Welcome to the UnCoRe Summer Project

  In this project, Self Organizing Feature Maps are trained to categorize Diana monkeys danger calls.  Features are extracted in time domain, frequency domain, and joint time-frequency domain from audio files of Diana monkey communication.  Unknown calls are then fed into the map to identify the sound.  Several contributions have been made to the maps to improve the quality, speed, and accuracy.  Correlation has been implemented as the activation function to improve the accuracy of identifying sounds.  A history function to update previous winning nodes has been implemented to decrease the time necessary to complete the training phase.  Sammon mapping has also been proposed to provide better initialization of vectors.  In addition, several types of distance metrics are tested to find best matching units including a blended Manhattan-Euclidean distance which has been found useful.


See the current status of the project.

Project Documents

Organization is key to any successful project and with page you can keep all you project documents in one place accessible to the whole team.

Recent Updates

Keep your team informed and on track using the recent updates page.


Immediately get in touch with your project manager by using the contact page.