and Hahn Polynomials 17

Speech Enhancement Algorithm using Deep Learning and Hahn Po...

引用

17th International Conference on Developments in eSystems engineering, DeSE 2024

作者： Al-Zubaidi, Ammar S. Abduljabbar, Riyadh Bassil Mahmmod, Basheera M. Abdulhussain, Sadiq H. Naser, Marwah A. Alsabah, Muntadher Hussain, Abir Al-Jumeily, Dhiya Computer Center University of Baghdad Baghdad Iraq Department of Computer Engineering University of Baghdad Baghdad Iraq Medical Technical College Al Farahidi University Baghdad Iraq Department of Electrical Engineering University of Sharjah Sharjah United Arab Emirates School of Computer Science and Mathematics Liverpool John Moores University Liverpool United Kingdom

ISBN: (纸本)9798350368697

Speech enhancement algorithms and machine learning can play a fundamental role in signal processing to improve speech quality. These techniques can be used to reduce noise and distortions in speech signals, hence ensuring clearer and more intelligible speech. By leveraging advanced machine learning, speech enhancement algorithms not only improve the listener’s auditory system, but also increase the efficacy of speech recognition systems. In particular, deep learning is a class of machine learning techniques, which have recently been used in speech enhancement. This paper proposes the use of Discrete Hahn polynomials (DHPs) o extract spectral features from noisy signals using fully connected neural networks and convolutional neural network. Deep learning can efficiently capture the contextual information of speech signals, resulting in superior improvements in speech quality and intelligibility properties. The results are evaluated based on the well-known TIMIT database. The results show that the presented model is able to enhance the speech signal for different conditions. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Underwater Image Enhancement Based on Improved U-Net Convolutional Neural Network 18

Underwater Image Enhancement Based on Improved U-Net Convolu...

引用

18th IEEE Conference on Industrial Electronics and Applications, ICIEA 2023

作者： Wang, Zhengcai Zhang, Ke Yang, Zhihao Da, Zikai Huang, Sanao Wang, Peizhen Anhui University of Technology School of Electrical and Information Engineering Ma'Anshan China Northeastern University College of Computer Science and Engineering Shenyang China

ISBN: (纸本)9798350312201

Aiming at the problems of low contrast, dim and color distortion of underwater images caused by the attenuation and scattering of light in water propagation, an underwater image enhancement algorithm, which is based on a U-Net convolutional Neural Network is proposed. The algorithm consists of an image synthesis module and an image enhancement module. Firstly, a style transfer network based on transfer learning is built and employed to synthesize underwater images from clear images, image pairs are composed of these synthesized and original images for data expansion. Secondly, an underwater image enhancement network with a U-shaped convolutional variational autoencoder is constructed, and the image pairs serve as input to the second module for training. The qualitative and quantitative analysis results show that the proposed algorithm has good performs favorably in the color fidelity and detailed reservation of the target object. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on An Interleaved Phase-Shift Half-Bridge LLC Resonant Converter 11

Research on An Interleaved Phase-Shift Half-Bridge LLC Reson...

引用

11th International Conference on Power Electronics - ECCE Asia, ICPE 2023-ECCE Asia

作者： Wang, Shu-Po Hong, Min-Rui Wu, Ping-Tsang Chuang, Ching-Chun Lu, Shiue-Der National Formosa University Department of Computer Science & Information Engineering Taiwan National Chin-Yi University of Technology Department of Electrical Engineering Taiwan

ISBN: (纸本)9788957083505

This paper presents the analysis and simulation for a novel high-power density electric vehicle dc-dc converter. In this paper, a novel interleaved phase-shift half-bridge converter that mainly comprises two modules of a half-bridge converter and a double full-bridge rectifier is proposed. In the case of interfacing the high-voltage battery module, the isolated DC/DC converter is used to control the voltage at the input of the battery according to the battery terminal voltage and optimize the efficiency of the dc-dc converter in a wider range of operating voltage. It operates as a voltage doubler to achieve an output voltage of 450V for the charging of a high-voltage battery. The isolated dc-dc converter is operated as an LLC resonant converter owing to its advantages of simple control and soft switching operation. This converter not only has a wide range of zero-voltage-switching (ZVS) turn-on of power switches on the primary side of the transformer but also has a zero-current-switching (ZCS) turn-off of rectifier diode on the secondary side of the transformer. The proposed converter can achieve the output voltage range of 250-450V by adapting the phase shift between the two square waves. The two LLC half-bridge resonant converters are connected in parallel, and it's operated at a fixed frequency and constant duty cycle. The simplified control strategy in the proposed converter can be achieved since the switching frequency of the converter operates at the resonant point. Finally, a 3.4kW design prototype with 400V input voltage and the 250-450V output voltage is simulated to verify the effectiveness of the phase-shift mode control method. © 2023 The Korean Institute of Power Electronics.

关键词： Resonant circuits

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5 Algorithm for Power Insulator Defect Detection 13

Improved YOLOv5 Algorithm for Power Insulator Defect Detecti...

引用

13th International Conference on Power, Energy and electrical engineering, CPEEE 2023

作者： Chen, Hefan Zhang, Zhaoyun Dongguan University of Technology School of Electrical Engineering & Intelligentization School of Computer Science and Technology Dongguan China Dongguan University of Technology School of Electrical Engineering & Intelligentization Dongguan China

ISBN: (纸本)9781665490146

Intelligent inspection of transmission lines by UAVs has become the mainstream of the industry, and insulator defect detection is a key part of the intelligent inspection operation. To address the problem of low accuracy of insulator defect detection in complex environments, this paper proposes an improved YOLOv5s-based insulator defect detection algorithm. First, the K-means algorithm is used to cluster the data set to obtain the best anchor frame size, which effectively improves the generalization ability and localization accuracy of the model;second, the Backbone part of YOLOv5s is embedded with the Coordinate Attention module to improve the feature extraction ability of the network to solve the influence of invalid features on the recognition accuracy;finally, the EIOU-Loss is used to improve the accuracy of insulator defect detection. Finally, the performance of the model is optimized using the EIOU-Loss function, and ablation experiments are set up to validate the proposed method. The experimental results show that the Precious and mAP of the improved YOLOv5s model are improved by2.S% and 1.6%, respectively, compared with the original YOLOv5s network. © 2023 IEEE.

关键词： K-means clustering

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：