Description

The essence of the project
1. The target is to select a range of data and understand its likelihood to be similar to another set of data? (Time series in this case) 
The use case is time series data from the internal sensors inside manufacturing tools.  It is what we are calling an IIoT case (Industrial Internet of Things) and is also part of our IT4.0 effort.  We store sensor data from hundreds of manufacturing tools in databases today.  We want to develop similarity metrics that would compare same sized time windows of sensor data throughout time on the same tool and/or throughout time comparing time windows from different tools of the same type.
2. The idea behind is to probably understand which data ranges are likely to be useful for the storage? 
The idea is to do at least three things:
 Search for all examples of ranges that are like an -interesting case-.  For example, a -questionable run- occurs on the manufacturing tool, and we want to find similar previous cases.
 Similarity metrics would be used to cluster example time ranges into interesting groups to show a user (unsupervised learning)
 You could train a classifier as well.
3. What will the usage of the library look like? (In brief)  
The usage pattern will be data scientists investigating IIoT data using Jupyter notebooks or VS Code in python.  Ultimately (maybe not part of this project) we might want to integrate this type of python library into a time series database like influxDB.

This project combines the best EDA practices from an angle of data storage optimization. 

Requirement: good familiarity with python.

Automatic Data Recognition

AI and Machine Learning

Description

Emphasis in project execution

The project is has cooperation with the industry and combines meeting deadlines while being creative and focused on the task