Using big data to make better decisions in the digital economy

The question this special issue would like to address is how to harvest big data to help decision-makers to deliver better fact-based decisions aimed at improving performance or to create better strategy? This special issue focuses on the big data applications in supporting operations decisions, including advanced research on decision models and tools for the digital economy. Responds to this special issue was great and we have included many high-quality papers. We are pleased to present 13 of the best papers. The techniques presented include data mining, simulation and expert system with applications span across online reviews, food retail chain to e-health.     

国内外农业大数据应用研究分析

针对农业领域数据规模大、数据结构复杂、空间数据挖掘能力不足等问题,研究了大数据开源技术在农业领域的数据分析体系中的应用。借鉴国内外学者在农业大数据的研究成果,基于农业数据时空属性的特征,结合农业数据的特点分析了Hadoop、Storm和Spark开源大数据挖掘技术,归纳性阐述了如何开发适合农业需求的大数据系统。最后,简要分析了农业大数据技术所面临的挑战和研究难题,指出需要加大力度进一步深入理论和应用研究,从而推动和实现基于数据的科学决策,为国家粮食提供安全保障。     

Analysing semiconductor manufacturing big data for root cause detection of excursion for yield enhancement

With the shrinking feature size of integrated circuits driven by continuous technology migrations for wafer fabrication, the control of tightening critical dimensions is critical for yield enhancement, while physical failure analysis is increasingly difficult. In particular, the yield ramp up stage for implementing new technology node involves new production processes, unstable machine configurations, big data with multiple co-linearity and high dimensionality that can hardly rely on previous experience for detecting root causes. This research aims to propose a novel data-driven approach for Analysing semiconductor manufacturing big data for low yield (namely, excursions) diagnosis to detect process root causes for yield enhancement. The proposed approach has shown practical viability to efficiently detect possible root causes of excursion to reduce the trouble shooting time and improve the production yield effectively.     

Big data in lean six sigma: a review and further research directions

Manufacturing and service organisations improve their processes on a continuous basis to have better operational performance. They use lean six sigma (LSS) projects for process improvement. Therefore, this study aims to investigate the existing literature in LSS and the application of big data analytics (BDA) to have more confident and predictable decisions in each phase of LSS. Fifty-two articles have been identified after a careful and vigilant screening of closely related themes. Future research directions in the big data and LSS have been highlighted on the basis of organisational theories. Review presents an investigation framework consisting of BDA techniques applicable to each phase of LSS in all the dimensions such as volume, variety, velocity and veracity of big data. Review highlights the concerns of big data in LSS such as system design and integration, system performance, security and reliability of data, sustaining the control and conducting the experiments, distributed material and information flow. The review unveils the application of 8 modern organisational theories to big data in LSS with 21 key aspects of related theories and 19 distinct research gaps as opportunities for future research.     

Modelling quality dynamics,business value and firm performance in a big data analytics environment

Big data analytics have become an increasingly important component for firms across advanced economies. This paper examines the quality dynamics in big data environment that are linked with enhancing business value and firm performance (FPER). The study identifies that system quality (i.e. system reliability, accessibility, adaptability, integration, response time and privacy) and information quality (i.e. completeness, accuracy, format and currency) are key to enhance business value and FPER in a big data environment. The study also proposes that the relationship between quality and FPER is mediated by business value of big data. Drawing on the resource-based theory and the information systems success literature, this study extends knowledge in this domain by linking system quality, information quality, business value and FPER.     

Reference materials and evaluation of thermophysical properties data

This paper presents a general review of the governmental activities in Japan on reference materials and evaluation of thermophysical properties data and then describes recent developments at the National Research Laboratory of Metrology (NRLM) in the field of thermophysical properties and related standards. As for reference materials, the past and present activities organized by the government and a few related associations are reviewed from the point of view of establishing traceability systems, whereas, on the evaluation of thermophysical properties, the framework of collaborative research for establishing data base systems by network sharing is mentioned. Then the recent studies of NRLM on the measurements and standards of thermophysical properties as well as its calibration services are summarized.Presented at the Japan-United States Joint Seminar on Thermophysical Properties, October 24–26, 1983, Tokyo, Japan.     

