检索结果-内蒙古大学图书馆

International Conference on Power Electronic Drives

作者： Bheemaiah Chikondra Venkateswarlu Gonuguntla Omar Al Zaabi Ranjan Kumar Behera Kalyana C Veluvolu Dept. of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE School of Electrical Engineering Vellore Institute of Technology Vellore India Symbiosis Center for Medical Image Analysis Symbiosis International University Pune India Dept. of Electrical Engineering IIT Patna India School of Electronics Engineering Kyungpook National University South Korea

Detecting early faults in an electric drive system in order to maintain reliability and uninterrupted post-fault operation is an extremely difficult task. In recent years, early fault detection has become one of the most important areas of cutting-edge research in the fields of electric vehicles, offshore-ship propulsion, air taxis, electric vertical take-off and landing, etc. In this paper, a generalized fault detection method for the five-phase induction motor drive is presented based on an optimized support vector machine (SVM) learning algorithm. Using the second low-frequency processing method, low-frequency signals were extracted from fault currents and employed for SVM training. This expedites fault detection and reduces memory allocation. The proposed fault detection algorithm has been validated through simulation in steady-state and dynamic loading conditions of the drive for a variety of fault scenarios.

关键词： Support vector machines Training Induction motor drives Machine learning algorithms Fault detection Heuristic algorithms Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Crystal structure prediction by joint equivariant diffusion 23

Crystal structure prediction by joint equivariant diffusion

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Rui Jiao Wenbing Huang Peijia Lin Jiaqi Han Pin Chen Yutong Lu Yang Liu Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University and Institute for AIR Tsinghua University Gaoling School of Artificial Intelligence Renmin University of China and Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China National Supercomputer Center in Guangzhou School of Computer Science and Engineering Sun Yat-sen University Stanford University

Crystal Structure Prediction (CSP) is crucial in various scientific disciplines. While CSP can be addressed by employing currently-prevailing generative models (e.g. diffusion models), this task encounters unique challenges owing to the symmetric geometry of crystal structures—the invariance of translation, rotation, and periodicity. To incorporate the above symmetries, this paper proposes DiffCSP, a novel diffusion model to learn the structure distribution from stable crystals. To be specific, DiffCSP jointly generates the lattice and atom coordinates for each crystal by employing a periodic-E(3)-equivariant denoising model, to better model the crystal geometry. Notably, different from related equivariant generative approaches, DiffCSP leverages fractional coordinates other than Cartesian coordinates to represent crystals, remarkably promoting the diffusion and the generation process of atom positions. Extensive experiments verify that our DiffCSP significantly outperforms existing CSP methods, with a much lower computation cost in contrast to DFT-based methods. Moreover, the superiority of DiffCSP is also observed when it is extended for ab initio crystal generation. Code is available at https://***/jiaor17/DiffCSP.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Learnable Prior Improves Inverse Tumor Growth Modeling

arXiv

引用

arXiv 2024年

作者： Weidner, Jonas Ezhov, Ivan Balcerak, Michal Metz, Marie-Christin Litvinov, Sergey Kaltenbach, Sebastian Feiner, Leonhard Lux, Laurin Kofler, Florian Lipkova, Jana Latz, Jonas Rueckert, Daniel Menze, Bjoern Wiestler, Benedikt Dept. of Computer Science The Center for Translational Cancer Research TranslaTUM Technical University of Munich Germany Dept. of Neuroradiology School of Medicine and Health Technical University of Munich Germany School of Engineering and Applied Sciences Harvard University MA United States Dept. of Quantitative Biomedicine University of Zurich Zurich Switzerland Helmholtz AI Helmholtz Zentrum Munich Germany Center for Translational Cancer Research TranslaTUM Technical University of Munich Germany Department of Pathology University of California IrvineCA United States Department of Mathematics University of Manchester United Kingdom Department of Computing Biomedical Image Analysis Group Imperial College London United Kingdom Klinikum rechts der Isar Technical University Munich Germany

Biophysical modeling, particularly involving partial differential equations (PDEs), offers significant potential for tailoring disease treatment protocols to individual patients. However, the inverse problem-solving aspect of these models presents a substantial challenge, either due to the high computational requirements of model-based approaches or the limited robustness of deep learning (DL) methods. We propose a novel framework that leverages the unique strengths of both approaches in a synergistic manner. Our method incorporates a DL ensemble for initial parameter estimation, facilitating efficient downstream evolutionary sampling initialized with this DL-based prior. We showcase the effectiveness of integrating a rapid deep-learning algorithm with a high-precision evolution strategy in estimating brain tumor cell concentrations from magnetic resonance images. The DL-Prior plays a pivotal role, significantly constraining the effective sampling-parameter space. This reduction results in a fivefold convergence acceleration and a Dice-score of 95%. Copyright © 2024, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Crystal Structure Prediction by Joint Equivariant Diffusion

arXiv

引用

arXiv 2023年

作者： Jiao, Rui Huang, Wenbing Lin, Peijia Han, Jiaqi Chen, Pin Lu, Yutong Liu, Yang Dept. of Comp. Sci. & Tech. Institute for AI Tsinghua University China Institute for AIR Tsinghua University China Gaoling School of Artificial Intelligence Renmin University China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China National Supercomputer Center in Guangzhou School of Computer Science and Engineering Sun Yat-sen University China Stanford University United States

