检索结果-南通市图书馆

A dynamic logistic regression for network link prediction

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2017年第1期60卷 165-176页

作者： ZHOU Jing HUANG DanYang wang hansheng Department of Statistics Renmin University of China Department of Statistics Peking University

In social network analysis, link prediction is a problem of fundamental importance. How to conduct a comprehensive and principled link prediction, by taking various network structure information into consideration,is of great interest. To this end, we propose here a dynamic logistic regression method. Specifically, we assume that one has observed a time series of network structure. Then the proposed model dynamically predicts future links by studying the network structure in the past. To estimate the model, we find that the standard maximum likelihood estimation(MLE) is computationally forbidden. To solve the problem, we introduce a novel conditional maximum likelihood estimation(CMLE) method, which is computationally feasible for large-scale networks. We demonstrate the performance of the proposed method by extensive numerical studies.

关键词： conditional likelihood dynamic logistic regression link prediction social networks

Network-based naive Bayes model for social network

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2018年第4期61卷 627-640页

作者： Danyang Huang Guoyu Guan Jing Zhou hansheng wang School of Statistics Renmin University of China KLAS of MOE and School of Economics Northeast Normal University Guanghua School of Management Peking University

Naive Bayes(NB) is one of the most popular classification methods. It is particularly useful when the dimension of the predictor is high and data are generated independently. In the meanwhile, social network data are becoming increasingly accessible, due to the fast development of various social network services and websites. By contrast, data generated by a social network are most likely to be dependent. The dependency is mainly determined by their social network relationships. Then, how to extend the classical NB method to social network data becomes a problem of great interest. To this end, we propose here a network-based naive Bayes(NNB) method, which generalizes the classical NB model to social network data. The key advantage of the NNB method is that it takes the network relationships into consideration. The computational efficiency makes the NNB method even feasible in large scale social networks. The statistical properties of the NNB model are theoretically investigated. Simulation studies have been conducted to demonstrate its finite sample performance.A real data example is also analyzed for illustration purpose.

关键词： classification naive Bayes Sina Weibo social network data

A case study on the shareholder network effect of stock market data:An SARMA approach

在线全文

学校读者我要写书评

暂无评论

Science China Mathematics 2022年第11期65卷 2219-2242页

作者： Rong Zhang Jing Zhou Wei Lan hansheng wang School of Mathematics and Statistics Yunnan UniversityKunming 650500China Center for Applied Statistics School of StatisticsRenmin University of ChinaBeijing 100872China The Center of Statistical Research Southwestern University of Finance and EconomicsChengdu 611130China Guanghua School of Management Peking UniversityBeijing 100871China

One of the key research problems in financial markets is the investigation of inter-stock dependence.A good understanding in this regard is crucial for portfolio *** this end,various econometric models have been *** of them assume that the random noise associated with each subject is ***,dependence might still exist within this random *** this valuable information might lead to biased estimations and inaccurate *** this article,we study a spatial autoregressive moving average model with exogenous *** dependence from both response and random noise is considered simultaneously.A quasi-maximum likelihood estimator is developed,and the estimated parameters are shown to be consistent and asymptotically *** then conduct an extensive analysis of the proposed method by applying it to the Chinese stock market data.

关键词： spatial autoregressive moving average model shareholder network effect quasi-maximum likelihood estimator stock market data

Glacier mass balance in High Mountain Asia inferred from a GRACE release-6 gravity solution for the period 2002–2016

在线全文

学校读者我要写书评

暂无评论

Journal of Arid Land 2021年第3期13卷 224-238页

作者： XIANG Longwei wang hansheng JIANG Liming SHEN Qiang Holger STEFFEN LI Zhen School of Geosciences Yangtze UniversityWuhan 430100China State Key Laboratory of Geodesy and Earth's Dynamics Innovation Academy for Precision Measurement Science and TechnologyChinese Academy of SciencesWuhan 430077China University of Chinese Academy of Sciences Beijing 100049China Geodetic Infrastructure LantmäterietGävle 80182Sweden

