检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Ye, Dongjie Ni, Zhangkai Wang, Hanli Zhang, Jian Wang, Shiqi Kwong, Sam The Department of Computer Science City University of Hong Kong 999077 Hong Kong The Department of Computer Science & Technology Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai Institute of Intelligent Science and Technology Tongji University Shanghai200092 China The School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen518055 China The Peng Cheng Laboratory Shenzhen518052 China The City University of Hong Kong Shenzhen Research Institute Shenzhen518057 China

Convolution neural networks (CNNs) have succeeded in compressive image sensing. However, due to the inductive bias of locality and weight sharing, the convolution operations demonstrate the intrinsic limitations in modeling the long-range dependency. Transformer, designed initially as a sequence-to-sequence model, excels at capturing global contexts due to the self-attention-based architectures even though it may be equipped with limited localization abilities. This paper proposes CSformer, a hybrid framework that integrates the advantages of leveraging both detailed spatial information from CNN and the global context provided by transformer for enhanced representation learning. The proposed approach is an end-to-end compressive image sensing method, composed of adaptive sampling and recovery. In the sampling module, images are measured block-by-block by the learned sampling matrix. In the reconstruction stage, the measurement is projected into dual stems. One is the CNN stem for modeling the neighborhood relationships by convolution, and the other is the transformer stem for adopting global self-attention mechanism. The dual branches structure is concurrent, and the local features and global representations are fused under different resolutions to maximize the complementary of features. Furthermore, we explore a progressive strategy and window-based transformer block to reduce the parameter and computational complexity. The experimental results demonstrate the effectiveness of the dedicated transformer-based architecture for compressive sensing, which achieves superior performance compared to state-of-the-art methods on different datasets. Copyright © 2021, The Authors. All rights reserved.

关键词： Compressed sensing

来源：评论

学校读者我要写书评

暂无评论

An Online Market Mechanism for Edge Emergency Demand Response via Cloudlet Control

An Online Market Mechanism for Edge Emergency Demand Respons...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE Computer and Communications Societies

作者： Shutong Chen Lei Jiao Lin Wang Fangming Liu Key Laboratory of Services Computing Technology and System Ministry of Education School of Computer Science and Technology Huazhong University of Science and Technology China University of Oregon USA VU Amsterdam The Netherlands

The computing frontier is moving from centralized mega datacenters towards distributed cloudlets at the network edge. We argue that cloudlets are well-suited for participation in Emergency Demand Response (EDR) programs due to their enormous energy consumption and flexible workload distribution, while existing EDR mechanisms for clouds and colocation datacenters are not suitable for cloudlets. We propose a novel online market mechanism, EdgeEDR, to incentivize cloudlets to participate in EDR, featuring multiple cloudlet-specific designs. At a high level, we observe that cloudlet operators can dynamically switch on/off entire cloudlets to compensate for the energy reduction required by the power grid. We formulate a long-term social cost minimization problem and decompose it into a series of one-round procurement auctions. In each auction instance, we propose to let the cloudlet tenants bid with cost functions of their service quality degradation tolerance, and let the cloudlet operator choose the service quality, allocate the workload, and shut down the cloudlets. Via rigorous analysis, we exhibit that our bidding policy is individually rational and truthful; our workload distribution algorithm has near-optimal performance in each auction; and our overall online algorithm achieves a provable competitive ratio. We further confirm the performance of our mechanism through extensive trace-driven simulations.

关键词： Cloud computing Delays Switches Generators Degradation Procurement Load management

来源：评论

学校读者我要写书评

暂无评论

DeeperForensics challenge 2020 on real-world face forgery detection: Methods and results

arXiv

引用

arXiv 2021年

作者： Jiang, Liming Guo, Zhengkui Wu, Wayne Liu, Zhaoyang Liu, Ziwei Loy, Chen Change Yang, Shuo Xiong, Yuanjun Xia, Wei Chen, Baoying Zhuang, Peiyu Li, Sili Chen, Shen Yao, Taiping Ding, Shouhong Li, Jilin Huang, Feiyue Cao, Liujuan Ji, Rongrong Lu, Changlei Tan, Ganchao S-Lab Nanyang Technological University Singapore Chinese University Hong Kong SenseTime Research Hong Kong Amazon Web Services. United States Shenzhen Key Laboratory of Media Information Content Security Shenzhen University China Media Analytics and Computing Lab Xiamen University China YouTu Lab Tencent Shanghai China University of Science and Technology China

