Big Data-Oriented Product Infant Failure Intelligent Root Cause Identification Using Associated Tree and Fuzzy DEA

He, Zhenzhen; He, Yihai; Liu, Fengdi; Zhao, Yuan

doi:10.1109/access.2019.2904759

Cited by 13 publications

(8 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors of [30] introduce a Regression Neural Network (RNN) based algorithm to troubleshoot the causes of stragglers by processing Spark logs. More algorithms such as the associated tree and fuzzy data envelopment analysis [31] and Reinforcement Learning [32] are applied for finding the reasons of stragglers in Hadoop and Spark.…”

Section: Related Workmentioning

confidence: 99%

AutoDiagn: An Automated Real-Time Diagnosis Framework for Big Data Systems

Demirbaga

Wen

Noor

et al. 2022

IEEE Trans. Comput.

View full text Add to dashboard Cite

Big data processing systems, such as Hadoop and Spark, usually work in large-scale, highly-concurrent, and multi-tenant environments that can easily cause hardware and software malfunctions or failures, thereby leading to performance degradation. Several systems and methods exist to detect big data processing systems' performance degradation, perform root-cause analysis, and even overcome the issues causing such degradation. However, these solutions focus on specific problems such as stragglers and inefficient resource utilization. There is a lack of a generic and extensible framework to support the real-time diagnosis of big data systems. In this paper, we propose, develop and validate AutoDiagn. This generic and flexible framework provides holistic monitoring of a big data system while detecting performance degradation and enabling root-cause analysis. We present an implementation and evaluation of AutoDiagn that interacts with a Hadoop cluster deployed on a public cloud and tested with real-world benchmark applications. Experimental results show that AutoDiagn can offer a high accuracy root-cause analysis framework, at the same time as offering a small resource footprint, high throughput and low latency.

show abstract

Section: Related Workmentioning

confidence: 99%

AutoDiagn: An Automated Real-Time Diagnosis Framework for Big Data Systems

Demirbaga

Wen

Noor

et al. 2022

IEEE Trans. Comput.

View full text Add to dashboard Cite

show abstract

“…Badiezadeh et al (2018) proposed a new NDEA model to assess the optimistic and pessimistic efficiency of sustainable supply chain management given undesirable outputs, under a big data environment. Last but not least, He et al (2019) proposed a novel big dataoriented root cause identification approach based on fuzzy DEA with the help of an established failure associated tree to study the infant failure of the vibration and noise of a washing machine.…”

Section: Herranz Et Al (2017) Used Principal Component Analysis Dea and Artificialmentioning

confidence: 99%

Data Envelopment Analysis and Big Data: A Systematic Literature Review with Bibliometric Analysis

Charles

Gherman

Zhu

2021

International Series in Operations Research &Amp; Management Science

View full text Add to dashboard Cite

Data envelopment analysis (DEA) is a powerful data-enabled, big data science tool for performance measurement and management, which over time has been applied across a myriad of domains. Over the past years, various advancements in big data have captured the attention of DEA scholars, which in turn, has translated into the emergence of new research strands. In the present work, we perform a systematic literature review with bibliometric analysis of studies integrating DEA with big data, in an attempt to answer the question: what are the current avenues of research for such studies? The results obtained are further complemented with a thematic analysis. Among others, findings indicate that big data is still a new entrant within the DEA literature, that most of the studies have focused on developing faster and more accurate computational techniques to handle problems with a large number of decision-making units (DMUs), and that most of the studies have been carried out in the area of environmental efficiency evaluation. This work should contribute to the construction of an overview of the existing literature on DEA-big data studies, as well as stimulate the interest in the topic.

show abstract

“…For this guide, on the subject of 4.0 Industry, the CA selection was as follows: Smart Factory of Industry 4.0: Key Technologies, Application Case, and Challenges [9], When Time Matters: Predictive Mission Planning in Cyber-Physical Scenarios [10], Big Data-Oriented Product Infant Failure Intelligent Root Cause Identification Using Associated Tree and Fuzzy DEA [11], Development of an instrument for the assessment of scenarios of work 4.0 based on socio-technical criteria [12], An ontology-based framework for the management of machining information in a data mining perspective [13], Complex System Health Management Based On Condition Monitoring And Test Data [14], Simulation-based dynamic shop floor scheduling for a flexible manufacturing system in the industry 4.0 environment [15]. ix) Structure (mechanism):…”

Section: Viii) Control Articles (Ca) (Mechanism)mentioning

confidence: 99%

“…Article published in scientific journals. [16], [9], [17], [11], [18], [19], [20], [13], [14], [22] and [23].…”

Section: Category Description Number Of Articles Journalmentioning

confidence: 99%

See 1 more Smart Citation

Systematic mapping approach to support administration quantitative research

Barbosa

Nonato

Leal

et al. 2020

ITEGAM- Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)

View full text Add to dashboard Cite

This paper explores guidelines for the execution of quantitative research on a specific topic. Using a systematic mapping, as explained here, it is possible to obtain large numbers of scientific publications and properly analyze them to achieve a better understanding of stateof-the-art research, overall topic maturity, and its relevance through time. Additionally, systematic mappings provide answers to research questions as defined by the researcher conducting the process, allowing for further exploration of specific knowledge concerning the studied domain. In this study, the topic of 4.0 Industry is analyzed to illustrate the process and its results.

show abstract

Big Data-Oriented Product Infant Failure Intelligent Root Cause Identification Using Associated Tree and Fuzzy DEA

Cited by 13 publications

References 26 publications

AutoDiagn: An Automated Real-Time Diagnosis Framework for Big Data Systems

AutoDiagn: An Automated Real-Time Diagnosis Framework for Big Data Systems

Data Envelopment Analysis and Big Data: A Systematic Literature Review with Bibliometric Analysis

Systematic mapping approach to support administration quantitative research

Contact Info

Product

Resources

About