检索结果-内蒙古大学图书馆

International Conference on Behavior, Economic and Social Computing (BESC)

作者： Jiangtao Ma Wenduo Jin Yonggang Chen Fan Zhang Shenyi Qian Yaqiong Qiao College of Computer and Information Engineering Tianjin Normal University Tianjin China School of Computer Science and Technology Zhengzhou University of Light Industry Zhengzhou China The State Information Center China National Digital Switching System Engineering and Technology R&D Center Zhengzhou China College of Cyber Science Nankai University Tianjin China

ISBN: (数字)9798331531904

ISBN: (纸本)9798331531911

Most existing multimodal named entity recognition (MNEr) methods cannot align image and text well, and fail to effectively fuse image-text semantic information, leading to suboptimal MNEr accuracy. To this end, this paper proposes a novel named entity recognition model based on Contrastive Learning and Multimodal Semantic Interaction (named CLMSI). Specifically, to narrow the semantic gap between image-text modalities, making semantically similar image-text representations closer and pushing dissimilar ones further apart, we propose a contrastive learning-based cross-modal alignment method. Moreover, to integrate multimodal information effectively and filter out the noise introduced by image features as thoroughly as possible, we propose to incorporate image descriptions as additional features to enrich the multimodal representation and to reduce the semantic bias of the image information. Extensive experiments conducted on two MNEr benchmark datasets, Twitter-2015 and Twitter-2017, demonstrate the superiority of the proposed method. Further ablation studies and case analyses also affirm the efficacy of CLMSI.

关键词： Visualization Social computing Accuracy Social networking (online) Computational modeling Semantics Noise Named entity recognition Feature extraction data mining

来源：评论

学校读者我要写书评

暂无评论

dVI-SLAM: A dual Visual Inertial SLAM Network

arXiv

引用

arXiv 2023年

作者： Peng, Xiongfeng Liu, Zhihua Li, Weiming Tan, Ping Cho, SoonYong Wang, Qiang SAIT-China Lab Samsung R&D Institute China-Beijing China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology China Multimedia System TU Samsung Advanced Institute of Technology Korea Republic of

recent deep learning based visual simultaneous localization and mapping (SLAM) methods have made significant progress. However, how to make full use of visual information as well as better integrate with inertial measurement unit (IMU) in visual SLAM has potential research value. This paper proposes a novel deep SLAM network with dual visual factors. The basic idea is to integrate both photometric factor and re-projection factor into the end-to-end differentiable structure through multi-factor data association module. We show that the proposed network dynamically learns and adjusts the confidence maps of both visual factors and it can be further extended to include the IMU factors as well. Extensive experiments validate that our proposed method significantly outperforms the state-of-the-art methods on several public datasets, including TartanAir, EuroC and ETH3d-SLAM. Specifically, when dynamically fusing the three factors together, the absolute trajectory error for both monocular and stereo configurations on EuroC dataset has reduced by 45.3% and 36.2% respectively. Copyright © 2023, The Authors. All rights reserved.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

Closed-loop Simulation Method of Stability Control system Based on Virtual Component Technology 6

Closed-loop Simulation Method of Stability Control System Ba...

引用

6th IEEE Conference on Energy Internet and Energy system Integration, EI2 2022

作者： Ma, Qinfeng Zhu, Yihua Liu, Mingshun Chang, dongxu Pu, Qingxin Li, Chengxiang Power Dispatching Control Center of Guizhou Power Grid Co. Ltd Guizhou China Southern Power Grid State Key Laboratory of HVDC Electric Power Research Institute China Guangzhou China National Energy Power Grid Technology R&D Centre Guangzhou China China Southern Power Grid CSG Key Laboratory for Power System Simulation Electric Power Research Institute Guangzhou China Guangdong Provincial Key Laboratory of Intelligent Operation and Control for New Energy Power System Guangzhou China

ISBN: (纸本)9798350347159

The stability control system is an important means to ensure the safe and stable operation of the power system. In view of the shortcomings of the existing offline/real-time simulation test methods, a closed-loop simulation scheme based on virtual component technology is proposed. The virtual component technology of the stability control device is researched, and the virtualization method of the external hardware interface of the device is designed. On this basis, a closed-loop simulation framework of the stability control system under the offline/real-time simulation test environment is proposed. The functional logic of each component under the framework are analyzed. The calculation and feedback process of the entire closed-loop simulation system are analyzed in depth, which effectively solves the difficulty of simulation analysis and test verification of large-scale stability control system, providing a new method for the research and verification of stability control system strategy. © 2022 IEEE.

