检索结果-南通市图书馆

Listwise approaches based on feature ranking discovery

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2012年第6期6卷 647-659页

作者： Yongqing WANG Wenji MAO daniel zeng Fen XIA Commercial Products Development Department Alibaba Inc.Hangzhou 310052China State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Department of Management Information Systems University of ArizonaTucsonAZ 85721USA Union Research and Development Department Baidu Inc.Beijing 100085China

Listwise approaches are an important class of learning to rank, which utilizes automatic learning techniques to discover useful information. Most previous research on listwise approaches has focused on optimizing ranking models using weights and has used imprecisely labeled training data; optimizing ranking models using features was largely ignored thus the continuous performance improvement of these approaches was hindered. To address the limitations of previous listwise work, we propose a quasi-KNN model to discover the ranking of features and employ rank addition rule to calculate the weight of combination. On the basis of this, we propose three listwise algorithms, FeatureRank, BL-FeatureRank, and DiffRank. The experimental results show that our proposed algorithms can be applied to a strict ordered ranking training set and gain better performance than state-of-the-art listwise algorithms.

关键词： learning to rank listwise approach feature's ranking discovery

Social influence and spread dynamics in social networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2012年第5期6卷 611-620页

作者： Xiaolong ZHENG Yongguang ZHONG daniel zeng Fei-Yue WANG State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China Department of Management Science and Engineering Qingdao UniversityQingdao 266071China

Social networks often serve as a critical medium for information dissemination, diffusion of epidemics, and spread of behavior, by shared activities or similarities be- tween individuals. Recently, we have witnessed an explosion of interest in studying social influence and spread dynamics in social networks. To date, relatively little material has been provided on a comprehensive review in this field. This brief survey addresses this issue. We present the current significant empirical studies on real social systems, including network construction methods, measures of network, and newly em- pirical results. We then provide a concise description of some related social models from both macro- and micro-level per- spectives. Due to the difficulties in combining real data and simulation data for verifying and validating real social sys- tems, we further emphasize the current research results of computational experiments. We hope this paper can provide researchers significant insights into better understanding the characteristics of personal influence and spread patterns in large-scale social systems.

关键词： social networks spread dynamics social influence computational experiment

Entity attribute discovery and clustering from online reviews

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2014年第2期8卷 279-288页

作者： Qingliang MIAO Qiudan LI daniel zeng Yao MENG Shu ZHANG Hao YU Fujitsu Research & Development Center Beijing 100025 China Institute of Automation Chinese Academy of Sciences Beijing 100190 China Ricoh Software Research Center (Beijing) Co. Ltd. Beijing 100082 China

The rapid increase of user-generated content （UGC） is a rich source for reputation management of enti- ties, products, and services. Looking at online product re- views as a concrete example, in reviews, customers usually give opinions on multiple attributes of products, therefore the challenge is to automatically extract and cluster attributes that are mentioned. In this paper, we investigate efficient at- tribute extraction models using a semi-supervised approach. Specifically, we formulate the attribute extraction issue as a sequence labeling task and design a bootstrapped schema to train the extraction models by leveraging a small quantity of labeled reviews and a larger number of unlabeled reviews. In addition, we propose a clustering By committee （CBC） ap- proach to cluster attributes according to their semantic simi- larity. Experimental results on real world datasets show that the proposed approach is effective.

关键词： opinion mining attribute extraction attributeclustering

Constructing public health evidence knowledge graph for decision-making support from COVID-19 literature of modelling study

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Safety Science and Resilience 2021年第3期2卷 146-156页

作者： Yunrong Yang Zhidong Cao Pengfei Zhao Dajun daniel zeng Qingpeng Zhang Yin Luo The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100190China Shenzhen Artificial Intelligence and Data Science Institute(Longhua) ShenzhenChina School of Data Science City University of Hong Kong-Hong Kong SARChina

The needs of mitigating COVID-19 epidemic prompt policymakers to make public health-related decision under the guidelines of *** unstructured COVID-19 publications make it challenging for policymakers to obtain relevant *** graphs(KGs)can formalize unstructured knowledge into structured form and have been used in supporting decision-making ***,we introduce a novel framework that can ex-tract the COVID-19 public health evidence knowledge graph(CPHE-KG)from papers relating to a modelling *** screen out a corpus of 3096 COVID-19 modelling study papers by performing a literature assessment *** define a novel annotation schema to construct the COVID-19 modelling study-related IE dataset(CPHIE).We also propose a novel multi-tasks document-level information extraction model SS-DYGIE++based on the *** the model on the new corpus,we construct CPHE-KG containing 60,967 entities and 51,140 ***,we seek to apply our KG to support evidence querying and evidence mapping *** SS-DYGIE++(SpanBERT)model has achieved a F1 score of 0.77 and 0.55 respectively in document-level entity recognition and coreference resolution *** has also shown high performance in the relation identification *** evidence querying,our KG can present the dynamic transmissions of COVID-19 pandemic in different countries and *** evidence mapping of our KG can show the impacts of variable non-pharmacological interventions to COVID-19 *** demonstrates the quality of our KG and shows that it has the potential to support COVID-19 policy making in public health.

