检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Liu, Si Sun, Yao Zhu, Defa Ren, Guanghui Chen, Yu Feng, Jiashi Han, Jizhong Institute of Information Engineering Chinese Academy of Sciences *** Department of Ece National University of Singapore Jiangsu Key Laboratory of Big Data Analysis Technology/B-DAT Nanjing University of Information Science and Technology Collab. Innov. Ctr. of Atmosph. Environ. and Equip. Technol. Nanjing Univ. of Info. Sci. and Technol. Nanjing China

Human parsing has been extensively studied recently (Yamaguchi et al. 2012;Xia et al. 2017) due to its wide applications in many important scenarios. Mainstream fashion parsing models (i.e., parsers) focus on parsing the high-resolution and clean images. However, directly applying the parsers trained on benchmarks of high-quality samples to a particular application scenario in the wild, e.g., a canteen, airport or workplace, often gives non-satisfactory performance due to domain shift. In this paper, we explore a new and challenging cross-domain human parsing problem: Taking the benchmark dataset with extensive pixel-wise labeling as the source domain, how to obtain a satisfactory parser on a new target domain without requiring any additional manual labeling? To this end, we propose a novel and efficient crossdomain human parsing model to bridge the cross-domain differences in terms of visual appearance and environment conditions and fully exploit commonalities across domains. Our proposed model explicitly learns a feature compensation network, which is specialized for mitigating the cross-domain differences. A discriminative feature adversarial network is introduced to supervise the feature compensation to effectively reduces the discrepancy between feature distributions of two domains. Besides, our proposed model also introduces a structured label adversarial network to guide the parsing results of the target domain to follow the high-order relationships of the structured labels shared across domains. The proposed framework is end-to-end trainable, practical and scalable in real applications. Extensive experiments are conducted where LIP dataset is the source domain and 4 different datasets including surveillance videos, movies and runway shows without any annotations, are evaluated as target domains. The results consistently confirm data efficiency and performance advantages of the proposed method for the challenging cross-domain human parsing problem. Copyright

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

How Does Knowledge Graph Embedding Extrapolate to Unseen data: A Semantic Evidence View

arXiv

引用

arXiv 2021年

作者： Li, Ren Cao, Yanan Zhu, Qiannan Bi, Guanqun Fang, Fang Liu, Yi Li, Qian Institute of Information Engineering Chinese Academy of Sciences China School of Cyber Security University of Chinese Academy of Sciences China Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China National Computer Network Emergency Response Technical Team Coordination Center of China China University of Technology Sydney Australia

Knowledge Graph Embedding (KGE) aims to learn representations for entities and relations. Most KGE models have gained great success, especially on extrapolation scenarios. Specifically, given an unseen triple (h, r, t), a trained model can still correctly predict t from (h, r,?), or h from (?, r, t), such extrapolation ability is impressive. However, most existing KGE works focus on the design of delicate triple modeling function, which mainly tells us how to measure the plausibility of observed triples, but offers limited explanation of why the methods can extrapolate to unseen data, and what are the important factors to help KGE extrapolate. Therefore in this work, we attempt to study the KGE extrapolation of two problems: 1. How does KGE extrapolate to unseen data? 2. How to design the KGE model with better extrapolation ability? For the problem 1, we first discuss the impact factors for extrapolation and from relation, entity and triple level respectively, propose three Semantic Evidences (SEs), which can be observed from train set and provide important semantic information for extrapolation. Then we verify the effectiveness of SEs through extensive experiments on several typical KGE methods. For the problem 2, to make better use of the three levels of SE, we propose a novel GNN-based KGE model, called Semantic Evidence aware Graph Neural Network (SE-GNN). In SE-GNN, each level of SE is modeled explicitly by the corresponding neighbor pattern, and merged sufficiently by the multi-layer aggregation, which contributes to obtaining more extrapolative knowledge representation. Finally, through extensive experiments on FB15k-237 and WN18RR datasets, we show that SE-GNN achieves state-of-the-art performance on Knowledge Graph Completion task and performs a better extrapolation ability. Our code is available at https://***/renli1024/SE-GNN. Copyright © 2021, The Authors. All rights reserved.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of time irreversibility and amplitude irreversibility based on joint permutation

arXiv

引用

arXiv 2022年

作者： Yao, Wenpo Yao, Wenli Xu, Rongshuang Wang, Jun School of Geographic and Biologic Information Smart Health Big Data Analysis and Location Services Engineering Lab of Jiangsu Province Nanjing University of Posts and Telecommunications Nanjing210023 China Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Fudan University Ministry of Education China Department of Hydraulic Engineering School of Civil Engineering Tsinghua University Beijing100084 China School of Applied Meteorology Nanjing University of Information Science & Technology Nanjing210044 China

