Pattern Recognition of Hydroacoustic Signals

Project Type: Student Project
Student: Nikolaus Mutsam


Short Description
The CTBTO (UN Organization) is currently setting up a global verification system to monitor the earth for nuclear explosions. Hydroacoustic sensors are used to measure the underwater acoustic signals. The aim of the thesis is to classify the hydroacoustic signals. Recently developed pattern recognition methods such as discriminatively optimized Graphical models should be applied and extended for this task. Furthermore, other classification algorithms (partly borrowed from speech processing) shall be used for comparison.

A list of tasks to be done within the thesis

  • Literature review
  • Implementation and application of classification methods
  • Empirical comparison
  • Report writing

Profile of prospective student
The candidate should be interested in machine learning, applied mathematics/statistics, Matlab programming, and algorithms. Interested candidates are encouraged to ask for further information.