移动网络数据中大数据处理的关键技术探索

最近几年以来,我国科技水平持续提升,计算机网络技术也逐渐在各行各业中获得了广泛运用,这也使得信息技术的深度融合发展受到一定的促进,数据规模愈发庞大,在此背景下,开始演变成大数据供不应求的状况.为此,国内陆续推出了一系列相关的管理法规与条例,同时扩大了对大数据的探究创新力度,有效提升了移动通信网络处理数据的速度,这同时促...     

Identification of approximately duplicate material records in ERP systems

The quality of master data is crucial for the accurate functioning of the various modules of an enterprise resource planning (ERP) system. This study addresses specific data problems arising from the generation of approximately duplicate material records in ERP databases. Such problems are mainly due to the firm’s lack of unique and global identifiers for the material records, and to the arbitrary assignment of alternative names for the same material by various users. Traditional duplicate detection methods are ineffective in identifying such approximately duplicate material records because these methods typically rely on string comparisons of each field. To address this problem, a machine learning-based framework is developed to recognise semantic similarity between strings and to further identify and reunify approximately duplicate material records – a process referred to as de-duplication in this article. First, the keywords of the material records are extracted to form vectors of discriminating words. Second, a machine learning method using a probabilistic neural network is applied to determine the semantic similarity between these material records. The approach was evaluated using data from a real case study. The test results indicate that the proposed method outperforms traditional algorithms in identifying approximately duplicate material records.     

Bartlett correction to the likelihood ratio test for MCAR with two‐step monotone sample

Assuming that two‐step monotone missing data is drawn from a multivariate normal population, this paper derives the Bartlett‐type correction to the likelihood ratio test for missing completely at random (MCAR), which plays an important role in the statistical analysis of incomplete datasets. The advantages of our approach are confirmed in Monte Carlo simulations. Our correction drastically improved the accuracy of the type I error in Little's (1988, Journal of the American Statistical Association, 83 , 1198–1202) test for MCAR and performed well even on moderate sample sizes.     

Conditional assessment of the impact of a Hausman pretest on confidence intervals

In the analysis of clustered and longitudinal data, which includes a covariate that varies both between and within clusters, a Hausman pretest is commonly used to decide whether subsequent inference is made using the linear random intercept model or the fixed effects model. We assess the effect of this pretest on the coverage probability and expected length of a confidence interval for the slope, conditional on the observed values of the covariate. This assessment has the advantages that it (i) relates to the values of this covariate at hand, (ii) is valid irrespective of how this covariate is generated, (iii) uses exact finite sample results, and (iv) results in an assessment that is determined by the values of this covariate and only two unknown parameters. For two real data sets, our conditional analysis shows that the confidence interval constructed after a Hausman pretest should not be used.     

THE MEANING OF FAILED REPLICATIONS: A REVIEW AND PROPOSAL

The welcome rise of replication tests in economics has not been accompanied by a consensus standard for determining what constitutes a replication. A discrepant replication, in current usage of the term, can signal anything from an unremarkable disagreement over methods to scientific incompetence or misconduct. This paper proposes a standard for classifying one study as a replication of some other study. It is a standard that places the burden of proof on a study to demonstrate that it should have obtained identical results to the original, a conservative standard that is already used implicitly by many researchers. It contrasts this standard with decades of unsuccessful attempts to harmonize terminology, and argues that many prominent results described as replication tests should not be described as such. Adopting a conservative standard like this one can improve incentives for researchers, encouraging more and better replication tests.     

NONPARAMETRIC AND SEMIPARAMETRIC PANEL DATA MODELS: RECENT DEVELOPMENTS

In this paper, we provide an intensive review of the recent developments for semiparametric and fully nonparametric panel data models that are linearly separable in the innovation and the individual-specific term. We analyze these developments under two alternative model specifications: fixed and random effects panel data models. More precisely, in the random effects setting, we focus our attention in the analysis of some efficiency issues that have to do with the so-called working independence condition. This assumption is introduced when estimating the asymptotic variance–covariance matrix of nonparametric estimators. In the fixed effects setting, to cope with the so-called incidental parameters problem, we consider two different estimation approaches: profiling techniques and differencing methods. Furthermore, we are also interested in the endogeneity problem and how instrumental variables are used in this context. In addition, for practitioners, we also show different ways of avoiding the so-called curse of dimensionality problem in pure nonparametric models. In this way, semiparametric and additive models appear as a solution when the number of explanatory variables is large.     

The significance of digital data systems for smart city policy

Our planet is gradually moving towards an urbanized world. Modern urban agglomerations tend to turn nowadays into advanced information hubs supporting a smart management of dynamic urban systems. The currently popular notion of ‘smart cities’ aims to provide a new perspective for sustainable and high-performance strategies of city stakeholders in our ‘urban century’. In this context, digital information technology provides a new tool for efficient and effective management and planning of urban space, inter alia in the field of transportation, environment, public facilities or advanced service provision to citizens. This paper aims to offer, first, a concise overview of the emerging opportunities of information and communication technology (ICT) for smart urban policy; digital technology in particular, appears to provide novel pathways for modern planning strategies in smart cities. Against this background, the paper sketches out the complex force field of global urbanisation phenomena and highlights the data and information needs for strategic planning of cities (using inter alia as a framework the so-called ‘urban piazza’ strategy framework). Secondly, various new decision support tools that are currently emerging and that offer a new promising scope for handling complex urban management issues (for instance, on accessibility, congestion, safety or sustainability) are briefly presented. And finally, the potential of such digital data systems for urban management and policy is concisely illustrated by means of some recent applications in the area of smartphone data systems. The paper concludes with a discussion of the challenges ahead for urban policy, inter alia by paying attention to institutional and governance aspects of ‘big digital data’ management in urban systems.     

Applying LSA text mining technique in envisioning social impacts of emerging technologies: The case of drone technology

This research proposes a novel method of identifying and understanding the holistic overview of emerging technologies’ unintended consequences. Latent Semantic Analysis (LSA) text mining technique is employed to yield multiple groups of contextually similar terms from future-oriented data sources, comprising both experts’ and the public's concerns regarding future technologies. Resulting term clusters are considered as new abstractions, or so-called scenarios, of future social impacts. Furthermore, the study acquires greater depth and breadth in conceptualizing social impacts through considering condition- and value-related terms as key linking factors to previous social impact-related literature. Our proposed methodology seeks to gain insights into the utilization of future-oriented data sources for the foresight activity, hoping to mitigate public skepticism and pursue a better social acceptance of emerging technologies.     

DEA在仓库运作管理中的应用

数据包络分析能对决策单元的有效性进行评价。本文应用数据包络分析的C2R模型,对仓库的运作效率进行研究。选取某部的8个备件仓库为样本,基于C2R模型计算结果,得到一些有价值的仓库运作管理方面的信息。     

Bayesian life test planning for the Weibull distribution with given shape parameter

This paper describes Bayesian methods for life test planning with Type II censored data from a Weibull distribution, when the Weibull shape parameter is given. We use conjugate prior distributions and criteria based on estimating a quantile of interest of the lifetime distribution. One criterion is based on a precision factor for a credibility interval for a distribution quantile and the other is based on the length of the credibility interval. We provide simple closed form expressions for the relationship between the needed number of failures and the precision criteria. Examples are used to illustrate the results.Received: October 2002 / Revised: March 2004