Automated drill-stop by SVM classified audible signals.

Autor: Pohl, Bernd M., Jungmann, Jan O., Christ, Olaf, Hofmann, Ulrich G.
Zdroj: 2012 Annual International Conference of the IEEE Engineering in Medicine & Biology Society; 1/ 1/2012, p956-959, 4p
Abstrakt: Neuroscience research often requires direct access to brain tissue in animal models which clearly requires opening of the protective cranium. Minimizing animal numbers requests only well-experienced surgeons, since clumsy performance may lead to premature death of the animal. To minimise those traumatic outcomes, an algorithmic approach for closed-loop control of our Spherical Assistant for Stereotaxic Surgery (SASSU) was designed. Controlling the surgical robot's micro-drill unit by audio pattern recognition proved to be a simple and reliable way to automatically stop the automated drill feed. Sound analysis based on the anatomical morphology of a rat skull was used to train a Support Vector Machine (SVM) classification of the time-frequency representations of the drill sound. Fully automated high throughput animal surgeries are the goal of this approach. [ABSTRACT FROM PUBLISHER]
Databáze: Complementary Index