Courses

The above topics are offered in project work in cooperation with Landmetzgerei Setzer. The aim is to analyze a given problem with real data from a company using the data analysis methods learned in AIDAHO modules. The topics are supervised by a researcher of the FG Food Informatics. The topics are supervised by a research assistant of the department of Food Informatics. Upon successful completion, the course will be credited as an AIDAHO Application seminar. Depending on the student's program of study, these can also be credited as a curricular module, e.g.: Introduction to Scientific Working Methods of Food Informatics (1511-011), Projekt work (1500-530), Portfolio-Modul or Applied Data Science Lab (5000-671).

Please check with us for desired credit before attending. The topic will be worked on in conjunction with the course Introduction to Scientific Working Methods in Food Informatics (1511-011). This is organized in the style of a scientific conference. All participants must write a scientific paper on the assigned topics. In this case, this is a short report on the methodology used, the presentation of the results, and a short discussion of the same.

Participation in three lectures is mandatory: kick-off and introductions to literature research, LaTeX/Overleaf, application of language models (e.g. ChatGPT), introduction to data visualization, and presentation techniques. Subsequently, the editing phase begins in which the students write a short scientific paper on their chosen topic under the supervision of their supervisor. At the end of the semester the "conference" takes place with the final presentations of the students. Participation in discussions of other papers is elementary. Participation in the kick-off meeting, seminar days, and final presentations is mandatory. Examination performances can be taken in English if required.

Contact Jan Dvorak for more information.

The topics and the exact schedule will be announced on the Department's website well in advance. In principle, this seminar is organized in the style of a scientific conference. Firstly, there will be two seminar days with kick-off and introductions to literature research, LaTeX/Overleaf, data visualization and presentation techniques. All participants must write a scientific paper on the assigned topics and submit these papers by the first draft deadline. After that, the peer review phase of the papers will begin and each paper will be assigned to at least two other participants who will have to review the papers. Each participant of the event will have to review 2-3 other papers. After the review phase, the reviews must be submitted to the supervisors who will distribute them to the authors of the papers. After that, authors have time to improve their papers based on the feedback from the reviews before they have to submit their final (camera-ready) version of the paper. At the end of the semester, the "conference" is held with the final presentations of the participants. Participation in discussions of other papers is elementary.

Topics in the winter semester 2022/23 and information on registrations

Schedule winter semester 2022/23

Topic announcement: 15.08.2022

Application for topics til: 16.10.2022

Topic assignment: 17.10.2022

Kick-off meeting, 1./2 seminar day: 18.10.2022, 14-17, informations follow

2./2 Seminar day: 25.10.2022, 14-17, informations follow

Submission of first draft: 22.12.2022

Deadline for review: Januar 2023, date to be announced

Submission of final paper: End of January (date to be announced)

Final presentation: 03.02.2023

Course information

The course is addressed to students who want to acquire technical basics about the functioning of information systems. In addition to basics about how computers work and programming, algorithms for standard problems, data structures and computer networks are introduced.

Contents of the course are:
- How computers work
- Fundamentals of programming
- Basic algorithms for searching and sorting information
- Data structures, e.g. arrays, trees, lists, hashing, graphs
- Distributed systems and computer networks.

Course information

The course is addressed to students of food science and biotechnology. In addition to a theoretical introduction to the topic, practical exercises using real data examples with Excel, R or Python are part of the course.

Possible contents of the course are:
- Events and quantity systems, descriptive and exploration of data
- Probability theory (one-dimensional and multivariate), random variables
- Parameter estimation
- Statistical tests and hypotheses
- Regression analysis, correlation analysis, variance analysis
- Time series analysis
- Excursus: machine learning methods for data analysis.

Course information

This module will provide essential knowledge of the technological foundations of information systems. Based on this, students will be able to assess technology but also to develop software and acquire fundamentals for learning machine learning techniques.
The students will learn basic concepts of computer hardware (von Neumann architecture) and system software (operating systems concepts), programming fundamentals (Java or Python), as well as algorithms and data structures (searching, sorting, lists, hash-tables, trees). This includes an understanding of the basic architectures of modern information systems, software implementation, and how to model problems in algorithms/software and how solve them using modern programming languages.

Course information

In the first part of the lecture, the students will learn the basics of programming and how to work with the Python ML ecosystem. After an overview and self-training of basic programming concepts, the focus is set on the acquisition of programming skills for the application and evaluation of machine learning (ML) techniques. Students will learn about most basic ML models and how to implement them in Python using state-of-the-art ML frameworks such as scikit-learn. Subsequently, Deep Learning, known from recent applications such as image recognition (e.g. for autonomous vehicles), will be the subject of discussion along with practical training sessions using PyTorch. Additionally, metrics and concepts for evaluating ML models, i.e., how to interpret the results, are taught. Also the aspect of data visualization as a central topic of data analytics will be trained in this course.            

Course information

The module introduces fundamental concepts of “Natural Sciences” and aims to deliver basic knowledge in Chemistry, Microbiology, Biotechnology, (Food) Engineering, and Material Science. A case study, for instance on ‘Time Temperature Indicators”, fosters knowledge transfer and enables the students to apply the different concepts to one concrete example of application. Lecture-accompanying experiments and guided tours through the laboratories and pilot plants of the Institute of Food Science and Biotechnology are part of the course schedule. Moreover, 2 industry – hosted lectures further highlight the importance of natural Sciences as one of the key disciplines in Bioeconomy.

Course information

Students learn advanced programming with Python with a focus on practical application in realistic use cases. The following contents are covered:

• Programming with Python
• AI Coding-Tools (e.g. ChatGPT, Github Copilot, ...) 
• Computer Networks
• Web development with Python
• API Programming
• Data Analytics

The course will be conducted in a project-based format. In addition to delivering theoretical lecture content, these concepts will be practically applied in projects, with students receiving guidance from tutors.

Course information

In this module a set of tools and skills are provided to identify, describe, evaluate, and improve the sustainability of the value chain of a (new) biobased product. The students analyze a whole biogenic value chain currently on the agenda of the bioeconomy transformation process to develop a deeper understanding of biobased industrial and commercial activities. With support from supervisors and in communication with partners from industry, students first identify a value chain related to food, feed, fibre or fuel production. They then describe, analyse and identify gaps in the value chain from biomass production to conversion and market introduction of the product.

The following methods and tools can be used for the system analysis:
- “energy and mass flows”, and “thermodynamic considerations”
- supply chain management based on “value stream mapping” and “continuous improvement techniques”.
- “life-cycle assessment”,
- “environmental and social impact assessment”.

These methods and tools are introduced to demonstrate how to carry out an internet-based case study using a step-by-step approach. Particular emphasis is placed on the selection of green materials, the design of factory operations and the management of market introduction of (new) bio-based products. Environmental and social impacts of the value chain will be assessed and approaches for waste reduction and energy saving will be elaborated in order to optimize production. Finally, based on their analysis, students develop a concept to improve an existing biogenic value chain or scientific and engineering pre-studies can be carried out to fill identified gaps or create new products. The results as well as the pros and cons of the applied methods are presented and discussed in class.

Course Information

Seminar for doctoral students by individual arrangement.

Possible topics:

• Project and time management, cooperation with research partners/companies
• Conception of projects in the context of digitalization of food processing
• Preparation of presentations adapted to the audience
• Discussion on hypothesis formation, planning of experiments to answer them
• Data evaluation, preparation in tables, pictures, diagrams, derivation of models and their integration in publication
• Planning of preparatory work for new research projects up to the submission of applications aligned to the respective funding body.