臺灣博碩士論文加值系統

智慧家庭的基本概念之一為有效地了解當使用者生活行為有所變化時的環境情境訊息，並適當做出決策以幫助環境內的用戶。為了取得較佳的情境訊息，經常會採用一般常用的感測器、可獲取到影像資料的攝影機以及收集音頻資料的麥克風等設備，這些設備都可針對環境內不同的形態的資料進行採集的動作。收集到的情境資料質量較高，雖然可以有較佳的決策結果，但相對的這將會提高電腦運算以及需要硬體較佳的電腦來處理這些資料。此外，在環境內安裝的監聽設備會對於用戶產生受到監控的感覺，因而產生出排斥感。其中，又以能採集到影像資料和音頻資料的監聽設備最被排斥。在本研究中，我們採用紅外線感測器所獲取的數據進行活動分析。由於行為者對於活動發生時所會產生出的動態程度難以用自然語言讓電腦了解，另一方面活動容易受到外部因素，產生出不同變化。為了有效地讓電腦了解活動量的差異以及不確定性問題，我們提出一套基於模糊邏輯的活動識別架構，使用模糊邏輯，分析感測器所收集到的數據，並識別用戶的活動。根據實驗的結果，可識別85.49%的簡易日常活動。

The basic concept of smart environment is to understand the context information of environmental and human behavioral changes to provide appropriate services accordingly. To obtain the context information, people often use video cameras, microphones, and other devices. These devices can obtain complex environmental data but they also need powerful equipment for handling the data. In addition, monitoring equipment will generate privacy issues. Users will generate sense of exclusion. In these devices, users generally do not like the graphic and audio monitoring equipment. We mainly collect user’s activity information through the most simple data quality of sensor. The activity of human is difficult to make computers understand by natural language. On the other hand, activity vulnerable to external factors produce different variations. In order to effectively address these issues, we propose an activity identification architecture based on fuzzy logic. This method uses fuzzy logic to deal with sensor data and uses fuzzy decision trees to identify user’s activities. According to the results of preliminary experiments, the system can identify 85.49% of the daily human activities.

中文摘要 ..................................................I
Abstract .................................................II
List of Figure ...........................................VII
List of Tables ...........................................VIII
Chapter 1 Introduction ...................................1
1.1 Background ...........................................1
1.2 Motivation ...........................................1
1.3 Purpose ..............................................3
1.4 The Framework of Thesis ..............................3
Chapter 2 Related Works ..................................4
2.1 Activity Recognition .................................4
2.1.1 Large Amount of Information ........................4
2.1.2 Less Amount of Information .........................5
2.1.3 Related Researches .................................6
2.2 Fuzzy Decision Trees .................................8
Chapter 3 Research Method ................................13
3.1 System Architecture ..................................13
3.2 Pretreatment .........................................14
3.3 Activities Execution Rate (AER) ......................20
3.4 Fuzzy Inference ......................................23
3.5 Detection Unit .......................................26
Chapter 4 Experimental Results ...........................28
4.1 Experimental Environment .............................28
4.2 Experiment Results ...................................30
4.2.1 The system using activity weight adjustments .......30
4.2.2 The system not using activity weight adjustments ...31
Chapter 5 Conclusions and Future Works ...................34
5.1 Conclusions ..........................................34
5.2 Future Works .........................................35
References ...............................................36

List of Figure
Figure 2-1 Fuzzy logic ...................................9
Figure 2-2 Membership function model .....................9
Figure 3-1 Activity identification flow ..................13
Figure 3-2 One day raw sensor data .......................15
Figure 3-3 Activity degree ...............................17
Figure 3-4 Comparison of the results of ADt and AAt ......18
Figure 3-5 Similar activities membership functions .......19
Figure 3-6. Activity weight computing concepts ...........21
Figure 3-7. AW_ adjustments code .........................22
Figure 3-8. NAER membership function .....................23
Figure 3-9 Fuzzy decision tree ...........................25
Figure 3- 10 C value .....................................27
Figure 4-1 Experimental environment ......................28

 
List of Table
Table 3-1 Activity code ..................................14
Table 3-2 The raw sensor data (One day) ..................15
Table 3-3 The record form of activities. .................20
Table 3-4 Fuzzy decision tree training data ..............24
Table 3-4 Rules table ....................................26
Table 4-1 Activity identification results.................30
(using activity weight adjustment)
Table 4-2 Activity identification results.................31
(not using activity weight adjustment)
Table 4-3 Comparison of results ..........................32

