检索结果-内蒙古大学图书馆

Exploiting global and local features for image retrieval

Journal of Central South University 2018年第2期25卷 259-276页

作者： LI Li FENG Lin WU Jun SUN Mu-xin LIU Sheng-lan School of Computer Science and Technology Faculty of Electronic Information and Electrical Engineering Dalian University of Technology School of Innovation and Entrepreneurship Dalian University of Technology School of Control Science and Engineering Faculty of Electronic Information and Electrical Engineering Dalian University of Technology

Two lines of image representation based on multiple features fusion demonstrate excellent performance in image ***,there are some problems in both of them:1)the methods defining directly texture in color space put more emphasis on color than texture feature;2)the methods extract several features respectively and combine them into a vector,in which bad features may lead to worse performance after combining directly good and bad *** address the problems above,a novel hybrid framework for color image retrieval through combination of local and global features achieves higher retrieval *** bag-of-visual words(BoW)models and color intensity-based local difference patterns(CILDP)are exploited to capture local and global features of an *** proposed fusion framework combines the ranking results of BoW and CILDP through graph-based density *** performance of our proposed framework in terms of average precision on Corel-1K database is86.26%,and it improves the average precision by approximately6.68%and12.53%over CILDP and BoW,*** experiments on different databases demonstrate the effectiveness of the proposed framework for image retrieval.

关键词： local binary patterns hue, saturation, value (HSV) color space graph fusion image retrieval

来源：评论

学校读者我要写书评

暂无评论

MirrorGAN: Learning text-to-image generation by redescription

arXiv

引用

arXiv 2019年

作者： Qiao, Tingting Zhang, Jing Xu, Duanqing Tao, Dacheng College of Computer Science and Technology Zhejiang University China Institute of System Science and Control Engineering Hangzhou Dianzi University China UBTECH Sydney AI Centre School of Computer Science FEIT University of Sydney Australia

Generating an image from a given text description has two goals: visual realism and semantic consistency. Although significant progress has been made in generating high-quality and visually realistic images using generative adversarial networks, guaranteeing semantic consistency between the text description and visual content remains very challenging. In this paper, we address this problem by proposing a novel global-local attentive and semantic-preserving text-to-image-to-text framework called MirrorGAN. MirrorGAN exploits the idea of learning text-to-image generation by redescription and consists of three modules: a semantic text embedding module (STEM), a global-local collaborative attentive module for cascaded image generation (GLAM), and a semantic text regeneration and alignment module (STREAM). STEM generates word- and sentence-level embeddings. GLAM has a cascaded architecture for generating target images from coarse to fine scales, leveraging both local word attention and global sentence attention to progressively enhance the diversity and semantic consistency of the generated images. STREAM seeks to regenerate the text description from the generated image, which semantically aligns with the given text description. Thorough experiments on two public benchmark datasets demonstrate the superiority of MirrorGAN over other representative state-of-the-art methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Multi-objective robot path planning based on bare bones particle swarm optimization with crossover operation 14

Multi-objective robot path planning based on bare bones part...

引用

14th International Conference on Natural Computation, Fuzzy Systems and Knowledge Discovery, ICNC-FSKD 2018

作者： Zhang, Jianhua Zhou, Yong Zhang, Yong School of Mechanical and Electrical Engineering Xuzhou Institute of Technology Xuzhou China School of Computer Science Technology China University of Mining and Technology Xuzhou China School of Information and Control Engineering China University of Mining and Technology Xuzhou China

ISBN: (纸本)9781538680971

This paper proposes an improved multi-objective robot path planning based on bare bones particle swarm optimization and crossover operation of Genetic algorithm. First, the path planning is mathematically formulated as a constrained multiobjective optimization problem with two indices, i.e. the path length and the safety degree of a path. Then, a multi-objective bare bones particle swarm optimization combined with crossover operation is developed to solve the above model. Aiming at the infeasible paths blocked by obstacles in evolution, three modified crossover operations, i.e. multi-point crossover, uniform crossover and arithmetic crossover, are designed to improve the feasibility of an infeasible path. Finally, simulation results confirm the effectiveness of our algorithm. © 2018 IEEE.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