We provide estimates of glacier mass changes in the High Mountain Asia (HMA) area from April2002 to August 2016 by employing a new version of gravity solutions of the Gravity Recovery and ClimateExperiment (GRACE) twin-satellite mission. We find a total mass loss trend of the HMA glaciers at a rateof –22.17 (±1.96) Gt/a. The largest mass loss rates of –7.02 (±0.94) and –6.73 (±0.78) Gt/a are found forthe glaciers in Nyainqentanglha Mountains and Eastern Himalayas, respectively. Although most glaciers inthe HMA area show a mass loss, we find a small glacier mass gain of 1.19 (±0.55) and 0.77 (±0.37) Gt/a inKarakoram Mountains and Western Kunlun Mountains, respectively. There is also a nearly zero massbalance in Pamirs. Our estimates of glacier mass change trends confirm previous results from the analysisof altimetry data of the ICESat (ICE, Cloud and Land Elevation Satellite) and ASTER (AdvancedSpaceborne Thermal Emission and Reflection Radiometer) DEM (Digital Elevation Model) satellites inmost of the selected glacier areas. However, they largely differ to previous GRACE-based studies which weattribute to our different post-processing techniques of the newer GRACE data. In addition, we explicitlyshow regional mass change features for both the interannual glacier mass changes and the 14-a averagedseasonal glacier mass changes. These changes can be explained in parts by total net precipitation (netsnowfall and net rainfall) and net snowfall, but mostly by total net radiation energy when compared to datafrom the ERA5-Land meteorological reanalysis. Moreover, nearly all the non-trend interannual masschanges and most seasonal mass changes can be explained by the total net radiation energy data. The massloss trends could be partly related to a heat effect due to increased net rainfall in Tianshan Mountains, QilianMountains, Nyainqentanglha Mountains and Eastern Himalayas. Our new results for the glacier mass changein this study could help improve the understanding of glac

关键词： glaciers mass balance GRACE precipitation snowfall radiation energy High Mountain Asia

An improved single-π equivalent circuit model for on-chip inductors in GaAs process

在线全文

学校读者我要写书评

暂无评论

Journal of Semiconductors 2017年第11期38卷 91-96页

作者： hansheng wang Weiliang He Minghui Zhang Lu Tang School of Information Science and Engineering Southeast University Nanjing 210096 China Institute of Radio Frequency and Optoelectronic Integrated Circuits Southeast University Nanjing 210096 China

An improved single-π equivalent circuit model for on-chip inductors in the GaAs process is presented in this paper. Considering high order parasites, the model is established by comprising an improved skin effect branch and a substrate lateral coupling branch. The parameter extraction is based on an improved characteristic function approach and vector fitting method. The model has better simulation than the previous work over the measured data of 2.5r and 4.5r on-chip inductors in the GaAs process.

关键词： on-chip inductors GaAs process equivalent circuit model substrate lateral coupling branch improved characteristic function approach vector fitting

Scalable wideband equivalent circuit model for silicon-based on-chip transmission lines

在线全文

学校读者我要写书评

暂无评论

Journal of Semiconductors 2017年第6期38卷 109-114页

作者： hansheng wang Weiliang He Minghui Zhang Lu Tang School of Information Science and Engineering Southeast University Nanjing 211189 China

A scalable wideband equivalent circuit model of silicon-based on-chip transmission lines is presented in this paper along with an efficient analytical parameter extraction method based on improved characteristic function approach,including a relevant equation to reduce the deviation caused by *** model consists of both series and shunt lumped elements and accounts for high-order parasitic *** equivalent circuit model is derived and verified to recover the frequency-dependent parameters at a range from direct current to 50 GHz *** scalability of the model is proved by comparing simulated and measured scattering parameters with the method of cascade,attaining excellent results based on samples made from CMOS 0.13 and 0.18 μm process.

关键词： on-chip transmission line equivalent circuit model wideband characteristic function scalability

The Low Lake-Level Record according to the Selin Co Stratigraphical Basis and Multi-Proxies during the Last Glacial Maximum in the Central Tibetan Plateau

在线全文

学校读者我要写书评

暂无评论

Acta Geologica Sinica(English Edition) 2018年第5期92卷 2058-2059页

作者： ZHANG Chengjun DEMBELE Blaise ZHANG Wanyi ZHANG Jingya wang hansheng E Gang ZHENG Qi College of Earth Sciences & Key Laboratory of Mineral Resources in Western China (Gansu Province) Lanzhou University

Objective The lake levels in the eastern and southern Asia are regarded as low lake-level owing to precipitation decreasing based on the records of lake-level fluctuation in the continental interior lakes since the last glacial maximum（LGM）（14C 18±1 kaBP,since 20 kaBP）in the Central *** lake-level appeared in the transition belt between western Kunlun Mountain and the central Tibetan Plateau.