[1]Â. Costa, J. C. Castillo, P. Novais, A. Fernández-Caballero, and R. Simoes (2012), “Sensor-Driven Agenda for Intelligent Home Care of The Elderly,” Expert Systems with Applications, Vol. 39, No. 15, pp. 12192-12204.
[2]C. C. Yang, and Y. L. Hsu (2012), “Remote Monitoring and Assessment of Daily Activities in the Home Environment,” Journal of Clinical Gerontology and Geriatrics, Vol. 3, No. 3, pp. 97-104.
[3]C. M. Tsai, Q. Zhao, R. C. Chen, and M. Taya (2014), “Activity Awareness Based on Simple Sensors,” IEEE 6th International Conference on in Awareness Science and Technology, pp. 1-6.
[4]D. Ding, R. A. Cooper, P. F. Pasquina, and L. Fici-Pasquina (2011), “Sensor Technology for Smart Homes,” Maturitas, Vol. 69, No. 2, pp. 131-136.
[5]D. Fuentes, L. Gonzalez-Abril, C. Angulo, and J. A. Ortega (2012), “Online Motion Recognition Using an Accelerometer in a Mobile Device,” Expert Systems with Applications, Vol. 39, No. 3, pp. 2461-2465.
[6]D. Ayers, and M. Shah, (2001), “Monitoring Human Behavior from Video Taken in an Office Environment,” Image and Vision Computing, Vol. 19, No. 12, pp. 833-846.
[7]E. Hüllermeier (2011), “Fuzzy Sets in Machine Learning and Data Mining,” Applied Soft Computing, Vol. 11, No. 2, pp. 1493-1505.
[8]H. Medjahed, D. Istrate, J. Boudy, and B. Dorizzi (2009), “Human Activities of Daily Living Recognition Using Fuzzy Logic for Elderly Home Monitoring,” IEEE Fuzzy Systems (FUZ-IEEE), pp. 2001-2006.
[9]J. Demongeot, G. Virone, F. Duchêne, G. Benchetrit, T. Hervé, N. Noury, and V. Rialle (2002), “Multi-Sensors Acquisition, Data Fusion, Knowledge Mining and Alarm Triggering in Health Smart Homes for Elderly People,” Comptes Rendus Biologies, Vol. 325, No. 6, pp. 673-682.
[10]J. Wen, M. Zhong, and Z. Wang (2015), “Activity Recognition with Weighted Frequent Patterns Mining in Smart Environments,” Expert Systems with Applications, Vol. 42 No. 17, pp. 6423-6432.
[11]L. A. Zadeh (1965), “Fuzzy Sets”, Information and Control, Vol. 8, No. 3, pp. 338-353.
[12]L. A. Zadeh (1973), “Outline of a New Approach to the Analysis of Complex Systems and Decision Processes,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, Vol. SMC-3, No. 1, pp. 28-44.
[13]L. Chen, C. D. Nugent, and H. Wang (2012), “A Knowledge-Driven Approach to Activity Recognition in Smart Homes,” IEEE Transactions on Knowledge and Data Engineering, Vol. 24, No. 6, pp. 961-974.
[14]M. Chan, E. Campo, D. Estève, and J. Y. Fourniols (2009), “Smart Homes—Current Features and Future Perspectives,” Maturitas, Vol. 64, No. 2, pp. 90-97.
[15]N. C. Krishnan, and J. C. Diane (2012), “Activity Recognition on Streaming Sensor Data,” Pervasive and Mobile Computing, Vol. 10, pp. 138-154.
[16]P. Rashidi, and D. J. Cook (2009), “Keeping the Resident in the Loop: Adapting the Smart Home to the User,” IEEE Transactions on Systems, Man and Cybernetics-Part A: Systems and Humans, Vol. 39, No. 5, pp. 949-959.
[17]P. C. Huang, S. S. Lee, Y. H. Kuo, and K. R. Lee (2010), “A Flexible Sequence Alignment Approach on Pattern Mining and Matching for Human Activity Recognition,” Expert Systems with Applications, Vol. 37, No. 1, pp. 298-306.
[18]S. Wang, M. Skubic, and Y. Zhu (2012), “Activity Density Map Visualization and Dissimilarity Comparison for Eldercare Monitoring,” IEEE Transactions on Information Technology in Biomedicine, Vol. 16, No. 4, pp. 607-614.
[19]S. Mohammed, A. Samé, L. Oukhellou, K. Kong, W. Huo, and Y. Amirat (2014), “Recognition of Gait Cycle Phases Using Wearable Sensors,” Robotics and Autonomous Systems.
[20]X. Hong, C. Nugent, M. Mulvenna, S. McClean, B. Scotney, and S. Devlin (2009), “Evidential Fusion of Sensor Data for Activity Recognition in Smart Homes,” Pervasive and Mobile Computing, Vol. 5, No. 3, pp. 236-252.
[21]Y. Yuan, and M. J. Shaw (1995), “Induction of Fuzzy Decision Trees,” Fuzzy Sets and Systems, Vol.69, No. 2, pp. 125-139.
[22]Y. Kwon, K. Kang, and C. Bae (2014), “Unsupervised Learning for Human Activity Recognition Using Smartphone Sensors,” Expert Systems with Applications, Vol. 41, No. 14, pp. 6067-6074.
[23]陳宏銘 (2001)，設計最佳化之演化式模糊決策樹，碩士論文，逢甲大學資訊工程學系，台中。
[24]李天祥 (2002)，以模糊語意塑模法萃取決策知識之研究，碩士論文，國立高雄第一科技大學資訊管理所，高雄。
[25]詹智翔 (2007)，具情境感知的授權控管模型於智慧型空間之研究，碩士論文，中華大學資訊管理學系所，新竹。
[26]林榮泰 (2007)，應用模糊決策樹分析於研發型專案風險之評估，碩士論文，國立成功大學製造工程研究所碩博士班，台南。
[27]蘇明雄 (2012)，基於有限狀態機之智慧型手機跌倒偵測機制，碩士論文，大同大學資訊工程學系，臺北市。
[28]莊豐柏 (2013)，以嵌入式影像處理系統為基礎之動作感測器實作，碩士論文，國立金門大學，金門。
[29]李允中、王小璠、蘇木春 (2012)，模糊理論及其應用，全華圖書股份有限公司，第514-517頁。