Lehrstuhl Kognitive Integrierte Sensorsysteme: Sensor Signal Processing

Sensor Signal Processing (V2/Ü2)

Instructor: Prof. Dr.-Ing. Andreas König

Lab/Exercises: Prof. Dr.-Ing. Andreas König and research assistants

Consultations: During the lecture period every Monday, 13:00-14:00, 12/455, else according to bulletin announcement or personal appointment (koenig@eit.uni-kl.de)

Contents:

Qualification aims:

Understanding of relevant principals and methods from the field of Computational Intelligence, in particular for the field of sensor technology
Mastery of application of selected relevant methods and their configuration in a common design environment (Matlab)
Ability to design, validate, and optimize a complete application-specific system system
Develop ability to adapt and extend the achieved implementation to changing needs
Understanding of interdependence of system solution with available, potentially restricted implementation platforms (Sensors/Hardware)

Teaching contents:

Basic methods of signal analysis and the computation of characteristic and invariant descriptors (features)
Processing of signals from single sensors und homogeneous or heterogeneous Sensor-Arrays
Dimensionality reduction of high-dimensional sensor data by linear and non-linear methods, e.g. by explicit selection of features
Methods for cluster analysis
Methods for multi-dimensional sensor data analysis: projection and visualisation, fusion
Methods for classification of sensor data: statistical pattern recognition, artificial neural networks, Methods of rule-based and fuzzy classification
Advanced ptimization methods for parameter- or structure optimization of sensor systems
Relations, dependencies, and optimization potential between sensor realization, electronics, and algorithmics.
New aspects of reliable sensor systems (self-x properties)

Readings

Haykin, Neural Networks A Comprehensive Foundation, Prentice Hall, 1998, ISBN 0132733501
K. Fukunaga, Introduction to Statistical Pattern Recognition, Academic Press, 1990, ISBN 0122698517
R. Duda, P. Hart, D. Stork, Pattern Classification, Wiley, 2000, ISBN 0471056693
R. Hoffmann, Signalanalyse und Erkennung, Springer 1998, ISBN 3-540-63443-6S

Prerequisites:

Basics in signal processing

Associated courses :

Messtechnik II, TESYS

Following courses :

Neurocomputing, HEIS

Examination:

Oral examination based on semester project. In a computer-based accompanying lab, students become acquainted with employing the presented methods using Matlab and QuickCog. Topics for semester projects, as individual or group projects will be given to students, which shall be elaborated, documented, and presented. The projects focus on the design and implementation of algorithms and systems for common recognition tasks. The work will be presented (20 min. slide presentation, get ISE ppt-style here), discussed, and assessed in the oral examination.

Selected semester projects :

Stefanie Peters	Recognition of Spoken Digits	2006
Avci Tunahan	Image-based Coin Recognition	2007
Jiawei Yang	''Cooky Letter Recognition''	2008
Mahesh Poolakaparambil	Color Object Classification based on SVM	2008
Yang Lei	Door Key Recognition System	2009
Naser Damer	Door Key Recognition System	2009
Sun Hao	Mushroom Classification System	2009
Group Project: Blazejowski, Marczynski, and Niedzwiedz	Speech, Music, and Advertisement Recognition	2009
Group Project: Katherine Sirois, Lorette Dousy, and Peter Tibenský	Emotiv-Kit Application for 'Mind'-Controlling Mouse Pointer	2023
Group Project: Sharath Lokesh and Tanmay Kota	Feature Extraction and Classification of ECG signal	2022/23

Course number: 85-112

Course materials :

For the course participants, lecture slides (ppt/pdf) and exercises (brief tutorials & tasks) based on Matlab and QuickCog will be provided here. The access information will be proliferated in the lecture. The materials are exclusively made available to the students of this course and can be subject to copyright of different holders without further explicit mentioning. Reprint of the course materials, dissemination of the course materials to third parties, and proliferation of the access information is prohibited without written consent of the course instructor, Prof. A. König, as well as copyright holders of the original materials donated for the purpose of teaching to a limited group.