White paper on broadband connectivity in 6G

arXiv

引用

arXiv 2020年

作者： Rajatheva, Nandana Atzeni, Italo Björnson, Emil Bourdoux, André Buzzi, Stefano Doré, Jean-Baptiste Erkucuk, Serhat Fuentes, Manuel Guan, Ke Hu, Yuzhou Huang, Xiaojing Hulkkonen, Jari Jornet, Josep Miquel Katz, Marcos Nilsson, Rickard Panayirci, Erdal Rabie, Khaled Rajapaksha, Nuwanthika Salehi, MohammadJavad Sarieddeen, Hadi Svensson, Tommy Tervo, Oskari Tölli, Antti Wu, Qingqing Xu, Wen Centre for Wireless Communications University of Oulu Finland Linköping University Sweden IMEC Belgium Department of Electrical and Information Engineering University of Cassino and Southern Latium Italy CEA-Leti France Department of Electrical and Electronics Engineering Kadir Has University Turkey Institute of Telecommunications and Multimedia Applications Universitat Politecnica de Valencia Spain State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong University Beijing Engineering Research Center of High-speed Railway Broadband Mobile Communications China Algorithm Department ZTE Corporation China School of Electrical and Data Engineering Faculty of Engineering and Information Technology University of Technology Sydney Australia Nokia Bell Labs Finland Department of Electrical and Computer Engineering Institute for the Wireless Internet of Things Northeastern University United States Department of Computer Science Electrical and Space Engineering Luleå University of Technology Sweden Department of Engineering Manchester Metropolitan University United Kingdom Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology Saudi Arabia Department of Electrical Engineering Chalmers University of Technology Sweden Department of Electrical and Computer Engineering National University of Singapore Singapore Huawei Technologies Germany

This white paper explores the road to implementing broadband connectivity in future 6G wireless systems. Different categories of use cases are considered, from extreme capacity with peak data rates up to 1 Tbps, to raising the typical data rates by orders-of-magnitude, to support broadband connectivity at railway speeds up to 1000 km/h. To achieve these goals, not only the terrestrial networks will be evolved but they will also be integrated with satellite networks, all facilitating autonomous systems and various interconnected structures. We believe that several categories of enablers at the infrastructure, spectrum, and protocol/algorithmic levels are required to realize the intended broadband connectivity goals in 6G. At the infrastructure level, we consider ultra-massive MIMO technology (possibly implemented using holographic radio), intelligent reflecting surfaces, user-centric and scalable cell-free networking, integrated access and backhaul, and integrated space and terrestrial networks. At the spectrum level, the network must seamlessly utilize sub-6 GHz bands for coverage and spatial multiplexing of many devices, while higher bands will be used for pushing the peak rates of point-to-point links. The latter path will lead to THz communications complemented by visible light communications in specific scenarios. At the protocol/algorithmic level, the enablers include improved coding, modulation, and waveforms to achieve lower latencies, higher reliability, and reduced complexity. Different options will be needed to optimally support different use cases. The resource efficiency can be further improved by using various combinations of full-duplex radios, interference management based on rate-splitting, machine-learning-based optimization, coded caching, and broadcasting. Finally, the three levels of enablers must be utilized not only to deliver better broadband services in urban areas, but also to provide full-coverage broadband connectivity must be one of the k

关键词： Visible light communication

来源：评论

学校读者我要写书评

暂无评论

Optimized Design of an Onboard Resonant Self-Heater for Automotive Lithium-Ion Batteries at Cold Climates

Optimized Design of an Onboard Resonant Self-Heater for Auto...

