請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71103完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 鄭士康(Shyh-Kang Jeng) | |
| dc.contributor.author | Yu-Yu Liu | en |
| dc.contributor.author | 劉昱佑 | zh_TW |
| dc.date.accessioned | 2021-06-17T04:53:07Z | - |
| dc.date.available | 2021-08-07 | |
| dc.date.copyright | 2018-08-07 | |
| dc.date.issued | 2018 | |
| dc.date.submitted | 2018-07-30 | |
| dc.identifier.citation | [1] P. R. M.Marshal F. Folstein, Susan E. Folstein, “Mini-mental state A practical method for grading the cognitive state of patients for the clinician,” Journal of Psychiatric Research, 1974. [Online]. Available: http://www.journalofpsychiatricresearch.com/article/0022-3956(75)90026-6/abstract. [Accessed: 10-Apr-2018].
[2] S. O. O.Borson, J.Scanlan, M.Brush, P.Vitaliano, andA.Dokmak, “the Mini ! Cog ] a Cognitive { Vital Signs | Measure for Dementia Screening in Multi ! Lingual Elderly,” no. January, pp. 910–916, 1999. [3] K. N.Lin, P. N.Wang, H. C.Liu, andE. L.Teng, “Cognitive abilities screening instrument, chinese version 2.0 (CASI C-2.0): Administration and clinical application,” Acta Neurol. Taiwan., vol. 21, no. 4, pp. 180–189, 2012. [4] T.Mikolov, K.Chen, G.Corrado, andJ.Dean, “Efficient Estimation of Word Representations in Vector Space,” pp. 1–12, 2013. [5] C.Guinn, B.Singer, andA.Habash, “A comparison of syntax, semantics, and pragmatics in spoken language among residents with Alzheimer’s disease in managed-care facilities,” IEEE SSCI 2014 - 2014 IEEE Symp. Ser. Comput. Intell. - CICARE 2014 2014 IEEE Symp. Comput. Intell. Healthc. e-Health, Proc., no. December 2014, pp. 98–103, 2015. [6] C.Boyd, R.Luitwieler, H.Eichelberger, Y.Eldogan, andK.Schmid, “Annals of the University of North Carolina Wilmington Master of Science in Computer Science and Information Systems,” no. June, 2011. [7] L. A.Breslow andD. W.Aha, “Simplifying decision trees: A survey,” Knowl. Eng. Rev., vol. 12, no. 1, pp. 1–40, 1997. [8] H.Zhang, “The Optimality of Naive Bayes,” Proc. Seventeenth Int. Florida Artif. Intell. Res. Soc. Conf. FLAIRS 2004, vol. 1, no. 2, pp. 1–6, 2004. [9] V.Masrani, T.Field, G.Murray, andG.Carenini, “Detecting Dementia through Retrospective Analysis of Routine Blog Posts by Bloggers with Dementia,” 2017. [10] D.Klein andC. D.Manning, “Accurate unlexicalized parsing,” Proc. 41st Annu. Meet. Assoc. Comput. Linguist. - ACL ’03, vol. 1, pp. 423–430, 2003. [11] H.Tanaka et al., “Detecting Dementia Through Interactive Computer Avatars,” IEEE J. Transl. Eng. Heal. Med., vol. 5, no. April, 2017. [12] H.Nagawaka, “Development of Dementia Evaluation System Using Daily Conversations ~ A Study on Dementia Evaluation Method Using Simple Conversation with Robot ~,” 28th Fuzzy Syst. Symp., 2012. [13] W.Jarrold et al., “Aided diagnosis of dementia type through computer-based analysis of spontaneous speech,” Proc. Work. Comput. Linguist. Clin. Psychol. From Linguist. Signal to Clin. Real., pp. 27–37, 2014. [14] S.Karlekar, T.Niu, andM.Bansal, “Detecting Linguistic Characteristics of Alzheimer’s Dementia by Interpreting Neural Models,” 2018. [15] E. L.Teng andH. C.Chui, “The Modified Mini-Mental State (3MS) examination,” J Clin Psychiatry, vol. 48, 1987. [16] J. C.Morris, “The Clinical Dementia Rating (CDR),” Neurology, vol. 43, no. 11, p. 2412 LP-2412-a, Nov.1993. [17] “中文斷詞 | CKIP Lab 中文詞知識庫小組.” [Online]. Available: http://ckip.iis.sinica.edu.tw:8080/wordsegment/. [Accessed: 30-Apr-2018]. [18] H.Tseng et al., “A Conditional Random Field Word Segmenter,” Proc. 4th {SIGHAN} Work. {C}hinese Lang. Process., no. X, 2005. [19] Q.V.Le andT.Mikolov, “Distributed Representations of Sentences and Documents,” vol. 32, 2014. [20] C. H. A.Chris Eliasmith, Neural Engineering computation, representation, and dynamics in neurobiological systems. . [21] P.Kanerva, “Hyperdimensional computing: An introduction to computing in distributed representation with high-dimensional random vectors,” Cognit. Comput., vol. 1, no. 2, pp. 139–159, 2009. [22] S. O.Orimaye, J. S.-M.Wong, andK. J.Golden, “Learning Predictive Linguistic Features for Alzheimer’s Disease and related Dementias using Verbal Utterances,” Work. Comput. Linguist. Clin. Psychol. From Linguist. Signal to Clin. Real., pp. 78–87, 2014. [23] M. S. C. P.Aper, “Longitudinal Detection of Dementia Through Lexical and Syntactic Changes in Writing Longitudinal Detection of Dementia Through Lexical and Syntactic Changes in Writing,” no. January, 2010. [24] G. K.Bucks, R.S., Singh, S., Cuerden, J.M. and Wilcock, Analysis of spontaneous, conversational speech in dementia of Alzheimer type: evaluation of an objective technique for analysing lexical performance. Taylor & Francis, 2000. [25] W. L.Taylor, “‘Cloze Procedure’: A New Tool for Measuring Readability,” Journal. Bull., vol. 30, no. 4, pp. 415–433, 1953. [26] B.Macwhinney, D.Fromm, M.Forbes, andA.Holland, “AphasiaBank : Methods for studying discourse AphasiaBank : Methods for studying discourse,” Aphasiology, vol. 25, no. 11, pp. 1286–1307, 2011. [27] C.Szegedy et al., “Going deeper with convolutions,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 07–12–June, pp. 1–9, 2015. [28] K.Cho et al., “Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation,” 2014. [29] C.Zhou, C.Sun, Z.Liu, andF. C. M.Lau, “A C-LSTM Neural Network for Text Classification,” 2015. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/71103 | - |
| dc.description.abstract | 這項研究是關於AD（阿茲海默症）的檢測，受到先前日本相關研究的啟發，在他們的研究中使用到了聊天機器人來陪伴老年人，並藉由穿插MMSE問題到日常對話中以利於評分老人目前的認知能力情況，此系統改善了老年人護理中短期追蹤的不利情況，雖然我們的研究並沒有用到聊天機器人，但是建構了一個完整的分類器與文字分析系統。
透過使用受測者的圖片獨白文字資料來完成AD的分類器，這裡有三個主要的貢獻如下，第一個是我們自己創建了的中文語料集(正常病患由我們自己收集，AD病患則是線上開源取得)。第二，我們提出一個新的特徵提取流程，它包括兩個主要部分，先驗特徵和抽象特徵，先驗特徵包括語法和語義特徵，這兩個都是藉由語言學上的知識求出。抽象特徵則是通過使用深度神經網絡技術，利用CNN和SPA建立一個端到端的模型來訓練求得。第三，對AD的特徵進行視覺化分析，並藉由多變量分析獲得每個先驗特徵之間的相關性。最後在比較結果的同時，也有與2017年的日本研究做相比，確實有較好的表現。 | zh_TW |
| dc.description.abstract | This research is about the AD (Alzheimer’s disease) detection. It is inspired by a former research in Japan, that they use a chatbot to keep elderlies company. The daily conversation is added with the MMSE questions to get the score of the elderly. This system improves the situation of short-term chasing in the elderly cares. Although we do not create a chatbot, a complete system of text analysis for the AD picture monologue data is built.
