1 i-Care Project Dietary-Aware Dining Table: Observing Dietary Behavior over Tabletop Surface Keng-hao Chang, Shih-yen Liu, Toung Lin, Hao Chu, Jane Hsu,

Slides:



Advertisements
Similar presentations
Outline Activity recognition applications
Advertisements

Slide 1 Today you will: Review knowledge and understanding of systems Understand what a system is and what it consists of Apply this understanding by working.
Adaptive Accurate Indoor-Localization Using Passive RFID Xi Chen, Lei Xie, Chuyu Wang, Sanglu Lu State Key Laboratory for Novel Software Technology Nanjing.
Hybrid Context Inconsistency Resolution for Context-aware Services
Energy Efficiency through Burstiness Athanasios E. Papathanasiou and Michael L. Scott University of Rochester, Computer Science Department Rochester, NY.
Agile Route Shopper Tracker Shopperception: Using a KINECT to build real world Google Analytics.
1 Playful Tray: Adopting Ubicomp and Persuasive Techniques into Play-based Occupational Therapy for Reducing Poor Eating Behavior in Young Children UBICOMP.
[Context to Make You More Aware] Presentation [Adrienne Andrew, Yaw Anokwa, Karl Koscher, Jonathan Lester, Gaetano Borriello Department of Computer Science.
Automated Assessment of Mobility in Bedridden Patients Advisor: Dr. Chun-Ju Hou Presenter: Si-Ping Chen Date:2014/12/10 35th Annual International Conference.
Yi Wang, Bhaskar Krishnamachari, Qing Zhao, and Murali Annavaram 1 The Tradeoff between Energy Efficiency and User State Estimation Accuracy in Mobile.
Week 3 Name ………………………………………….. MonTueWedThuFriSatSun Pre- breakfast Lunch time activity Afternoon activity Evening activity Bed time stretch Activity.
SensEye: A Multi-Tier Camera Sensor Network by Purushottam Kulkarni, Deepak Ganesan, Prashant Shenoy, and Qifeng Lu Presenters: Yen-Chia Chen and Ivan.
BlindAid Semester Final Presentation Sandra Mau, Nik Melchior, and Maxim Makatchev.
SoundSense: Scalable Sound Sensing for People-Centric Application on Mobile Phones Hon Lu, Wei Pan, Nocholas D. lane, Tanzeem Choudhury and Andrew T. Campbell.
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields Yong-Joong Kim Dept. of Computer Science Yonsei.
Chapter 8 Prediction Algorithms for Smart Environments
1 Chapter 16 Assistive Environments for Individuals with Special Needs.
1 Pervasive & Ubiquitous Computing (UbiComp) Lecture #1: Introduction Hao-hua Chu ( 朱浩華 )
Augmenting everyday life with sentient artefacts Fahim Kawsar, Kaori Fujinami, Tatsuo Nakajima Department of Information and Computer Science, Waseda University.
Playful Tray : Adopting Ubicomp and Persuasive Techniques into Play-based Occupational Therapy for Correcting Eating Behaviors in Young Children Presenter.
Multimedia Specification Design and Production 2013 / Semester 2 / week 8 Lecturer: Dr. Nikos Gazepidis
Agent-based Device Management in RFID Middleware Author : Zehao Liu, Fagui Liu, Kai Lin Reporter :郭瓊雯.
Beyond One-dollar Mouse: A Battery-free Device for 3D Human-Computer Interaction via RFID Tags Qiongzheng Lin Lei Yang,Yuxin Sun,Tianci Liu,Xiang-Yang.
PROJECT TITLE : AUTOMATED EVALUATION OF RETAIL PRICE OF PRODUCTS IN THE TROLLEY SYSTEM AND WIRELESS TRANSMISSION OF THE BILLING SYSTEM.
Demo. Overview Overall the project has two main goals: 1) Develop a method to use sensor data to determine behavior probability. 2) Use the behavior probability.
DATA COLLECTION METHODS CONTENT PAGE How data is collected via questionnaires. How data is collected via questionnaires. How data is collected with mark.
SixthSense RFID based Enterprise Intelligence Lenin Ravindranath, Venkat Padmanabhan Interns: Piyush Agrawal (IITK), SriKrishna (BITS Pilani)
NEURAL NETWORKS FOR DATA MINING
A PowerPoint about Algorithm’s. What is an algorithm?  a process or set of rules to be followed in calculations or other problem-solving operations,
1 EnviroStore: A Cooperative Storage System for Disconnected Operation in Sensor Networks Liqian Luo, Chengdu Huang, Tarek Abdelzaher John Stankovic INFOCOM.
Vikramaditya Jakkula & Diane J. Cook Artificial Intelligence Lab Washington State University 2 nd International Conference on Technology and Aging (ICTA)
