By continuing your visit to this site, you accept the use of cookies. These ensure the smooth running of our services. Learn more.

Oct 27, 2012

Using Activity-Related Behavioural Features towards More Effective Automatic Stress Detection

Giakoumis D, Drosou A, Cipresso P, Tzovaras D, Hassapis G, Gaggioli A, Riva G.

PLoS One. 2012;7(9):e43571. doi: 10.1371/journal.pone.0043571. Epub 2012 Sep 19

This paper introduces activity-related behavioural features that can be automatically extracted from a computer system, with the aim to increase the effectiveness of automatic stress detection. The proposed features are based on processing of appropriate video and accelerometer recordings taken from the monitored subjects. For the purposes of the present study, an experiment was conducted that utilized a stress-induction protocol based on the stroop colour word test. Video, accelerometer and biosignal (Electrocardiogram and Galvanic Skin Response) recordings were collected from nineteen participants. Then, an explorative study was conducted by following a methodology mainly based on spatiotemporal descriptors (Motion History Images) that are extracted from video sequences. A large set of activity-related behavioural features, potentially useful for automatic stress detection, were proposed and examined. Experimental evaluation showed that several of these behavioural features significantly correlate to self-reported stress. Moreover, it was found that the use of the proposed features can significantly enhance the performance of typical automatic stress detection systems, commonly based on biosignal processing.

Full paper available here

DARPA Robotics Challenge

Via KurzweilAI

DARPA has announced the start of the next DARPA Robotics Challenge. This time, the goal is to develop ground robots that perform complex tasks in "dangerous, degraded human-engineered environments". That means robots that perform humanitarian, disaster relief operations. The robots must use standard human hand tools and vehicles to navigate a debris field, open doors, climb ladders, and break through a concrete wall. Most but not all of the robots will be humanoid in design.

The challenge is divided into two parts with a Virtual Robotics Challenge scheduled for 10 - 24 June, 2013 to test simulated robots and the actual DARPA Robotics Challenge scheduled for 21 December, 2013. DARPA has adopted the free software Gazebo simulator, which supports ROS. There are two competition "tracks" - competitors in Track A will develop their own humanoid robot and control software, while competitors in Track B will develop control software that runs on a DARPA-supplied Atlas robot built by Boston Dynamics. Already University teams are making announcements of participation. Read on for more info about some of the teams, as well as some awesome photos and videos of the robots in action.

3D Projection Mapping