scholarly journals Anomaly data management and big data analytics: an application on disability datasets

2018 ◽  
Vol 2 (2) ◽  
pp. 164-176
Author(s):  
Zhiwen Pan ◽  
Wen Ji ◽  
Yiqiang Chen ◽  
Lianjun Dai ◽  
Jun Zhang

Purpose The disability datasets are the datasets that contain the information of disabled populations. By analyzing these datasets, professionals who work with disabled populations can have a better understanding of the inherent characteristics of the disabled populations, so that working plans and policies, which can effectively help the disabled populations, can be made accordingly. Design/methodology/approach In this paper, the authors proposed a big data management and analytic approach for disability datasets. Findings By using a set of data mining algorithms, the proposed approach can provide the following services. The data management scheme in the approach can improve the quality of disability data by estimating miss attribute values and detecting anomaly and low-quality data instances. The data mining scheme in the approach can explore useful patterns which reflect the correlation, association and interactional between the disability data attributes. Experiments based on real-world dataset are conducted at the end to prove the effectiveness of the approach. Originality/value The proposed approach can enable data-driven decision-making for professionals who work with disabled populations.

2019 ◽  
Vol 25 (2) ◽  
pp. 308-321 ◽  
Author(s):  
Arfan Majeed ◽  
Jingxiang Lv ◽  
Tao Peng

Purpose This paper aims to present an overall framework of big data-based analytics to optimize the production performance of additive manufacturing (AM) process. Design/methodology/approach Four components, namely, big data application, big data sensing and acquisition, big data processing and storage, model establishing, data mining and process optimization were presented to comprise the framework. Key technologies including the big data acquisition and integration, big data mining and knowledge sharing mechanism were developed for the big data analytics for AM. Findings The presented framework was demonstrated by an application scenario from a company of three-dimensional printing solutions. The results show that the proposed framework benefited customers, manufacturers, environment and even all aspects of manufacturing phase. Research limitations/implications This study only proposed a framework, and did not include the realization of the algorithm for data analysis, such as association, classification and clustering. Practical implications The proposed framework can be used to optimize the quality, energy consumption and production efficiency of the AM process. Originality/value This paper introduces the concept of big data in the field of AM. The proposed framework can be used to make better decisions based on the big data during manufacturing process.


2020 ◽  
Vol 37 (4) ◽  
pp. 1-5
Author(s):  
Nove E. Variant Anna ◽  
Endang Fitriyah Mannan

Purpose The purpose of this paper is to analyse the publication of big data in the library from Scopus database by looking at the writing time period of the papers, author's country, the most frequently occurring keywords, the article theme, the journal publisher and the group of keywords in the big data article. The methodology used in this study is a quantitative approach by extracting data from Scopus database publications with the keywords “big data” and “library” in May 2019. The collected data was analysed using Voxviewer software to show the keywords or terms. The results of the study stated that articles on big data have appeared since 2012 and are increasing in number every year. The big data authors are mostly from China and America. Keywords that often appear are based on the results of terminology visualization are including, “big data”, “libraries”, “library”, “data handling”, “data mining”, “university libraries”, “digital libraries”, “academic libraries”, “big data applications” and “data management”. It can be concluded that the number of publications related to big data in the library is still small; there are still many gaps that need to be researched on the topic. The results of the research can be used by libraries in using big data for the development of library innovation. Design/methodology/approach The Scopus database was accessed on 24 May 2019 by using the keyword “big data” and “library” in the search box. The authors only include papers, which title contain of big data in library. There were 74 papers, however, 1 article was dropped because of it not meeting the criteria (affiliation and abstract were not available). The papers consist of journal articles, conference papers, book chapters, editorial and review. Then the data were extracted into excel and analysed as follows (by the year, by the author/s’s country, by the theme and by the publisher). Following that the collected data were analysed using VOX viewer software to see the relationship between big data terminology and library, terminology clustering, keywords that often appear, countries that publish big data, number of big data authors, year of publication and name of journals that publish big data and library articles (Alagu and Thanuskodi, 2019). Findings It can be concluded that the implementation of big data in libraries is still in an early stage, it is shown from the limited number of practical implementation of big data analytics in library. Not many libraries that use big data to support innovation and services since there were lack of librarian skills of big data analytics. The library manager’s view of big data is still not necessary to do. It is suggested for academic libraries to start their adoption of big data analytics to support library services especially research data. To do so, librarians can enhance their skills and knowledge by following some training in big data analytics or research data management. The information technology infrastructure also needs to be upgraded since big data need big IT capacity. Finally, the big data management policy should be made to ensure the implementation goes well. Originality/value This paper discovers the adoption and implementation of big data in library, many papers talk big data in business and technology context. This is offering new idea for many libraries especially academic library about the adoption of big data to support their services. They can adopt the big data analytics technology and technique that suitable for their library.