This paper reports methods and results in the DeeperForensics Challenge 2020 on real-world face forgery detection. The challenge employs the DeeperForensics-1.0 dataset, one of the most extensive publicly available real-world face forgery detection datasets, with 60,000 videos constituted by a total of 17.6 million frames. The model evaluation is conducted online on a high-quality hidden test set with multiple sources and diverse distortions. A total of 115 participants registered for the competition, and 25 teams made valid submissions. We will summarize the winning solutions and present some discussions on potential research directions. Copyright © 2021, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Model Parameter Analysis of Cracked Photovoltaic Module under Outdoor Conditions

Model Parameter Analysis of Cracked Photovoltaic Module unde...

引用

2020 47th IEEE Photovoltaic Specialists Conference (PVSC)

作者： Jingwei Zhang Yongjie Liu Kun Ding Li Feng Frank U. Hamelmann Xiang Chen College of Mechanical and Electrical Engineering Hohai University Changzhou China Solar Computing Lab University of Applied Science Bielefeld Minden Germany Changzhou Key Laboratory of Photovoltaic System Integration and Production Equipment Technology Changzhou China

ISBN: (数字)9781728161150

ISBN: (纸本)9781728161167

In the recent decade, the intelligent maintenance of the PV systems is a new trend in this area. In order to facilitate the further fault prognosis of the PV module, in this paper, the model parameters of the single diode model for a glass-cracked PV module with cracked cells, which cannot be visually inspected, are extracted based on the outdoor measured current-voltage (I-V) curves. The cracks of the solar cells are also observed from the electroluminescence images. The comparison results of the I-V curves from a referenced normal PV module and the glass-cracked PV module indicate that the photocurrent and the equivalent shunt resistance of the cracked solar cells in the fault PV module decreases significantly. The extracted parameters can quantitatively describe the failure degree of the cracked solar cells. The extracted parameter can also be used to further predict the degradation trend of the fault PV module and realize fault prognosis of PV modules.

关键词： Photovoltaic cells Resistance Temperature measurement Photovoltaic systems Photoconductivity Analytical models Market research

来源：评论

学校读者我要写书评

暂无评论

The effects of different travel modes and travel destinations on COVID-19 transmission in global cities

引用

Science Bulletin 2022年第6期67卷 588-592,M0003页

作者： Rui Zhu Luc Anselin Michael Batty Mei-Po Kwan Min Chen Wei Luo Tao Cheng Che Kang Lim Paolo Santi Cheng Cheng Qiushi Gu Man Sing Wong Kai Zhang Guonian Lü Carlo Ratti Department of Land Surveying and Geo-Informatics the Hong Kong Polytechnic UniversityHong KongChina Key Laboratory of Virtual Geographic Environment(Ministry of Education) Nanjing Normal UniversityNanjing 210023China Senseable City Laboratory Future Urban Mobility IRGSingapore-MIT Alliance for Research and TechnologySingapore 138602Singapore Center for Spatial Data Science Division of the Social SciencesUniversity of ChicagoChicago IL 60637USA School of Geography Science Nanjing Normal UniversityNanjing 210023China Centre for Advanced Spatial Analysis Faculty of the Built EnvironmentUniversity College LondonLondon WC1E 6BTUK Department of Geography and Resource Management the Chinese University of Hong KongHong KongChina Institute of Space and Earth Information Science the Chinese University of Hong KongHong KongChina Department of Human Geography and Spatial Planning Utrecht UniversityUtrecht 3584 CSNetherlands State Key Laboratory Cultivation Base of Geographical Environment Evolution Nanjing 210023China Department of Geography National University of SingaporeSingapore 117570Singapore SpaceTimeLab Department of CivilEnvironmental and Geomatic EngineeringUniversity College LondonLondon WC1E 6BTUK Department of Clinical Translational Research Singapore General HospitalSingapore 169856Singapore Division of Clinical Immunology and Transfusion Medicine Department of Laboratory MedicineKarolinska InstitutetStockholm 17177Sweden Senseable City Laboratory Department of Urban Studies and PlanningMassachusetts Institute of TechnologyCambridgeMA 02139USA Istituto di Informatica e Telematica del CNR Pisa 56124Italy Department of System Science Institute of High Performance Computing Agency for ScienceTechnology and ResearchSingapore 138632Singapore Department of Tourism Studies School of HumanitiesSoutheast UniversityNanjing 210096China

The international community has made significant efforts to flatten the COVID-19 curve,including predicting transmission[1,2],executing unprecedented global lockdowns and social distancing[3,4],promoting the wearing of facemasks and social distancing measures[5],and isolating confirmed cases and contacts[6].Because of the adverse consequences of these lockdown measures[7],many cities have reopened so they can rebuild their ***,as mobility has gradually returned towards normal,imported cases from unknown sources have disrupted the recovery situation,and cities are continually at high risk of new waves of infection[8,9]since airborne transmission is the dominant transmission route[10].

关键词：多变量时间序列疫情传播出行方式谷歌公司交通出行病毒传播出行行为大城市

来源：评论

学校读者我要写书评

暂无评论

A knowledge acquisition automatizing framework from literature exemplified by Na + activation energy prediction of NASICON solid-state electrolyte

引用

Energy Storage Materials 2025年 80卷

作者： Yue Liu Dahui Liu Zhengwei Yang Xianyuan Ge Wenxuan Yao Jie Wu Maxim Avdeev Siqi Shi State Key Laboratory of Materials for Advanced Nuclear Energy & School of Computer Engineering and Science Shanghai University Shanghai 200444 China Shanghai Engineering Research Center of Intelligent Computing System Shanghai 200444 China Australian Nuclear Science and Technology Organisation Sydney 2232 Australia School of Chemistry The University of Sydney Sydney 2006 Australia State Key Laboratory of Materials for Advanced Nuclear Energy & School of Materials Science and Engineering Shanghai University Shanghai 200444 China Materials Genome Institute Shanghai University Shanghai 200444 China

Materials science literature contains vast amount of structure-activity relationship knowledge crucial for materials discovery and design. However, automatic extraction of domain knowledge from literature remains challenging due to its unstructured and heterogeneous format. Herein, we propose a framework for automating knowledge acquisition, which involves a materials entity-aware relational extraction model (MatRE) to mine triples, an approach to construct a knowledge graph (KG) for the detection of associations among triples, as well as inference and representation of structure-activity relationships in a machine learning (ML)-compatible format. We demonstrate its application in predicting sodium ion activation energy for the NASICON solid-state electrolyte (SSE) system. MatRE trained on a NASICON SSE dataset, achieves an F1-score of 0.80, and is used to extract 260,475 entity–relation triples from 1,808 scientific publications. Furthermore, embedding 24 knowledge bullets from the KG into data pre-processing and feature engineering stages improves the performance and interpretability of six common ML models by up to 25.7%. This work offers key insights into automatic knowledge acquisition from literature and heralds a new paradigm for AI-assisted materials genome engineering driven by both data and knowledge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HDTCNet: A hybrid-dimensional convolutional network for multivariate time series classification

引用

Pattern Recognition 2025年 168卷

作者： Yongli Gu Xiang Yan Hanlin Qin Naveed Akhtar Shuai Yuan Honghao Fu Shuowen Yang Ajmal Mian School of Optoelectronic Engineering Xidian University Xi’an 710071 China Xi’an Key Laboratory of Infrared Technology and System Xi’an 710071 China School of Computing and Information Systems The University of Melbourne Parkville VIC 3052 Australia School of Electrical and Electronic Engineering Nanyang Technological University Singapore 639798 Singapore School of Computer Science and Software Engineering The University of Western Australia Crawley WA 6009 Australia

Currently, transformer-based models dominate time series classification due to their ability to capture global data dependencies. However, their large memory footprint and high computational demands make them less desirable for long multivariate time series modeling. At the same time, convolution-based models promise a desirable performance versus efficiency trade-off for the task. Nevertheless, the popularity of transformer models has impeded exploration of sophisticated convolution-based modeling for time series classification. In this work, we introduce a novel convolution-based model, called HDTCNet, that alternates between 1D and 2D convolutional modes to capture temporal pattern correlations between intra- and inter-sensor variations. We develop a Wavelet Time Convolution block to expand the effective receptive field of the underlying neural model with a small convolutional kernel that embeds a set of 1D convolution operators between a cascade of wavelet decomposition and reconstruction of the input time series. To efficiently represent the local features of multivariate time series, we devise a hierarchical difference convolution network to capture intra- and inter-sensor gradient variations. To refine the feature representation of sensor-level time series and achieve multi-view self-enhancement, we design a self-enhancing module. These innovations enable HDTCNet to achieve superior performance while maintaining efficiency as a purely convolutional model. Experimental results demonstrate that HDTCNet achieves 2.1% accuracy and 1% F1-score performance improvements over state-of-the-art methods on 25 UEA classification datasets and 3 anomaly detection datasets, respectively, while reducing parameter counts by two orders of magnitude. Our code will be available at https://***/Guuuli/HDTCNet .

