圖模型分解運用於活動辨識與推論｜國立臺灣科技大學博碩士論文系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	孫郁喬 Yu-Chiao Sun
論文名稱：	圖模型分解運用於活動辨識與推論 Model Decomposition for Activity Recognition and Reasoning
指導教授：	鮑興國 Hsing-Kuo Pao
口試委員:	李育杰 Yuh-Jye Lee 項天瑞 Tien-Ruey Hsiang 孫敏德 Min-Te Sun
學位類別：	碩士 Master
系所名稱：	電資學院 - 資訊工程系 Department of Computer Science and Information Engineering
論文出版年：	2016
畢業學年度：	104
語文別：	英文
論文頁數：	55
中文關鍵詞：	活動辨識、貝氏網路、快速檢驗模型、推論
外文關鍵詞：	Activity Recognition, Bayesian Network, QMR model, Reasoning
相關次數：	點閱：258 下載：4
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

上一筆

因為大數據近年來的蓬勃發展，物聯網也開始與我們的生活息息相關，物聯網目前主要的應用即是建造一個智慧型環境，並且藉由物聯網的技術能夠即時的偵測這個智慧型環境。而打造一個智慧型環境，其最主要的目的就是人類活動辨識，而能夠即時的辨識人類活動成為一個重要的挑戰。

此篇論文以快速檢驗模型(Quick Medical Reference Model)做為基礎架構，在此架構下我們針對人類於一個有著許多感測器下的智慧型環境，能夠在不使用監視器或錄影機的情況下，藉由這些感測器來達到即時的活動辨識，並且考量到硬體計算的成本與網路和感測器之間的溝通頻寬，我們能夠將建置好的模型分成數個較小的模型，在犧牲一點點辨識準確率的情況下，能夠有非常高的效能提升。而再成功辨識人類活動之後，我們從過去使用者的生活資料來找出使用者的個人生活習慣，而更進一步的從使用者現在的行為來預測使用者的下一步行為。

Because the big data booming in recent years, Internet of Things is closely related to our life. And the main applicaiton of IoT is building a smart environment. By using the IoT technology, we can monitor the whole smart environment in real time. The main purpose in build a smart environment is human activity recognization in real time become an important challenge.

In this thesis, we use the Quick Medical Reference Model as our framework and apply it to a smart environment which have a lot of sensors. In this environment, we can recognize human activity by these sensors and without using camera or monitor. And we also consider the computing cost and the internet bandwidth, therefore, we decompose the original big model into several small models, thus trading off accuracy and computation time. After we can detect the human activities precisely, we want to use the historical data to find the personal habits, and use the personal information to predict the next activity given current activity.

Recommendation Letter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i
Approval Letter . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii
Abstract in Chinese . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii
Abstract in English . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iv
Acknowledgements . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . v
Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi
List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . viii
List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . x
List of Algorithms . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xi
Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1
2 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
3 Thesis Outline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
Methodology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
1 Bayesian Network . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2 Quick Medical Reference . . . . . . . . . . . . . . . . . . . . . . . . . . 8
2.1 Building Quick Medical Reference Model . . . . . . . . . . . . . 9
2.2 Quickscore Algorithm . . . . . . . . . . . . . . . . . . . . . . . 10
3 Unweighted Pair Group Method with Arithmetic Mean . . . . . . . . . . 13
4 Reasoning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
Case Study . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
vi3.1 Dataset . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14
1.1 Sensor Deployment . . . . . . . . . . . . . . . . . . . . . . . . . 15
1.2 Activities and Location . . . . . . . . . . . . . . . . . . . . . . . 18
Experiment and result . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
1 Bayesian Network Toolbox . . . . . . . . . . . . . . . . . . . . . . . . . 22
2 Experimental setting . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3 Data preprocessing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
4 Experiment,Result and Analysis . . . . . . . . . . . . . . . . . . . . . . 25
4.1 Activity Recognition . . . . . . . . . . . . . . . . . . . . . . . . 25
4.2 Hierarchical Clustering . . . . . . . . . . . . . . . . . . . . . . . 27
4.3 Power and Bandwidth Saving. . . . . . . . . . . . . . . . . . . . 31
4.4 Model Decomposition . . . . . . . . . . . . . . . . . . . . . . . 35
4.5 Reasoning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 39
Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41

                                

[1] E. M. Tapia, S. S. Intille, and K. Larson, Activity recognition in the home using simple and ubiquitous
sensors. Springer, 2004.
[2] B. Logan, J. Healey, M. Philipose, E. M. Tapia, and S. Intille, A long-term evaluation of sensing
modalities for activity recognition. Springer, 2007.
[3] C. Lombriser, N. B. Bharatula, D. Roggen, and G. Tröster, “On-body activity recognition in a dynamic
sensor network,” in Proceedings of the ICST 2nd international conference on Body area networks,
p. 17, ICST (Institute for Computer Sciences, Social-Informatics and Telecommunications Engineer-
ing), 2007.
[4] 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, no. 2, pp. 274–283, 2010.
[5] T. Huỳnh, U. Blanke, and B. Schiele, “Scalable recognition of daily activities with wearable sensors,”
in Location-and context-awareness, pp. 50–67, Springer, 2007.
[6] D. J. Patterson, D. Fox, H. Kautz, and M. Philipose, “Fine-grained activity recognition by aggregating
abstract object usage,” in Wearable Computers, 2005. Proceedings. Ninth IEEE International Sympo-
sium on, pp. 44–51, IEEE, 2005.
[7] D. L. Vail, M. M. Veloso, and J. D. Lafferty, “Conditional random fields for activity recognition,” in
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems,
p. 235, ACM, 2007.
[8] T. Van Kasteren, A. Noulas, G. Englebienne, and B. Kröse, “Accurate activity recognition in a home
setting,” in Proceedings of the 10th international conference on Ubiquitous computing, pp. 1–9, ACM,
2008.
[9] F. V. Jensen, An introduction to Bayesian networks, vol. 210. UCL press London, 1996.
[10] D. Heckerman, A tutorial on learning with Bayesian networks. Springer, 1998.
[11] J. Pearl and S. Russell, Bayesian networks. Computer Science Department, University of California,
1998.
[12] D. Heckerman, “A tractable inference algorithm for diagnosing multiple diseases,” arXiv preprint
arXiv:1304.1511, 2013.
[13] T. S. Jaakkola and M. I. Jordan, “Variational probabilistic inference and the qmr-dt network,” Journal
of artificial intelligence research, pp. 291–322, 1999.
[14] S. Srinivas, “A generalization of the noisy-or model,” in Proceedings of the Ninth international confer-
ence on Uncertainty in artificial intelligence, pp. 208–215, Morgan Kaufmann Publishers Inc., 1993.
42[15] Y. Halpern and D. Sontag, “Unsupervised learning of noisy-or bayesian networks,” arXiv preprint
arXiv:1309.6834, 2013.
[16] K. Murphy et al., “The bayes net toolbox for matlab,” Computing science and statistics, vol. 33, no. 2,
pp. 1024–1034, 2001.

簡易檢索 / 詳目顯示

相關論文