大数据在民爆行业信息化中的应用

在工业化与信息化深度融合的当下,及时、准确、全面的信息是分析民爆安全生产机制、构建民爆信息管理体系的前提。针对因民爆行业的特殊性,出现的信息化地区垄断、信息孤岛等问题,对目前民用爆炸物品安全生产的信息化程度进行了探讨,提出了将大数据思维运用到民爆行业一体化进程中,构建民爆安全生产大数据服务云平台,即对现有的民爆信息化系统的数据进行收集、存储、归类、分析、挖掘,并将分析结果作为民爆安全生产大数据服务云平台的重要数据支撑。依据大数据建立的民爆安全生产大数据服务云平台对保障民爆行业的安全生产管理具有现实意义。     

大数据在民爆行业信息化中的应用

在工业化与信息化深度融合的当下,及时、准确、全面的信息是分析民爆安全生产机制、构建民爆信息管理体系的前提。针对因民爆行业的特殊性,出现的信息化地区垄断、信息孤岛等问题,对目前民用爆炸物品安全生产的信息化程度进行了探讨,提出了将大数据思维运用到民爆行业一体化进程中,构建民爆安全生产大数据服务云平台,即对现有的民爆信息化系统的数据进行收集、存储、归类、分析、挖掘,并将分析结果作为民爆安全生产大数据服务云平台的重要数据支撑。依据大数据建立的民爆安全生产大数据服务云平台对保障民爆行业的安全生产管理具有现实意义。     

Understanding big consumer opinion data for market-driven product design

Big consumer data provide new opportunities for business administrators to explore the value to fulfil customer requirements (CRs). Generally, they are presented as purchase records, online behaviour, etc. However, distinctive characteristics of big data, Volume, Variety, Velocity and Value or ‘4Vs’, lead to many conventional methods for customer understanding potentially fail to handle such data. A visible research gap with practical significance is to develop a framework to deal with big consumer data for CRs understanding. Accordingly, a research study is conducted to exploit the value of these data in the perspective of product designers. It starts with the identification of product features and sentiment polarities from big consumer opinion data. A Kalman filter method is then employed to forecast the trends of CRs and a Bayesian method is proposed to compare products. The objective is to help designers to understand the changes of CRs and their competitive advantages. Finally, using opinion data in Amazon.com, a case study is presented to illustrate how the proposed techniques are applied. This research is argued to incorporate an interdisciplinary collaboration between computer science and engineering design. It aims to facilitate designers by exploiting valuable information from big consumer data for market-driven product design.     

A review of current techniques for the evaluation of powder mixing

Blending a mixture of powders to a homogeneous system is a crucial step in many manufacturing processes. To achieve a high quality of the end product, powder mixtures should be made with high content uniformity. For instance, producing uniform tablets depends on the homogeneous dispersion of active pharmaceutical ingredient (API), often in low level quantities, into excipients. To control the uniformity of a powder mixture, the first required step is to estimate the powder content information during blending. There are several powder homogeneity evaluation techniques which differ in accuracy, fundamental basis, cost and operating conditions. In this article, emerging techniques for the analysis of powder content and powder blend uniformity, are explained and compared. The advantages and drawbacks of all the techniques are reviewed to help the readers to select the appropriate equipment for the powder mixing evaluation. In addition, the paper highlights the recent innovative on-line measurement techniques used for the non-invasive evaluation of the mixing performance.     

LFF:一种面向大数据应用的众核处理器访存公平性调度机制

研究了众核处理器的访存公平性问题。针对众核处理器距离访存资源较近的处理单元拥有较大的访存带宽而造成的访存公平性问题,提出了一种面向大数据应用的众核处理器访存公平性调度机制:最少最远(LFF)优先访存。这种机制的原理如下:依据处理单元距离访存资源的距离以及处理单元访存的次数来调度访存顺序,以保证各个处理单元的公平性。首先,访问次数较少的节点被赋予更高的访存优先权。其次,在具有相同访问次数的节点中,距离更远的节点优先访存。再次,在相同距离的节点中,已被选中优先次数少的有优先级。实验评估表明,该调度机制能够有效解决众核处理器的访存公平性问题,其公平性调度效果优于FR-FCFS,PAR-BS、ATLAS。在1024核情况下,系统异步率由FR-FCFS的15.5%降低到1.89%。     

