A classification of data quality assessment methods

Data quality (DQ) assessment can be significantly enhanced with the use of the right DQ assessment methods, which provide automated solutions to assess DQ. The range of DQ assessment methods is very broad: from data profiling and semantic profiling to data matching and data validation. This paper gives an overview of current methods for DQ assessment and classifies the DQ assessment methods into an existing taxonomy of DQ problems. Specific examples of the placement of each DQ method in the taxonomy are provided and illustrate why the method is relevant to the particular taxonomy position. The gaps in the taxonomy, where no current DQ methods exist, show where new methods are required and can guide future research and DQ tool development.

Product intelligence in industrial control: Theory and practice

This paper explores the evolving industrial control paradigm of product intelligence. The approach seeks to give a customer greater control over the processing of an order - by integrating technologies which allow for greater tracking of the order and methodologies which allow the customer [via the order] to dynamically influence the way the order is produced, stored or transported. The paper examines developments from four distinct perspectives: conceptual developments, theoretical issues, practical deployment and business opportunities. In each area, existing work is reviewed and open challenges for research are identified. The paper concludes by identifying four key obstacles to be overcome in order to successfully deploy product intelligence in an industrial application. © 2013 Elsevier Ltd. All rights reserved.

Understanding and navigating industrial emergence

Industrial emergence is a broad and complex domain, with relevant perspectives ranging in scale from the individual entrepreneur and firm with the business decisions and actions they make to the policies of nations and global patterns of industrialisation. The research described in this article has adopted a holistic approach, based on structured mapping methods, in an attempt to depict and understand the dynamics and patterns of industrial emergence across a broad spectrum from early scientific discovery to large-scale industrialisation. The breadth of scope and application has enabled a framework and set of four tools to be developed that have wide applicability. The utility of the approaches has been demonstrated through case studies and trials in a diverse range of industrial contexts. The adoption of such a broad scope also presents substantial challenges and limitations, with these providing an opportunity for further research. © IMechE 2013.

An exploration of risk management in global industrial investment

This article explores risk management in global industrial investment by identifying linkages and gaps between theories and practices. It identifies opportunities for further development of the field. Three related bodies of literature have been reviewed: risk management, global manufacturing and investment. The review suggests that risk management in global manufacturing is overlooked in the literature; that existing theoretical risk management processes are not well developed in the global manufacturing context and that the investment literature applies mainly to financial risk assessment rather than investment risk management structures. Further, there appears to be a serious lack of systematic industrial risk management in investment decision making. This article highlights the opportunities to deploy current good practices more effectively as well as the need to develop more robust theories of industrial investment risk management. The approach adopted to investigate this multidisciplinary topic included a historical review of literature to understand the diverse background of theoretical development. A case study research approach was adopted to collect data, involving four global manufacturing companies and one risk management advisory company to observe the patterns and rationale of current practices. Supporting arguments from secondary data sources reinforced the findings. The research focuses risk management in global industrial investment. It links theories with practice to understand the existing knowledge gap and proposes key research themes for further research. © 2013 Macmillan Publishers Ltd. 1460-3799 Risk Management.

The industrial emergence of commercial inkjet printing

Purpose: The purpose of this paper is to investigate how supply and demand interact during industrial emergence. Design/methodology/approach: The paper builds on previous theorising about co-evolutionary dynamics, exploring the interaction between supply and demand in a study of the industrial emergence of the commercial inkjet cluster in Cambridge, UK. Data are collected through 13 interviews with professionals working in the industry. Findings: The paper shows that as new industries emerge, asynchronies between technology supply and market demand create opportunities for entrepreneurial activity. In attempting to match innovative technologies to particular applications, entrepreneurs adapt to the system conditions and shape the environment to their own advantage. Firms that successfully operate in emerging industries demonstrate the functionality of new technologies, reducing uncertainty and increasing customer receptiveness. Research limitations/implications: The research is geographically bounded to the Cambridge commercial inkjet cluster. Further studies could consider commercial inkjet from a global perspective or test the applicability of the findings in other industries. Practical implications: Technology-based firms are often innovating during periods of industrial emergence. The insights developed in this paper help such firms recognise the emerging context in which they operate and the challenges that need to overcome. Originality/value: As an in depth study of a single industry, this research responds to calls for studies into industrial emergence, providing insights into how supply and demand interact during this phase of the industry lifecycle. © Emerald Group Publishing Limited.

Classification using log Gaussian Cox processes

McCullagh and Yang (2006) suggest a family of classification algorithms based on Cox processes. We further investigate the log Gaussian variant which has a number of appealing properties. Conditioned on the covariates, the distribution over labels is given by a type of conditional Markov random field. In the supervised case, computation of the predictive probability of a single test point scales linearly with the number of training points and the multiclass generalization is straightforward. We show new links between the supervised method and classical nonparametric methods. We give a detailed analysis of the pairwise graph representable Markov random field, which we use to extend the model to semi-supervised learning problems, and propose an inference method based on graph min-cuts. We give the first experimental analysis on supervised and semi-supervised datasets and show good empirical performance.