检索结果-南通市图书馆

Noise Reduction for Images with Non-uniform Noise Using Adaptive Block Matching 3D Filtering

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2017年第6期26卷 1227-1232页

作者： CHEN Guangyi luo guangchun TIAN Ling CHEN Aiguo School of Computer Science and Engineering University of Electronic Science and Technology of China Department of Mechanical and Industrial Engineering Concordia University

Noise reduction is a very important topic in image processing. We propose a new method to deal with the case where the noisy image has different noise levels in different regions. The main idea is to segment automatically the noisy image into several sub-images so that each sub-image has approximately the same noise level. We perform Block matching 3D filtering(BM3D) to these subimages in order to obtain denoised sub-images. We then merge sub-images together and enhance the discontinuous regions between the sub-images by performing BM3D again on small image patches. Our experimental results show the effectiveness of this proposed method in terms of Peak signal to noise ratio(PSNR) when compared with the bivariate wavelet shrinkage and the standard BM3D method. In addition to Gaussian white noise, our method performs better than the bivariate wavelet shrinkage and the standard BM3D method even for signal dependent noise.

关键词： Image denoising noise reduction Block matching and 3D filtering(BM3D) Dual-tree complex wavelet transform(DTCWT) k-means

Denoising Graph Inference Network for Document-Level Relation Extraction

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2023年第2期6卷 248-262页

作者： Hailin Wang Ke Qin Guiduo Duan guangchun luo School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China School of Computing and Artificial Intelligence Southwestern University of Finance and EconomicsChengdu 611130China

Relation Extraction(RE)is to obtain a predefined relation type of two entities mentioned in a piece of text,e.g.,a sentence-level or a document-level *** existing studies suffer from the noise in the text,and necessary pruning is of great *** conventional sentence-level RE task addresses this issue by a denoising method using the shortest dependency path to build a long-range semantic dependency between entity ***,this kind of denoising method is scarce in document-level *** this work,we explicitly model a denoised document-level graph based on linguistic knowledge to capture various long-range semantic dependencies among *** first formalize a Syntactic Dependency Tree forest(SDT-forest)by introducing the syntax and discourse dependency ***,the Steiner tree algorithm extracts a mention-level denoised graph,Steiner Graph(SG),removing linguistically irrelevant words from the *** then devise a slide residual attention to highlight word-level evidence on text and ***,the classification is established on the SG to infer the relations of entity *** conduct extensive experiments on three public *** results evidence that our method is beneficial to establish long-range semantic dependency and can improve the classification performance with longer texts.

关键词： Relation Eextraction(RE) document-level denoising linguistic knowledge attention mechanism

A Hybrid Forecasting Framework Based on Support Vector Regression with a Modified Genetic Algorithm and a Random Forest for Traffic Flow Prediction

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2018年第4期23卷 479-492页

作者： Lizong Zhang Nawaf R Alharbe guangchun luo Zhiyuan Yao Ying Li School of Computer Science and Engineering University of Electronic Sciences and Technology of China College of Community Taibah University Al-Madinah Saudi Arabia

The ability to perform short-term traffic flow forecasting is a crucial component of intelligent transportation systems. However, accurate and reliable traffic flow forecasting is still a significant issue due to the complexity and variability of real traffic systems. To improve the accuracy of short-term traffic flow forecasting, this paper presents a novel hybrid prediction framework based on Support Vector Regression （SVR） that uses a Random Forest （RF） to select the most informative feature subset and an enhanced Genetic Algorithm （GA） with chaotic characteristics to identify the optimal forecasting model parameters. The framework is evaluated with real-world traffic data collected from eight sensors located near the 1-605 interstate highway in California. Results show that the proposed RF- CGASVR model achieves better performance than other methods.

关键词： traffic flow forecasting feature selection parameter optimization genetic algorithm machine learning

Disseminating Authorized Content via Data Analysis in Opportunistic Social Networks

在线全文

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2019年第1期2卷 12-24页

作者： Chenguang Kong guangchun luo Ling Tian Xiaojun Cao the Department of Computer Science Georgia State University the School of Computer Science and Engineering University of Electronic Science and Technology of China

Authorized content is a type of content that can be generated only by a certain Content Provider(CP).The content copies delivered to a user may bring rewards to the CP if the content is adopted by the user. The overall reward obtained by the CP depends on the user's degree of interest in the content and the user's role in disseminating the content copies. Thus, to maximize the reward, the content provider is motivated to disseminate the authorized content to the most interested users. In this paper, we study how to effectively disseminate the authorized content in Interest-centric Opportunistic Social Networks(IOSNs) such that the reward is *** first derive Social Connection Pattern(SCP) data to handle the challenging opportunistic connections in IOSNs and statistically analyze the interest distribution of the users contacted or connected. The SCP is used to predict the interests of possible contactors and connectors. Then, we propose our SCP-based Dissemination(SCPD)algorithm to calculate the optimum number of content copies to disseminate when two users meet. Our dataset based simulation shows that our SCPD algorithm is effective and efficient to disseminate the authorized content in IOSNs.

