Data Analytics in Industry 4.0: In the Perspective of Big Data

Data Analytics in Industry 4.0: In the Perspective of Big Data

Mahir Oner, Sultan Ceren Oner
DOI: 10.4018/978-1-5225-2944-6.ch018
(Individual Chapters)
No Current Special Offers


The new form of future generation machines and automated systems could be synchronized by IoT adaptation. By this way, a very large size data can be carefully stored in data repositories and have to be analyzed for extracting knowledge. Thus, optimization techniques are becoming invaluable tools for finding patterns from parallel distributed machines. On the other hand, statistical methods and optimization models could not be utilized efficiently due to excessive dimension of data. Additionally, data analytics should be applied and results should be gathered by using practical approaches especially for security, access control and fault detection issues. In this study, optimization techniques are evaluated in the perspective of big data analytics and both mathematical and statistical methods will be extensively analyzed for different versions of problem solving and decision making in Industry 4.0 era.
Chapter Preview


The main idea of Industry 4.0 is first declared by Kagermann in 2011 and supported by German National Academy of Science and Engineering in 2013. The context of Industry 4.0 was introduced by Industrial Internet Consortium (ICC) and wide range of applications could be found in Bosch, Siemens, Apple etc. (Stock and Seliger, 2016). The main idea of Industry 4.0 is the installation of smart products and smart services with smart factories using Internet of Things, Cyber-Physical Systems in order to provide communication of each objects and decentralized systems. (Weyer et al., 2015) The four design principles are listed as follows:

Interoperability: The connection and communication of machines, devices, sensors, and people using Internet of Things (IoT) or Internet of People (IoP).

Key Terms in this Chapter

Hierarchical Clustering: A data mining method for gathering hierarchical structure when grouping related data via top down or bottom up approach.

Partitional Clustering: Dissociating a data set into a set of disjoint clusters.

Fuzzy Logic: A form of explanations of crisp values to 0-1 values in order to represent the “truth” via determining membership function.

Data Mining: Methodologies that contribute the extraction of information among large scale data.

Fuzzy Clustering: Decomposition of data elements with respect to each element could be belong to one or more classes via a set of membership functions.

Segmentation: Grouping individuals according to the similar properties.

Beacon: A technology that assists indoor location based system using Bluetooth Low Energy.

Bluetooth: A technology that connects mobile devices via wireless connection infrastructure.

Complete Chapter List

Search this Book: