Premium
Streaming analytics for real‐time and data‐driven decision making in Automation Industry
Author(s) -
Maganti Ramesh,
Swamy Manjunatha
Publication year - 2016
Publication title -
incose international symposium
Language(s) - English
Resource type - Journals
ISSN - 2334-5837
DOI - 10.1002/j.2334-5837.2016.00325.x
Subject(s) - computer science , analytics , data stream mining , automation , big data , data science , data analysis , process (computing) , scope (computer science) , batch processing , business intelligence , real time data , stream processing , predictive analytics , data mining , engineering , distributed computing , world wide web , mechanical engineering , programming language , operating system
With disruptive technologies such as IoT, pervasive computing and drones, automation is spreading to every process from house hold to large industry, with that tremendous amount of data being generated from multiple systems and sub systems. Tons of valuable critical data is available, there is need for live analysis and actionable insights for process improvements and controls. Traditional analytics method such as data‐mining, ETL (Extract, Transform, Load) with batch processing and delayed insights, are becoming more and more irrelevant. There is a stressing need for real‐time and data‐driven decision making. Streaming analytics is getting in to fast lane, to analyse multiple streams of data, events generated by components across the physical spectrum to generate real‐time insights. With machine learning and artificial intelligence trends, there is huge scope to generate learning models from historical data and provide predictive analysis out of real‐time data streams to automate the decision making process.