SAKE Semantical analysation of complex events

A Platform for the integration of big data streams with the support of machine learning

Type of content: Assets
Type of asset:
Use case
Big data potential
Yes
Policy domains: Innovation, Science & Technology
Phase in the policy cycle:
Agenda Setting
Policy Design and Analysis
Policy Implementation
Policy Monitoring and Evaluation
Open license availability
No
Ease of use
High
Tags: Machine learning Big data
SWOT Analysis for
SAKE Semantical analysation of complex events
Helpful Harmful
Internal
Strengths• Optimization of internal processes and reduction of production costs
• Analysing vast streams of data
• Reduction in the workload required of the system resources: data gathered by the sensors will be modularized, in order to process only the aspects of data relevant to the purpose of the analysis.
• Automatic language generation provides high degree of user friendliness: Analytical results and the causes of errors to be processed in natural language available via a combination of modern learning methods and automatic language generation processes
• Unsupervised learning in streaming is able to detect novel patterns in streaming data in real time without any re-analysis of previously examined data
• To cope with the potentially large amount of data, the architecture utilizes state-of-the-art distributed cloud-based big data technologies
Weaknesses• Enormous amounts of real time data generated
• The technological advances related to real-time data analytics are moving and changing as rapidly as data itself.
• Basic design of the architecture is considered complete, there is still rom for further developments on the module level
External
Opportunities• Facilitate the timely detection and data driven prediction of failures from event data
• Increase of data: Increasing use of automation in machine and plant construction has led to a large growth in the amount of data generated from the number of industrial production processes being recorded and monitored by sensors.
• Centrally evaluating the data in real time, could lead to optimization of internal processes and reduction of production costs
• Strongly heterogeneous data streams can be consolidated and subsequently analysed using modern machine learning processes.
• Development of a scalable distributed data storage layer relating to event descriptions in accordance with the Resource Description Framework (RDF)
• Efficient supervised and unsupervised machine learning modules for modularised data to discover the causes of errors and to predict sensor configurations which can lead to errors
• Development of intuitive user interfaces
Threats• The technological advances related to real-time data analytics are moving and changing as rapidly as data itself.
• Enormous amounts of real time data generated
• Data quality

Open data - Download the Knowledge base

You are free to download the data of this Knowledge base.

To do this you must be an authenticated user: log in or sign in now.

All the data are licensed as Creative Common CC-BY 4.0.