|
Comparisons of Auditory, Audiovisual, and Visual Modalities in Feature Domain for Auditory Brain-Computer Interfaces |
|
Yun-Joo Choi, Minju Kim, Jongsu Kim, Dojin Heo, Sung-Phil Kim(UNIST, Korea) |
| The development of non-visual P300-based brain-computer interfaces (BCIs) is needed for patients with unreliable gaze control or healthy users with visual distractors. As an alternative means, auditory BCIs have been developed, but reportedly showed relatively low performance. To elucidate the performance gap, this study investigated the feature domain between the auditory and visual BCIs, along with the audiovisual BCI as the combination of the two. |
|
|
Wearable fNIRS Device based on Frequency Division Multiplexing |
|
Changhyun Park, SungWoo Woo, Keum-Shik Hong, Chang-seok Kim(Pusan National University, Korea) |
| Conventional fNIRS is inconvenient to wear on the scalp as most of the skin contact surface is made of a hard substrate. In addition, the disadvantage of using a continuous wave (CW) light source is the speed limit due to the sequential alternating illumination of multiple wavelengths. In this study, to solve these two problems, we propose a new fNIRS patch design based on a flexible substrate medium to improve the fit of the subject and to propose a frequency multiplexing method that can solve the problem of time delay due to an increase in the number
of channels. |
|
|
Simultaneous Photoacoustic and Ultrasound Imaging System for Preclinical Small Animal Studies |
|
Haeni Lee(Pusan National University, Korea), Byullee Park, Chulhong Kim(Pohang University of Science and Technology, Korea), Jeesu Kim(Pusan National University, Korea) |
| We have successfully implemented a dual-modal photoacoustic and ultrasound imaging system for whole-body imaging of small animals in vivo. The developed system can visualize both structural and functional information by combining ultrasound and photoacoustic images. Compared to the previous photoacoustic imaging system, the developed system can provide a depth-resolved position based on the corresponding ultrasound signals. The results show the great potential of the system to be a biomedical research tool for preclinical small animal studies. |
|
|
Assessment of Functional Near-Infrared Spectroscopy by Comparing Prefrontal Cortex Activity: A Cognitive Impairment Screening Tool |
|
Jisoo Baik(Pusan National University, Korea), MYOUNG-HWAN KO(Jeonbuk National University Hospital, Korea), JIHONG MIN, NAYEON JEONG, TAEYOUNG LEE, SUNGHWA KO, YONG-IL SHIN(Pusan National University Yangsan Hospital, Korea) |
| We aimed to evaluate whether functional near-infrared spectroscopy(fNIRS) to measure the prefrontal cortex(PFC) is suitable as a screening tool for cognitive impairments. Sixty subjects, divided into the normal, mild cognitive impairment(MCI), and dementia groups, were wore a fNIRS during four tasks to assess whether there is a significant difference in the PFC activity between the groups. A significant difference in PFC activity between the groups was observed during the verbal fluency test(VFT). Also, the PFC activity during VFT significantly correlated with the existing cognitive test score. These results demonstrated that PFC fNIRS can be used as a cognitive impairment screening tool. |
|
|
Application of Deep Learning Techniques to Diagnose Mild Cognitive Impairment: Functional Near-Infrared Spectroscopy Study |
|
Min-Kyoung Kang, Keum-Shik Hong(Pusan National University, Korea) |
| I propose a novel deep learning algorithm (i.e., multi-scale convolutional neural network (CNN) accompanied by long short-term memory (LSTM) layers) for diagnosing patients with functional near-infrared spectroscopy (fNIRS). |
| |