請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/19852
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 周俊廷(Chun-Ting Chou) | |
dc.contributor.author | Chih-Wei Ho | en |
dc.contributor.author | 何致緯 | zh_TW |
dc.date.accessioned | 2021-06-08T02:23:07Z | - |
dc.date.copyright | 2015-08-25 | |
dc.date.issued | 2015 | |
dc.date.submitted | 2015-08-19 | |
dc.identifier.citation | [1] Yuan Yuan Li; Lynne E. Parker. Detecting and monitoring time-related abnormal events using a wireless sensor network and mobile robot,' Proc. of IEEE International Conference on Intelligent Robots and Systems, Nice, France, 2008.
[2] Jian Xu; Maynard-Zhang, P. ; Jianhua Chen. ' Predictive Data Mining to Learn Health Vitals of a Resident in a Smart Home,' Data Mining Workshops, 2007. ICDM Workshops 2007. Seventh IEEE International Conference on 28-31 Oct. 2007. doi: 10.1109/ICDMW.2007.57 [3] JJie Yin; Qiang Yang; Je_rey Junfeng Pan. Sensor-based Abnormal Human- Activity Detection,' IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING. [4] Arcelus, A; Goubran, R. ; Sveistrup, H. ; Bilodeau, M. ; Knoefel, F. Context-aware smart home monitoring through pressure measurement sequences,' Medical Measurements and Applications Proceedings (MeMeA), 2010 IEEE International Workshop on, vol., no., pp.32,37, April 30 2010-May 1 2010. doi: 10.1109/MEMEA.2010.5480223 [5] Nazerfard, Ehsan; Rashidi, P. ; Cook, D.J. Discovering Temporal Features and Relations of Activity Patterns,' Medical MData Mining Workshops (ICDMW), 2010 IEEE International Conference on, vol., no., pp.1069,1075, 13-13 Dec. 2010. doi: 10.1109/ICDMW.2010.164 [6] Y. Miao, A. Rhuma, S. M. Naqvi, W. Liang, and J. Chambers, 'A posture recognition-based fall detection system for monitoring an elderly person in a 48 REFERENCES 49 smart home environment,' Information Technology in Biomedicine, IEEE Transactions on, vol. 16, no. 6, pp. 12741286, 2012. [7] B. Woon-Sung, K. Dong-Min, F. Bashir, and P. Jae-Young, Real life applica- ble fall detection system based on wireless body area network,' in Consumer Communications and Networking Conference (CCNC), 2013 IEEE, pp. 6267. [8] Jakkula, V.; Cook, D.J. ; Crandall, A.S. Knowledge Discovery in Entity Based Smart Environment Resident Data Using Temporal Relation Based Data Mining,' Data Mining Workshops, 2007. ICDM Workshops 2007. Seventh IEEE International Conference on, vol., no., pp.625,630, 24-28-31 Oct. 2007. [9] Chun-Yu Chen; Yu-Jen Ku ; Chih-Wei Ho ; Yan-Ze Lin ; Chung-Ting Chou. 'A Green Context-Aware Platform for Smart Living,' Service-Oriented Computing and Applications (SOCA), 2013 IEEE 6th International Conference on, vol., no., pp.275 - 281, 16-18 Dec. 2013. doi:10.1109/SOCA.2013.22 [10] Taketoshi MORI; Ryo URUSHIBATA; Masamichi SHIMOSAKA; Hiroshi NOGUCHI; Tomomasa SATO. Anomaly Detection Algorithm Based on Life Pattern Extraction from Accumulated Pyroelectric Sensor Data,' doi:10.1109/SOCA.2013.22 [11] Marek Novak; Frantisek Jakab; Luis Lain. 'Anomaly Detection in User Daily Patterns in Smart-Home Environment,'Cyber Journals: Multidisciplinary Jour- nals in Science and Technology, Journal of Selected Areas in Health Informatics(JSHI), June Edition, 2013 Volume 3, Issue 6 [12] VARUN CHANDOLA; ARINDAM BANERJEE; VIPIN KUMAR. 