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Co-Located Human-Human Interaction analysis using Nonverbal Cues: A Survey

arXiv

引用

arXiv 2022年

作者： Beyan, Cigdem Vinciarelli, Alessandro Del Bue, Alessio Dept. of Management Information and Production Engineering University of Bergamo Via A. Einstein 2 Dalmine24044 Italy School of Computing Science University of Glasgow GlasgowG12 8QQ United Kingdom Pattern Analysis and Computer Vision Istituto Italiano di Tecnologia Enrico Melen 83 Genoa16152 Italy

Automated co-located human-human interaction analysis has been addressed by the use of nonverbal communication as measurable evidence of social and psychological phenomena. We survey the computing studies (since 2010) detecting phenomena related to social traits (e.g., leadership, dominance, personality traits), social roles/relations, and interaction dynamics (e.g., group cohesion, engagement, rapport). Our target is to identify the nonverbal cues and computational methodologies resulting in effective performance. This survey differs from its counterparts by involving the widest spectrum of social phenomena and interaction settings (free-standing conversations, meetings, dyads, and crowds). We also present a comprehensive summary of the related datasets and outline future research directions which are regarding the implementation of artificial intelligence, dataset curation, and privacy-preserving interaction analysis. Some major observations are: the most often used nonverbal cue, computational method, interaction environment, and sensing approach are speaking activity, support vector machines, and meetings composed of 3-4 persons equipped with microphones and cameras, respectively;multimodal features are prominently performing better;deep learning architectures showed improved performance in overall, but there exist many phenomena whose detection has never been implemented through deep models. We also identified several limitations such as the lack of scalable benchmarks, annotation reliability tests, cross-dataset experiments, and explainability analysis. © 2022, CC BY-NC-ND.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Object classification using artificial neural network processing of data obtained by impulse GPR with 1 Tx + 4Rx antenna system

Object classification using artificial neural network proces...

引用

2020 IEEE Ukrainian Microwave Week, UkrMW 2020

作者： Dumin, Oleksandr Plakhtii, Vadym Pochanin, Gennadiy Shyrokorad, Dmytro V. N. Karazin Kharkiv National University School of Radio Physics Biomedical Electronics and Computer Systems Kharkiv Ukraine O. Ya. Usikov Institute for Radiophysics and Electronics National Academy of Science of Ukraine Kharkiv Ukraine Zaporizhzhja National Technical University Dept. of System Analysis and Computer Mathematics Zaporizhzhja Ukraine

ISBN: (纸本)9781728173139

The system for detection of landmines and similar object is investigated. The processing of data obtained by impulse GPR with 1 Tx + 4Rx antenna system is proposed on the basis of artificial neural network approach. The unique antenna system collects important characteristics of subsurface object from reflected impulse electromagnetic wave. The filtration of received signals from interferences caused by experimental setup, its wave-like movement, and ground surface permits to prepare the data of the needed level of quality for further processing by artificial neural network. The network successfully classify a type of object and distance to them. The stability of the object recognition is checked for different level of additional noise. © 2020 IEEE.

关键词： Ground penetrating radar systems

来源：评论

学校读者我要写书评

暂无评论

Big data classification for the analysis mel scale features using knn parameterization

引用

International Journal of Circuits, Systems and Signal Processing 2020年 14卷 978-989页

作者： Osadchyy, Volodymyr Skuratovskii, Ruslan V. Dept. of computer science UCF FL United States Institute for applied system analysis of Igor Sikorsky Kyiv Polytechnic Institute Peremohy Ave 37 Kiev03056 Ukraine

The role of human speech is intensified by the emotion it conveys. The parameterization of the vector obtained from the sentence divided into the containing emotional-informational part and the informational part is effectively applied. There are several characteristics and features of speech that differentiate it among utterances, i.e. various prosodic features like pitch, timbre, loudness and vocal tone which categorize speech into several emotions. They were supplemented by us with a new classification feature of speech, which consists in dividing a sentence into an emotionally loaded part of the sentence and a part that carries only informational load. Therefore, the sample speech is changed when it is subjected to various emotional environments. As the identification of the speaker’s emotional states can be done based on the Mel scale, MFCC is one such variant to study the emotional aspects of a speaker’s utterances. In this work, we implement a model to identify several emotional states from MFCC for two datasets, classify emotions for them on the basis of MFCC features and give the comparison of both. Overall, this work implements the classification model based on dataset minimization that is done by taking the mean of features for the improvement of the classification accuracy rate in different machine learning algorithms. © 2020, North Atlantic University Union NAUN. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Performance Enhancing Proxy for Evolved Protocols and Networks

A Lightweight Performance Enhancing Proxy for Evolved Protoc...