Although time irreversibility (TIR) and amplitude irreversibility (AIR) are relevant concepts for nonequilibrium analysis, their association has received little attention. This paper conducts a systematic comparative analysis of the relationship between TIR and AIR based on statistical descriptions and numerical simulations. To simplify the quantification of TIR and AIR, the amplitude permutation and global information of the associated vector are combined to produce a joint probability estimation. Chaotic logistic, Henon, and Lorenz series are generated to evaluate TIR and AIR according to surrogate theory, and the distributions of joint permutations for these model series are measured to compare the degree of TIR and AIR. The joint permutation TIR and AIR are then used to investigate nonequilibrium pathological features in epileptic electroencephalography data. Test results suggest that epileptic brain electrical activities, particular those during the onset of seizure, manifest higher nonequilibrium characteristics. According to the statistical definitions and targeted pairs of joint permutations in the chaotic model data, TIR and AIR are fundamentally different nonequilibrium descriptors from time- and amplitude-reversibility, respectively, and thus require different forms of numerical analysis. At the same time, TIR and AIR both provide measures for fluctuation theorems associated with nonequilibrium processes, and have similar probabilistic differences in the pairs of joint permutations and consistent outcomes when used to analyze both the model series and real-world signals. Overall, comparative analysis of TIR and AIR contributes to our understanding of nonequilibrium features and broadens the scope of quantitative nonequilibrium measures. Additionally, the construction of joint permutations contributes to the development of symbolic time series analysis. Copyright © 2022, The Authors. All rights reserved.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

A Nontrivial Interplay between Triadic Closure, Preferential, and Anti-Preferential Attachment: New Insights from Online data

arXiv

引用

arXiv 2022年

作者： Kozitsin, Ivan V. Sayfulin, Eduard R. Goiko, Vyacheslav L. Laboratory of Active Systems V. A. Trapeznikov Institute of Control Sciences Russian Academy of Sciences 65 Profsoyuznaya street Moscow117997 Russia Department of Higher Mathematics Moscow Institute of Physics and Technology 9 Institutskiy per. Moscow Region Dolgoprudny141701 Russia The Center of Applied Big Data Analysis National Research Tomsk State University 36 Lenina Street Tomsk634050 Russia

This paper presents an analysis of a temporal network that describes the social connections of a large-scale (~30,000) sample of online social network users, inhabitants of a fixed city. We tested how the main network formation determinants - transitivity, preferential attachment, and social selection - contribute to network evolution. Among other things, we found that opinion social selection does affect tie appearing whereas its impact on tie removing is rather unclear. We report that transitivity displayed the strongest effect on network dynamics. Surprisingly, a closer look revealed an intriguing and complex interplay between the transitivity, preferential attachment, and anti-preferential attachment mechanisms. For a given pair of unconnected nodes, if they have no mutual connections, then the probability of tie creation goes up with the total number of nodes' friends - that is exactly what the preferential attachment mechanism is assumed to do. Instead, if the nodes have at least one common friend, then the highest probability of tie appearing is achieved if both the nodes have only a few friends - a phenomenon that is called anti-preferential attachment. We attempted to explain this finding by appealing to the notions of social communities and leaders. Copyright © 2022, The Authors. All rights reserved.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Renewable-to-Ammonia: Configuration Strategy and Technoeconomic analysis

