進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-1308201320390400
論文名稱(中文) 基於LDA演算法及可攜式單一頻道腦波儀之IADL評測系統
論文名稱(英文) Instrumental Activities of Daily Living (IADL) Evaluation from EEG Signal Based on LDA Algorithm and Portable Single Channel EEG Device
校院名稱 成功大學
系所名稱(中) 電機工程學系碩博士班
系所名稱(英) Department of Electrical Engineering
學年度 101
學期 2
出版年 102
研究生(中文) 詹勝中
研究生(英文) Sheng-Chung Chan
學號 n26991491
學位類別 碩士
語文別 英文
論文頁數 50頁
口試委員 指導教授-王駿發
口試委員-林博川
口試委員-陳璽煌
口試委員-龔俊嘉
中文關鍵字 工具性日常生活活動評測系統  線性判別分析  單一頻道腦波儀 
英文關鍵字 Instrumental Activities of Daily Living evaluation system  Linear Discriminant Analysis  Single Channel EEG Device 
學科別分類
中文摘要 摘要
本論文提出一自動化IADL (Instrumental Activities of Daily Living) 評測系統,將IADL總和分數分為三類:高(正常人,IADL分數16~24分)、中(輕度失能,IADL分數8~15分)、低(高度失能,IADL分數0~7分),使用單一頻道非塗膠式腦波儀針對30位70~96歲IADL分數均勻分布的年長者進行 (1) 打電話 (2) 財務管理情境的腦波資料收集。並額外收集聊天情境的腦波資料,同時使用五組可有效分類IADL分數所屬群組的特徵 (1) Average Amplitude (2) Power Ratio (3) Spectral Central (4) Spectral Edge Frequency 25% (5) Spectral Edge Frequency 50%,並搭配線性判別分析演算法進行IADL評量,為了找出最佳的IADL評量分類器,除了使用線性判別分析分類器之外也使用了支援向量機及第k位最接近的鄰居進行IADL評量準確度比較,並使用LOOCV (Leave-One-Out Cross-Validation) 進行驗證,最後在使用相同的特徵下,使用線性判別分析當作分類器時的辨識率可達到90%,比另外兩種分類器可達到的辨識率更高,且同時發現若使用聊天情境的腦波資料也可以正確分類出受測者的IADL總和分數所屬群組。
未來此系統可協助專業的醫師在進行患者的IADL訪談評量之前,可經由本系統得到的評量結果進行科學化的客觀評估,再加上醫師的專業判斷,獲得更為準確客觀的IADL評量分數。
英文摘要 Abstract
An automatic evaluation system of IADL (Instrumental Activities of Daily Living) is proposed, the system separates the total IADL scores into three categories: high (disability-free, IADL scores from 16 to 24 points), medium (mild disability, IADL scores from 8 to 15 points) and low (severe disability, IADL scores from 0 to 7 points). Single channel EEG device is applied to thirty seniors (from age 70 to 96) of the IADL scores uniform distribution to do the following IADL scenarios: (1) telephone using, (2) financial management. The brainwave data of chatting scenario is collected additionally and 5 features to classify the group of IADL scores are used as follows: (1) Average Amplitude (2) Power Ratio (3) Spectral Centroid (4) Spectral Edge Frequency 25% (5) Spectral Edge Frequency 50%. Besides, LDA (Linear Discriminant Analysis) algorithm is combined with 5 features mentioned above to evaluate IADL score. To find out the best classifier of IADL assessment, not only LDA classifier but SVM (Support Vector Machine) and KNN (K-th Nearest Neighbor) are used to compare the accuracy of IADL evaluation, and LOOCV (Leave-One-Out Cross-Validation) is used to verify the proposed system. Finally, the accuracy is about 90% and also higher than the other two classifiers when using LDA under the same feature. The groups of IADL scores of patients are classified exactly when using the brainwave data of chatting scenario.
The proposed system can help doctors to evaluate the results objectively before proceed the IADL interview to patients and combine with the judgment of doctors, the objective and accurate IADL scores are obtained.
