Big data analytics and machine learning for industrial cyber-physical systems - Archive ouverte HAL Accéder directement au contenu
Chapitre D'ouvrage Année : 2022

Big data analytics and machine learning for industrial cyber-physical systems

Résumé

Through the concepts of Big Data and machine learning, this chapter illustrates how it is possible to exploit the immense mass of data that can be capitalized at the level of the cyber layer of industrial cyber-physical systems (ICPS). Many data mining techniques are available for the analysis of these large masses of data. In the context of ICPS, the chapter develops two of them: multi-relational data mining and machine learning. Machine learning includes different tools that can be used to perform this step of data mining such as naive Bayes, decision tree, random forest, k nearest neighbors, support vector machine, multilayer perceptron (MLP) and deep learning. Although deep learning is currently the most popular tool, it is not necessarily the most suitable tool for industrial data. The classic MLP is a feedforward neural network with only one hidden layer.
Fichier non déposé

Dates et versions

hal-03838224 , version 1 (03-11-2022)

Identifiants

Citer

Yasamin Eslami, Mario Lezoche, Philippe Thomas. Big data analytics and machine learning for industrial cyber-physical systems. Olivier Cardin, Damien Trentesaux, William Derigent. Digitalization and Control of Industrial Cyber‐Physical Systems, ISTE - Wiley, 149-170, Part 5, Chapter 9, 2022, 9781789450859. ⟨10.1002/9781119987420.ch9⟩. ⟨hal-03838224⟩
45 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More