朱浩華臺灣大學：資訊工程學研究所張耿豪Chang, Keng-haoKeng-haoChang2007-11-262018-07-052007-11-262018-07-052006http://ntur.lib.ntu.edu.tw//handle/246246/53639We are what we eat. Our everyday food choices affect our long-term and short-term health. In the traditional health care, professionals assess and weigh each individual’s dietary intake using intensive labor at high cost. In this paper, we design and implement a diet-aware dining table that can track what and how much we eat. To enable automated food tracking, the dining table is augmented with two layers of weighing and RFID sensor surfaces. We devise a weight-RFID matching algorithm to detect and distinguish how people eat. To validate our diet-aware dining table, we have performed experiments, including live dining scenarios (afternoon tea and Chinese-style dinner), multiple dining participants, and concurrent activities chosen randomly. Our experimental re-sults have shown encouraging recognition accuracy, around 80%. We believe monitoring the dietary behaviors of individuals potentially contribute to diet-aware healthcare.Acknowledgments i Abstract iii List of Figures ix List of Tables xi Chapter 1 Introduction 1 1.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 ProblemandSolution . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.3 Challenge andContribution . . . . . . . . . . . . . . . . . . . . . . . . . 2 1.4 Generalization into aSmartSurface . . . . . . . . . . . . . . . . . . . . 4 1.5 ThesisOrganization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 Chapter 2 Related Work 5 2.1 Traditional Dietary Assessment Methods . . . . . . . . . . . . . . . . . . 5 2.2 UbiquitousDietaryTrackingSystems . . . . . . . . . . . . . . . . . . . 6 2.3 Intelligent (Tabletop) Surfaces . . . . . . . . . . . . . . . . . . . . . . . 7 2.4 Behavior Recognition . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.5 Persuasive Technologies . . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.6 SmartKitchen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9 Chapter 3 Design Choices, Assumptions, and Limitations 11 3.1 Why RFID and Weighing Surfaces? . . . . . . . . . . . . . . . . . . . . 11 3.2 Complex and Concurrent Interactions Involving Multiple Tabletop Objects 12 3.3 Intelligent Surface vs. Intelligent Containers . . . . . . . . . . . . . . . . 14 3.4 Assumptions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15 Chapter 4 Design and Implementation 17 4.1 HardwareDesignandImplementation . . . . . . . . . . . . . . . . . . . 18 4.1.1 Stable Weight Detection Algorithm . . . . . . . . . . . . . . . . 19 4.2 SoftwareDesign andImplementation . . . . . . . . . . . . . . . . . . . 20 4.2.1 Law of Conservation of Mass . . . . . . . . . . . . . . . . . . . 22 4.2.2 Weight Matching Algorithm . . . . . . . . . . . . . . . . . . . . 23 4.2.3 Common Sense Semantics . . . . . . . . . . . . . . . . . . . . . 24 Chapter 5 Experimental Set-up and Results 25 5.1 Evaluationmetric, dining scenarios, anddining settings . . . . . . . . . . 25 5.2 Dining Scenario #1: Afternoon Tea - Single User - Predefined Activity Sequence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 29 5.3 Dining Scenario #2: Afternoon Tea - Two users - Predefined Activity Sequence . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30 5.4 Dining Scenario #3: Afternoon Tea - Two Users - Random Activities . . 30 5.5 Dining Scenario #4: Chinese-style dinner - Three users - Random activities 33 5.6 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 35 5.6.1 Methods to Reduce Recognition Misses . . . . . . . . . . . . . . 36 5.6.2 Removing No Cross-cell Objects Assumption . . . . . . . . . . . 37 5.6.3 Probabilistic Inference . . . . . . . . . . . . . . . . . . . . . . . 39 Chapter 6 Application I: Persuasive Game 41 6.1 Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 6.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41 6.3 DesignConsiderations . . . . . . . . . . . . . . . . . . . . . . . . . . . 42 6.4 DesignandImplementation . . . . . . . . . . . . . . . . . . . . . . . . . 44 6.4.1 Smart Lunch Tray . . . . . . . . . . . . . . . . . . . . . . . . . 45 6.4.2 Persuasive Game . . . . . . . . . . . . . . . . . . . . . . . . . . 46 6.5 PreliminaryExperiment . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 6.6 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 48 Chapter 7 Application II: Smart Kitchen 49 7.1 Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 7.2 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 7.3 Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 51 7.4 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 53 Chapter 8 Conculsion and FutureWork 55 Bibliography 57 Appendices 63 Chapter A Publication of Keng-hao Chang 63988314 bytesapplication/pdfen-US感測器人工智慧飲食健康sensorsaritficial intelligencerule-based inferencedietthesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/53639/1/ntu-95-R93922018-1.pdf