Building IIoT analytics
Identifying the right parameters and techniques is the most important part of building IIoT analytics. In 1977, John Tukey wrote the book Exploratory Data Analysis. The following method is based on Exploratory Data Analysis (EDA) and is applied to the new cloud DevOps requirements.
ML operability
When we work with ML and AI we speak about Machine Learning Operability (MLOps). The word MLOps is a compound of ML and the continuous development practice of DevOps in the software field. MLOps aims to deploy and maintain ML models in production.
The following are the steps that we need to accomplish:
Figure 13.4 – Analytics development workflow
Step 0 – problem statement
Step 0, or the problem statement, always requires us to define the scope of the problem, the constraint of the problem, and the expected behavior. Then, we should align the business expectation with the technical expectation. It is a good...
