Big Data Semantics in Industry 4.0

Obitko, Marek; Jirkovský, Václav

doi:10.1007/978-3-319-22867-9_19

Cited by 46 publications

(21 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The new idea took hold, and that is why in industrially advanced countries, the development is currently heading towards the fourth stage of industrialization, and after mechanization, electrification and information, this fourth stage was called Industry 4.0 (Zhou, Liu, & Zhou, 2015;Schuh, Potente, Wesch-Potente, Weber, & Prote, 2014). These are fully mechanized and automated systems based on advanced digitization, a combination of Internet and future-oriented technologies and machine intelligence (Lasi, Fettke, Kemper, Feld, & Hoffmann, 2014, Obitko & Jirkovský, 2015. However, the impact of the Fourth Industrial Revolution is more widespread and affects the engineering processes of SMEs.…”

Section: Introductionmentioning

confidence: 99%

Division of Enterprises and Their Strategies in Relation to Industry 4.0

Vrchota¹,

Vlčková²,

Frantíková³

2020

CEBR

View full text Add to dashboard Cite

In today's turbulent times, businesses must cope with an increasing focus on digital technology, automation and robotics systems. It represents the fourth industrial revolution, called Industry 4.0. The goals of Industry 4.0 are achieving higher levels of operational efficiency and productivity, as well as a higher level of automation. Concerning Industry 4.0, therefore, not only the technological aspect but also the size of the organization, the scope of business by industry and other elements are considered and analyzed based on Mann-Whitney U test and Fisher test. According to statistical analysis, it was found that the size of the company affects its relationship to Industry 4.0, and we can say that the larger the business, the more it is affected by Industry 4.0. This influence was manifested primarily in companies operating in the field of commercial activities, or Agriculture and Construction. In terms of the relationship between the written strategy and Industry 4.0, it can be stated that the link between them has occurred in small and medium-sized enterprises operating in the areas of Professional and Administrative Activities, Manufacturing and Wholesale, Transport and Accommodation. In contrast, this effect has not been proven in micro-enterprises. Implications for a Central European audience: The paper primarily deals with the analysis of the relationship between enterprise size and Industry 4.0 and the study of the relationship between the division of enterprises by industry in relation to CZ-NACE. A significant difference was found between the enterprises affected and unaffected by Industry 4.0 when evaluating the size of the enterprise. Enterprises involved by Industry 4.0 employ more workers, which may be due to the introduction of automation and robotic automation, which means the initial phase. As the results further show, the written strategy is mostly the domain of medium-sized enterprises, with only 29 % of micro-enterprises and 41 % of small enterprises having it defined.

show abstract

Section: Introductionmentioning

confidence: 99%

Division of Enterprises and Their Strategies in Relation to Industry 4.0

Vrchota¹,

Vlčková²,

Frantíková³

2020

CEBR

View full text Add to dashboard Cite

show abstract

“…e experiments are carried out on the Google Cloud Platform (GCP). In the GCP server (us-west1-b region), we installed the Compute Engine 2//For feature extraction task (2) Perform convolution operation with F � 64 and nonlinearity, via equations 3and 4(3) Add Gaussian noise, via equation 6(4) Apply max-pooling, via equation 7(5) Activate and deactivate neurons using dropout with p, via equation 8 Forward accuracy to the performance feedback module (5) Determine the ensemble accuracies using voting, via Algorithm 2 //Spectral band stream are classifying with their respective instances in the DEC module (6) if % accuracy for B ≥ //if sample does not misclassify (7) Repeat steps 3, 4, and 5 (8) if % accuracy for B ≤ //if sample misclassify (9) Save the B //Save misclassified sample in training repository //as potential new spectral band (10) Counter++ (11) Repeat steps 3, 4, and 5 (12) if counter � 50 //number of misclassified instances reached to 50 (13) Cluster M c using K-mean where K � 1, [35]. //Cluster all the misclassified data samples using the K-means approach with //K � 1, K � 1 the case is assigned to the class of its nearest neighbor (14) Determine optimized centroid, [35]//to optimize the similar sample instances (15) Compare cosine distance cluster sample with cluster centroid, via equation (12) //to segregate most relevant samples in cluster (16) Assign the all nearest samples a hypothetical class X � B n+1 //A new class with additional spectral band information (17) Create new instance classifier i n+1 //New Single Instance, 20 layered architecture (18) Train new instance classifier I � i n+1 with hypothetical class X � B n+1 , via Table 3 //Online training with selected hyperparameters as depicted in Table 3 ALGORITHM 3: Continued.…”

