Delivered at:: Department of Business Informatics

Course type:: Elective course

When:: 2 year, 1, 2 module

Instructor

Ковалев Илья Александрович

Full Syllabus Ask Question

Abstract

Manufacturing Data Collection and Analytics is an elective course given in the second year of the master's program. The course introduces Internet of Things field of computer science and hardware implementation as an overview of an industrial environment as a source of data. The course covers two modules and includes physics on electrical schemes and networking, different kinds of the things themselves, various fields of the things implementation, software needed to code the things behaviour and store the data including Internet of Things operating systems and some simple examples of data analytics. During the practice classes students have a lot of assignments based on two hardware plat-forms: Arduino Uno and Raspberry Pi 3/4 with Arduino IDE and Android Studio for Android Things OS (or other Unix/Linux-based OS like Raspbian with its software) respectively. Then students are given a home assignment which replaces the course exam. The home assignment is a hardware-software project based on a simple network of the things with a certain purpose to collect and analyze/react to sensors data (smart home, smart weather station, smart plant, smart lock etc.). The assignment is divided into two parts: the first part is hardware (with systems on module mentioned and various sensors, controls, LEDs etc.) and the second part is software (preferably mobile application) controlling the hardware. This course is practice oriented – much more attention is given to practice, not lectures.

Learning Objectives

getting to know the Internet of Things field including terms, basic concepts and implementations
learning to work with hardware (system on modules and various wires and sensors)
studying coding and programming the hardware
getting skills in mobile application developing to control the hardware
learn how to use, collect, store and analyze the sensors data (machine data collection) with a help of an IoT cloud platform

Expected Learning Outcomes

Be able to understand the main problems of the Big Data Analytics in Industry, get acquainted to the architectural components and programming models used for scalable data analysis
Know the fundamental concepts, principles and approaches to description of the Big Data Landscape in Industry
Learn how to use one of the most common frameworks and tools
basics of Internet of Things functionality, purposes, implementations, applications
how to work with the according hardware
how to use various libraries in the software environment dedicated to Internet of Things
how to code and use the hardware boards to run the code
how to use IoT cloud platforms for collecting and analyzing the sensors data
how to develop a mobile application

Course Contents

Industrial revolutions.
Data analytics concepts.
Data Analytics. Manufacturing Analytics.
Reference architectures in Industry 4.0. RAMI 4.0
Smart Factory
IoT Gateway: collecting low-level shopfloor data
SQL and noSQL databases
Predictive Analytics
CUDA
WEB technologies for data analytics
Data Science for Industrial Data
Criteria for I4.0 products
Industrial Data Collection Methodology
IoT and IIoT.
Industrial Control Fundamentals
HBASE
Python DS
Industrial Protocols
Industrail control systems
Reference architectures in Industry 4.0
National and alternative reference architectures
Industrial use cases
IoT and IIoT devices
Big Data in Smart Factory
Auto Identification

Assessment Elements

Home task
Exam
Activity during classes
Participation in lectures and topics discussions

Interim Assessment

2023/2024 2nd module
0.2 * Activity during classes + 0.52 * Exam + 0.28 * Home task

Bibliography

Recommended Core Bibliography

Buyya, R., Calheiros, R. N., & Vahid Dastjerdi, A. (2016). Big Data : Principles and Paradigms. Cambridge, MA: Morgan Kaufmann. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1145031
Lin, J., & Dyer, C. (2010). Data-Intensive Text Processing with MapReduce. Morgan & Claypool Publishers.
White T. Hadoop: The Definitive Guide. - O'Reilly Media, 2015.
White, T. (2015). Hadoop: The Definitive Guide : Storage and Analysis at Internet Scale: Vol. 4th edition. O’Reilly Media.

Recommended Additional Bibliography

Mahmood, Z. (2016). Data Science and Big Data Computing : Frameworks and Methodologies. Switzerland: Springer. Retrieved from http://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=edsebk&AN=1203573

Authors

KOVALEV ILYA ALEXANDROVICH
Beklarian Armen Levonovich
YAKOVLEVA NATALIYA VADIMOVNA

Master’s Programme 'Business Informatics: Digital Enterprise and Information Systems Management'

Contacts

Manufacturing Data Collection and Analytics