評估注意力偵測之穿戴式腦電電極放置有效性;Evaluating the effectiveness of wearable EEG electrode placement for attention detection

NCUIR > College of Electrical Engineering & Computer Science > Graduate Institute of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/89982

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/89982

Title:	評估注意力偵測之穿戴式腦電電極放置有效性;Evaluating the effectiveness of wearable EEG electrode placement for attention detection
Authors:	王俊隆;Wang, Jun-Long
Contributors:	資訊工程學系
Keywords:	腦電圖;數據融合;多模態數據;虛擬現實;機器學習;眼睛追蹤;Electroencephalography;Data Fusion;Multimodal Data;Virtual reality;Machine Learning;Eye-tracking
Date:	2022-08-22
Issue Date:	2022-10-04 12:06:34 (UTC+8)
Publisher:	國立中央大學
Abstract:	多動症的問題在世界越來越嚴重。注意力檢測問題與對多動症患者的評估密切相關，它決定了受試者的集中程度。人腦的額葉和前額葉決定受試者的注意力。其中，反應抑制是注意力的關鍵。它可以控制衝動的反應。在本實驗中，我們進行了與反應抑制有關的任務，並收集了正常成年人的數據，使用可穿戴式腦電設備OpenBCI Ganglion，集成並結合VR 一體機進行實驗，並結合之前研究的腦電（Looxid）電極。根據國際10-20 系統的腦電定位電極，對額頭的AF4、FP7、FP8、AF7、AF8 進行了比較，通過機器學習驗證了目前應用於特定三點的可穿戴腦電設備FCz、FC3、Pz 在注意力檢測方面的有效性。此外，我們還通過特徵探索了EEG 和眼球追踪之間的相關性。最後，我們成功地確定了我們的EEG 電極位置的更好的有效性。;The problem of ADHD is getting more and more serious in the world. The attention detection problem is closely related to the assessment of ADHD patients that determines how concentrated the subject is. The frontal and prefrontal of the human brain decide the subjects’ attention. Among them, response inhibition is the key to attention. It can control impulsive responses. In this experiment, we conduct a task related to response inhibition and we collected the data from normal adults, and use the wearable EEG device OpenBCI Ganglion, integrated and combined with the VR all-in-one machine to conduct the experiment, and combined with the EEG (Looxid) electrode of the previous study. According to the international 10-20 system for EEG location electrodes, AF4, FP7, FP8, AF7, and AF8 in the forehead are compared, and we validate the effectiveness of the current wearable EEG devices that applied to specific three points are FCz, FC3, and Pz in attention detection through Machine Learning. Moreover, the correlation between EEG and eye-tracking is explored through features. Finally, we successfully determine the better effectiveness of our EEG electrode placement.
Appears in Collections:	[Graduate Institute of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	26	View/Open

社群 sharing

Loading...