'Anomaly Detection : A Survey,' ACM computing Surveys, vol., no., pp.1,72, 09, 2009. [13] Ian Davidson 'Anomaly Detection, Explanation and Visualization,' SGI.REFERENCES 50 [14] C. Fraley. 'Algorithms for Model-Based Gaussian Hierarchical Clustering,' [15] Je_rey D.Ban_eld; Adrian E. Raftery, 'Model-Based Gaussian and Non Gaussian Clustering,' Biometrics, Vol. 49,No.3(Sep.,1993), 803-821 [16] Gilles Celeux; G. Govaert, 'Gaussian parsimonious clustering models,' RR-2028, 1993 [17] Chris Fraley; Adrian E Raftery, 'Model-Based Clustering, Discriminant Analysis, and Censity Estimation,' Journal of the American Statistical Association, June 2002, Vol. 97, No. 485, Review Paper [18] Vikramaditya Jakkula; Diane J. Cook., 'Detecting Anomalous Sensor Events in Smart. Home Data for Enhancing the Living Experience,' Arti_cial Intelligence and Smarter Living The Conquest of Complexity: Papers from the 2011 AAAI Workshop (WS-11-07) [19] Mennatallah Amer; Markus Goldstein, 'Comparison of Unsupervised Anomaly Detection Techniques,' Bachelor Thesis [20] Markus M. Breunig; Hans-Peter Kriegel; Raymond T. Ng; Jrg Sander, 'LOF:Identifying Density-Based Local Outliers,'In Proceedings of the 2000 ACM SIGMOD International Conference on Management of Data, pages 93104, Dallas, Texas, USA, May 2000. ACM. [21] Kohonen; Teuvo, 'Self-Organized Formation of Topologically Correct Feature Maps,'Biological Cybernetics 43 (1): 5969. doi:10.1007/bf00337288. [22] Bernhard Scholkopf; Robert Williamson; Alex Smola; John Shawe-Taylor; John Platt, 'Support Vector Method for Novelty Detection,' REFERENCES 51 [23] Anastasios Bellas; Charles Bouveyron; Marie Cottrell; Jerome Lacaille, 'Anomaly Detection Based on Con_dence Intervals Using SOM with an Application to Health Monitoring,' [24] Woon-Sung Baek; Dong-Min Kim; Bashir, F.; Jae-young Pyun, 'Real life applicable fall detection system based on wireless body area network,' Consumer Communications and Networking Conference (CCNC), 2013 IEEE , vol., no., pp.62,67, 11-14 Jan. 2013 doi: 10.1109/CCNC.2013.6488426 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/19852 | - |
dc.description.abstract | 隨著越來越多的物聯網裝置出現,在智慧家庭中的異常偵測成為一項重要的問題。透過分析這些裝置收集到的資料,異常偵測技術可以偵測到一些不正常的行為,例如:不尋常活動、失去意識、跌倒、健康問題、未授權的入侵等等
然而,現今在智慧家庭中的異常偵測,仍然有兩個問題尚未解決。首先,大部分被部屬在智慧家庭的感測器會有一些問題,例如:會侵犯到使用者的隱私權、不舒服的穿戴式裝置以及需要更換大量的電池。第二,大部分的異常偵測採用監督式或半監督式,需要使用者親自標記許多的資料,對於他們來說,這是一件非常有負擔的工作,尤其是對於老年人來說,那更是不合理的要求。 為了解決這兩個問題,一個使用電燈開關資訊的非監督式異常偵測演算法被我們提出,它是一個基於模型的異常偵測演算法,可以降低訓練資料中異常資料的影響。透過增加混合模型的限制以及遞迴地估測決策邊界,最後估計出的決策邊界更能辨識正常資料與異常資料存在的區域,因此錯誤警報率能夠被降低。而我們最終的目標是偵測異常開始時間的事件、異常持續時間的事件並且提供使用者相關異常原因的提示,使他們能夠做出最適當的反應。 為了驗證我們提出的演算法,十一個電燈開關被安裝在一個四人的單層公寓中,在公寓中資料的收集不間斷地持續了7個月。我們將演算法偵測到的異常事件與使用者標記過的事件做比對,結果顯示百分之八十的異常事件可以被偵測到,其中有百分之二十五的錯誤警報,而且在要求漏失偵測率小於百分之二十的情況下,比起現有的非監督式異常偵測演算法,我們提出的方法有較好的效能對於分析智慧家庭中電燈開關的資訊。 | zh_TW |
dc.description.abstract | Anomaly detection in smart homes has become one of the most important issues recently with the emergence of Internet of Things(IoT). By analyzing the enormous amount of data collected via IoT, anomaly detection techniques are able to detect anomalous behavior such as unusual activities, unconsciousness, falling down, health vitals, unauthorized intrusion, etc.
However, current anomaly detection in smart homes has two issues that are not well addressed. First, most of deployed sensors lead to problems such as privacy violation, uncomfortable wear experiences, and a huge amount of battery replacement. Second, most anomaly detection algorithms adopt supervised or semi-supervised approaches that require users to label data, which is a heavy load especially for the elderly. To solve these problems, an unsupervised anomaly detection algorithm using light switches is proposed. It is an adapted model-based anomaly detection algorithm that can reduce the effect of outliers in training data. By adding constrains to the evaluated mixture model and recursively estimating the decision boundaries, the found decision boundaries are more representative of the normal regions where normal data frequently appear. The false alarm rate can be reduced in a given miss detection rate. Our goal is to find events that occur at unusual time point or last for unusual length and indicate where they occurred and why they are anomalous. To evaluate the proposed algorithm, 11 light switches are installed in an apartment with 4 permanent residents. The data collection is conducted in real life with 24 hours non-stopped and last for over 7-months. The detected anomalous events are compared with the ground truth provided by the residents, and the result shows that 80% anomalous events are detected with 25% false alarm rate. Our method also performs better than the existing unsupervised anomaly detection algorithms while analyzing the events with the requirement of miss detection rate less than 20%. | en |
dc.description.provenance | Made available in DSpace on 2021-06-08T02:23:07Z (GMT). No. of bitstreams: 1 ntu-104-R02942106-1.pdf: 1842999 bytes, checksum: 8d4c9b969226a91cbade28821e1624ce (MD5) Previous issue date: 2015 | en |
dc.description.tableofcontents | ABSTRACT . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii
LIST OF TABLES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi LIST OF FIGURES . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vii CHAPTER 1 INTRODUCTION . . . . . . . . . . . . . . . . . . . . . 1 1.1 Services in Smart Homes . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Anomaly Detection . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2.1 Phase 0: Events collection . . . . . . . . . . . . . . . . . . . 2 1.2.2 Phase 1: Training . . . . . . . . . . . . . . . . . . . . . . . . 3 1.2.3 Phase 2: Testing . . . . . . . . . . . . . . . . . . . . . . . . . 4 1.3 Problems of Anomaly Detection . . . . . . . . . . . . . . . . . . . . 4 1.3.1 Problems in Phase 0: Using External Sensors . . . . . . . . . 4 1.3.2 Problems in Phase 1: Labeling . . . . . . . . . . . . . . . . . 7 1.4 Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 1.5 The Contributions . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 1.6 Thesis Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 CHAPTER 2 RELATED WORK . . . . . . . . . . . . . . . . . . . . . 11 2.1 Temporal Pattern Discovery . . . . . . . . . . . . . . . . . . . . . . 11 2.2 Nearest Neighbor-based Anomaly Detection . . . . . . . . . . . . . . 12 2.3 Clustering-based Anomaly Detection . . . . . . . . . . . . . . . . . . 13 2.4 Model-based Anomaly Detection . . . . . . . . . . . . . . . . . . . . 13 2.5 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 CHAPTER 3 SYSTEM SETTING . . . . . . . . . . . . . . . . . . . . 18 3.1 Format of a light switch . . . . . . . . . . . . . . . . . . . . . . . . . 18 3.1.1 An Event . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19 CHAPTER 4 PROPOSED UNSUPERVISED ANOMALY DETECTION . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 4.1 Used Techniques . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 4.1.1 Expectation Maximization . . . . . . . . . . . . . . . . . . . 21 4.1.2 Bayesian Information Criteria . . . . . . . . . . . . . . . . . 23 4.1.3 Model-based Gaussian Hierarchical Clustering . . . . . . . . 24 4.2 Unsupervised Anomaly Detection Algorithm . . . . . . . . . . . . . 25 4.2.1 Three Problems in Phase 1 . . . . . . . . . . . . . . . . . . . 26 4.2.2 Approach 1: Suppress the High Variance Distribution . . . . 28 4.2.3 Approach 2: Identify and Remove the Outliers . . . . . . . . 29 4.2.4 Deciding a Future Event is Normal or Anomalous . . . . . . 34 CHAPTER 5 IMPLEMENTATAION AND RESULTS . . . . . . . 38 5.1 Test Bed Setting . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 5.1.1 Layout . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 38 5.1.2 Residents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39 5.2 Ground Truth . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 40 5.3 Compared with Ground Truth . . . . . . . . . . . . . . . . . . . . . 41 5.4 Comparison . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 CHAPTER 6 CONCLUSIONS . . . . . . . . . . . . . . . . . . . . . . 47 | |
dc.language.iso | en | |
dc.title | 智慧家庭中使用電燈開關資訊之非監督式異常偵測 | zh_TW |
dc.title | Unsupervised Anomaly Detection Using Light Switch Information in Smart Homes | en |
dc.type | Thesis | |
dc.date.schoolyear | 103-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 林軒田(Hsuan-Tien Lin),李育杰(Yuh-Jye Lee),鮑興國(Hsing-Kuo Pao),楊劭文(Shao-Wen Yang) | |
dc.subject.keyword | 異常偵測,不正常偵測,非監督式,智慧家庭,電燈,物聯網, | zh_TW |
dc.subject.keyword | Anomaly detection,unsupervised,smart home,light,IoT, | en |
dc.relation.page | 51 | |
dc.rights.note | 未授權 | |
dc.date.accepted | 2015-08-19 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電信工程學研究所 | zh_TW |
顯示於系所單位: | 電信工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-104-1.pdf 目前未授權公開取用 | 1.8 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。