|
Face-Machine Interface (FMI) for Communication of Patients with Amyotrophic Lateral Sclerosis (ALS) |
|
Chang-Hwan Im(Hanyang University, Korea) |
| In this talk, a face-machine interface (FMI) technology is introduced as a new way of communication for patients with amyotrophic lateral sclerosis (ALS). We used surface electromyogram (EMG) and electrooculogram (EOG) to decode the intention of patients with ALS. Our preliminary experimental results demonstrated that the biomedical signals recorded from the human face can be successfully used for communication of the paralyzed. |
|
|
Threeclass Classification of fNIRS Signals for RGB Color Stimulus in Visual Cortex |
|
Xiaolong Liu, Keum-Shik Hong(Pusan National University, Korea) |
| In this study, we have used fNIRS to measure the hemodynamic response in the visual cortex. We measure and discriminate the fNIRS signals evoked by RGB color stimuli. 7 healthy subjects were asked to perform the experiment during a 10 s task and 25 s rest period. Using a continuous-wave fNIRS system, brain signals were acquired concurrently from the visual cortex. Multiclass LDA was utilized to classify RGB stimuli, which resulted in an average classification accuracy of 66.67% across the 7 subjects. A 3~8 s time window during a 10 s task period provided the best result in classification. |
|
|
Bundled-Optode Method for Detection of Brain Activity in Functional Near-Infrared Spectroscopy |
|
Hoang-Dung Nguyen, Keum-Shik Hong(Pusan National University, Korea) |
| This paper presents a bundled-optode method in fNIRS for detection of absolute concentrations of oxy- and deoxy-hemoglobin. To remove physiological noises, short/long-separation detectors are used in the spatially resolved spectroscopy approach. The proposed method is applied to measure the brain activity of five healthy male subjects in mental arithmetic tasks targeting the prefrontal cortex. Most of all, the proposed method can remove physiological noises better than the conventional method. Finally, the present work can be extended to a 3D imaging of brain with improved spatial resolution. |
|
|
A Simulation Study on Decoding Algorithms for Brain-Machine Interfaces with the Non-Stationary Neuronal Ensemble Activity |
|
Min-Ki Kim, Sung-phil Kim(UNIST, Korea) |
| Intracortical brain-machine interfaces (BMIs) aim to provide motor functions via neural prosthetics to patients with tetraplegia. BMI simulation can be useful to evaluate functional environments of neuronal conditions, avoiding clinical issues such as tissue damage. We investigated two key decoding algorithms, the Kalman filter (KF) and the optimal linear estimator (OLE), for the reconstruction of three dimensional arm movements when neuronal preferred directions varied over time. The results may provide a guidance for selecting an appropriate decoder for various conditions. |
|
|
Investigation of initial dip in mental arithmetic task: an fNIRS study |
|
Amad Zafar, Keum-Shik Hong, Muhammad Jawad Khan(Pusan National University, Korea) |
| In this paper, we investigate the feasibility of identifying the fNIRS signal occurred from a single trial arithmetic task, in which the rest state hemodynamic response, the occurrence of an initial dip, and the regular hemodynamic response are involved. Four different features including the signal mean, skewness, signal slope, and kurtosis are compared with five different window sizes: 0~1, 0~1.5, 0~2, 0~2.5, and 0~3 sec for classification. The result shows that the initial dip can be classified from the baseline and hemodynamic by using signal mean and signal slope as a features. |
| |