A classifier of AD is implemented by using the subject’s picture monologue language data. Here come three main contributions as follows. The first one is the Chinese language data set are created by ourselves. The second one is we propose a new process of feature extraction, which consists of two main part, i.e., prior features and abstract features. Prior features consist of syntactic and semantic features by linguistic knowledge. Abstract features are acquired by using the deep neural network techniques, CNN and semantic pointer architecture, and training on an end-to-end model. The third one is making a visualization analysis on the features of AD and control normal to get the underlying knowledge. The multivariate analysis is also done and gets the correlation coefficients of each feature-pairs. The results have been compared with the former works and get a better performance. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-17T04:53:07Z (GMT). No. of bitstreams: 1 ntu-107-R04921070-1.pdf: 1553172 bytes, checksum: f50f8ceea2b1194b68c1aa9fcbad1abf (MD5) Previous issue date: 2018 | en |
| dc.description.tableofcontents | 誌謝 II
中文摘要 III ABSTRACT IV TABLE OF CONTENTS V LIST OF FIGURES VII LIST OF TABLES VIII CHAPTER 1 INTRODUCTION 1 1.1 MOTIVATION 2 1.2 LITERATURE REVIEW 3 1.3 CONTRIBUTIONS 5 1.4 CHAPTER OUTLINE 6 CHAPTER 2 BACKGROUND 7 2.1 TRADITIONAL DEMENTIA EVALUATION 7 2.1.1 Mini-Mental State Estimation (MMSE) 7 2.1.2 Cognitive Abilities Screening Instrument 8 2.1.3 Mini-Cog 8 2.1.4 Clinical Dementia Rating 9 2.2 NATURAL LANGUAGE PROCESSING 9 2.2.1 Text Analysis 9 2.2.2 Distributed Representations on Text 11 2.3 SEMANTIC POINTER/HYPER-DIMENSIONAL COMPUTING 12 2.4 MACHINE LEARNING ON CLASSIFICATION 12 CHAPTER 3 SYSTEM DESIGN 14 3.1 PREPROCESS ON TEXT 14 3.2 PRIOR FEATURE EXTRACTION 16 3.2.1 Syntactic Feature 16 3.2.2 Semantic Feature 19 3.3 ABSTRACT FEATURE EXTRACTION 20 3.4 CLASSIFIER 23 CHAPTER 4 IMPLEMENTATION AND EXPERIMENTS 24 4.1 DATA COLLECTION 24 4.2 SENTENCE EMBEDDING 25 4.2.1 CNN-LSTM 26 4.2.2 SPA-LSTM 30 4.3 PARAGRAPH EMBEDDING 32 4.4 FULLY CONNECTED LAYERS FOR BINARY CLASSIFICATION 33 CHAPTER 5 RESULTS AND DISCUSSION 34 5.1 MULTIVARIATE ANALYSIS ON PRIOR TEXT FEATURES 35 5.2 K-MEANS CLUSTERING 40 5.3 CLASSIFICATION WITH SENTENCE EMBEDDING 43 5.4 CLASSIFICATION WITH PARAGRAPH EMBEDDING 46 CHAPTER 6 CONCLUSION 47 REFERENCES 48 APPENDIX 51 | |
| dc.language.iso | en | |
| dc.subject | 阿茲海默病 | zh_TW |
| dc.subject | 老年人護理 | zh_TW |
| dc.subject | 深度學習神經網絡 | zh_TW |
| dc.subject | 多變量分析 | zh_TW |
| dc.subject | 特徵工程 | zh_TW |
| dc.subject | 自然語言處理 | zh_TW |
| dc.subject | natural language processing | en |
| dc.subject | Alzheimer’s disease | en |
| dc.subject | elderly care | en |
| dc.subject | multivariate analysis | en |
| dc.subject | feature engineering | en |
| dc.subject | deep learning neural network | en |
| dc.title | 基於獨白文字紀錄之失智症評估分類器 | zh_TW |
| dc.title | A Classifier for Alzheimer’s Disease Evaluation Based on
Monologue Transcription Data | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 106-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 張智星(Jyh-Shing Jang),高照明(Zhao-Ming Gao) | |
| dc.subject.keyword | 阿茲海默病,老年人護理,深度學習神經網絡,多變量分析,特徵工程,自然語言處理, | zh_TW |
| dc.subject.keyword | Alzheimer’s disease,elderly care,deep learning neural network,multivariate analysis,feature engineering,natural language processing, | en |
| dc.relation.page | 52 | |
| dc.identifier.doi | 10.6342/NTU201802191 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2018-07-30 | |
| dc.contributor.author-college | 電機資訊學院 | zh_TW |
| dc.contributor.author-dept | 電機工程學研究所 | zh_TW |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-107-1.pdf 未授權公開取用 | 1.52 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。