关键词： Evidence-based public health Knowledge graph COVID-19 Decision-making support

The Chinese ‘‘HumanFlesh’’ Web:the first decade and beyond

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 Science Bulletin 2014年第26期59卷 3352-3361页

作者： Fei-Yue Wang daniel zeng Qingpeng Zhang James A. Hendler Jianping Cao The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Department of Management Information Systems The University of Arizona Tucson Department of Systems Engineering and Engineering Management City University of Hong Kong Tetherless World Constellation Department of Computer Science Rensselaer Polytechnic Institute Troy The Research Center for Computational Experiments and Parallel Systems National University of Defense Technology

Human flesh search(HFS), a Web-enabled crowdsourcing phenomenon, originated in China a decade ago. In this article, we present the first comprehensive empirical analysis of HFS, focusing on the scope of HFS activities, the patterns of HFS crowd collaboration process, and the characteristics of HFS participant networks. A survey of HFS participants was conducted to provide an in-depth understanding of the HFS community and various factors that motivate these participants to contribute. This article also advocates a new stream of Web science and social computing research that will be important in predicting the future growth and use of the World Wide Web.

关键词：中国人网址肉 Web功能实证分析参与者共同体万维网

Platform governance in the era of AI and the digital economy

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Frontiers of Engineering Management 2023年第1期10卷 177-182页

作者： Xiaolong ZHENG Gang ZHOU daniel Dajun zeng The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence Chinese Academy of SciencesBeijing 100190China

1 Introduction Companies that supply online services such as Twitter,Weibo,and Taobao are known as platform companies(Gorwa,2019).Many top companies offer their services through platforms and use Internet technology to facilitate economic transactions,transmit information,connect people,and make predictions(Fenwick et al.,2019).Such platforms cover all areas of society,including politics(Gillespie,2017),labor relations,cultural production(Scholz,2016;van Doorn,2017),and consumption(Nieborg and Poell,2018).The rapid development of Internet technology has increased the influence of network *** platforms have changed the rules of global business operations and influenced the global political *** some high-profile negative events,calls for strengthening the regulation of online platforms and holding them accountable have been growing(Suzor,2019).

关键词： companies services operations

A social computing method for energy safety

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Journal of Safety Science and Resilience 2024年第1期5卷 64-82页

作者： Pengfei Zhao Shuangqi Li Zhidong Cao Paul Jen-Hwa Hu daniel Dajun zeng Da Xie Yichen Shen Jiangfeng Li Tianyi Luo Institute of Automation Chinese Academy of SciencesUniversity of Chinese Academy of SciencesBeijing 100090China Systems Engineering Cornell UniversityIthacaNY 14853USA David Eccles School of Business the University of UtahUtahUSA Department of Electrical Engineering Shanghai Jiao Tong UniversityShanghai 200240China China University of Mining and Technology China

Information and communication technologies enable the transformation of traditional energy systems into cyber-physical energy systems(CPESs),but such systems have also become popular targets of ***,available methods for evaluating the impacts of cyberattacks suffer from limited resilience,efficacy,and practical *** mitigate their potentially disastrous consequences,this study suggests a two-stage,discrepancy-based optimization approach that considers both preparatory actions and response measures,integrating concepts from social *** proposed Kullback-Leibler divergence-based,distributionally robust optimization(KDR)method has a hierarchical,two-stage objective function that incorporates the operating costs of both system infrastructures(e.g.,energy resources,reserve capacity)and real-time response measures(e.g.,load shedding,demand-side management,electric vehicle charging station management).By incorporating social computing principles,the optimization framework can also capture the social behavior and interactions of energy consumers in response to *** preparatory stage entails day-ahead operational decisions,leveraging insights from social computing to model and predict the behaviors of individuals and communities affected by potential *** mitigation stage generates responses designed to contain the consequences of the attack by directing and optimizing energy use from the demand side,taking into account the social context and preferences of energy consumers,to ensure resilient,economically efficient CPES *** method can determine optimal schemes in both stages,accounting for the social dimensions of the *** original disaster mitigation model uses an abstract formulation to develop a risk-neutral model that characterizes cyberattacks through KDR,incorporating social computing techniques to enhance the understanding and response to cyber *** approach can mitigate the impacts more

