inf1210 - Practical multimodal-multisensor data analysis pipelines (Complete module description)

Module label	Practical multimodal-multisensor data analysis pipelines
Module code	inf1210
Credit points	6.0 KP
Workload	180 h
Institute directory	Department of Computing Science
Applicability of the module	Master's Programme Computing Science (Master) > Praktische Informatik
Responsible persons	Sonntag, Daniel (module responsibility) Lehrenden, Die im Modul (authorised to take exams)
Prerequisites	Basic familiarity with Python and machine learning concepts
Skills to be acquired in this module	review the current literature on multimodal-multisensor data analysis identify unexplored research topics recognize good practices and practical aspects of all steps in the data analysis process gain hands-on experience on multimodal-multisensor data analysis pipelines Professional competence The students: recognize the basic concepts of data analysis identify the basic steps of data analysis pipelines Methological competence The students: clean data based on the principles of tidy data visualize data using different libraries and frameworks identify relevant data questions and implement machine learning models apply version control to data and models design and implement a User Interface to interact with the data and models Social competence The students: present their solutions to the group discuss with each other different solution approaches to a given problem review and discuss relevant research papers on data analysis Self competence The students: acknowledge the limits of their ability to cope with approaching assignment deadlines reflect on the limits of their ability to structure their project workload
Module contents	Multimodal-multisensor data is profoundly different from past data sources. It is extremely rich and dense data that typically involves multiple time-synchronized data streams, and it also can be analyzed at multiple levels such as signal, activity pattern, representational, transactional, etc. When multimodal-multisensor data are analysed at multiple levels, they constitute a vast multi-dimensional space for discovering important new phenomena with applied artificial intelligence methods. This course focusses on Data Analysis Pipelines and covers good practices and practical aspects of all steps in the process: handling file input, organising a project’s code, transforming the data with spectral andmachine learning methods, and generating models and visualisations that capture relevant structure in the data.
Recommended reading
Links
Languages of instruction	German, English
Duration (semesters)	1 Semester
Module frequency	every winter term
Module capacity	unlimited
Teaching/Learning method	V+Ü oder S+Ü

Examination	Prüfungszeiten	Type of examination
Final exam of module	at the end of the lecture period	oral examination or practical work or term paper

Type of course	Seminar
SWS	0
Frequency	SuSe or WiSe
Workload attendance time	4 h