SSRN

引用

SSRN 2023年

作者： Pan, Li Li, Jiarong Huang, Jingsi An, Qi Lin, Jin Mujeeb, Asad Xu, Yanhui Li, Gengyin Zhou, Ming Wang, Jianxiao School of Electrical and Electronic Engineering North China Electric Power University Beijing102206 China Department of Electrical Engineering Tsinghua University Beijing100084 China Harvard John A. Paulson School of Engineering and Applied Sciences CambridgeMA02138 United States Department of Industrial Engineering and Management College of Engineering Peking University Beijing100871 China National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing100871 China PKU-Changsha Institute for Computing and Digital Economy Changsha410000 China

The increasing demand for nitrogen fertilizer and chemical raw materials has provided an opportunity for the ammonia (NH3) industry. Although there are many excellent reviews proposing operation control strategies and capacity configuration strategies of renewable-to-ammonia (RE2A) systems, surprisingly little attention has been devoted to topics of public interest. Therefore, this paper proposes a technoeconomic model to research the optimal capacity configuration and quantify the levelized cost of ammonia (LCOA) for RE2A. A cost model of coal-to-ammonia (C2A) is established as a benchmark to evaluate the economic feasibility of RE2A. A case study is adopted to verify the validity of the proposed approach. It is shown that the monthly NH3 output is 6-10% of the annual output, which satisfies actual industrial production. The LCOA of RE2A is 507$/t, with investments in wind turbines and electrolysers accounting for 57% and 20%, respectively, which is lower than the NH3 market price (605-650$/t) in China at present. The LCOA of RE2A will equal the LCOA of C2A with an extra carbon tax of 47.5$/t, which confirms the economic and environmental advantages of RE2A in the long run. The sensitivity analysis of RE2A in comparison with C2A provides valuable guidelines for the application of RE2A. © 2023, The Authors. All rights reserved.

关键词： Ammonia

来源：评论

学校读者我要写书评

暂无评论

NTIRE 2023 Challenge on Light Field Image Super-Resolution: dataset, Methods and Results

NTIRE 2023 Challenge on Light Field Image Super-Resolution: ...

引用

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Wang, Yingqian Wang, Longguang Liang, Zhengyu Yang, Jungang Timofte, Radu Guo, Yulan Jin, Kai Wei, Zeqiang Yang, Angulia Guo, Sha Gao, Mingzhi Zhou, Xiuzhuang Van Duong, Vinh Huu, Thuc Nguyen Yim, Jonghoon Jeon, Byeungwoo Liu, Yutong Cheng, Zhen Xiao, Zeyu Xu, Ruikang Xiong, Zhiwei Liu, Gaosheng Jin, Manchang Yue, Huanjing Yang, Jingyu Gao, Chen Zhang, Shuo Chang, Song Lin, Youfang Chao, Wentao Wang, Xuechun Wang, Guanghui Duan, Fuqing Xia, Wang Wang, Yan Xia, Peiqi Wang, Shunzhou Lu, Yao Cong, Ruixuan Sheng, Hao Yang, Da Chen, Rongshan Wang, Sizhe Cui, Zhenglong Chen, Yilei Lu, Yongjie Cai, Dongjun An, Ping Salem, Ahmed Ibrahem, Hatem Yagoub, Bilel Kang, Hyun-Soo Zeng, Zekai Wu, Heng National University of Defense Technology China Aviation University of Air Force China University of Würzburg Germany Eth Zürich Switzerland Sun Yat-sen University The Shenzhen Campus of Sun Yat-sen University China Bigo Technology Pte. Ltd. Singapore Smart Medical Innovation Lab Beijing University of Posts and Telecommunications China Global Explorer Ltd. Suzhou China National Engineering Research Center of Visual Technology School of Computer Science Peking University China School of Artificial Intelligence Beijing University of Posts and Telecommunications China Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of University of Science and Technology of China China School of Electrical and Information Engineering Tianjin University China Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University China Beijing Normal University China Toronto Metropolitan University Canada Beijing Institute of Technology China Shenzhen MSU-BIT University China State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University China Beihang Hangzhou Innovation Institute Yuhang China Faculty of Applied Sciences Macao Polytechnic University China School of Communication and Information Engineering Shanghai University China School of Information and Communication Engineering Chungbuk National University Korea Republic of Guangdong University of Technology China