引用

IEEE International Workshop on computer-Aided Modeling, analysis, and Design of Communication Links and Networks, CAMAD

作者： Zsolt Krämer Sándor Molnár Marcus Pieskä Attila Mihály Dept. of Telecomm. and Media Informatics Budapest University of Technology and Economics Hungary Dept. of Mathematics and Computer Science Karlstad University Sweden Traffic Analysis and Network Performance Laboratory Ericsson Research Hungary

ISBN: (数字)9781728163390

ISBN: (纸本)9781728163406

In this paper we present the design and prototype implementation of a multi-domain congestion control framework based on a non-ossifying Lightweight Performance Enhancing Proxy. We demonstrate that our solution can be both used for evolved protocols such as end-to-end encrypted QUIC and for evolved cellular access networks like 5G. We also show the performance of our Multi-Domain Congestion Control algorithm by a simulation study. Moreover, we expose its behavior in realistic use cases like sudden capacity changes in 5G mmWave cellular networks. Our results highlight that significant performance improvements can be achieved by cooperative traffic management frameworks in protocols and networks of the future.

关键词： Servers 5G mobile communication Prototypes Cryptography Protocols Middleboxes Microsoft Windows

来源：评论

学校读者我要写书评

暂无评论

Mathematical model for heterogeneous databases parameters estimation in distributed systems with dynamic structure 2

Mathematical model for heterogeneous databases parameters es...

引用

2nd IEEE International Conference on Advanced Trends in Information Theory, ATIT 2020

作者： Mukhin, Vadym Kornaga, Yaroslav Bondarenko, Viktor Zavgorodnii, Valerii Herasymenko, Oksana Sholokhov, Oleksii National Technical University of Ukraine 'Igor Sikorsky Kiev Polytechnic Institute' Dept. of Mathematical Methods of System Analysis Kiev Ukraine Dept. of Technical Cybernetics National Technical University of Ukraine "igor Sikorsky Kiev Polytechnic Institute" Kiev Ukraine National University of Life and Environmental Sciences of Ukraine Deptatment of Computer Science Kiev Ukraine State University of Infrastructure and Technologies Department of Information Technology and Desing Kiev Ukraine Taras Shevchenko National University of Kiev Dept. of Networking and Internet Technologies Kiev Ukraine Taras Shevchenko National University of Kiev Dept. of Applied Information Systems Kiev Ukraine

ISBN: (纸本)9781728197999

A model for information processing parameters estimation in distributed systems with a dynamic structure that realize the heterogeneous distributed databases is suggested. The model is based on the choice of the tuple of parameters of the distributed system and takes into account the limitations, which allows formalize the structure for query processing control in distributed *** suggested model allows develop the new models and methods to support the effective control of the distributed data processing system with dynamic structure. © 2020 IEEE.

关键词： Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

Urban Intelligence: Toward the Digital Twin of Matera and Catania

Urban Intelligence: Toward the Digital Twin of Matera and Ca...

引用

Blockchain for Renewables Integration (BLORIN), Workshop on

作者： Giordana Castelli Amedeo Cesta Mario Ciampi Riccardo De Benedictis Giuseppe De Pietro Matteo Diez Giovanni Felici Roberto Malvezzi Barbara Masini Riccardo Pellegrini Andreas Scalas Giuseppe Stecca Lucanos Strambini Gabriella Tognola Paolo Ravazzani Emilio Fortunato Campana Engineering ICT and Technology for Energy and Transportation Dept. (DIITET) National Research Council (CNR) Rome Italy Institute of Cognitive Sciences and Technologies (ISTC) National Research Council (CNR) Rome Italy Institute for High Performance Computing and Networking (ICAR) National Research Council (CNR) Naples Italy Institute of Marine Engineering (INM) National Research Council (CNR) Rome Italy Institute for Systems Analysis and Computer Science (IASI) National Research Council (CNR) Rome Italy Engineering ICT and Technology for Energy and National Research Council (CNR) Rome Italy Institute of Electronics Computer and Telecommunication Engineering (IEIIT) National Research Council (CNR) Bologna Italy Institute for Applied Mathematics and Information Technologies (IMATI) National Research Council (CNR) Genoa Italy Institute for Systems Analysis and Computer Science “Antonio Ruberti” (IASI) National Research Council (CNR) Rome Italy Institute of Electronics Computer and Telecommunication Engineering (IEIIT) (CNR) Pisa Italy

ISBN: (纸本)9781665472500

The Urban Intelligence (UI) paradigm conceived by CNR consists of an ecosystem of digital technologies joined within a Digital Twin (DT) of the city aimed at improving the city governance towards goals addressed also by the UN Agenda 2030, such as urban environment, sustainability and resilience, wellbeing and quality of life, local development, and social inclusion. In particular, UI provides a set of candidate policies in complex scenarios, and supports policy makers and stakeholders in designing shared, evidence-based, and integrated solutions. UI is being applied for the first time to two Italian cities, Matera and Catania, paving the way for a deeper scientific framing of the paradigm, as well as for the technological development and testing of the core UI ecosystem in real-life situations. The paper introduces the UI key-concepts and components, illustrates the ongoing experimentations in these pilot cities related to the development of two DTs on parts of the urban areas, and presents some initial results.

关键词： Renewable energy sources Urban areas Ecosystems Lakes Digital twins Sensors Stakeholders

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：