傅立成臺灣大學：資訊工程學研究所林志豪Lin, Zhi-HaoZhi-HaoLin2007-11-262018-07-052007-11-262018-07-052007http://ntur.lib.ntu.edu.tw//handle/246246/53780在智慧型家庭環境中如何根據居住者的偏好提供適當的服務是一個重要課題。本文的目標是建立一個系統能學習多個居住者的偏好並能適切的表示使用者之間的關係以及服務和感測器觀測資料的關係。因此可以基於學習後的偏好模型推論多個居住者所偏好的服務。所以我們提出一個三層偏好學習模型。在第一層中，從感測器所得到的原始數據中清除雜訊再被轉換成具有意義的高階資訊。 在第二層我們利用動態貝式網路模型考慮觀察資訊的相對時間關係來推論 各個居住者分別所想要的服務。 在最高層中，我們把第二層推論的結果、環境資訊和多個居住者間的關係來 推論目前在環境中居住者所需要的服務，並透過服務建議機制推薦服務給居住 者。 在實驗中，我們證明了我們的模型可以在智慧型家庭環境中推薦可靠和準確 的服務給居民。An important issue to be addressed in a smart home environment is how to provide appropriate services according to the preference of inhabitants. In this paper, we aim at developing a system to learn a multiple users’ preference model that represents relationships among users as well as dependency between services and sensor observations. Thus, the service can be inferred based on the learnt model. To achieve this, we propose a three-layer model in our work. At the first layer, raw data from sensors are interpreted as context information after noise removal. The second layer is dynamic Bayesian networks which model the observation sequences including inhabitants’ location and electrical appliance information. At the highest layer, we integrate the results of the second layer, environment information and the relations between inhabitants to recommend the service to inhabitants. Therefore, the system can infer appropriate services to inhabitants at right time and right place and let them feel comfortable. In experiments, we show that our model can reliably recommend and precise services to inhabitants in a smart home environment.Table of Contents Acknowledgement i Abstract in Chinese iii Abstract v Contents vii List of Figures xi 1 Introduction 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 Objectives . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 Related Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 1.4 Organization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2 Preliminaries 10 2.1 Introduction to Graphical Models . . . . . . . . . . . . . . . . . . . 10 2.1.1 Introduction to Bayesian networks . . . . . . . . . . . . . . 12 2.1.2 Introduction to Dynamic Bayesian Network . . . . . . . . . 17 2.2 Data Representation . . . . . . . . . . . . . . . . . . . . . . . . . . 21 2.2.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21 2.2.2 Definition of Environment Data . . . . . . . . . . . . . . . . 22 2.2.3 Collection of Environment Data . . . . . . . . . . . . . . . . 25 2.2.4 Environment Data Preprocessing . . . . . . . . . . . . . . . 26 3 Preference Model for Multiple Users 32 3.1 Overview . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 32 3.1.1 Context Interpreter . . . . . . . . . . . . . . . . . . . . . . . 40 3.2 Electrical Appliance Controller Model . . . . . . . . . . . . . . . . . 43 3.2.1 Training and Learning . . . . . . . . . . . . . . . . . . . . . 47 3.2.2 Inference . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 3.3 Multiple Users Interaction Model . . . . . . . . . . . . . . . . . . . 50 3.3.1 Inference . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53 3.3.2 Learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 54 3.4 Service Recommendation . . . . . . . . . . . . . . . . . . . . . . . . 55 4 Experiments 58 4.1 Environment Description . . . . . . . . . . . . . . . . . . . . . . . . 58 4.1.1 Sensor Description . . . . . . . . . . . . . . . . . . . . . . . 59 4.1.2 Description of Electrical Appliance Controller . . . . . . . . 61 4.2 Evaluation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 62 4.2.1 Single-user Preference Evaluation . . . . . . . . . . . . . . . 63 4.2.2 Multi-user Preference Evaluation . . . . . . . . . . . . . . . 65 5 Conclusions and Future Works 74 5.1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 74 5.2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 75 Reference 772942185 bytesapplication/pdfen-US智慧家庭家庭自動化偏好學習服務提供多人環境Smart HomeHome AutomationPreference modelingService rovisionMulti-user Environmentthesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/53780/1/ntu-96-R94922083-1.pdf