ISBN: (纸本)9798350302493

In this report, we summarize the first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4. This challenge develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development. Compared with single image SR, the major challenge of LF image SR lies in how to exploit complementary angular information from plenty of views with varying disparities. In total, 148 participants have registered the challenge, and 11 teams have successfully submitted results with PSNR scores higher than the baseline method LF-InterNet [1]. These newly developed methods have set new state-of-the-art in LF image SR, e.g., the winning method achieves around 1 dB PSNR improvement over the existing state-of-the-art method DistgSSR [2]. We report the solutions proposed by the participants, and summarize their common trends and useful tricks. We hope this challenge can stimulate future research and inspire new ideas in LF image SR. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

An accuracy comparison between the time-series and the computational intelligence models on the Taiwan-central America free trade agreements

引用

ICIC Express Letters, Part B: Applications 2016年第9期7卷 1925-1932页

作者： Tsai, Pei-Wei Yang, Li-Hui Zhang, Jing Xue, Xingsi Chen, Jung-Fang Chang, Jui-Fang Pan, Jeng-Shyang College of Information Science and Engineering Fujian University of Technology University Town No. 3 Xueyan Road Minhou Fuzhou350118 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology University Town No. 3 Xueyan Road Minhou Fuzhou350118 China Department of International Business National Kaohsiung University of Applied Sciences No. 415 Chien-Kong Road Kaohsiung City80778 Taiwan Department of Business Administration National Kaohsiung University of Applied Sciences No. 415 Chien-Kong Road Kaohsiung City80778 Taiwan

Starting from the mid-20th century, Taiwanese economy is extremely exportoriented due to the lack of natural resources. To ensure the growing of the economy, Taiwan government keeps actively looking for opportunities for participation in the world economic system to avoid the slowdown of multinational liberalization. As one example, Taiwan vigorously participates in FTAs with countries of Central America. International economic conditions are significantly important to international trade and the export/import volume will be affected by the foreign exchange rate. If the impact level of an incident or an event occurrence is analyzed along with the foreign exchange rate forecasting, there is a chance to maximize the trade surplus, thus boosting the economic growth. Based on the event study methodology, the selected agreements include four Taiwan signed FTAs with countries in Central America. The observation period setting is 70 days of pre-event period and 70 days of post-event period. In this paper, we use two commonly used time-series models including the GARCH and the EGARCH and a Computational Intelligence (CI) model established by the Interactive Artificial Bee Colony (IABC) method for finding the impact on the foreign exchange rate forecasting. The Mean Absolute Percentage Error (MAPE) is adopted to compare the accuracy of exchange rate prediction. The experimental results indicate that the IABC based foreign exchange rate forecasting model presents higher forecasting accuracy than the conventional time-series models and is able to resist the impact caused by the FTAs. © 2016 ICIC International.

关键词： International trade

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network-Based Direct Power Control to Enhance the Performance of a Pmsg-Wind Energy Conversion System Under Real Wind Speed and Parameter Uncertainties: An Experimental Validation

SSRN

引用

SSRN 2023年

作者： Majout, Btissam Bossoufi, Badre Karim, Mohammed Skruch, Pawel Mobayen, Saleh El Mourabit, Youness El Zair Laggoun, Zakaria Laboratory of Engineering Modelling and Systems Analysis SMBA University Fez Morocco Department of Automatic Control and Robotics AGH University of Science and Technology Kraków30-059 Poland Graduate School of Intelligent Data Science National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou640301 Taiwan National School of Applied Sciences Abdelmalek Essaadi University Tetouan Morocco Laboratory of Electrotechnique Constantine Mentouri Brothers Constantine 1 University Constantine Algeria