引用

IEEE Energy Conversion Congress and Exposition

作者： Chong Zhu Yunlong Shang Fei Lu Hua Zhang School of Mechanical Engineering Shanghai Jiao Tong University Shanghai P. R. China School of Control Science and Engineering Shandong University Jinan P. R. China Department of Electrical and Computer Engineering Drexel University Philadelphia PA USA

The automotive lithium-ion batteries suffer severe capacity and power degradation at subzero temperatures, leading to serious "range anxiety" of the electric vehicles (EVs). Therefore, the onboard battery preheating equipment is essential for EVs at cold climates. In this study, an interleaved resonant onboard battery self-heater is developed for internally preheating the automotive batteries without external power supplies, thereby providing great flexibility for EVs at different parking areas. By properly adjusting the switching frequency, the self-heater can achieve the zero-current-switching (ZCS) to improve the energy consumption and eliminate the voltage spikes during the turn-off. Meanwhile, a detailed guideline for optimizing the resonant tank parameters is presented so that the efficiency of the self-heater can be further developed by reducing the circulating current. The experimental validation on 18650 cells demonstrates the proposed heater can preheat the battery from -20℃ to 0℃ within only 3.5 minutes, and only consumes 5% of the cell energy.

关键词： connected and automated hybrid electric vehicles (CAHEVs) battery thermal management model predictive control energy saving

来源：评论

学校读者我要写书评

暂无评论

Visual tracking of dynamic overhead cranes via sparse representation 8

Visual tracking of dynamic overhead cranes via sparse repres...

引用

8th International Congress of Information and Communication Technology, ICICT 2018

作者： Wang, Tianlei Tan, Nanlin Zhang, Chi Zhou, Chang Zhi, Yihang School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China School of Information Engineering Wuyi University Jiangmen529020 China School of Mechanical and Electrical Engineering Wuyi University Jiangmen529020 China School of Computer Wuyi University Jiangmen529020 China

Fast and accurate tracking is ultimate important to dynamic overhead cranes control. This work presents a simple yet effective fast dynamic overhead cranes tracking method, enabling it to be applied to accurate and real time controlled. Firstly, a sparse measurement matrix is utilized to acquire the features. Secondly, compressed samples are utilized in constructing sparse measurement matrix. Finally, tracking of dynamic overhead cranes is represented as a binary classification with Bayesian classifier. Experimental results on VOT2013 benchmark and self-built Cranes40 dataset show that the proposed sparse representation tracking algorithm could achieve satisfying results on tracking overhead cranes. © 2018 The Authors. Published by Elsevier Ltd.

关键词： Bridge cranes

来源：评论

学校读者我要写书评

暂无评论

A novel anti-swing positioning controller for two dimensional bridge crane via dynamic sliding mode variable structure 8

A novel anti-swing positioning controller for two dimensiona...

引用

8th International Congress of Information and Communication Technology, ICICT 2018

作者： Wang, Tianlei Tan, Nanlin Zhou, Chang Zhang, Chi Zhi, Yihang School of Mechanical Electronic and Control Engineering Beijing Jiaotong University Beijing100044 China School of Information Engineering Wuyi University Jiangmen529020 China School of Mechanical and Electrical Engineering Wuyi University Jiangmen529020 China School of Computer Wuyi University Jiangmen529020 China

To improve the control performance of anti-swinging and the orientation of two-dimensional bridge crane, a novel dynamic sliding mode variable structure control algorithm is presented here. The proposed controller can ensure global stability through improved design of sliding surface for the drive control force, and obtain the continuous driving control force in time domain, by using the Sigmoid function for switching function to suppress chattering. Experimental results demonstrated that it is effective on chattering suppression, swing reduction, and robust with various load qualities and friction resistances. © 2018 The Authors. Published by Elsevier Ltd.

