Machine Learning is per se a huge full topic alone. The same is with Big Data. If you combine this - it's size will grow up near to infinity.
I think you need firstly to narrow down the search space in being a little more specific than you already did: Description: - to find out how ML and Bigdata can contribute to improve manufacturing process
- to find the research gap on methodologies and approach
Which manufacturing process is in your focus? What you will find out by ML? How fast should be the solution? What are your objectives?
If you can provide a problem definition first, then it's easier to narrow down and find the Gap. The Gap not necessarily need to be a fully new topic - it can be that it exist something already, but can be optimized for your problem - then you also fill a Gap...
I browsed the useful sources provided by Stephan Kühnel. I thought the following was missing, to find the gaps you need a theory or model of what you want. The sources mentioned provides guidelines for developing such a theory or model, but you can sometimes start of with a theory and check if something is amiss (i.e., there is a gap) during your survey and analysis. For example, if you have a prescriptive theory stating that certain steps have to be be to improve the likelihood of succeeding, then you can check if and how sources meet these steps.
Machine Learning is per se a huge full topic alone. The same is with Big Data. If you combine this - it's size will grow up near to infinity.
I think you need firstly to narrow down the search space in being a little more specific than you already did: Description: - to find out how ML and Bigdata can contribute to improve manufacturing process
- to find the research gap on methodologies and approach
Which manufacturing process is in your focus? What you will find out by ML? How fast should be the solution? What are your objectives?
If you can provide a problem definition first, then it's easier to narrow down and find the Gap. The Gap not necessarily need to be a fully new topic - it can be that it exist something already, but can be optimized for your problem - then you also fill a Gap...
Thank you very much to Stephan Kuhnel, Jonas Mellin & Peter Michael Goebel for all your valuable & important advices, guidelines & sharing...my heartfelt appreciation...may God blessing your good research R & D works & studies...
- Badges
- Science topic