Pattern Extraction for the Design of Predictive Models in Industry 4.0

Sittón, Inés; Rodrı́guez, Sara

doi:10.1007/978-3-319-61578-3_31

Cited by 26 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multidimensional nature of the uncertainty and the purpose of its complexity and dynamic changes, should be observed from diverse standpoints [56]. Uncertainty is an independent measure which relates to the detached risks and concerns that are problematic or impossible to estimate [63]. When the probability of certain events is quantifiable, then one should talk about the risks, as there is uncertainty in the strict sense [60].…”

Section: Discussionmentioning

confidence: 99%

“…[56]. Uncertainty regarding Industry 4.0 is triggered by the high intricacy of the subject and a deficiency of current guidance in the direction of the comprehension of the visions and concepts [60][61][62][63][64][65]. Particularly, this phenomenon is interesting for evaluating several case studies on communication among the main network components of Industry 4.0 based on massive amounts of data collected regarding self-control, beyond a secure internal network [61][62][63].…”

Section: Degree Of Uncertainty In Industry 40mentioning

confidence: 99%

See 1 more Smart Citation

Evaluating the Degree of Uncertainty of Research Activities in Industry 4.0

et al. 2019

View full text Add to dashboard Cite

Research and development (R&D) are always oriented towards new discoveries, based on original terms or hypotheses, and their concluding outcomes are often uncertain. The present work focused on the degree of uncertainty for R&D activities. In fact, uncertainty makes it difficult to quantify the time and resources needed to achieve a final outcome, create a work plan and budget, and finalize the resulting “innovative” products or services that could be transferred or exchanged in a specific market. The present work attempts to indicate the degree of uncertainty of the research activities developed by a set of firms. The method used aimed to quantify the five criteria defined by the Manual of Frascati. Through the creation of an uncertainty cloud, a cone of uncertainty was defined following an approach based on project management. The evaluation grid was characterized by the decomposition of the different variables divided into quartiles, which allowed for the detection of the evolution of the project and each of its component. The ancillary objective aim was to also observe the development degree of these industries towards a framework of Industry 4.0.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Degree Of Uncertainty In Industry 40mentioning

confidence: 99%

Evaluating the Degree of Uncertainty of Research Activities in Industry 4.0

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Numerous sensors are critical in tracking and regulating an organization's activities that leverage emerging technologies. For instance, hundreds of sensors are deployed in IoT-enabled sectors to strengthen industrial control due to their remote sensing and tracking capabilities [54]. For example, wireless sensors monitor and adjust business processes, enhance connectivity, and provide real-time insights [53].…”

Section: Sensors Are Used To Regulate Processesmentioning

confidence: 99%

A Bibliometric Analysis of the role of Industry 4.0 Sensors in Digital Transformation

Dias¹,

Rosário²

2023

Preprint

View full text Add to dashboard Cite

This study aims to determine the role of Industry 4.0 sensors in digital transformation. Using a systematic literature review with a bibliometric analysis, we examine a sample of 52 studies from the SCOPUS database to identify research activity on this topic until December 2022. We find that 2022 was the year with the highest number of peer-reviewed documents on the subject, with 18 publications. We also examine current themes and find that sensors can connect multiple systems and devices, thus enabling machine-to-machine communication and facilitating great precision during product designing, development, and production, thus enabling customization and improving quality. However, despite these benefits, the current sensor technologies face multiple challenges that undermine their maximum adoption.

show abstract

“…The IIoT emerges as a new milestone on the Internet so that billions of machines in the industry are equipped with various types of sensors, connected to the Internet through heterogeneous networks [28]. Possible applications of the IIoT include abnormal pattern detection [29] or predictive maintenance [25], among many others.…”

Section: Challenges In Internet Of Things and Industrial Internet Of Things Scenariosmentioning

confidence: 99%

Deep Reinforcement Learning for the Management of Software-Defined Networks and Network Function Virtualization in an Edge-IoT Architecture

et al. 2020

View full text Add to dashboard Cite

The Internet of Things (IoT) paradigm allows the interconnection of millions of sensor devices gathering information and forwarding to the Cloud, where data is stored and processed to infer knowledge and perform analysis and predictions. Cloud service providers charge users based on the computing and storage resources used in the Cloud. In this regard, Edge Computing can be used to reduce these costs. In Edge Computing scenarios, data is pre-processed and filtered in network edge before being sent to the Cloud, resulting in shorter response times and providing a certain service level even if the link between IoT devices and Cloud is interrupted. Moreover, there is a growing trend to share physical network resources and costs through Network Function Virtualization (NFV) architectures. In this sense, and related to NFV, Software-Defined Networks (SDNs) are used to reconfigure the network dynamically according to the necessities during time. For this purpose, Machine Learning mechanisms, such as Deep Reinforcement Learning techniques, can be employed to manage virtual data flows in networks. In this work, we propose the evolution of an existing Edge-IoT architecture to a new improved version in which SDN/NFV are used over the Edge-IoT capabilities. The proposed new architecture contemplates the use of Deep Reinforcement Learning techniques for the implementation of the SDN controller.

show abstract

Pattern Extraction for the Design of Predictive Models in Industry 4.0

Cited by 26 publications

References 5 publications

Evaluating the Degree of Uncertainty of Research Activities in Industry 4.0

Evaluating the Degree of Uncertainty of Research Activities in Industry 4.0

A Bibliometric Analysis of the role of Industry 4.0 Sensors in Digital Transformation

Deep Reinforcement Learning for the Management of Software-Defined Networks and Network Function Virtualization in an Edge-IoT Architecture

Contact Info

Product

Resources

About