检索结果-内蒙古大学图书馆

2023 systems and Information engineering Design Symposium, SIEDS 2023

作者： Nayhouse, S. Chadha, S. Hourican, P. Moore, C. Bezzo, N. University of Virginia Departments of Systems and Information Engineering and Electrical and Computer Engineering CharlottesvilleVA22903 United States University of Virginia Department of Electrical and Computer Engineering CharlottesvilleVA22903 United States

ISBN: (纸本)9798350300642

Recent advancements in unmanned aerial vehicles (UAVs), has allowed their deployment for numerous applications like aerial photography, infrastructure inspection, search and rescue, and surveillance. Despite the potential for full autonomy, many applications still necessitate human operators for navigating complex environments and decision-making. Existing solutions often employ high-precision and simple sensors like 2-D or 3-D LiDAR, which may provide more data than necessary and contribute to increased system complexity and cost. To address these challenges and bridge the gap between full autonomy and human-controlled UAVs, this work develops a shared-autonomy framework for UAVs, leveraging lightweight, low-cost 1-D LiDAR sensors combined with mobility behaviors to obtain performance comparable to more advanced 2-D/3-D LiDAR sensors while minimizing energy, computation overhead, and weight. Our framework includes a novel state machine method that exploits the UAV mobility to compensate for the limitations of 1-D LiDAR sensors, ensuring safety and obstacle avoidance through a physics-based algorithm that transitions between teleoperation and autonomous mode as needed based on environmental conditions and safety-critical issues. Experimental validations on real UAVs demonstrates the effectiveness of this shared autonomy scheme in complex environments, and the system is further generalized to larger UAVs and prototyped with a custom sensor configuration and onboard obstacle avoidance. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

An Inductance Testing Method of Dual Three-phase Permanent Magnet Synchronous Machines Using Equivalent Electromagnetic Field Analysis

An Inductance Testing Method of Dual Three-phase Permanent M...

引用

2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023

作者： Zeng, Depeng Zhang, Qiang Zou, Jibin Xu, Yongxiang Pan, Hailang Harbin Engineering University College of Intelligent Systems Science and Engineering Harbin150001 China Harbin Institute of Technology Department of Electrical Engineering Harbin150001 China

ISBN: (纸本)9798350338362

Nowadays, in the test of permanent magnet synchronous machines (PMSMs) with traditional q-axis and d-axis inductances testing methods, the machine needs to be connected to a mechanical load, and the test must be performed in the normal operating situation. However, there are some problems existing in traditional q-axis and d-axis inductances testing methods for PMSMs, such as complexity of test systems, high testing cost, etc. It restricts the testing method development of PMSMs. In this paper, a normal method for testing q-axis and d-axis inductances of dual three-phase PMSMs is proposed based on its structural characteristics and AC standstill test. The key point of the proposed method is using equivalent electromagnetic field analysis. The advantages of this method are avoiding auxiliary equipment and considering the saturation effect. In the process of testing the q-axis and d-axis inductances of dual three-phase PMSMs, AC current with DC bias is excited in a set of windings of dual three-phase PMSMs. The DC current component is used to reflect the saturation of the magnetic circuit, and the AC current component is used for the inductance test;DC current is excited the other set of winding of the machine, and it is used to adjust and fix the rotor position. Finally, the method is validated in simulation and experiment, and the error analysis of the test results is performed. © 2023 IEEE.

关键词： Inductance

来源：评论

学校读者我要写书评

暂无评论

TECMH:Transformer-Based Cross-Modal Hashing For Fine-Grained Image-Text Retrieval

引用

Computers, Materials & Continua 2023年第5期75卷 3713-3728页

作者： Qiqi Li Longfei Ma Zheng Jiang Mingyong Li Bo Jin College of Computer and Information Science Chongqing Normal UniversityChongqing401331China Institute of Systems and Robotics(ISR) Department of Electrical and Computer Engineering(DEEC)University of CoimbraCoimbraPortugal

In recent years,cross-modal hash retrieval has become a popular research field because of its advantages of high efficiency and low ***-modal retrieval technology can be applied to search engines,crossmodalmedical processing,*** existing main method is to use amulti-label matching paradigm to finish the retrieval ***,such methods do not use fine-grained information in the multi-modal data,which may lead to suboptimal *** avoid cross-modal matching turning into label matching,this paper proposes an end-to-end fine-grained cross-modal hash retrieval method,which can focus more on the fine-grained semantic information of multi-modal ***,the method refines the image features and no longer uses multiple labels to represent text features but uses BERT for ***,this method uses the inference capabilities of the transformer encoder to generate global fine-grained ***,in order to better judge the effect of the fine-grained model,this paper uses the datasets in the image text matching field instead of the traditional label-matching *** article experiment on Microsoft COCO(MS-COCO)and Flickr30K datasets and compare it with the previous *** experimental results show that this method can obtain more advanced results in the cross-modal hash retrieval field.

关键词： Deep learning cross-modal retrieval hash learning transformer

来源：评论

学校读者我要写书评

暂无评论

An Overview and Experimental Study of Learning-Based Optimization Algorithms for the Vehicle Routing Problem

引用

IEEE/CAA Journal of Automatica Sinica 2022年第7期9卷 1115-1138页

作者： Bingjie Li Guohua Wu Yongming He Mingfeng Fan Witold Pedrycz School of Traffic and Transportation Engineering Central South UniversityChangsha 410075China College of Systems Engineering National University of Defense TechnologyChangsha 410073China Department of Electrical and Computer Engineering University of AlbertaEdmontonAB T6G 2V4Canada the Department of Electrical and Computer Engineering Faculty of EngineeringKing Abdulaziz UniversityJeddah 21589Saudi Arabia the Systems Research Institute Polish Academy of SciencesWarsaw 01447Poland IEEE

The vehicle routing problem(VRP)is a typical discrete combinatorial optimization problem,and many models and algorithms have been proposed to solve the VRP and its *** existing approaches have contributed significantly to the development of this field,these approaches either are limited in problem size or need manual intervention in choosing *** solve these difficulties,many studies have considered learning-based optimization(LBO)algorithms to solve the *** paper reviews recent advances in this field and divides relevant approaches into end-to-end approaches and step-by-step *** performed a statistical analysis of the reviewed articles from various aspects and designed three experiments to evaluate the performance of four representative LBO ***,we conclude the applicable types of problems for different LBO algorithms and suggest directions in which researchers can improve LBO algorithms.

关键词： End-to-end approaches learning-based optimization(LBO)algorithms reinforcement learning step-by-step approaches vehicle routing problem(VRP)

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition

引用

IEEE Access 2024年 12卷 106070-106083页

作者： Hsieh, I-Ting Wu, Chung-Hsien Zhao, Zhe-Hong National Cheng Kung University Graduate Program of Multimedia Systems and Intelligent Computing Tainan70101 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Under-resourced automatic speech recognition (ASR) has become an active field of research and has experienced significant progress during the past decade. However, the performance of under-resourced ASR trained by existing methods is still far inferior to high-resourced ASR for practical applications. In this paper, speech data from languages that share the most phonemes with the under-resourced language are selected as supplementary resources for meta-training based on the Model-Agnostic Meta-Learning (MAML) strategy. Besides supplementary language selection, this paper proposes a dynamic sampling method instead of the original random sampling method to select support and query sets for each task in MAML to improve meta-training performance. In this study, Taiwanese is selected as the under-resourced language, and the speech corpus of five languages, including Mandarin, English, Japanese, Cantonese, and Thai, are chosen as supplementary training data for acoustic model training. The proposed dynamic sampling approach uses phonemes, pronunciation, and speech recognition models as the basis to determine the proportion of each supplementary language to select helpful utterances for MAML. For evaluation, with the selected utterances from each supplementary language for meta-training, we obtained a Word Error Rate of 20.24% and a Syllable Error Rate of 8.35% for Taiwanese ASR, which were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and other methods. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Highly stable integration of graphene Hall sensors on a microfluidic platform for magnetic sensing in whole blood