Section: Platform and Librariesmentioning

confidence: 99%

“…In the modern era of digitization, real-time and online analysis of big data is an essential task [9]. Multispectral imagery is one of the dominant and information-intensive types of big data.…”

Section: Introductionmentioning

confidence: 99%

Adaptive CNN Ensemble for Complex Multispectral Image Analysis

et al. 2020

View full text Add to dashboard Cite

Multispectral image classification has long been the domain of static learning with nonstationary input data assumption. The prevalence of Industrial Revolution 4.0 has led to the emergence to perform real-time analysis (classification) in an online learning scenario. Due to the complexities (spatial, spectral, dynamic data sources, and temporal inconsistencies) in online and time-series multispectral image analysis, there is a high occurrence probability in variations of spectral bands from an input stream, which deteriorates the classification performance (in terms of accuracy) or makes them ineffective. To highlight this critical issue, firstly, this study formulates the problem of new spectral band arrival as virtual concept drift. Secondly, an adaptive convolutional neural network (CNN) ensemble framework is proposed and evaluated for a new spectral band adaptation. The adaptive CNN ensemble framework consists of five (05) modules, including dynamic ensemble classifier (DEC) module. DEC uses the weighted voting ensemble approach using multiple optimized CNN instances. DEC module can increase dynamically after new spectral band arrival. The proposed ensemble approach in the DEC module (individual spectral band handling by the individual classifier of the ensemble) contributes the diversity to the ensemble system in the simple yet effective manner. The results have shown the effectiveness and proven the diversity of the proposed framework to adapt the new spectral band during online image classification. Moreover, the extensive training dataset, proper regularization, optimized hyperparameters (model and training), and more appropriate CNN architecture significantly contributed to retaining the performance accuracy.

show abstract

“…Access to real-time data contributes to a reduction of bullwhip effects, reduction of misplacement and theft, reduction of identification errors, better replenishment policies, better scheduling, securing dangerous goods and temperature collected goods, improved traceability of products in the routing and improved the distribution planning are some other examples of these benefits [3]. Besides all these, real-time data is an imperative for any CPS (cyber-physical system) and Industry 4.0 concept [4,8]. So far, researches have tried to clarify these concepts and their applications for PL systems.…”

Section: Introductionmentioning

confidence: 99%

Real-Time Data Sharing in Production Logistics: Exploring Use Cases by an Industrial Study

Zafarzadeh

Hauge

Wiktorsson

et al. 2019

IFIP Advances in Information and Communication Technology

View full text Add to dashboard Cite

Production logistics systems consist often of a number of low valueadded activities combined with a high degree of manual work. Therefore, increasing effectivity and responsiveness has always been a target for production logistics systems. Sharing data in real-time may have a considerable potential to increase effectivity and responsiveness. The first step to realise real-time data sharing is to have a clear understanding of current state of PL systems and their requirements. This work is performed an 'as-is' situation analysis of an industrial case aiming at identifying which areas and applications would benefit most from real-time data sharing. The findings take a step closer to have a better understanding of CPS and Industry 4.0.

show abstract

Big Data Semantics in Industry 4.0

Cited by 46 publications

References 7 publications

Division of Enterprises and Their Strategies in Relation to Industry 4.0

Division of Enterprises and Their Strategies in Relation to Industry 4.0

Adaptive CNN Ensemble for Complex Multispectral Image Analysis

Real-Time Data Sharing in Production Logistics: Exploring Use Cases by an Industrial Study

Contact Info

Product

Resources

About