Data mining in large audio collections of dolphin signalsReport as inadecuate

Data mining in large audio collections of dolphin signals

Data mining in large audio collections of dolphin signals - Download this document for free, or read online. Document in PDF available to download.

The study of dolphin cognition involves intensive research of animal vocal-izations recorded in the field. In this dissertation I address the automated analysisof audible dolphin communication. I propose a system called the signal imager thatautomatically discovers patterns in dolphin signals. These patterns are invariant tofrequency shifts and time warping transformations. The discovery algorithm is basedon feature learning and unsupervised time series segmentation using hidden Markovmodels. Researchers can inspect the patterns visually and interactively run com-parative statistics between the distribution of dolphin signals in different behavioralcontexts. The required statistics for the comparison describe dolphin communicationas a combination of the following models: a bag-of-words model, an n-gram modeland an algorithm to learn a set of regular expressions. Furthermore, the system canuse the patterns to automatically tag dolphin signals with behavior annotations. Myresults indicate that the signal imager provides meaningful patterns to the marinebiologist and that the comparative statistics are aligned with the biologists’ domainknowledge.

Georgia Tech Theses and Dissertations - College of Computing Theses and Dissertations -

Author: Kohlsdorf, Daniel - -


Related documents