2019 ◽  
Vol 119 (5) ◽  
pp. 1072-1088
Author(s):  
Shuai Luo ◽  
Hongwei Liu ◽  
Ershi Qi

Purpose The purpose of this paper is to propose a comprehensive framework for integrating big data analytics (BDA) into cyber-physical system (CPS) solutions. This framework provides a wide range of functions, including data collection, smart data preprocessing, smart data mining and smart data visualization. Design/methodology/approach The architecture of CPS was designed with cyber layer, physical layer and communication layer from the perspective of big data processing. The BDA model was integrated into a CPS that enables managers to make sound decisions. Findings The effectiveness of the proposed BDA model has been demonstrated by two practical cases − the prediction of energy output of the power grid and the estimate of the remaining useful life of the aero-engine. The method can be used to control the power supply system and help engineers to maintain or replace the aero-engine to maintain the safety of the aircraft. Originality/value The communication layer, which connects the cyber layer and physical layer, was designed in CPS. From the communication layer, the redundant raw data can be converted into smart data. All the necessary functions of data collection, data preprocessing, data storage, data mining and data visualization can be effectively integrated into the BDA model for CPS applications. These findings show that the proposed BDA model in CPS can be used in different environments and applications.


2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ahmed Aboud ◽  
Barry Robinson

Purpose This paper aims to explore the effectiveness of fraud prevention and detection techniques, including data analytics, machine learning and data mining, and to understand how widespread the use of data analytics is across different sectors and to identify and understand the potential barriers to implementing these techniques to detect and prevent fraud. Design/methodology/approach A survey was administered to 73 Irish businesses to determine to what extent traditional approach, data mining or text mining are being used to prevent or detect fraudulent financial reporting, and to determine the perception level of their effectiveness. Findings The study suggests that whilst data analytics is widely used by businesses in Ireland there is an under-utilisation of data analytics as an effective tool in the fight against fraud. The study suggests there are barriers that may be preventing companies from implementing advanced data analytics to detect financial statement fraud and identifies how those barriers may be overcome. Originality/value In contrast to the majority of literature on big data analytics and auditing, which lacks empirical insight into the diffusion, effectiveness and obstacles of data analytics, this explanatory study contributes by providing useful insights from the field on big data analytics. While the extant auditing literature generally addresses the avenues of big data utilisation in auditing domain, our study explores particularly the use big data analytics as a fraud prevention and detection techniques.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Narender Kumar ◽  
Girish Kumar ◽  
Rajesh Kr Singh

PurposeThe study presents various barriers to adopt big data analytics (BDA) for sustainable manufacturing operations (SMOs) post-coronavirus disease (COVID-19) pandemics. In this study, 17 barriers are identified through extensive literature review and experts’ opinions for investing in BDA implementation. A questionnaire-based survey is conducted to collect responses from experts. The identified barriers are grouped into three categories with the help of factor analysis. These are organizational barriers, data management barriers and human barriers. For the quantification of barriers, the graph theory matrix approach (GTMA) is applied.Design/methodology/approachThe study presents various barriers to adopt BDA for the SMOs post-COVID-19 pandemic. In this study, 17 barriers are identified through extensive literature review and experts’ opinions for investing in BDA implementation. A questionnaire-based survey is conducted to collect responses from experts. The identified barriers are grouped into three categories with the help of factor analysis. These are organizational barriers, data management barriers and human barriers. For the quantification of barriers, the GTMA is applied.FindingsThe study identifies barriers to investment in BDA implementation. It categorizes the barriers based on factor analysis and computes the intensity for each category of a barrier for BDA investment for SMOs. It is observed that the organizational barriers have the highest intensity whereas the human barriers have the smallest intensity.Practical implicationsThis study may help organizations to take strategic decisions for investing in BDA applications for achieving one of the sustainable development goals. Organizations should prioritize their efforts first to counter the barriers under the category of organizational barriers followed by barriers in data management and human barriers.Originality/valueThe novelty of this paper is that barriers to BDA investment for SMOs in the context of Indian manufacturing organizations have been analyzed. The findings of the study will assist the professionals and practitioners in formulating policies based on the actual nature and intensity of the barriers.