关键词： Cyberattacks Cyber-physical energy systems Distributionally robust optimization False data injections Two-stage modeling Social computing

Adaptively temporal graph convolution model for epidemic prediction of multiple age groups

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Fundamental Research 2022年第2期2卷 311-320页

作者： Yuejiao Wang Dajun daniel zeng Qingpeng Zhang Pengfei Zhao Xiaoli Wang Quanyi Wang Yin Luo Zhidong Cao The State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijingChina School of Artificial Intelligence University of Chinese Academy of SciencesBeijingChina Shenzhen Artificial Intelligence and Data Science Institute(Longhua) ShenzhenChina School of Data Science City University of Hong Kong-Hong Kong SARChina Institute for Infectious Disease and Endemic Disease Control Beijing Center for Disease Prevention and Control BeijingChina

Introduction:Multivariate time series prediction of infectious diseases is significant to public health,and the deep learning method has attracted increasing attention in this research *** and methods:An adaptively temporal graph convolution(ATGCN)model,which leams the contact patterns of multiple age groups in a graph-based approach,was proposed for COVID-19 and influenza *** compared ATGCN with autoregressive models,deep sequence learning models,and experience-based ATGCN models in short-term and long-term prediction ***:Results showed that the ATGCN model performed better than the autoregressive models and the deep sequence learning models on two datasets in both short-term(12.5%and 10%improvements on RMSE)and longterm(12.4%and 5%improvements on RMSE)prediction *** the RMSE of ATGCN predictions fluctuated least in different age groups of COVID-19(0.029±0.003)and influenza(0.059±0.008).Compared with the Ones-ATGCN model or the Pre-ATGCN model,the ATGCN model was more robust in performance,with RMSE of 0.0293 and 0.06 on two datasets when horizon is ***:Our research indicates a broad application prospect of deep learning in the field of infectious disease *** characteristics and domain knowledge of infectious diseases should be further applied to the design of deep learning models and feature ***:The ATGCN model addressed the multivariate time series forecasting in a graph-based deep learning approach and achieved robust prediction on the confirmed cases of multiple age groups,indicating its great potentials for exploring the implicit interactions of multivariate variables.

关键词： Graph convolution model Infectious disease prediction Multiple age group Multivariate time series Public health

The Chinese Carbon-Neutral Goal:Challenges and Prospects

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in Atmospheric Sciences 2022年第8期39卷 1229-1238,I0027-I0030页

作者： Ning zeng Kejun JIANG Pengfei HAN Zeke HAUSFATHER Junji CAO daniel KIRK-DAVIDOFF Shaukat ALI Sheng ZHOU Department of Atmospheric and Oceanic Science and Earth System Science Interdisciplinary CenterUniversity of MarylandCollege Park 20742MarylandUSA State Key Laboratory of Numerical Modeling for Atmospheric Sciences and Geophysical Fluid Dynamics Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China Energy Research Institute National Development and Reform CommissionBeijing 100045China Carbon Neutrality Research Center Institute of Atmospheric PhysicsChinese Academy of SciencesBeijing 100029China Breakthrough Institute Oakland 94612CaliforniaUSA Institute of Atmospheric Physics Chinese Academy of SciencesBeijing 100029China Global Change Impact Study Centre Ministry of Climate ChangeIslamabad 45250Pakistan Institute of Energy Environment and EconomyTsinghua UniversityBeijing 100084China

On 22 September 2020,within the backdrop of the COVID-19 global pandemic,China announced its climate goal for peak carbon emissions before 2030 and to reach carbon neutrality before *** carbon-neutral goal is generally considered to cover all anthropogenic greenhouse *** planning effort is now in full swing in China,but the pathway to decarbonization is *** needed transition towards non-fossil fuel energy and its impact on China and the world may be more profound than its reform and development over the past 40 years,but the challenges are *** of four representative scenarios shows significant differences in achieving the carbon-neutral goal,particularly the contribution of non-fossil fuel energy *** high target values for nuclear,wind,and bioenergy have approached their corresponding resource limitations,with solar energy being the exception,suggesting solar’s critical *** also found that the near-term policies that allow for a gradual transition,followed by more drastic changes after 2030,can eventually reach the carbon-neutral goal and lead to less of a reduction in cumulative emissions,thus inconsistent with the IPCC 1.5°C *** challenges and prospects are discussed in the historical context of China’s socio-economic reform,globalization,international collaboration,and development.

关键词： carbon neutral carbon dioxide reductions energy system transformation distributed energy system model projections