关键词： Classification Convolutional network Difference calculation Multivariate time series Wavelet transform

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic Array Power Prediction Model Based on EEMD and PSO-KELM

Photovoltaic Array Power Prediction Model Based on EEMD and ...

引用

2020 47th IEEE Photovoltaic Specialists Conference (PVSC)

作者： Kun Ding Xiang Chen Jingwei Zhang Li Feng Frank U. Hamelmann Shuai Weng College of Mechanical and Electrical Engineering Hohai University Changzhou China Solar Computing Lab University of Applied Science Bielefeld Minden Germany Changzhou Key Laboratory of Photovoltaic System Integration and Production Equipment Technology Changzhou China

ISBN: (数字)9781728161150

ISBN: (纸本)9781728161167

In order to improve the accuracy of short-term photovoltaic (PV) power prediction, the PV array power prediction model based on ensemble empirical mode decomposition (EEMD) and kernel extreme learning machine (KELM) optimized by particle swarm optimization algorithm (PSO-KELM) is proposed in this paper. The EEMD algorithm is used to decompose the power sequence of the PV array into a series of intrinsic mode functions (IMFs) with different features, the IMFs with similar features are divided into new components by sample entropy (SE), and establishing the KELM power prediction model corresponding to the new component. The PSO is used to optimize the output weight of KELM, seeking the optimal solution of upper and lower limits, and improving the performance of KELM. The actual data is used to compare the proposed prediction model with the traditional back-propagation (BP) and extreme learning machine (ELM) prediction models. The results validate that the proposed model can predict power of PV array with good accuracy and calculation speed.

关键词： Predictive models Kernel Biological system modeling Prediction algorithms Power generation Particle swarm optimization Neural networks

来源：评论

学校读者我要写书评

暂无评论

Extracting and Clustering the Evaluation Objects of the Chinese Product Recommendation system Based on the Opinion Mining

Extracting and Clustering the Evaluation Objects of the Chin...

引用

2019 3rd International Conference on Informatization in Education,Management and Business(IEMB 2019)

作者： Yingbin Xue Xiaoye Wang Yingyuan Xiao Yukun Li Wenguang Zheng Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Key Laboratory of Computer Vision and System Tianjin University of Technology Ministry of Education

The research of product recommendation system mainly focuses on the user s behavior or the commodities. contents, but rarely focuses on the commodies. reviews. This paper extracts useful information hidden in the commodies. reviews by opinion mining technology. It is more targeted that recommending product to users according to the user’s favorite property. The main process of opinion mining is the extraction of topic words and the polarity judgement of polar words. Because the time complexity of the topic extracting algorithm is high, this paper extracts the explicit evaluation object and evaluation words by using the method of matching noun phrase and then setting up a semantic mapping set of evaluation objects and evaluation words to determine the implicit evaluation object. In this paper, k-means and BIRCH are combined to cluster the evaluation objects. K-Means algorithm is used for pre-clustering for the BIRCH algorithm to solve local optimum. And the advantage of BIRCH is it can get the number of clusters by self-learning. And delete the clusters contained few contents to pruning evaluation objects. It can reduce the time complexity and guarantees the clustering effect.

关键词： Product recommendation opinion mining extraction of theme words clustering

来源：评论

学校读者我要写书评

暂无评论

Spike Sorting Based on Window-Gradient Feature

Spike Sorting Based on Window-Gradient Feature

引用

2018计算机科学与工程技术国际研讨会

作者： Min Dai Feng Jia Wen Yang Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology

Spike sorting is difficult when there is high waveforms similarity between different spike or when there is a large number of superimposed spikes in the sample. A new sample optimization method is proposed in the paper, called window-gradient feature. Every spike waveform is segmented into successive fragments in terms of the width σ, and each segment is called a window. Then calculate the gradient change of each window and use the ratio as the new alternative feature of the window. Finally, all window-gradient features of the spike waveforms are used to replace the original waveform features for spike sporting. The method is verified on the simulation data at different SNR. The experimental results show that when using SVM for spike sorting, the optimization effect of the proposed method is better than PCA, especially for data sets data sets with high noise or large sampling waveform similarity.

关键词： SNR Spike Sorting Based on Window-Gradient Feature

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：