关键词： Co TOC The Low Lake-Level Record according to the Selin Co Stratigraphical Basis and Multi-Proxies during the Last Glacial Maximum in the Central Tibetan Plateau

A review of distributed statistical inference

在线全文

学校读者我要写书评

暂无评论

Statistical Theory and Related Fields 2022年第2期6卷 89-99页

作者： Yuan Gao Weidong Liu hansheng wang Xiaozhou wang Yibo Yan Riquan Zhang School of Statistics and Key Laboratory of Advanced Theory and Application in Statistics and Data Science–MOE East China Normal UniversityShanghaiPeople’s Republic of China School of Mathematical Sciences and Key Lab of Articial Intelligence–MOE Shanghai Jiao Tong UniversityShanghaiPeople’s Republic of China Guanghua School of Management Peking UniversityBeijingPeople’s Republic of China

The rapid emergence of massive datasets in various fields poses a serious challenge to tra-ditional statistical ***,it provides opportunities for researchers to develop novel *** by the idea of divide-and-conquer,various distributed frameworks for statistical estimation and inference have been *** were developed to deal with large-scale statistical optimization *** paper aims to provide a comprehensive review for related *** includes parametric models,nonparametric models,and other frequently used *** key ideas and theoretical properties are *** trade-off between communication cost and estimate precision together with other concerns is discussed.

关键词： Distributed computing divide-and-conquer communication-efficiency shrinkage methods nonparametric estimation principal component analysis feature screening bootstrap

GRACE-based estimates of groundwater variations over North America from 2002 to 2017

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

Geodesy and Geodynamics 2022年第1期13卷 11-23页

作者： hansheng wang Longwei Xiang Holger Steffen Patrick Wu Liming Jiang Qiang Shen Zhen Li Masaki Hayashi State Key Laboratory of Geodesy and Earth's Dynamics Innovation Academy for Precision Measurement Science and TechnologyChinese Academy of SciencesWuhan 430077China University of Chinese Academy of Sciences Beijing 100049China School of Geosciences Yangtze UniversityWuhan 430100China Lantmateriet 80182GavleSweden Department of Geoscience University of CalgaryCalgaryCanada

GRACE-based estimates for groundwater storage(GWS)changes in North America substantially depend upon correction of glacialisostatic adjustment(GIA)effects,which are usually removed with GIA *** this study,GIA effects are eliminated by employing an independent separation approach with the aid of Global Navigation Satellite System(GNSS)vertical velocity *** goal is to provide an independent estimate for monthly GWS changes within North America in 1-degree-grids and their trends over the whole GRACE mission lifetime from April 2002 to June *** estimate is derived from the release-6 version of GRACE monthly level-2 data,GNSS data,land surface models for soil moisture and snow wa-ter equivalent,and satellite altimetric lake *** find a GWS anomaly in form of an increasing trend in Saskatchewan,which affects the Saskatchewan Province and the states of Montana,North Dakota and Minnesota,and 4 GWS anomalies with declining trends in Nevada,California,Arizona and Texas,*** monthly changes of these GWS anomalies,except for the one in Nevada,are validated by well level *** provide results for average monthly GWS changes and the trends for the 5 anomalies but also in separate form for the 13 affected states or *** increasing trends of the Saskatchewan GWS anomaly and the affected 3 states are related to increasing precipitation and can be elucidated by the decreasing drought intensity *** the contrary,the declining trends in GWS can be explained by weakening precipitation and are mostly supported by the increasing drought intensity level in the other 4 anomalies and the affected states,which are Nevada,California,Arizona,New Mexico,Texas,Oklahoma,Kansas,and *** of monthly GWS changes and their trendscan serveas alternativeand beneficial input for the sustainable management of groundwater resources in North America.

关键词： North America Gravity recovery and climate experiment (GRACE) GNSS Groundwater Precipitation Drought