Data have been expanding enormously in latest years, enormous amounts of structured, unstructured and semi-structured information have been produced in various areas around the globe, collectively known as big data. The health sector has produced enormous amounts of heterogeneous information that must be handled and analyzed. In this paper, we discuss about the characteristics of data generated by healthcare and how to manage this data using big data tools. We also explore tools to analyse this data and discuss the implementations of this data. A conceptual architecture of big data analytics is also given, which includes data cleaning, data injection, data management, data mining, data visualization and data analysis.


2019 ◽  
Author(s):  
Meghana Bastwadkar ◽  
Carolyn McGregor ◽  
S Balaji

BACKGROUND This paper presents a systematic literature review of existing remote health monitoring systems with special reference to neonatal intensive care (NICU). Articles on NICU clinical decision support systems (CDSSs) which used cloud computing and big data analytics were surveyed. OBJECTIVE The aim of this study is to review technologies used to provide NICU CDSS. The literature review highlights the gaps within frameworks providing HAaaS paradigm for big data analytics METHODS Literature searches were performed in Google Scholar, IEEE Digital Library, JMIR Medical Informatics, JMIR Human Factors and JMIR mHealth and only English articles published on and after 2015 were included. The overall search strategy was to retrieve articles that included terms that were related to “health analytics” and “as a service” or “internet of things” / ”IoT” and “neonatal intensive care unit” / ”NICU”. Title and abstracts were reviewed to assess relevance. RESULTS In total, 17 full papers met all criteria and were selected for full review. Results showed that in most cases bedside medical devices like pulse oximeters have been used as the sensor device. Results revealed a great diversity in data acquisition techniques used however in most cases the same physiological data (heart rate, respiratory rate, blood pressure, blood oxygen saturation) was acquired. Results obtained have shown that in most cases data analytics involved data mining classification techniques, fuzzy logic-NICU decision support systems (DSS) etc where as big data analytics involving Artemis cloud data analysis have used CRISP-TDM and STDM temporal data mining technique to support clinical research studies. In most scenarios both real-time and retrospective analytics have been performed. Results reveal that most of the research study has been performed within small and medium sized urban hospitals so there is wide scope for research within rural and remote hospitals with NICU set ups. Results have shown creating a HAaaS approach where data acquisition and data analytics are not tightly coupled remains an open research area. Reviewed articles have described architecture and base technologies for neonatal health monitoring with an IoT approach. CONCLUSIONS The current work supports implementation of the expanded Artemis cloud as a commercial offering to healthcare facilities in Canada and worldwide to provide cloud computing services to critical care. However, no work till date has been completed for low resource setting environment within healthcare facilities in India which results in scope for research. It is observed that all the big data analytics frameworks which have been reviewed in this study have tight coupling of components within the framework, so there is a need for a framework with functional decoupling of components.


2017 ◽  
Vol 21 (1) ◽  
pp. 12-17 ◽  
Author(s):  
David J. Pauleen

Purpose Dave Snowden has been an important voice in knowledge management over the years. As the founder and chief scientific officer of Cognitive Edge, a company focused on the development of the theory and practice of social complexity, he offers informative views on the relationship between big data/analytics and KM. Design/methodology/approach A face-to-face interview was held with Dave Snowden in May 2015 in Auckland, New Zealand. Findings According to Snowden, analytics in the form of algorithms are imperfect and can only to a small extent capture the reasoning and analytical capabilities of people. For this reason, while big data/analytics can be useful, they are limited and must be used in conjunction with human knowledge and reasoning. Practical implications Snowden offers his views on big data/analytics and how they can be used effectively in real world situations in combination with human reasoning and input, for example in fields from resource management to individual health care. Originality/value Snowden is an innovative thinker. He combines knowledge and experience from many fields and offers original views and understanding of big data/analytics, knowledge and management.


Sign in / Sign up

Export Citation Format

Share Document