关键词： Control system stability

来源：评论

学校读者我要写书评

暂无评论

Preface: Security and safety in physical layer systems

引用

Security and Safety 2024年第1期3卷 4-6页

作者： Aiqun Hu Liang Jin Xiangyun Zhou Feng Shu Xiangwei Zhou State Key Laboratory of Mobile Communications Southeast UniversityNanjing 210096China National Digital Switching System Engineering&Technological R&D Center Zhengzhou 450002China School of Engineering Australian National UniversityCanberra 2601Australia School of Information and Communication Engineering Hainan UniversityHaikou Hainan 570100China Division of Electrical and Computer Engineering Louisiana State UniversityBaton Rouge 70803USA

This special topic mainly focuses on the progress of physical-layer security(PLS)technologies and their potential applications for the future beyond fifth-generation(B5G)and sixth-generation(6G)*** tremendous growth in connectivity and the ubiquity of wireless communications have resulted in an unprecedented awareness of the importance of security and *** secure and trusted communications is vital for future intelligent connected applications,especially life-critical vehicle-toeverything(V2X)***,the heterogeneous,dynamic and decentralized architecture of these networks leads to difficulties for cryptographic key management,and *** exploiting the physical characteristics of devices,wireless channels and noise,PLS offers reliable solutions against eavesdropper attacks as complementary approaches to cryptographic techniques.

关键词： layer complementary networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of EMI Mitigation Techniques in High Speed Printed Circuit Board

Analysis of EMI Mitigation Techniques in High Speed Printed ...

引用

Innovation in Technology (INOCON), IEEE International Conference for

作者： M. Anandan L. P. Sajitha S. Geerthik Department of ECE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Department of Information Technology Agni College of technology Chennai Department of Computer Science and Business System R.M.K Engineering College Chennai

To serve the numerous services, today’s wireless communication devices require microwave network systems with multiband and multifunctional capabilities. A growing number of microwave circuits and parts that can handle several frequency bands and larger bandwidths are needed to support the unprecedented systems. The issues in EMI/EMC have grown as a result of research and advances in contemporary wireless network communication equipment. Generally speaking, there are several ways to reduce different EMI issues. Therefore, the necessary tunable and downsized components are required to make these systems smaller, lighter, and less expensive. Most studies on emission measurements have been done in the time domain recently and one of the widely used techniques is the creation of EMI band pass filters. This article presents band pass filters with HIddS (Hybrid Inter digital defected Ground Structure). Additionally, a number of uses for the hybrid S-parameters are provided by fusing Agilent AdS circuit tool and full-wave EM solvers. To provide a complete EM response of the filter construction, 3d EM simulations are performed. The analysis of the simulated findings with the results of previous experiments has revealed that HIddS (Hybrid Inter digital defected ground Structure) provides minimal insertion loss and a larger range of stop band frequencies. Therefore, wireless systems might benefit from the band pass filters with HIddS that have been proposed.

关键词： Band-pass filters Magnetic separation Wireless networks Electromagnetic interference Insertion loss Microwave communication Microwave theory and techniques

来源：评论

学校读者我要写书评

暂无评论

Moisture stable and ultrahigh-rate Ni/Mn-based sodium-ion battery cathodes via K^(+)decoration

引用

Nano research 2023年第5期16卷 6890-6902页

作者： Tao Yuan Yuanyuan Sun Siqing Li Haiying Che Qinfeng Zheng Yongjian Ni Yixiao Zhang Jie Zou Xiaoxian Zang Shi-Hao Wei Yuepeng Pang Shuixin Xia Shiyou Zheng Liwei Chen Zi-Feng Ma School of Materials and Chemistry University of Shanghai for Science and TechnologyShanghai 200093China Zhejiang Natrium Energy Co. Ltd.Shaoxing 312000China In-situ Center for Physical Sciences Shanghai Electrochemical Energy Device Research CenterFrontiers Science Center for Transformative MoleculesSchool of Chemistry and Chemical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315000China Key Laboratory of Solar Energy Utilization&Energy Saving Technology of Zhejiang Province Zhejiang Energy R&D Institute Co.Ltd.Hangzhou 311121China