Snacks and Drinks.
For this unit, you will develop a new swimming / leisure business. 2. You will need to think of a name & concept for the business. 3. Over the.
Senior undergrads – intro to ubicomp lab 朱浩華教授 Presented by 高新綠.
Nutrition Analysis Super tracker. Nutritional Analysis Students will record all of the food they eat for 3 days and enter the information into a program.
Dining Etiquette. Ronald Reagan All great change in America begins at the dinner table. Complete the Table Setting Worksheet.
The Second Life of a Sensor: Integrating Real-World Experience in Virtual Worlds using Mobile Phones Mirco Musolesi, Emiliano Miluzzo, Nicholas D. Lane,
Audio Location Accurate Low-Cost Location Sensing James Scott Intel Research Cambridge Boris Dragovic Intern in 2004 at Intel Research Cambridge Studying.
Slide 1 What makes up an information system? Input Process Output Temperature and rainfall from a variety of places Analyse the information and present.
Beyond the PC Kiosks & Handhelds Albert Huang Larry Rudolph Oxygen Research Group MIT CSAIL.
Computing for Social Needs Jennifer Mankoff UC Berkeley.
Learn about the system life cycle Plan the outline of your project
Table Setting and Etiquette. Why Dining Etiquette? Definition: Courtesy shown by good manners at meals. Makes eating a pleasant experience for everyone.
Diet-Aware Dining Table – Observing Dietary Behaviors over Tabletop Surface Shih-yen Liu, Cheryl Chen, Tung-yun Lin, Polly Huang National Taiwan University.
Secure Unlocking of Mobile Touch Screen Devices by Simple Gestures – You can see it but you can not do it Muhammad Shahzad, Alex X. Liu Michigan State.
Muhammad Shahzad Alex X. Liu Dept. of Computer Science and Engineering
Workshop on Smart Object Systems Dietary-Aware Dining Table – Tracking What and How Much You Eat Keng-hao Chang, Shih-yen Liu, Jr-ben Tian, Hao-hua Chu,
CISC 849 : Applications in Fintech Namami Shukla Dept of Computer & Information Sciences University of Delaware iCARE : A Framework for Big Data Based.
An Energy-Efficient Approach for Real-Time Tracking of Moving Objects in Multi-Level Sensor Networks Vincent S. Tseng, Eric H. C. Lu, & Kawuu W. Lin Institute.
Semantic Web in Context Broker Architecture Presented by Harry Chen, Tim Finin, Anupan Joshi At PerCom ‘04 Summarized by Sungchan Park
Understanding Naturally Conveyed Explanations of Device Behavior Michael Oltmans and Randall Davis MIT Artificial Intelligence Lab.
Using Service-Oriented Architecture in Context-Aware Applications Damião Ribeiro de Almeida Information System Laboratory Universidade Federal de Campina.
Nutrition and Wellness Chapter 3 12/3/12 Students will finish Chapter 2 Test Eating for Your Future Parts 3 and 4 Recipe Search tomorrow in Computer lab.
Shadow Detection in Remotely Sensed Images Based on Self-Adaptive Feature Selection Jiahang Liu, Tao Fang, and Deren Li IEEE TRANSACTIONS ON GEOSCIENCE.
Sensor-Assisted Wi-Fi Indoor Location System for Adapting to Environmental Dynamics Yi-Chao Chen, Ji-Rung Chiang, Hao-hua Chu, Polly Huang, and Arvin Wen.
Privacy Vulnerability of Published Anonymous Mobility Traces Chris Y. T. Ma, David K. Y. Yau, Nung Kwan Yip (Purdue University) Nageswara S. V. Rao (Oak.
SENSOR-INDEPENDENT PLATFORM FOR CIRCADIAN RHYTHM ANALYSIS Andrea Caroppo Institute for Microelectronics and Microsystems (IMM) National Research Council.
Introduction to UbiComp
MobileMiner: Mining Your Frequent Behavior Patterns On Your Phone
RF2ID: A Reliable Middleware Framework for RFID Deployment
Real-time Wall Outline Extraction for Redirected Walking
A Framework for Automatic Resource and Accuracy Management in A Cloud Environment Smita Vijayakumar.
th IEEE International Conference on Sensing, Communication and Networking Online Incentive Mechanism for Mobile Crowdsourcing based on Two-tiered.
Evaluation of Mobile Interfaces
How to Build Smart Appliances?
C7: Complex Event Processing
Anindya Maiti, Murtuza Jadliwala, Jibo He Igor Bilogrevic
Food Inventory Tracker
Presented by Xiaoyu (Veronica) Liang
Mole: Motion Leaks through Smartwatch Sensors
Presentation transcript:

1 i-Care Project Dietary-Aware Dining Table: Observing Dietary Behavior over Tabletop Surface Keng-hao Chang, Shih-yen Liu, Toung Lin, Hao Chu, Jane Hsu, Polly Huang, (Cheryl Chen) i-space Laboratory National Taiwan University

2 What is it? A dietary-tracker built into an everyday dining table –Track what & how much you eat over tabletop surface Motivation –We are what we eat –Food choices affect long-term & short-term health Show a demo video

3 Smart Everyday Object Digital-enhanced everyday objects –Provide digital services Support natural human interactions –Natural human interactions = inputs to digital services Goals –Providing digital services without (users) operating digital devices → better usability –Human-centric computing: technology adapting to users rather than users adapting & learning about technology

4 Outline for Reminder of Talk Related work Approach Assumptions & Limitations Design & Implementation Experimental Evaluation Future work

5 Related Work Dietary trackers –Shopping receipt scanner (GaTech) –Chewing Sound (ETH) –My food phone (startup) Intelligent surfaces –Load sensing table (Lancester) –Smart floor (GaTech, NTU) –Posture Chair (MIT) What’s new here? –Accuracy –Fine-grained tracking –Simultaneous concurrent interactions

6 Contribution claims It is a fine-granularity (automated) dietary tracker. –It can track multiple concurrent interactions from multiple individuals over the same tabletop surface. People usually don’t eat alone It is an enhanced loading sensing table.

7 General Approach RFID tags on food containers Two sensor surfaces on table –Each surface is made of cells –RFID reader surface Detect RFID(s) in each cell –Weighting surface (load cells) Measure weight change in each cell Track the food path from container(s) → container(s) → mouth using these two sensor surfaces

8 Assumptions (Limitations) Closed system rather than open system. –Food transfers among tabletop objects and mouths, no external objects and food sources Users identified by personal containers (personal plates and cups) Food containers tagged with RFID tags No cross-cell objects No leaning their hands on the table Not a mobile tracker

9 Single Interaction Example Bob pours tea from the tea pot to his personal cup, and drinks it Detect tea transfer from one container to another container 1)Identify the presence & absence of containers RFID tags on containers tag-food mapping 2)Track tea transfer Weight change detection Weight matching algorithm