A GA-based optimisation model for big data analytics supporting anticipatory shipping in Retail 4.0

In Retail 4.0, omni-channels require a seamless and complete integration of all available channels for purchasing. The diversification of channels not only diversifies data sources, but also rapidly generates an enormous amount of data. This highlights a need of big data analytics to extract meaningful knowledge for decision-making. In addition, anticipatory shipping is getting more popular to ensure fast product delivery. The goal is to predict when a customer will make a purchase and then begin shipping the product to the nearest distribution centres before the customer places the orders online. This paper proposes a genetic algorithm (GA)-based optimisation model to support anticipatory shipping. Cloud computing is deployed to store the big data generated from all channels. Cluster-based association rule mining is applied to discover the purchase pattern and predict future purchase in terms of If-Then prediction rules. A modified GA is then used to generate optimal anticipatory shipping plans. Apart from transportation cost and travelling distance, the confidence of prediction rules is also considered in the GA. A number of numerical experiments have been carried out to demonstrate the trade-off of different factors in anticipatory shipping, and the optimisation reliability of the model is verified.     

The use of narrative text for injury surveillance research: A systematic review

Objective

To summarise the extent to which narrative text fields in administrative health data are used to gather information about the event resulting in presentation to a health care provider for treatment of an injury, and to highlight best practise approaches to conducting narrative text interrogation for injury surveillance purposes.

Design

Systematic review.

Data sources

Electronic databases searched included CINAHL, Google Scholar, Medline, Proquest, PubMed and PubMed Central. Snowballing strategies were employed by searching the bibliographies of retrieved references to identify relevant associated articles.

Selection criteria

Papers were selected if the study used a health-related database and if the study objectives were to a) use text field to identify injury cases or use text fields to extract additional information on injury circumstances not available from coded data or b) use text fields to assess accuracy of coded data fields for injury-related cases or c) describe methods/approaches for extracting injury information from text fields.

Methods

The papers identified through the search were independently screened by two authors for inclusion, resulting in 41 papers selected for review. Due to heterogeneity between studies meta-analysis was not performed.

Results

The majority of papers reviewed focused on describing injury epidemiology trends using coded data and text fields to supplement coded data (28 papers), with these studies demonstrating the value of text data for providing more specific information beyond what had been coded to enable case selection or provide circumstantial information. Caveats were expressed in terms of the consistency and completeness of recording of text information resulting in underestimates when using these data. Four coding validation papers were reviewed with these studies showing the utility of text data for validating and checking the accuracy of coded data. Seven studies (9 papers) described methods for interrogating injury text fields for systematic extraction of information, with a combination of manual and semi-automated methods used to refine and develop algorithms for extraction and classification of coded data from text. Quality assurance approaches to assessing the robustness of the methods for extracting text data was only discussed in 8 of the epidemiology papers, and 1 of the coding validation papers. All of the text interrogation methodology papers described systematic approaches to ensuring the quality of the approach.

Conclusions

Manual review and coding approaches, text search methods, and statistical tools have been utilised to extract data from narrative text and translate it into useable, detailed injury event information. These techniques can and have been applied to administrative datasets to identify specific injury types and add value to previously coded injury datasets. Only a few studies thoroughly described the methods which were used for text mining and less than half of the studies which were reviewed used/described quality assurance methods for ensuring the robustness of the approach. New techniques utilising semi-automated computerised approaches and Bayesian/clustering statistical methods offer the potential to further develop and standardise the analysis of narrative text for injury surveillance.     

Investments in big data analytics and firm performance: an empirical investigation of direct and mediating effects

Big data has recently been recognised as one of the most important areas of future technology. It has attracted the attention of many industries, since it has the potential to provide companies with high business value. This paper examines the forms of business value that companies can create from big data analytics investments, the direct impacts it has on the financial performance of a firm, and the mediating effects of market performance and customer satisfaction. Drawing on the resource-based view theory, this study demonstrates that the business value achieved from investments in big data analytics leads to advantages in terms of the financial performance of a firm. The results offer evidence of the existence of a customer satisfaction mediation effect and of the absence of a market performance mediation effect. Theoretical and practical implications are discussed at the end of the paper.     