As one of the most promising cathodes for sodium-ion batteries(SIBs),the layered transition metal oxides have attracted great attentions due to their high specific capacities and facile ***,their applications are still hindered by the problems of poor moisture stability and sluggish Na^(+)diffusion caused by intrinsic structural Jahn–Teller ***,we demonstrate a new approach to settle the above issues through introducing K^(+)into the structures of Ni/Mn-based *** physicochemical characterizations reveal that K^(+)induces atomic surface reorganization to form the birnessite-type K_(2)Mn_(4)O_(8).Combining with the phosphate,the mixed coating layer protects the cathodes from moisture and hinders metal dissolution into the electrolyte ***,K^(+)substitution at Na site in the bulk structure can not only widen the lattice-spacing for favoring Na^(+)diffusion,but also work as the rivet to restrain the grain crack upon *** as achieved K^(+)-decorated P2-Na_(0.67)Mn_(0.75)Ni_(0.2)5O_(2)(NKMNO@KM/KP)cathodes are tested in both coin cell and pouch cell configurations using Na metal or hard carbon(HC)as ***,the NKMNO@KM/KP||Na half-cell demonstrates a high rate performance of 50 C and outstanding cycling performance of 90.1%capacity retention after 100 cycles at 5 ***,the NKMNO@KM/KP||HC fullcell performed a promising energy density of 213.9 Wh·kg^(−1).This performance significantly outperforms most reported state-ofthe-art ***,by adopting this strategy on O3-NaMn_(0.5)Ni_(0.5)O_(2),we further proved the universality of this method on layered cathodes for SIBs.

关键词： sodium-ion battery cathode layered oxide material K^(+)decoration

来源：评论

学校读者我要写书评

暂无评论

The Frontier of Geospatial AI deep Learning Applications in data Mining and Spatial Analysis

The Frontier of Geospatial AI Deep Learning Applications in ...

引用

2024 IEEE International Conference on Intelligent systems and Advanced Applications, ICISAA 2024

作者： Mishra, Ajit Kumar Verma, Vikash Manivannan, r. Kumar, N. Krishna Srividya, Mudunuru Sharma, Sanskriti IES College of Technology Department of Electrical & Electronics Engineering M.P Bhopal462044 India GGITS Dept of Artificial Intelligence & Machine Learning M.P Jabalpur India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology School of Computing Computer Science & Engineering TN Chennai India Guru Nanak Institutions Technical Campus Ibrahimpatam Dept.of CSE Telangana Hyderabad India MLR Institute of Technology Dept. of CSE Telangana Hyderabad India GGITS Dept of Computer Science & Business System M.P Jabalpur India

ISBN: (纸本)9798331539948

Modern artificial intelligence uses geographical data mining and regional analysis to analyze large datasets. deep learning is a new geographic AI method. Example: Geographic deep Mining Network (GdMN). The Spatial Feature Extractor (SFE), Temporal Geospatial Attention Mechanism (TGAM), and Geospatial data Fusion Module (GdFM) comprise this technique. We examined six popular approaches and found GdMN performed best. It worked successfully for several reasons. GdMN always outperforms its competitors in memory, F1 score, IoU, training time, and inference time. This is always true. These findings suggest that GdMN might boost geospatial AI's data mining and location analysis abilities. After all the effort, we have developed a solid basis for location intelligence, making it useful in various subject areas. Because it's versatile, mapping specialists may use GdMN for better environmental monitoring or city development. deep learning helps GdMN make better space choices and uncover insights in large, challenging data sets that no one knew about. GdMN's cutting-edge approaches make space and time research and prediction simpler. This wide perspective offers a more full and all-encompassing picture of today's challenges than previous techniques. This makes it impossible to overstate how significant this work is to location intelligence. Its unmatched research and insights usher in a new era. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Forward Monitoring for Automated Train Operation based on Sensor Fusion of Stereo Camera and LidAr

引用

Japanese railway Engineering 2023年第2期63卷 21-23页

作者： Suzuki, Yoshihiko Kimura, Katsityuki Ohdake, Tatsuya Takahashi, Yusuke Automation and Image Applied Systems R&D Department Infrastructure Systems Research and Development Center Toshiba Infrastructure Systems & Solutions Corporation Japan IoT Edge Laboratory Information and Communications Platform Laboratories Corporate Research & Development Center Toshiba Corporation Japan Assistance System Project Team Automation and Image Applied Systems R&D Department Infrastructure Systems Research and Development Center Toshiba Infrastructure Systems & Solutions Corporation Japan

This article describes the challenges in the use of the stereo camera for forward obstacle detection for automatic operation and verifies the possibility of the use of LidAr as a complementing device. Particularly, we evaluated the detection performance of LidAr under environmental conditions in which the stereo camera has difficulty in distance measurement. We confirmed that the detection performance of the stereo camera can be complemented by combining with LidAr to improve forward obstacle detection performance. We will further collect data under various weather conditions and conduct evaluation and performance verification. © 2023 Japan railway Engineers' Association. All rights reserved.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

Optimization of Power Management in distributed Energy systems by Considering Power Loss due to Power Conversion and Electric-vehicle Movement

Optimization of Power Management in Distributed Energy Syste...

