Brain Computer Interfaces Benefit from Cloud Advancements From; HPC in the Cloud - 03/23/2011 By: Kate Ericson Brain Computer Interfaces (BCIs) have been gaining traction in recent years. These applications range from allowing people who have lost voluntary motor control to type at a keyboard [1] and also to allow navigating a wheelchair through a crowded room [2]. These applications rely on EEG data gathered from electrodes held close to the scalp. Machine Learning techniques, such as artificial neural networks, can then be used to interpret the user’s intent from these signals. EEG analysis is usually performed in physical proximity to the user that, in turn, can lead to limitations in the processing power available for analyzing the EEG signals. For example, the wheelchair application relies on a laptop carried by the user for all EEG analysis. Colorado State University (CSU) researchers are conducting experiments involving brain computer interfaces (BCIs) run in cloud computing environments. The CSU team's approach involves training many smaller neural networks that can work together to classify data and build predictions as a group. The team moved its electroencephalogram (EEG) analysis to the cloud and used the Granules cloud runtime, created by CSU professor Shrideep Pallickara, to process the EEG streams. The technique is a good fit for the MapReduce paradigm that is supported by Granules, which allows computations to be activated as more data is available. The method enabled the CSU team to train neural networks on a set of resources within Granules, and stream the EEG signals to the cloud for classification. In their experiments, the researchers supported EEG streams generated by 150 users on a cloud of 10 computers. The cloud returned classification results in under 250 milliseconds in 99.9 percent of cases. By moving EEG analysis to the cloud, researchers can avoid the limitations that many mobile BCI applications have. Read the entire article at: http://www.hpcinthecloud.com:80/features/Brain-Computer-Interfaces-Benefit-from-Cloud-Advancements-118483354.html Links: Kathleen Ericson http://www.cs.colostate.edu/~ericson/ Analyzing Electroencephalograms Using Cloud Computing Techniques http://salsahpc.indiana.edu/CloudCom2010/slides/PDF/Analyzing%20Electroencephalograms%20Using%20Cloud%20Computing%20Techniques.pdf References: [1] C. W. Anderson and J. A. Bratman, "Translating Thoughts into Actions by Finding Patterns in Brainwaves," in Fourteenth Yale Workshop on Adaptive and Learning Systems, New Haven, CT, 2008, pp. 1-6. [2] F. Galan, et al., "A brain-actuated wheelchair: Asynchronous and non-invasive Brain-computer interfaces for continuous control of robots," Clinical Neurophysiology, vol. 119, pp. 2159-2169, 2008.