A systematic review on the effectiveness of thermography in diagnosis of diseases

Collecting and analyzing appropriate information and performing comprehensive systematic studies, considering safety, effectiveness, and cost effectiveness of the technologies are prerequisites for making decisions on buying and using different diagnostic and therapeutic equipment. This study aimed to systematically identify and analyze available evidences related to the effectiveness of contact thermography technique in diagnosis of different diseases. This study was a systematic review of published and gray literature. We searched relevant databases, bibliography of related papers, and companies' websites, using appropriate search strategies and key words. The CASP tool was used by two experts to evaluate the quality of retrieved papers and inconsistencies were resolved by discussion. After removal of duplicate citations, 308 titles were identified through database searching, among which 276 were excluded on reviewing of the titles and abstracts. The full texts of the remaining papers (32) were assessed against the inclusion criteria and 14 papers were recognized qualified, which were categorized into three groups of: breast cancer, DVT, and others. The results showed although contact thermography is a safe, rapid and cheap technique to be used in screening and diagnosing different diseases, but results did not show any acceptable diagnostic value in comparison to other diagnostic techniques. It might be beneficial to use it as a complementary technique. More research is recommended in this area. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 188–193, 2013     

Analyzing Behavioral Big Data: Methodological,practical, ethical,and moral issues

ABSTRACT

The term “big data” evokes emotions ranging from excitement to exasperation in the statistics community. Looking beyond these emotions reveals several important changes that affect us as statisticians and as humans. I focus on Behavioral Big Data (BBD), or very large and rich multidimensional datasets on human behaviors, actions, and interactions, which have become available to companies, governments, and researchers. This article describes the BBD landscape and examines opportunities and critical issues that arise when applying statistical and data mining approaches to Behavioral Big Data, including the move from macro- to micro-decisioning and its implications.     

大数据下的深度学习研究

给出了大数据和机器学习的子领域——深度学习的概念,阐述了深度学习对获取大数据中的有价值信息的重要作用。描述了大数据下利用图像处理单元(GPU)进行并行运算的深度学习框架,对其中的大规模卷积神经网络(CNN)、大规模深度置信网络(DBN)和大规模递归神经网络(RNN)进行了重点论述。分析了大数据的容量、多样性、速率特征,介绍了大规模数据、多样性数据、高速率数据下的深度学习方法。展望了大数据背景下深度学习的发展前景,指出在不远的将来,大数据与深度学习融合的技术将会在计算机视觉、机器智能等多个领域获得突破性进展。     

计量性是复杂工业产品技术状态控制及大数据管理的基石

以质量控制观念及大数据管理为视角,阐述了计量性的概念、意义和价值,指出了计量性实质上就是产品状态参量的可激励性、可控制性和可观测性。按照技术目标与能力要求,将计量性划分为5个不同的技术等级,以贯穿从产品的设计制造到使用维护的全寿命过程。讨论了计量性对提升产品成熟度的作用。     

Research on coordinated development between metropolitan economy and logistics using big data and Haken model

To quantitatively study the relationship and mutual effects between metropolitan economy and logistics is an important, yet pending issue, which can scientifically guide the urban planning and investment. Through the identified evaluation indexes of metropolitan logistics and economic development, this paper first builds up an evaluation process model of metropolitan economic and logistics development, based on big data analytics (BDA), the entropy evaluation method, and the maximum deviation method. BDA can help extract the exact data about the indicators of metropolitan economy and logistics. Then a Haken model is adopted to ravel out the dynamic co-evolutionary law of economy and logistics in five Chinese cities, which complements the above static evaluation. The results show that the economic development is an order parameter and plays a key role in the coordinated development of metropolitan logistics and economy. However, from 2013 to 2014, these five cities had not established an orderly evolved positive-feedback mechanism through which economic development promotes the coordinated development of metropolitan logistics and economic development.