引用

Microsystems & Nanoengineering 2023年第3期9卷 115-127页

作者： Nishal Shah Vasant Iyer Zhiping Zhang Zhaoli Gao Juhwan Park Venkata Yelleswarapu Firooz Aflatouni A.T.Charlie Johnson David Issadore Department of Bioengineering University of PennsylvaniaPhiladelphiaPA 19104USA Department of Electrical and Systems Engineering University of PennsylvaniaPhiladelphiaPA 19104USA Department of Biomedical Engineering Chinese University of Hong KongShatinHong Kong Department of Physics and Astronomy University of PennsylvaniaPhiladelphiaPA 19104USA Department of Chemical and Biomolecular University of PennsylvaniaPhiladelphiaPA 19104USA

The detection and analysis of rare cells in complex media such as blood is increasingly important in biomedical research and clinical ***-Hall detectors(μHD)for magnetic detection in blood have previously demonstrated ultrahigh sensitivity to rare *** sensitivity originates from the minimal magnetic background in blood,obviating cumbersome and detrimental sample ***,the translation of this technology to clinical applications has been limited by inherently low throughput(<1 mL/h),susceptibility to clogging,and incompatibility with commercial CMOS foundry *** help overcome these challenges,we have developed CMOS-compatible graphene Hall sensors for integration with PDMS microfluidics for magnetic sensing in *** demonstrate that these grapheneμHDs can match the performance of the best publishedμHDs,can be passivated for robust use with whole blood,and can be integrated with microfluidics and sensing electronics for in-flow detection of magnetic *** show a proof-of-concept validation of our system on a silicon substrate and detect magnetic agarose beads,as a model for cells,demonstrating promise for future integration in clinical applications with a custom CMOS chip.

关键词： integration magnetic fluid

来源：评论

学校读者我要写书评

暂无评论

Coordinated-axis Weight for Real-Time Trace Transform

Coordinated-axis Weight for Real-Time Trace Transform

引用

2023 International electrical engineering Congress, iEECON 2023

作者： Jundang, Nattapong Sitjongsataporn, Suchada Mahanakorn University of Technology The Electrical Engineering Graduate Program Faculty of Engineering and Technology Bangkok Thailand Mahanakorn University of Technology Faculty of Engineering and Technology Department of Electronic Engineering Bangkok Thailand

ISBN: (纸本)9798350332360

This paper presents a method for building Coordinated-axis Weight (CW) that has the advantage can be used to increase the speed for converting image data into the domain of real-time trace transforms. The main idea for this method is to use a feature reduction method for image data that must be used in cooperation with supervised machine learning outcome predictions. But the obtained result still retains the distinctive features of the data image in the form of a trace transform. Start by reducing the number of features from the image data, which will be used to reduce the size of the image to the appropriate image size, which in this article will reduce the image size to 45x45 pixels. The next step is to train the data using a Decision Tree (DT) method by aligning the reduced image data in a 1D model. In addition to the image data, two more features are added, i.e. the φ and ρ positions, to inform the prediction that each position has a different value. And the last step is to bring the data to create a model for predicting the answer. The weights obtained from the model are called Coordinated-axis Weights (CW). The experiments within this paper were experimented using the Caltech-256 database, which was able to measure the MSE, RMSE, and PNSR of the images compared to the original trace transform response images at 4.1, 2.02, and 42.00, respectively, including the highest predictive speed of 0.2 ms per image. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Toward Semantic MAC Protocols for 6G: From Protocol Learning to Language-Oriented Approaches

IEEE BITS the Information Theory Magazine

引用

IEEE BITS the Information Theory Magazine 2024年第1期4卷 59-72页

作者： Park, Jihong Ko, Seung-Woo Choi, Jinho Kim, Seong-Lyun Choi, Junil Bennis, Mehdi Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore Inha University Department of Smart Mobility Engineering Incheon21999 Korea Republic of University of Adelaide School of Electrical and Mechanical Engineering Adelaide5005 Australia Yonsei University School of Electrical and Electronic Engineering Seoul03722 Korea Republic of KAIST School of Electrical Engineering Daejeon34141 Korea Republic of University of Oulu Centre for Wireless Communications Oulu90014 Finland

