After successful completion of the course, students are able to...

• Apply basic knowledge about Industrial Data Science
• Participate and perform in IDS projects
• Work with numeric and textual data sources for predictive analysis
• Use basic AI/ML/NLP Algorithms
• Built their own domain Ontology
• Work with Jupyter Notebooks on a cluster infrastructure

In the exercise, students will learn basic Industrial Data Science concepts, including:

• Introduction Python for IDS
• Data Preprocessing in Python
• Exploratory data analytics
• Application of a Data Mining Process Modell: CRISP-DM
• Introduction to basic Supervised and Unsupervised Learning Techniques
• Introduction to Natural Language Processing
• Introduction to Knowledge Based Methods, including Case-based Reasoning and Ontology Modelling with Protégé.

The Pre-requisite for the exercise is 330.267 Knowledge Management 4.0 (VO)

Participation in all 4 exercise units, see TUWEL, is mandatory

• Teamwork - The exercise will be structured in the format of Group Project (Collaborative Teamwork).
• The students will practice the lessons in a collaborative environment, which supports improving their transversal skills, including presentation of key-findings, discussion with team members and learning by participating in teamwork activities.
• Jupyter Notebooks will be used in the exercise and submitted by the students for the assignment including a detailed description of the result of the teamwork.

Completion of:

• Multiple Choice Tests
• Exercises
• Assignment

Basic knowledge in production, logistics, quality, process and project management

The Pre-requisite for the exercise is the lecture of 330.267 Knowledge Management 4.0 (VO).