請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/61120完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 陳銘憲(Ming-Syan Chen) | |
| dc.contributor.author | Shu-Bo Chao | en |
| dc.contributor.author | 趙勗博 | zh_TW |
| dc.date.accessioned | 2021-06-16T10:47:40Z | - |
| dc.date.available | 2013-08-22 | |
| dc.date.copyright | 2013-08-22 | |
| dc.date.issued | 2013 | |
| dc.date.submitted | 2013-08-12 | |
| dc.identifier.citation | [1] H. Cao, T. Bao, Q. Yang, E. Chen and J. Tian. 2010. “An effective approach for mining mobile user habits.” In Proceedings of the 19th ACM international conference on Information and knowledge management (CIKM '10). ACM, New York, NY, USA, 1677-1680, 2010.
[2] L. Devroye, L. Gyorfi and G. Lugosi, “A probabilistic theory of pattern recognition.” Springer, 1996. [3] T. M. T. Do and D. Gatica-Perez. “Contextual conditional models for smartphone-based human mobility prediction.” In Proceedings of the 2012 ACM Conference on Ubiquitous Computing (UbiComp '12). ACM, New York, NY, USA, 163-172, 2012. [4] J. B. Gomes, S. Krishnaswamy, M. M. Gaber, P. A. C. Sousa and E. Menasalvas. “MARS: A personalised mobile activity recognition system.” In Proceedings of the 2012 IEEE 13th International Conference on Mobile Data Management (mdm 2012) (MDM '12). IEEE Computer Society, Washington, DC, USA, 316-319, 2012. [5] A. Goni, A. Burgos, L. Dranca, J. Rodriguez, A. Illarramendi and J. Bermudez, “Architecture, cost-model and customization of real-time monitoring systems based on mobile biological sensor data-streams.” In Proc. of Computer Methods and Programs in Biomedicine, 96(2): 141-157, 2009. [6] M. Hall, E. Frank, G. Holmes, B. Pfahringer, P. Reutemann, I. H. Witten, “The WEKA data mining software: an update.” SIGKDD Explorations, Volume 11, Issue 1, 2009. [7] A. Karatzoglou, L. Baltrunas, K. Church, and M. Bohmer. “Climbing the app wall: enabling mobile app discovery through context-aware recommendations.” In Proceedings of the 21st ACM international conference on Information and knowledge management (CIKM '12). ACM, New York, NY, USA, 2527-2530, 2012. [8] H. Kargupta, B.-H. Park, S. Pittie, L. Liu, D. Kushraj and K. Sarkar. “MobiMine: monitoring the stock market from a PDA.” In Proc. of SIGKDD Explor. Newsl. 3, 2 (January 2002), p.37-46, 2002. [9] H. Kargupta, R. Bhargava, K. Liu, M. Powers, P. Blair, S. Bushra, J. Dull, K. Sarkar, M. Klein, M. Vasa and D. Handy. “VEDAS: A mobile and distributed data stream mining system for real-time vehicle monitoring.” In Proc. of the SIAM DM Conference, 2004. [10] S. Kullback, R. A. Leibler, “On information and sufficiency.” Annals of Mathematical Statistics 22 (1): 79–86, 1951. [11] J. R. Kwapisz, G. M. Weiss, and S. A. Moore. “Activity recognition using cell phone accelerometers.” SIGKDD Explor. Newsl. 12, 2 (March 2011), 74-82, 2011. [12] D. J. Patterson, L. Liao, D. Fox and H. Kautz. “Inferring high-level behavior from low- level sensors.” In Proc. of Ubicomp’03, Springer Press, p. 73-89, 2003. [13] J. Ross Quinlan. “C4.5: programs for machine learning.” Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 1993. [14] T. Saponas., J. Lester, J. Froehlich, J. Fogarty and J. Landay. “iLearn on the iPhone: real-time human activity classification on commodity mobile phones.” In Proc. of UW-CSE-08-04-02 Tech Report, 2008. [15] B. Yan and G. Chen. “AppJoy: personalized mobile application discovery.” In Proceedings of the 9th international conference on Mobile systems, applications, and services(MobiSys '11). ACM, New York, NY, USA, 113-126, 2011. [16] T. Yan, D. Chu, D. Ganesan, A. Kansal and J. Liu. “Fast app launching for mobile devices using predictive user context.” In Proceedings of the 10th international conference on Mobile systems, applications, and services (MobiSys'12). ACM, New York, NY, USA, 113-126, 2012. [17] Y. Zheng, L. Zhang, X. Xie and W.-Y. Ma. “Mining interesting locations and travel sequences from GPS trajectories.” In Proceedings of the 18th international conference on World wide web (WWW '09). ACM, New York, NY, USA, 791-800, 2009. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/61120 | - |