关键词： opportunistic social networks content dissemination interest centric data analytics

Location Prediction on Trajectory Data: A Review

在线全文

学校读者我要写书评

暂无评论

Big Data Mining and Analytics 2018年第2期1卷 108-127页

作者： Ruizhi Wu guangchun luo Junming Shao Ling Tian Chengzong Peng School of Computer Science and Engineering University of Electronic Science and Technology of China

Location prediction is the key technique in many location based services including route navigation, dining location recommendations, and traffic planning and control, to mention a few. This survey provides a comprehensive overview of location prediction, including basic definitions and concepts, algorithms, and applications. First, we introduce the types of trajectory data and related basic concepts. Then, we review existing location-prediction methods, ranging from temporal-pattern-based prediction to spatiotemporal-pattern-based prediction. We also discuss and analyze the advantages and disadvantages of these algorithms and briefly summarize current applications of location prediction in diverse fields. Finally, we identify the potential challenges and future research directions in location prediction.

关键词： location prediction trajectory data data mining

Compressive and energy absorption properties of closed-cell magnesium foams

在线全文

学校读者我要写书评

暂无评论

Rare Metals 2010年第4期29卷 417-420页

作者： JI Haibin,YAO guangchun,luo Hongjie,ZU Guoyin,and LIU Letian School of Material and Metallurgy,Northeastern University,Shenyang 110004,China School of Material and Metallurgy Northeastern University Shenyang China

The quasi-static compressive mechanical behavior and deformation mechanism of closed-cell magnesium foams were studied, and the ef- fects of the density of magnesium foams on the compressive and energy absorption properties were also discussed. The results show that the compressive process of closed-cell magnesium foams is characterized by three deformation stages： linear elastic stage, collapsing stage and densification stage. At the linear elastic stage, the peak compressive strength （t70） and Young＇s modulus （E0） increase as the density increases Magnesium foams can absorb energy at the collapsing stage. In a certain strain range, the energy absorption capacity also increases as the density of magnesium foams increases.

关键词： magnesium foams compression energy absorption closed-cell Young's modulus

Cloud Computing,Fog Computing, and Dew Computing

在线全文

学校读者我要写书评

暂无评论

ZTE Communications 2017年第4期15卷 1-2页

作者： PAN Yi luo guangchun Georgia State University Graduate School of the UESTC

SOctober 2017 Vol.15 No. 4 ZTE COMMUNICATIONS 01ince the first computer was invented in 1946, a few major mile?stones have stood along the way of Information Technology’s development. Among them, most notable ones are personal computers (PC), the Internet, World Wide Web (WWW), and cloud computing. Cloud computing has drastically changed the landscape of IT industry by providing some major benefits to IT customers: eliminating upfront IT investment, scalability, proportional costs, and so on. In addition, cloud computing also prompts new challenges and brings in new progress. However, the delaysensitive applications face the problem of large latency, especially when several smart devices are getting involved. Therefore, cloud computing is unable to meet the requirements of low latency, location awareness, and mobility support.

关键词： SOctober 2017 Vol.15 No. 4 ZTE COMMUNICATIONS 01ince the first computer was invented in 1946

HCOS:A Unified Model and Architecture for Cloud Operating System

在线全文

学校读者我要写书评

暂无评论

ZTE Communications 2017年第4期15卷 23-29页

作者： CHEN Aiguo WU Huaigu TIAN Ling luo guangchun University of Electronic Science and Technology of China

Currently, Infrastructure as a Service(IaaS) and Platform as a Service(PaaS) platforms play a role as a cloud operating system(COS).They are separated from each other in resource management,which may cause inconsistent resource status and result in the decrease of performance. Moreover, heterogeneous resources are not managed well in existing cloud computing platforms. Referring to the theory of operating system, we propose a unified architecture model of cloud operating system, which has six layers corresponding to the layered architecture of legacy operating system. Based on this architecture, a new cloud operating system called Hua-Cloud Computing System(HCOS) is realized. In HCOS, the hybrid resources are managed in a unified way. This method improves the unified scheduling capability of heterogeneous resources and eliminates the problem of resource status *** main characteristics of HCOS are introduced and two typical applications are illustrated in this paper.

关键词： cloud computing IaaS PaaS cloud operating system

在线全文

学校读者我要写书评

暂无评论

空间众包中的位置隐私保护技术综述

计算机应用研究 2018年第8期35卷 2241-2244,2264页

作者：安莹秦科罗光春电子科技大学计算机科学与工程学院成都611731

随着移动设备和无线网络的迅速发展,传感器能够更加精确地获取用户的位置、移动速度和方向等信息,空间众包中用户的位置隐私安全问题日益凸显,基于空间众包的位置隐私保护技术成为互联网隐私领域的研究热点。首先系统介绍了空间众包的... 详细信息

随着移动设备和无线网络的迅速发展,传感器能够更加精确地获取用户的位置、移动速度和方向等信息,空间众包中用户的位置隐私安全问题日益凸显,基于空间众包的位置隐私保护技术成为互联网隐私领域的研究热点。首先系统介绍了空间众包的基本概念、工作流程以及已有空间众包平台;归纳了空间众包中基于差分隐私、空间匿名以及加密技术的三种主流的隐私保护模型,对比分析了三种主流的隐私保护方法。最后总结并展望了未来的研究方向。

关键词：空间众包隐私保护 k-匿名差分隐私