The course delves into the entire data lifecycle in industrial and distributed contexts: from collection via IoT devices, to protection through anonymization techniques, and finally to data analysis to extract value and support decision-making processes. The focus is technical and operational, with real-world examples and applications, aiming to provide solid skills for effectively, securely, and practically managing field data, without delving into regulatory or cybersecurity aspects. The course has a strong component of customization based on client needs.
CONTENT
- Architecture and technologies for data collection from IoT objects and systems.
- Data ingestion: protocols, buffering, edge computing, raw data management.
- Data quality and integrity: controls and strategies.
- Data anonymization and pseudonymization techniques: methods, scenarios, limitations.
- Data protection by design: minimization, separation, abstraction.
- Data lakes and transformation pipelines for analysis.
- Basic and advanced data analysis techniques: descriptive, predictive, clustering, pattern recognition.
- Use cases: monitoring, predictive maintenance, process optimization.
OBJECTIVES
- Understand how to design and implement an efficient data collection system for connected devices.
- Gain familiarity with the main anonymization techniques that protect data without compromising usability.
- Learn how to prepare and analyze industrial datasets in a consistent and scalable manner.
- Develop an integrated view of data, from source to insight.
LEARNING OUTCOMES
- Ability to set up robust and flexible data collection architectures.
- Hands-on knowledge of the main anonymization techniques and their applicability.
- Proficiency in establishing data analysis pipelines for datasets collected from heterogeneous systems.
- Awareness of the strategic value of data when handled correctly throughout its life cycle.
PREREQUISITES
To benefit from the course, basic knowledge of IoT systems in industrial contexts is required.