| dc.description.abstract | 這篇論文專注在開發行動裝置上的每日活動摘要技術。我們提出了新的每日摘要應用,能夠讓行動裝置的使用者記錄他們每天的日常活動,並且提供介面讓使用者能夠回顧過往的活動摘要。除此之外,產生的摘要能夠用來分析使用者習慣和喜好,產生許多附加價值。例如使用者可以記錄在麥當勞用餐,或是踢足球的運動。有了使用者活動的歷史記錄,我們可以找出使用者經常在周末中午時刻在麥當勞用餐的規則,或是找出使用者最喜歡的運動是踢足球等。這樣的摘要能夠找出個人化的習慣,並且有許多潛在的應用,例如行動廣告和行動搜尋等。
由於使用者傾向只記錄重要且印象深刻的活動,我們試圖利用各種手機情境資訊以自動產生完整而全面的活動摘要。在本論文中,我們將活動摘要的自動產生塑造為分類問題,並且提出了基於情境感知之每日活動摘要產生架構(簡稱CADAS)。此架構根據時間、地點、裝置及使用者情境來分類活動的類型。此外,我們設計了一個使用者介面,讓使用者能夠回顧產生的摘要,並且根據使用者活動的實際情況對分類錯誤的活動進行校正,給予分類模型回饋。我們在Android平台實作CADAS,並從13位志願者收集了一個月的真實使用者活動資料。藉由實際使用者的測試與實驗分析,我們驗證了所提出系統能夠使活動分類達到95%的高準確率,符合此自動摘要產生應用之需求。 | zh_TW |
| dc.description.abstract | This thesis focuses on the problem of daily activity summary generation with mobile devices. We propose a novel daily activity summary application which allows users to record their activities and get an overview of their daily lives. Motivated by the fact that users are prone to only record important and impressive activities, we attempt to automatically generate more complete and comprehensive summaries according to miscellaneous mobile contexts. In this thesis, we model the activity summary generation problem as a classification task. We propose the Context-Aware Daily Activity Summarization framework (abbreviated as CADAS) that can classify activity types based on time, location, device, and user contexts collected on mobile devices. Moreover, we design a mobile user interface to help users get an overview of the generated summaries, and users can provide feedback by correcting misclassified results to refine the activity classification model. The CADAS framework is implemented on Android platform, and a 1-month real dataset contributed from 13 volunteers is exploited to conduct extensive experiments. The experiment results show that the classification accuracy can be very high, justifying the effectiveness of CADAS framework. | en |
| dc.description.provenance | Made available in DSpace on 2021-06-16T10:47:40Z (GMT). No. of bitstreams: 1 ntu-102-R00921040-1.pdf: 3335837 bytes, checksum: bed244777fa2d1667cf37699ceb3dd24 (MD5) Previous issue date: 2013 | en |
| dc.description.tableofcontents | 口試委員會審定書 i
Acknowledgements ii 中文摘要 iii ABSTRACT iv CONTENTS v LIST OF FIGURES vii LIST OF TABLES viii Chapter 1 Introduction 1 Chapter 2 Preliminaries 6 2.1 Daily Activity Summary Generation 6 2.2 System Architecture 8 Chapter 3 Feature Extraction 9 3.1 Mobile Context Record and Activity Record 11 3.2 Stay Point Extraction 13 3.3 Location-related Features 14 3.4 Time-related Features 16 3.5 Device-related Features 16 3.6 User-related Features 18 Chapter 4 Daily Activity Summary Generation 19 4.1 Time Segmentation 20 4.2 Context-Aware Activity Classification 22 Chapter 5 Performance Evaluation 26 5.1 Experimental Setup 26 5.2 Performance of Activity Classification and Effects of Different Parameters 28 5.3 Case Study 31 Chapter 6 Related Works 34 6.1 Context-Aware Mobile Application 34 6.2 Mobile Activity Recognition 34 Chapter 7 Conclusion 36 REFERENCES 37 | |
| dc.language.iso | en | |
| dc.subject | 活動摘要技術 | zh_TW |
| dc.subject | 情境感知之活動分類 | zh_TW |
| dc.subject | 行動計算 | zh_TW |
| dc.subject | Activity Summarization | en |
| dc.subject | Mobile Computing | en |
| dc.subject | Context-Aware Activity Classification | en |
| dc.title | 基於行動裝置情境感知之每日活動摘要產生機制 | zh_TW |
| dc.title | Context-Aware Daily Activity Summarization with Mobile Devices | en |
| dc.type | Thesis | |
| dc.date.schoolyear | 101-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 陳孟彰(Meng-Chang Chen),彭文志(Wen-Chih Peng),葉彌妍(Mi-Yen Yeh) | |
| dc.subject.keyword | 情境感知之活動分類,活動摘要技術,行動計算, | zh_TW |
| dc.subject.keyword | Context-Aware Activity Classification,Activity Summarization,Mobile Computing, | en |
| dc.relation.page | 39 | |
| dc.rights.note | 有償授權 | |
| dc.date.accepted | 2013-08-12 | |
| 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-102-1.pdf 未授權公開取用 | 3.26 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。
