Short description

For infrastructure monitoring we use glas fiber cables as used for communications as an acoustic sensor that provides us with »1000 virtual channels along up to 40 km. In order to detect possibly dangerous events, we need to classify the data that is recorded. Most data will be not interesting activity, since dangerous events are avoided and therefore rare. The aim of this project/thesis is to work on a framework that allows to detect anomalous events in those audio channels in real-time with a latency of around one minute and classify the type of event.

Your Tasks

• Review of toolboxes and approaches available
• Implementation of classification algorithms
• Documentation

Your Profile/Prerequisites

• Motivation and interest in the topic
• Background in Signal Processing and Machine Learning
• Strong programming background, ideally in Python or Julia

Contact:

Martin Hagmüller (hagmueller@tugraz.at or 0316/873 4377)