論文目次 Contents
Chapter 1 Introduction.....................................4
1.1 Background and Motivation..............................4
1.2 Thesis Objectives......................................4
1.3 Thesis Organization....................................5
Chapter 2 Related Works....................................6
2.1 Human Brain............................................6
2.2 Brain Wave.............................................7
2.3 ADL and IADL...........................................9
2.4 EEG and Cognitive Ability.............................11
Chapter 3 IADL Evaluation from EEG Signal Based on LDA Algorithm.................................................13
3.1 System Overview.......................................13
3.2 Feature Extraction and Feature........................15
3.2.1 Power Ratio.........................................16
3.2.2 Spectral Edge Frequency.............................16
3.2.3 Spectral Centroid...................................17
3.3 Classifiers...........................................18
3.3.1 Introduction to Support Vector Machine..............18
3.3.2 Introduction to Linear Discriminant Analysis........24
3.3.3 Introduction to K-th Nearest Neighbor...............26
3.4 Leave-One-Out Cross-Validation........................27
3.5 Instrumental Activities of Daily Living (IADL) Evaluation System.........................................29
Chapter 4 Experiments and Comparison......................31
4.1 Introduction of the Database..........................31
4.2 Experimental Setup....................................31
4.2.1 Scenario Illustration...............................31
4.2.2 Experimental Flowchart..............................33
4.3 Experiment Result.....................................34
4.4 Classifiers Comparison................................36
Chapter 5 Conclusion and Future Works.....................39
5.1 Conclusions...........................................39
5.2 Future Works..........................................39
References................................................40
Appendix..................................................43
Appendix A The IADL Scale of Three Groups.................43
Appendix B The Experimental Information of Three Groups...45
參考文獻 References
[1]Yung-teng Lo,"The Feasibility Study of the Eldercare Center Establishment in Taiwan Hot Spring Area - A Case Study of Guanze Hill Hot Spring." Master thesis, CNUPSSA 2012
[2]FatiNourhashémi and Sandrine Andrieu, "Instrumental Activities of Daily Living as a PotentialMarker of Frailty: A Study of 7364 Community-Dwelling Elderly Women (the EPIDOS Study)." MEDICAL SCIENCES 2001, Vol. 56A, No. 7, M448-M453
[3]Yu-Fang Liu, "Analysis of Procedures for Clinical Experiments of Brain-Computer Interface Systems." Master thesis, NUTN 2005
[4]From Wikipedia, http://en.wikipedia.org/wiki/Brain
[5]Cerebral Cortex Function, http://www.buzzle.com/articles/corebral-cortex-function.html
[6]Delta wave, http://en.wikipedia.org/wiki/Delta_wave
[7]Theta rhythm, http://en.wikipedia.org/wiki/Theta_wave
[8]Alpha wave, http://en.wikipedia.org/wiki/Alpha_wave
[9]Beta wave, http://en.wikipedia.org/wiki/Beta_wave
[10]ADLs-and IADLs-whats-the-difference, http://asourparentsage.net/2009/12/17/adls-and-iadls-whats-the-difference/
[11]M. P. Lawton, and E. M. Brody, "Assessment of older people: self-maintaining and instrumental activities of daily living," Gerontologist. 1969;9(3):179-186.
[12]Berger, H. 1929. Übert das Elektrenkephalogramm des Menschen (On the human electroencephalogram). Archiv f. Psychiatrie u. Nervenkrankheiten 87:527-70
[13]M. Matousek, M. Brunovsky,AÊ . Edman, A. Wallin, EEG abnormalities in dementia reflect the parietal lobe syndrome Clinical Neurophysiology 112 (2001) 1000~1005
[14]D. V. Moretti, A. Prestia, C. Fracassi, G. B. Zanetti, and G. B. Frisoni, "Specific EEG Changes Associated with Atrophy of Hippocampus in Subjects with Mild Cognitive Impairment and Alzheimer's Disease," International Journal of Alzheimer's Disease, vol. 2012, 2012.
[15]F. Vecchio and C. Babiloni, "Direction of Information Flow in Alzheimer's Disease and MCI Patients," International Journal of Alzheimer's Disease, vol. 2011, pp. 1-7, 2011.
[16]S. I. Novikova, E. V. Malakhovskaya, N. P. Pushina, M. M. Tsetlin, A. I. Filatov, I. N. Posikera, T. A. Stroganova. Relationships between EEG θ and α spectral amplitudes and cognitive ability in preschool children. Human Physiology July 2009, Volume 35, Issue 4, pp 409-415.
[17]Martin Brunovsky, Milos Matousek, AkeEdman, Katerina Cervena,VladimirKrajca Objective Assessment of the Degree ofDementia by Means of EEGNeuropsychobiology 2003;48:19–26
[18]Yaozhang Pan, S.S. Ge, Al Mamun. A, Feng Ru Tang. “Detection of seizures in EEG signal using weighted locally linear embedding and SVM classifier” Cybernetics and Intelligent Systems, IEEE Conference on 21-24 Sept. 2008.
[19]L. Shoker , S. Sanei and A. Sumich. “Distinguishing between left and right finger movement from EEG using SVM.” IEEE Engineering in Medicine and Biology Society conference (EMBC 2005), 5420-5423, 2005.
[20]S.Bhattacharyya,A.Khasnobish,S.Chatterjee,A.Konar,D.N.Tibarewala,Performance analysis of LDA, QDAandKNN algorithms in left–rightlimb movement classification from EEG data, in: Proceedings of 2010 International Conference on Systems in Medicine and Biology, Kharagpur, India, 2010.
[21]Gallego-Jutgla, E. ; Elgendi, M. ; Vialatte, F. ; Sole-Casals, J. ; Cichocki, A. ; Latchoumane, C. ; JaesungJeong ; Dauwels, J. “Diagnosis of Alzheimer's disease from EEG by means of synchrony measures in optimized frequency bands” IEEE Engineering in Medicine and Biology Society conference (EMBC 2012), 4266 - 4270, 2012.
[22]Electroncephalography,http://en.wikipedia.org/wiki/Electroencephalography
[23]C.-C. Chen, H.-W. Chiu, and C.-Y. Hsu, "Correlation of EEG power ratio and severity of Alzheimer's disease," presented at the Towards Global Interperability for Electronic Health Records, Taipei, Taiwan, 2006.
[24]T. Staudinger and R. Polikar, "Analysis of complexity based EEG features for the diagnosis of Alzheimer's disease," in Engineering in Medicine and Biology Society,EMBC, 2011 Annual International Conference of the IEEE, 2011, pp. 2033-2036.
[25]Hung-Tzu Kao, "Voice Driven Multimedia Interactive System with Ubiquitous Sound Recognition for Digital Home Application," Master thesis, NCKU 2008
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2023-12-01起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw