Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51966
Full metadata record
???org.dspace.app.webui.jsptag.ItemTag.dcfield??? | Value | Language |
---|---|---|
dc.contributor.advisor | 傅立成(Li-Chen Fu) | |
dc.contributor.author | Tsung-Chi Chiang | en |
dc.contributor.author | 蔣宗圻 | zh_TW |
dc.date.accessioned | 2021-06-15T14:00:08Z | - |
dc.date.available | 2020-08-21 | |
dc.date.copyright | 2015-08-21 | |
dc.date.issued | 2015 | |
dc.date.submitted | 2015-08-20 | |
dc.identifier.citation | [1] M. Farooq, M. Waseem, S. Mazhar, A. Khairi, and T. Kamal, 'A Review on Internet of Things (IoT),' International Journal of Computer Applications, vol. 113, 2015.
[2] E. Kim, S. Helal, and D. Cook, 'Human activity recognition and pattern discovery,' IEEE International Conference on Pervasive Computing, vol. 9, pp. 48-53, 2010. [3] A. Fleury, M. Vacher, and N. Noury, 'SVM-based multimodal classification of activities of daily living in health smart homes: sensors, algorithms, and first experimental results,' Information Technology in Biomedicine, IEEE Transactions on, vol. 14, pp. 274-283, 2010. [4] P. Rashidi, D. J. Cook, L. B. Holder, and M. Schmitter-Edgecombe, 'Discovering activities to recognize and track in a smart environment,' IEEE Transactions on Knowledge and Data Engineering, vol. 23, pp. 527-539, 2011. [5] L. Bao and S. S. Intille, 'Activity recognition from user-annotated acceleration data,' in Pervasive computing, ed: Springer, 2004, pp. 1-17. [6] T. Van Kasteren, A. Noulas, G. Englebienne, and B. Krose, 'Accurate activity recognition in a home setting,' in Proceedings of the 10th international conference on Ubiquitous computing, 2008, pp. 1-9. [7] K. Farrahi and D. Gatica-Perez, 'Discovering routines from large-scale human locations using probabilistic topic models,' ACM Transactions on Intelligent Systems and Technology (TIST), vol. 2, p. 3, 2011. [8] F.-T. Sun, Y.-T. Yeh, H.-T. Cheng, C. Kuo, and M. Griss, 'Nonparametric discovery of human routines from sensor data,' in IEEE International Conference on Pervasive Computing and Communications, 2014, pp. 11-19. [9] B. Chikhaoui, S. Wang, and H. Pigot, 'A new statistical model for activity discovery and recognition in pervasive environments,' in International Conference on Pattern Recognition 2012, pp. 3435-3438. [10] L. G. Fahad, S. F. Tahir, and M. Rajarajan, 'Activity recognition in smart homes using clustering based classification,' in International Conference on Pattern Recognition, 2014, pp. 1348-1353. [11] B. J. Frey and D. Dueck, 'Clustering by passing messages between data points,' science, vol. 315, pp. 972-976, 2007. [12] S. P. Lloyd, 'Least squares quantization in PCM,' Information Theory, IEEE Transactions on, vol. 28, pp. 129-137, 1982. [13] L. K. P. J. RDUSSEEUN, 'CLUSTERING BY MEANS OF MEDOIDS.' [14] S. Wold, K. Esbensen, and P. Geladi, 'Principal component analysis,' Chemometrics and intelligent laboratory systems, vol. 2, pp. 37-52, 1987. [15] C.-L. Wu, M.-Y. Weng, C.-H. Lu, and L.-C. Fu, 'Hierarchical generalized context inference or context-aware smart homes,' in Intelligent Robots and Systems (IROS), 2012 IEEE/RSJ International Conference on, 2012, pp. 5227-5232. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/51966 | - |
dc.description.abstract | 隨著物聯網的科技趨漸普及與流行,使得低運算能力的裝置在嵌入相應的感應器與控制器後,大量的佈建於智慧環境中。此外,這些感應器所產生的大數據可被進一步的分析,並應用於以人為本更人性化的系統中。其中一個具代表性的應用系統就是智慧家庭,這類應用利用機器學習或資料探勘的方式分析所收集的大數據,根據分析的結果建立情境感知系統於辨識使用者的活動與相對應的服務設定。但是,智慧家庭中的大數據隨時隨地的產生,資料量不斷得成長,使得傳統的監督式學習必須使用大量的人力標註每個資料的意義而不易應用於現實環境中。此外分析結果所建立的模型必須精簡且精確,而能在低運算力的裝置中運行並且佈建於智慧家庭。因此本研究提出一個非監督式學習分析方法於多人的環境中的情境探勘與相對應的服務參數,導入適合智慧家庭特性之情境結構以降低演算法複雜度同時不失正確率,並提供多人情境下滿足使用者偏好最佳化之服務。
本研究的主要貢獻有以下三點: 第一,為了有效的分析智慧家庭所產生的大數據與降低人為的資料標示成本,我們提出一個非參數式的模型用以探索家中使用者之行為。第二,我們提出一個非監督式的方法學習使用者於智慧家庭中的服務偏好參數。第三,為了主動地提供最適合的服務,我們提出一個服務決策系統,並根據探索而得的使用者當下行為與對應的服務參數提高系統提供服務時使用者的滿意度。 | zh_TW |
dc.description.abstract | As we are moving towards the Internet of Things (IoT), a significant number of heterogeneous sensors deployed around the word. The amounts of Big Data are contin-uously generated from those sensors in activity daily living (ADL). One of the applica-tions in IoT is smart home that proactively provides context-aware services by recog-nizing user activities among sensory data. In the other word, activity recognition (AR) plays a key component to add value to raw sensor data we need to understand it. Collec-tion, modeling, reasoning, and distribution of context in relation to sensor data plays critical role in this challenge. Context-aware computing has proven to be successful in understanding sensor data. However, for AR to build personalization activity daily liv-ing for each user and overcome the human labeling effort in Big Data, it is important to exploit unsupervised way from activity discovery (AD) [2], which is finding unknown patterns directly from low-level sensor data without any pre-defined assumptions.
There are three major contributions in this thesis. Firstly, a novel nonparametric model of activity discovery is proposed to reduce the effort of data annotation while the analysis of Big Data is being performed. Secondly, we propose a service discovery en-gine to learning user preference in an unsupervised way. Thirdly, a decision engine for proactively providing suitable service is proposed. We combine both the discovered user activity and corresponding service preference to improve the suitability of service with smart environment. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T14:00:08Z (GMT). No. of bitstreams: 1 ntu-104-R02922097-1.pdf: 1924872 bytes, checksum: 22c7e9140fdd0630f78401bfc3a775f5 (MD5) Previous issue date: 2015 | en |
dc.description.tableofcontents | 中文摘要 i
ABSTRACT ii Table of Contents iii List of Figures vi List of Tables vii Chapter 1 Introduction 1 1.1 Motivation 1 1.2 Challenges 2 1.2.1 Challenges of discovery for various activities in a multi-user environment 3 1.2.2 Challenges of analytics for large-scale data deployed in resource-constrained home gateway 4 1.3 Related Work 5 1.3.1 Activity Recognition 5 1.3.2 Activity Discovery 6 1.4 Objective 8 1.5 System Overview 10 1.6 Thesis Organization 11 Chapter 2 Preliminaries 13 2.1 Affinity Propagation 13 2.1.1 AP Initialization 14 2.1.2 AP Message Exchange 16 2.1.3 AP Making Assignment 18 2.2 Principal Component Analysis 19 2.2.1 PCA: Computing Principal Component 20 2.2.2 PCA: Dimensionality Reduction 21 2.3 IoT-based Wireless Sensor Networks 22 Chapter 3 Nonparametric Context and Preference Discovery Engine 25 3.1 System Overview of Context Discovery 27 3.1.1 Data Quantization 28 3.1.2 Room-level Activity Discovery 29 3.1.3 Home-level Activity Discovery 30 3.2 Context Structure 32 3.2.1 Definition of Context Structure 32 3.2.2 Home Layout as a Context Structure 32 3.2.3 Feature correlation as a Context Structure 33 3.3 Density-enhanced Affinity Propagation for AD 34 3.3.1 Problem Formulation 34 3.3.2 Density-enhanced Affinity Propagation 36 3.4 System Overview of Preference Discovery 39 3.5 Problem Formulation of Preference Discovery 40 3.6 Nonparametric Service Discovery using DAP 42 Chapter 4 Experiment Result 46 4.1 Data Collection 46 4.2 Analysis of Context Discovery 47 4.3 Case Study of Preference Discovery 51 Chapter 5 Conclusion 55 5.1 Summary 55 5.2 Future work 56 REFERENCE 57 | |
dc.language.iso | en | |
dc.title | 基於智慧環境之資料驅動情境與偏好探勘 | zh_TW |
dc.title | Data-driven Context and Preference Discovery in Smart Environment | en |
dc.type | Thesis | |
dc.date.schoolyear | 103-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 施吉昇(Chi-Shen Shih),周俊廷(Chun-Ting Chou),吳兆麟(Chao-Lin Wu),陸敬互(Ching-Hu Lu) | |
dc.subject.keyword | 智慧家庭,行為辨識,行為探索,服務探索,非監督式學習, | zh_TW |
dc.subject.keyword | Smart Home,Activity Recognition,Activity Discovery,Unsupervised Learning, | en |
dc.relation.page | 58 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2015-08-20 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 資訊工程學研究所 | zh_TW |
Appears in Collections: | 資訊工程學系 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-104-1.pdf Restricted Access | 1.88 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.