关键词： controllers

来源：评论

学校读者我要写书评

暂无评论

Mobility in MANET Using Robot: A Review 1st

Mobility in MANET Using Robot: A Review

引用

1st International Conference on Futuristic Trends in Network and Communication Technologies, FTNCT 2018

作者： Muchtar, Farkhana Abdullah, Abdul Hanan Ahmmad, Siti Nor Zawani Kumar, Yugal Faculty of Computing Universiti Teknologi Malaysia SkudaiJohor81310 Malaysia School of Computer Sciences Universiti Sains Malaysia GelugorPenang11800 Malaysia Instrumentation and Control Engineering University Kuala Lumpur MITEC Persiaran Sinaran Ilmu Bandar Seri Alam MasaiJohor81750 Malaysia Department of Science and Engineering and Information Technology Jaypee University of Information Technology Waknaghat SolanHimachal Pradesh173234 India

ISBN: (纸本)9789811338038

Recently, MANET (Mobile Ad Hoc Network) researchers have shown increased interest towards using mobile robot technology for their testbed platforms. Despite the existence of articles that discuss the usage of mobile robot technology pertaining to MANET testbed from the perspective of MANET researcher, the discussion provided in the papers are rather lacklustre as it is not the sole purpose of those articles. Hence, this review aims to discuss MANET testbeds that were facilitated with mobile robot technology from previous undertaken researches. With the wealth of information provided in this paper, it is hoped that this paper will be the ultimate source of reference for other MANET researchers who need to choose the most suitable mobile robots with real mobility in their MANET testbeds. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Exploiting contextual information via dynamic memory network for event detection

arXiv

引用

arXiv 2018年

作者： Liu, Shaobo Cheng, Rui Yu, Xiaoming Cheng, Xueqi School of Computer and Control Engineering University of CAS

The task of event detection involves identifying and categorizing event triggers. Contextual information has been shown effective on the task. However, existing methods which utilize contextual information only process the context once. We argue that the context can be better exploited by processing the context multiple times, allowing the model to perform complex reasoning and to generate better context representation, thus improving the overall performance. Meanwhile, dynamic memory network (DMN) has demonstrated promising capability in capturing contextual information and has been applied successfully to various tasks. In light of the multi-hop mechanism of the DMN to model the context, we propose the trigger detection dynamic memory network (TD-DMN) to tackle the event detection problem. We performed a five-fold cross-validation on the ACE-2005 dataset and experimental results show that the multi-hop mechanism does improve the performance and the proposed model achieves best F1 score compared to the state-of-the-art methods. Copyright © 2018, The Authors. 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

Wind Turbine Performance Assessment and Condition Monitoring with Performance Index

Wind Turbine Performance Assessment and Condition Monitoring...

引用

Sustainable Power and Energy Conference (iSPEC)

作者： Xiangyu Zhou Xin Huang Zhulin Dong Weizhi Li Minghao Jiang Department of Electrical and Computer Engineering Georgia Institute of Technology Atlanta GA U.S.A. School of Control and Computer Engineering North China Electric Power University Beijing China Department of Computer Science Purdue University West Lafayette IN U.S.A. Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Champaign IL U.S.A.

ISBN: (纸本)9781728149318

The major wind turbine performance assessment methodology established in the field of wind energy is observing and comparing wind turbine power curves (WTPC) of multiple wind turbines. In this paper, adjustments to this method are proposed to improve overall accuracy of the assessment. While preprocessing the supervisory control and data acquisition (SCADA) data points, density peak clustering (DPC) filters out invalid points such as maintenance and peak-power limitation for a more accurate WTPC. This paper introduces a new variable, performance index "S", to evaluate both overall and segmented wind turbine performance without the influence of wind distribution. Further researches are also discussed in this paper.

关键词： wind turbine diagnosis performance assessment power curve density peak clustering (DPC) supervisory control and data acquisition (SCADA) power curve performance indicators Wind Energy Conversion Systems Performance assessment Supervisory control and data acquisition Condition monitoring Supervisory control Wind energy

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：