With the increasing emphasis on embedding advanced technology into system controls, the Direct Power Control (DPC) approach has garnered significant attention, owing to its straightforward and highly adaptable algorithm. It has been adopted in many applications. However, the variable frequency, harmonic distortion of the currents, and power ripples caused by Hysteresis controllers and switching tables decrease its effectiveness and robustness, affecting the system’s performance. For this reason, this paper proposed a new DPC based on Artificial Neural Network (ANN) approaches. In this approach, the hysteresis comparator and the switching table are substituted with ANN controllers and then applied on both sides: machine-side converter (MSC) and grid-side converter (GSC) of a Permanent Magnet Synchronous Generator based Wind Energy Conversion System (PMSG-WECS). Moreover, to make the system more efficient in varying wind conditions, this study expands the utilization of the artificial neural networks (ANN) to encompass the maximum power point tracking (MPPT) control strategy. To demonstrate the effectiveness of the proposed approach on the system behaviors, a simulation test was carried out in the Matlab/Simulink environment, using a real wind profile of a Moroccan city (Essaouira). In comparison to the classical DPC control, the simulation results showed the superior performance of the proposed ANN-DPC control in terms of reference tracking, response time, overshoot, precision, and its capacity to reduce the rate of power ripples and total harmonic distortion (THD) in the injected currents. Furthermore, a robustness test was also included in this work to check the robustness of the proposed control against parameters variation. In conclusion, the feasibility and effectiveness of the ANN-DPC control approach were confirmed through experimental validation using the dSPACE DS1104 board. © 2023, The Authors. All rights reserved.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

A new certificate-based aggregate signature scheme for wireless sensor networks

引用

Journal of Information Hiding and Multimedia Signal Processing 2018年第5期9卷 1264-1280页

作者： Chen, Jian-Neng Zou, Fu-Min Wu, Tsu-Yang Zhou, Yu-Ping College of computer Minnan Normal University ZhangzhouFujian363000 China Beidou Navigation and Smart Traffic Innovation Center of Fujian Province FuzhouFujian350008 China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology China National Demonstration Center for Experimental Electronic Information and Electrical Technology Education Fujian University of Technology FuzhouFujian350008 China College of Computer Science and Engineering Shandong University of Science and Technology QingdaoShandong266590 China Key Laboratory of Applied Mathematics Putian University Fujian Province University PutianFujian351100 China

data transmission is one of the important basic technologies in wireless sensor networks (WSN). Due to the limited energy, storage capacity, computing power and communication ability of sensor nodes, the efficiency of data transmission is greatly limited. Certificate-based aggregate signature scheme provides an efficient way to combine numerous signatures into one short signature. In this paper, we propose a certificate-based aggregate signature scheme in WSN. In the random oracle model and under the computational Diffie-Hellman (CDH) Problem and bilinear Diffie-Hellman (BDH), we demonstrate that our scheme is provably secure against forgery attack. The performance analysis demonstrates that our scheme provides an efficient way for data transmission and is suitable in WSN. © 2018, Ubiquitous International. All rights reserved.

关键词： data transfer

来源：评论

学校读者我要写书评

暂无评论

Hierarchical Attention Feature Fusion and Refinement Network for Point Cloud Upsampling

Hierarchical Attention Feature Fusion and Refinement Network...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yaori Zhang Shujin Lin Fan Zhou Ruomei Wang National Engineering Research Center of Digital Life School of Computer Science and Engineering Guangdong Provincial Science and Technology Collaborative Innovation Center for Culture and Tourism Sun Yat-sen University Guangzhou China School of Communication and Design Guangdong Key Laboratory for Big Data Analysis and Simulation of Public Opinion Guangdong Provincial Science and Technology Collaborative Innovation Center for Culture and Tourism Sun Yat-sen University Guangzhou China Guangdong Provincial Science and Technology Collaborative Innovation Center for Culture and Tourism National Engineering Research Center of Digital Life School of Computer Science and Engineering Sun Yat-sen University Guangzhou China National Engineering Research Center of Digital Life School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

This paper presents a novel hierarchical attention feature fusion and refinement network designed to address challenges in existing deep learning based point cloud upsampling methods. The network combines self-attention layers with a multi-level feature extraction architecture, effectively integrating local and global features, thereby enhancing the robustness and uniformity of the point cloud. Furthermore, a spatial refinement module is employed to predict the offset between the generated coarse dense point clouds and real point clouds, thereby enhancing consistency with the ground truth. Concurrently, a filter function is applied in the loss function to handle outliers of generated point clouds. Extensive experimental results across multiple datasets indicate that our method outperforms existing approaches.

关键词： Point cloud compression Deep learning Feature extraction Robustness Encoding

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：