The forthcoming 6G systems are expected to address a wide range of nonstationary tasks. This poses challenges to traditional medium access control (MAC) protocols that are static and predefined. In response, data-driven MAC protocols have recently emerged, offering ability to tailor their signaling messages for specific tasks. This article presents a novel categorization of these data-driven MAC protocols into three levels. Level 1 MAC: task-oriented neural protocols constructed using multiagent deep reinforcement learning;Level 2 MAC: neural network-oriented symbolic protocols developed by converting Level 1 MAC outputs into explicit symbols;and Level 3 MAC: language-oriented semantic protocols harnessing large language models and generative models. With this categorization, we aim to explore the opportunities and challenges of each level by delving into their foundational techniques. Drawing from information theory and associated principles as well as selected case studies, this study provides insights into the trajectory of data-driven MAC protocols and sheds light on future research directions. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Open-Switches Fault Diagnosis and Fault Tolerant Direct Torque Control of Voltage Source Inverter Fed Induction Motor 5th

Open-Switches Fault Diagnosis and Fault Tolerant Direct Torq...

引用

5th International Conference on electrical engineering and Control Applications, ICEECA 2022

作者： Boubou, Fouad Eddine Nedjai, Abd Elouahed Ammar, Abdelkarim Power and Control Engineering Department Institute of Electrical and Electronic Engineering University of M’hamed Bougara of Boumerdes Boumerdes35000 Algeria Signals and Systems Laboratory LSS Institute of Electrical and Electronic Engineering University of M’hamed Bougara of Boumerdes Boumerdes35000 Algeria

ISBN: (纸本)9789819700448

Fault diagnosis and fault tolerance are considered essential features in critical industrial applications in order to maintain the necessary levels of availability and dependability. The components that are most frequently affected by failures in closed-loop controlled power converters are semiconductors and sensors. This work focuses on fault tolerant direct torque control (DTC) of induction motor drive systems under inverter open-switch failure. This system detects and isolates the fault, and then ensures the system’s operation under the new conditions. The solution was accomplished using a new reduced switch converter. This system modifies the DTC switching table using available stator voltage vectors in two-phase mode with a Four Switch Three Phase Inverter (FSTPI) topology to maintain the performance of the motor as in the Six Switch Three Phase Inverter (SSTPI) mode. The effectiveness of the fault detection method and fault tolerant control algorithm have been investigated using MATLAB/Simulink software. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Distributed equilibrium seeking in aggregative games: linear convergence under singular perturbations lens 63

Distributed equilibrium seeking in aggregative games: linear...

引用

63rd IEEE Conference on Decision and Control, CDC 2024

作者： Carnevale, Guido Fabiani, Filippo Fele, Filiberto Margellos, Kostas Notarstefano, Giuseppe Alma Mater Studiorum - University of Bologna Department of Electrical Electronic and Information Engineering Italy Imt School for Advanced Studies Lucca Italy University of Sevilla Department of Systems Engineering and Automation Spain University of Oxford Department of Engineering Science United Kingdom

ISBN: (纸本)9798350316339

We present a fully-distributed algorithm for Nash equilibrium seeking in aggregative games over networks. The proposed scheme endows each agent with a gradient-based scheme equipped with a tracking mechanism to locally reconstruct the aggregative variable, which is not available to the agents. We show that our method falls into the framework of singularly perturbed systems, as it involves the interconnection between a fast subsystem - the global information reconstruction dynamics - with a slow one concerning the optimization of the local strategies. This perspective plays a key role in analyzing the scheme with a constant stepsize, and in proving its linear convergence to the Nash equilibrium in strongly monotone games with local constraints. By exploiting the flexibility of our aggregative variable definition (not necessarily the arithmetic average of the agents' strategy), we show the efficacy of our algorithm on a realistic voltage support case study for the smart grid. © 2024 IEEE.

关键词： Nash equilibrium

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：