Team/Contributors: Nwankwo Linus | Vedant Dave | Fotios Lygerakis | Nikolaus Feith | Melanie Neubauer | Elmar Rueckert
Chair of Cyber-Physical-Systems (CPS)
- Course Format and Organisation
- Location and Date
- Attendance
- Notes
- Communication and Academic Integrity
- Prerequisites
- Lecture Time Table
- If you miss the course
- The Project Workflow
- Task Presentation, Q & A
- Report and Code
- Alternative Submission Method
- Project Grading
- Grading Scheme
- Projects Overview
- Getting Started Tools
- Project Objectives
- Resources and Literature
- Contacts
Mode of attendance: Physical or via Webex
-
Join Webex Meeting: https://unileoben.webex.com/unileoben/j.php?MTID=m5492385776dd885ca5dde72e52563c61
-
Meeting number (access code): 2785 518 6804
-
Meeting password: fgJq3UEKf67
Weekly online meetings: Every Wednesday from 17:00 - 18:00 via Webex
-
Join Webex Meeting: https://unileoben.webex.com/unileoben/j.php?MTID=m5e17e864e5784737dffd2fa1d27d161c
-
Meeting number (access code): 2789 858 4770
-
Meeting password: vTHYP5QMj77
- Location: HS 3 Studienzentrum, Montanuniversität, Leoben
- Dates: 02.10 – 06.10.2023 and Every Wednesday from 17:00 - 18:00 via Webex.
- Online assistance will be limited, therefore, it is encouraged to attend the course in person so that you can get unlimited help to enable you to finish or at least figure out how to finish the assignment before the due time.
- An account will be created for each group in our JupyterHub for submission of the assignments.
- The accounts will remain active till the end of the semester.
- The final project results will be presented in a written report in the form of a git repository wiki page and presented for at least 5 - 10 mins.
- Office Hours: If you have any questions or need assistance, please come during the office hour. If you cannot make it to office hours, email me to schedule an appointment.
- Emails: It is extremely hard to discuss technical questions through emails. Therefore, we encourage you to come to the lab for such a discussion.
- Discussions among teams are encouraged for a better understanding of the course materials. However, each of you (or your team) should work on your code independently after the discussions.
- Lab safety: In case your chosen project requires a physical robot or other hardware in our lab, please seek permission from the technician or the person in charge of such hardware.
- Citation: Reference any website or academic material used in your project. If you use ChatGPT for your work, please provide details of the prompt and the results.
- A laptop or tablet.
- Internet access. You could use the Uni. internet or eduroam.
- Basic Python programming. No worries if you do not have some experience, we will start with the basics.
- Basic background in statistics, e.g., probability, descriptive statistics (measures of central tendency and dispersion), visual representation of data (histograms, bar charts, pie charts, scatter plots, etc.).
- Recommended Prerequisites: Introduction to Machine Learning (“190.012” and “190.013”).
- The timetable for the lecture will be updated from time to time.
- You can access the timetable at https://cloud.cps.unileoben.ac.at/index.php/apps/
- If you miss some course content, you can watch recordings of the sessions online.
- All recordings will be hosted via Moodle at: https://moodle.unileoben.ac.at/course/view.php?id=3082.
- Introduction to the task: 06.10.2023
- Motivation & Objectives
- Research Questions & Related Work
- Problem & Dataset Description
- Approach & Methods
- Results and Discussions
Q & A
- During the Lecture
- During office hours
- If technical question(s) that involves hardware: come to the lab or schedule an appointment
| Reports | Codes |
|---|---|
| All reports must be in the Wiki repository or READMe.md format | All the code must be written using Jupyter Notebook or Google Colab |
| HANDWRITTEN reports will not be accepted | Use our JupyterHub templates at: https://jupyter.cps.unileoben.ac.at. Just open it and start filling it |
| Inline comments in the code are necessary, but not mandatory | |
| The file must be in .ipynb format |
If there are hitches, or you are unable to work with our JupyterHub, then:
- Create a .zip file with the following contents:
- .ipynb of your code
- .md of the wiki report
- Name it m-number_firstname_lastname_task<#>.zip
- For example, m123456789_john_smith_assign1.zip
- Upload it to the cloud at Direct Upload.
- Note: No submission will be accepted via email.
- Note: Submissions with no reports or no code are not considered and will receive 0 total points.
- You must score at least 50% of the points* at every assignment to pass the course.
| Cumulative Points | Final Grade |
|---|---|
| 0 - 49.9 | 5 |
| 50 - 65.9 | 4 |
| 66 - 79.9 | 3 |
| 80 - 91.9 | 2 |
| 92 - 100 | 1 |
- Note: Final grading will be based on the quality of the code, the report, and the final short presentation.
For the course, we have five (6) projects to be worked on by the students (individual or group):
- [Steel Production Data]: Application and comparison of deep neural networks for steel quality prediction in continuous casting plants with data from the ‘Stahl- und Walzwerk Marienhütte GmbH Graz’
- [Mechanical Eng. Data]: Predictive maintenance of bearing shells using frequency analysis in decision trees and deep neural networks based on acoustic measurement data
- [Robotics 1]: Motion analysis and path planning for human-machine interaction in logistics tasks with mobile robots of the Chair of CPS
- [Robotics 2]: Autonomous navigation and mapping with RGB-D cameras of the four-legged robot Unitree Go1 for excavation inspection in mining
- [Sign Language]: Letter-level Sign-Language Recognition
- [Own Problem]: I want to work on my own dataset and research problem. Please provide us with the details of the project.
Necessary tools to get started:
- Linux: Basic commands may be required
- Python: You just need to have a basic idea about data structures, operators, functions, etc.
- ROS: ROS Wiki Documentation has all that you need to get started (project 3)
- Virtual Machines: If your OS is not Linux, do not worry, VMware will work on Windows and Mac (optional)
- Git: To better manage your codes, we recommend Git
At the end of the project, you should be able to:
- Implement or independently adapt modern machine learning methods, and in particular deep learning methods, in Python
- Analyse data of complex industrial problems, process (filter) the data, and divide it into training- and test data sets such that a meaningful interpretation is possible
- Define criteria and metrics to evaluate, predict, and generate statistical analysis of data
- Develop, evaluate, and discuss meaningful real-world experiments
- Identify and describe assumptions, problems, and ideas for improvement of practical learning problems
Machine learning and data modelling:
- Rueckert Elmar 2022. An Introduction to Probabilistic Machine Learning. https://cloud.cps.unileoben.ac.at/index.php/s/iDztK2ByLCLxWZA
- James-A. Goulet 2020. Probabilistic Machine Learning for Civil Engineers. MIT Press
- Bishop 2006. Pattern Recognition and Machine Learning, Springer
Learning method & programming in Python:
- Matthieu Deru and Alassane Ndiaye 2020. Deep Learning mit TensorFlow, Keras und TensorFlow.js, Rheinwerk-verlag, DE.
- Sebastian Raschka, YuxiH. Liu and Vahid Mirjalili 2022. Machine Learning with PyTorch and Scikit- Learn. Packt Publishing Ltd, UK.
Problem specific literature:
- B. Siciliano, L.Sciavicco 2009. Robotics: Modelling, Planning and Control, Springer.
- Kevin M. Lynch and FrankC. Park 2017. MODERN ROBOTICS, MECHANICS, PLANNING, AND CONTROL, Cambridge University Press.
- E.T. Turkogan 1996. Fundamentals of Steelmaking. Maney Publishing, UK.
Should you have any question(s), please contact:
- Nwankwo Linus {[email protected]}