:: ICCAS 2015 ::

FP02		Bio-Systems
Time : 16:30~18:00 Room : 201~204		Chair : (, )



	FP02-17

EEG Characteristics Related to Prediction of What Others Prefer
Jonghyeok Park, Taeyang Yang(UNIST, Korea, Republic of ), Hakjin Kim(Korea university, Korea, Republic of ), Sung-phil Kim(UNIST, Korea, Republic of )

This study aims to investigate EEG characteristics on a single-trial basis when people successfully or errantly predict the preference of others from the rapid evaluation of face images. The success and failure trials of the preference prediction task showed differences in phase resetting latency patterns of alpha oscillations between frontal and right posterior regions. These phase resetting patterns indicated the likelihood of success or failure trials. EEG phase resetting latencies between frontal and right parietal areas could indicate the likelihood of success or failure.



	FP02-18

Classification performance analysis of combined fNIRS-polygraph system using different temporal windows
Muhammad Raheel Bhutta, Keum-Shik Hong(Pusan National University, Korea, Republic of ), Melissa Jiyoun Hong(FIRST 5 Santa Clara County, United States), Yun-Hee Kim(Samsung Medical Center, Sungkyunkwan University School of Medicine, Korea, Republic of )

In this paper, we have analyzed the effect of different temporal windows in classification of combined fNIRS-polygraph signals for lie detection. To investigate the hemodynamic response related to deception, fNIRS is used at the PFC of the subject. Commercially available polygraph system, Paragon acquisition system (PAS) is used to measure the physiological parameters like respiration and electrodermal activity (EDA) during the deception process. The results show that the best time window for fNIRS-polygraph system is 2-7 s and 0-7 s for fNIRS and polygraph data respectively.



	FP02-19

EEG Signal Analysis for Measuring the Quality of Virtual Reality
Jinsung Chun, Netiwit Kaongoen(Korea Advanced Institute of Science and Technology, Korea, Republic of ), Sungho Jo(KAIST, Korea, Republic of )

Virtual Reality (VR) is becoming popular and has been used in many kind of different purposes including entertainment, daily life activities and medical field. However, with the current VR technology, people are still be able to discriminate the VR from the real world very easily. Perhaps, the better way to develop the VR technology is not by considering how much VR looks like the real world but how much similar humans perceive from VR comparing to the real world. In this paper, we suggests that the similarity of brain signal can be used as the measurement for VR quality.



	FP02-20

Experiments on classification of electroencephalography (EEG) signals in imagination of direction using a wireless portable EEG headset
Kenta Tomonaga, Sou Wakamizu, Jun Kobayashi(Kyushu Institute of Technology, Japan)

We present experimental results of classification methods for brain activity in the imagination of direction. A portable EEG headset was used to collect EEG from subjects in the experiments, during which the subjects imagined arrows indicating one of four directions. The classification methods that consisted of FFT, PCA, and NN, estimated the direction imagined by the subjects based on their EEG recorded by an electrode of the headset. The results showed that the NN trained with the EEG of all subjects achieved a 52% classification rate. When using the EEG of each subject, the best one was 55%



	FP02-21

Drowsiness Detection in Dorsolateral-Prefrontal Cortex using fNIRS for a Passive-BCI
Muhammad Jawad Khan, Keum-Shik Hong, Noman Naseer, Muhammad Raheel Bhutta(Pusan National University, Korea, Republic of )

In this paper, we have investigated the feasibility of detecting drowsiness using hemodynamic brain signals for a passive brain-computer interface (BCI). Functional near-infrared spectroscopy (fNIRS) is used to measure the right dorsolateral-prefrontal brain region in order to investigate the hemodynamic changes corresponding to drowsy and alert states. . The results show that drowsy and alert states are distinguishable from the right dorsolateral prefrontal brain region. Also, fNIRS modality can be used for drowsiness detection for a passive BCI.



	FP02-22

Comparison of Artificial Neural Network and Support Vector Machine Classifications for fNIRS-based BCI
Noman Naseer, Keum-Shik Hong, Muhammad Jawad Khan, Muhammad Raheel Bhutta(Pusan National University, Korea, Republic of )

In this paper we analyze and compare the performance of support vector machine (SVM) and artificial neural network (ANN) for classification of fNIRS signals. fNIRS signals due to mental arithmetic and mental counting are acquired from the prefrontal cortex of ten healthy subjects. After preprocessing and filtering, SVM and ANN classification is performed on the same feature set – mean and slope of the changes in concentration of oxy-hemoglobin. It is concluded that SVM offers stable classification accuracies and fast computation as compared to ANN.

1 | [2] | [3] | [4] | [5]