腦波儀整合穿戴式裝置於睡眠評估之研究;The research on Integrating EEG Devices with Wearable Technology for Sleep Assessment

NCUIR > college of Health Sciences and Technology > Institute of Biomedical Engineering > Electronic Thesis & Dissertation > Item 987654321/99246

Please use this identifier to cite or link to this item: https://ir.lib.ncu.edu.tw/handle/987654321/99246

Title:	腦波儀整合穿戴式裝置於睡眠評估之研究;The research on Integrating EEG Devices with Wearable Technology for Sleep Assessment
Authors:	許益彰;Hsu, I-Chang
Contributors:	生醫科學與工程學系
Keywords:	乾式腦波儀;智慧型穿戴裝置;睡眠監測;腦波分析;心律變異性;機器學習;Dry-electrode EEG;Smartwatch;Sleep Monitoring;EEG Analysis;Heart Rate Variability;Machine Learning
Date:	2026-01-27
Issue Date:	2026-03-06 18:25:53 (UTC+8)
Publisher:	國立中央大學
Abstract:	睡眠品質對於個人健康與生活品質至關重要。然而，現有的臨床睡眠監測方法（如多導睡眠圖，Polysomnography, PSG）往往受限於高成本、環境侷限性及使用不便性，難以應用於日常長期監測。本研究旨在評估整合可穿戴式乾式腦波儀（BrainLink Lite）與智慧型穿戴裝置（Apple Watch）於睡眠與腦功能監測的可行性。研究透過非侵入性方式，同步記錄多頻段腦波波形（Delta、Theta、Low Alpha、High Alpha、Low Beta、High Beta、Low Gamma、High Gamma）與生理數據（心率 HR、心率變異性 HRV、活動能量、睡眠階段），分析兩者間的關聯性。研究對象為一名健康成年受試者，於每日定時進行腦波記錄與生理數據同步蒐集。採用Pearson相關性分析、Spearman秩相關分析及隨機森林回歸等統計方法，探討前一晚睡眠生理數據與早晨腦波活動的關聯性。本研究期望證實了整合可穿戴式腦波儀與智慧型裝置進行睡眠與腦功能監測交互搭配的可行性，為發展基於消費級設備的個人化睡眠健康評估系統提供了實證基礎與分析方法框架。 ;Sleep quality is crucial for personal health and quality of life. However, existing clinical sleep monitoring methods, such as Polysomnography (PSG), are often limited by high costs, environmental constraints, and practical inconvenience, making them unsuitable for routine long-term monitoring. This study aims to evaluate the feasibility of integrating a wearable dry-electrode EEG device (BrainLink Lite) with a smartwatch (Apple Watch) for sleep and brain function monitoring. Through non-invasive methods, the study simultaneously records multi-band EEG waveforms (Delta, Theta, Low Alpha, High Alpha, Low Beta, High Beta, Low Gamma, High Gamma) and physiological data (heart rate HR, heart rate variability HRV, active energy, sleep stages) to analyze the correlations between them. The study involves one healthy adult participant who undergoes daily EEG recordings and synchronized physiological data collection. Statistical methods including Pearson correlation analysis, Spearman rank correlation, and Random Forest regression are employed to explore the associations between previous night′s sleep physiological data and morning EEG activity. This study aims to confirm the feasibility of integrating wearable EEG devices with smartwatches for combined sleep and brain function monitoring, providing empirical evidence and an analytical framework for developing personalized sleep health assessment systems based on consumer-grade devices.
Appears in Collections:	[Institute of Biomedical Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	126	View/Open

社群 sharing

Loading...