Application Group

August 2013

No Date Title Speaker Presentation Discussion
1 2013-08-07  Optimizing the Channel Selection and Classification Accuracy in EEG-Based BCI  Seung-Chan  (pdf)
 Multichannel EEG is generally used in brain–computer interfaces (BCIs). This paper proposes a novel sparse common spatial pattern (SCSP) algorithm for EEG channel selection. The proposed SCSP algorithm is formulated as an optimization problem to select the least number of channels within a constraint of classification accuracy. The proposed SCSP algorithm is evaluated using two motor imagery datasets, one with a moderate number of channels and another with a large number of channels. The proposed SCSP algorithm yielded an average improvement of 10% in classification accuracy compared to the use of three channels (C3, C4, and Cz).
2 2013-08-14  Compressive Sensing in Photoaccoustic Tomography  Pavel Ni  ppt
 The data acquisition speed in photoacoustic computed tomography (PACT) is limited by the laser repetition rate and the number of parallel ultrasound detecting channels. Reconstructing an image with fewer measurements can effectively accelerate the data acquisition and reduce the system cost. We adapt compressed sensing (CS) for the reconstruction in PACT. CS-based PACT is implemented as a nonlinear conjugate gradient descent algorithm and tested with both phantom and in vivo experiments.
3 2013-08-21  Toward Brain-Actuated Humanoid Robot: Asynchronous Direct Control Using an EEG-Based BCI  Soogil Woo  (pdf)   (pdf)
 The brain–computer interface (BCI) technique is a novel control interface to translate human intentions into appropriate motion commands for robotic systems. The aim of this study is to apply an asynchronous direct-control system for humanoid robot navigation using an electroencephalograph (EEG), based active BCI. The experimental procedures consist of offline training, online feedback testing, and real-time control sessions.  For the performance test, five healthy subjects controlled a humanoid robot navigation to reach a target goal in an indoor maze by using their EEGs based on real-time images obtained from a camera on the head of the robot. In experimental results, the subjects successfully controlled  the robot in the indoor maze.
4 2013-08-28  Temporal classification of multichannel near-infrared spectroscopy signals of motor imagery for developing a brain-computer interface  Evgenii

In this paper, they describe a study conducted to test the feasibility of using multichannel NIRS in the development of a BCI. They used a continuous wave 20-channel NIRS system over the motor cortex of 5 healthy volunteers to measure oxygenated and deoxygenated hemoglobin changes during left hand and right-hand motor imagery.
They applied two different pattern recognition algorithms separately, Support Vector Machines (SVM) and Hidden Markov Model (HMM), to classify the data offline. SVM classified left-hand imagery from right hand imagery with an average accuracy of 73% for all volunteers, while HMM performed better with an average accuracy of 89%. Their results indicate potential application of NIRS in the development of BCIs.