引用

Communications, Information, Electronic and Energy systems (CIEES), International Conference on

作者： Hiroshi Uchigaito Yuki Hayashi Yusuke Yasugahira Mamoru Okamoto Thantip Krasienapibal Kazumasa Ide ryoichi Hara Takashi Takemoto Laboratory Center for Exploratory Research R&D Group Hitachi Ltd. Hitachi Hokkaido University Sapporo Hokkaido Japan Division of System Science and Informatics Faculty of Information Science and Technology Hokkaido University Sapporo Hokkaido Japan

To achieve a sustainable low-carbon society and stable power supply to local areas, a self-sustaining distributed energy system” is proposed and evaluated. The system consists of multiple stand-alone small grids (“nanogrids”) that utilize renewable energy sources and multiple electric vehicles (EVs) serving as power-interchange agents among nanogrids and as means of regional mobility. Two technologies required for constructing the system were developed. The first is “nanogrid power-flow modeling” enabling quantitative evaluation including electricity loss in general nanogrid power systems including AC and dC nanogrids. The second is a “powermanagement algorithm” for multiple-electric-vehicle operations using simulated annealing in which power consumption by moving EVs is considered. Also, a simulation environment that enables quantitative evaluation of the proposed system using regional demand data was built. The performance of the system, in the case that three nanogrids were installed in Iwamizawa city, Hokkaido, was evaluated by simulation. According to the results of the simulation (performed for 365 days), as compared to the electricity loss in the case of an AC system, that in the case of a dC system was reduced by 8%. Also, in the case of the dC system, the power supply from external power grids was reduced by 33% by increasing the number of EVs. These results suggest that the higher efficiency of the dC nanogrid system makes it more suitable for regional energy supply.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-based scheduling with Multi-Objective Power Optimization in Smart Homes Utilizing Particle Swarm Optimizer

Artificial Intelligence-based scheduling with Multi-Objectiv...

引用

2023 International Conference for Technological Engineering and its Applications in Sustainable development, ICTEASd 2023

作者： Jagan, S. Murugan, G. rajasathiya, K. Badhoutiya, Arti Hemalatha, S. Ilyos, Kabulov Alzubaidi, Laith H. Indupalli, Tabitha Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology CSE India E.G.S. Pillay Engineering College Department of Computer Science and Business System Tamil Nadu Nagapattinam India P.S.R.R College of Engineering Department of Computer Science and Engineering Sivakasi626140 India GLA University Department of Electrical Engineering Mathura India Padmavathy Engineering College EEE Prince Shri Venkateshwara Chennai127 India National Research University Tashkent Institute of Irrigation and Agricultural Mechanization Engineers Tashkent Uzbekistan The Islamic University Najaf Iraq GRIET Telangana Hyderabad India

ISBN: (纸本)9798350336474

This research proposes a novel approach that integrates distinct Artificial Intelligence (AI) methodologies to address the issue of energy demand planning in Smart Homes (SH). The novel technique is designed to address a multi-objective scheduling issue, aiming to strike a balance between energy consumption and user convenience. The AI-based Power Scheduling issue in a Smart Home (AI-PSSH) involves efficiently scheduling intelligent home equipment within specified constraints and flexible pricing schemes. Various methods have been suggested to tackle the problem of AI-PSSH effectively, including both optimal and non-optimal strategies. This study presents a novel formulation for the Intelligent Home Batteries (IHB) in the context of AI-PSSH, which mitigates the impact of constraints in achieving the optimum or near-optimum outcomes. IHB may optimize the scheduling of intelligent home devices by saving excess power when it is not needed and using saved power when it is more suited to achieve the goals of PSSH. PSSH is a multi-objective optimization problem aimed at concurrently achieving all goals. Incorporating AI into smart homes has facilitated the development of sophisticated energy management techniques in scheduling and power optimization. The approach utilizes Particle Swarm Optimization (PSO) to improve the effectiveness of scheduling algorithms. Integrating PSO into the scheduling process enhances flexibility and enables smart decision-making based on real-time adjustments. The simulation results assess the proposed multi-objective AI-PSSH utilizing the IHB (MO-AI-PSSH) strategy by considering five possibilities of energy use and flexible pricing strategies. The efficiency of the suggested MO-AI-PSSH technique is compared to that of existing cutting-edge algorithms using the suggested databases utilizing the provided datasets. The MO-AI-PSSH technique, as suggested, demonstrates superior performance compared to the other algorithms in almost all instances. ©

关键词： Artificial intelligence

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：