10 Single Interaction Example Pour tea? Weight increases ∆ w 2. Bob pours tea from the tea pot to personal cup, and drinks it Pick up tea pot. RFID tag disappears Weight decreases ∆ w 1 Put on tea pot. RFID tag appears Weight increases ∆w 3 Pour tea! | ∆ w 3 - ∆ w 1 | ≈ ∆w 2

11 Single Interaction Example Bob pours tea from the tea pot to personal cup, and drinks it Pick up cup. RFID tag disappears. Weight decreases ∆w 1. Put on cup. RFID tag appears. Weight increases ∆w2. Drink tea? (only if no match) Amount | ∆w2 - ∆w1 |

12 Concurrent Interactions Example Bob pours tea & Alice cuts cake Pour tea? Cut cake? Weight change ∆ w Pour tea Weight increases ∆ w 1 Cut cake Weight decreases ∆w 2

13 Concurrent Interactions Example Multiple, concurrent person-object interactions –The larger the cell, the higher the possibility of concurrent interactions over a cell –Cell size = average size of container –Reduce the possibility of concurrent interactions over one cell

14 Design Architecture Tag-object mappings Behavior Inference Engine Event Interpreter Weight Change DetectorObject Presence Detector Weighing surface (weighing sensors) RFID Surface (readers) Applications (Dietary-aware Dining Table) Common sense semantics Sensor Events Intermediate Events Dietary Behaviors

15 Inference Rule Dietary behaviorsBehavior Inference Rules Transfer(u, w, type)Weight-Change(Object-i1, Δ w1) ∩ ( Δ w1 0) ∩ Contains(Object-i1, type) ∩ Owner(Object-i2, u) ∩ (| Δ w1 + Δ w2 |< ε ) → Transfer (u, Δ w2, type) Eat(u, w, type)Weight-Change(Object-i, Δ w) ∩ ( Δ w<0) ∩ Contains(Object-i, type) ∩ Owner(Object-i, u) → Eat(u, - Δ w, type)

16 Experimental setup 2 Dining settings –Afternoon tea –Chinese-style dinner 2 Parameters –# of participants –Predefined vs. Random Sequence A Willy Keng-hao

17 Experimental Results ScenariosEvent StatisticsResults Dining Scenarios # Users Activity Sequence Time Duration (seconds) # of Dietary Behavior Average Activity Interval Behavior Recognition Accuracy #1 Afternoon tea 1Predefined % #2 Afternoon tea 2Predefined % #3 Afternoon tea 2Random % #4 Chinese- style dinner 3Random %

18 Predefined Activity Sequence Afternoon Tea (Single User) 1.cut a piece of cake and transfer it to the personal plate; 2.pour tea from the tea pot to the personal cup; 3.add milk to the personal cup from the creamer; 4.eat the piece of cake from the personal plate; 5.drink tea from the personal cup; 6.add sugar to the personal cup from the sugar jar. Afternoon Tea (Multi-users) 1.A cuts cake and transfers it to A’s personal plate; 2.B pours tea from the tea pot to B’s personal cup; 3.A pours tea to A’s personal cup while B cuts a piece of cake and transfers it to B’s personal plate; 4.A adds sugar from the sugar jar to A’s personal cup while B adds milk from the creamer to B’s personal up; 5.A eats cake and B drinks tea; 6.B eats cake from B’s personal plate while A drinks tea from A’s personal cup; 7.A pours tea from the tea pot to both A’s and B’s personal cups.

19 Activity Recognition Accuracy in Scenario #3 Dietary Behavior# of Actual EventsRecognition Accuracy Transfer event % Eat event %

20 Causes of Misses in Scenario #3 Causes of misses# of misses of transfer events # of misses of eat events Total Event interference within the weighing cell’s weight stabilization time 628 Weight matching threshold202 Slow RFID sample rate303 Touching table123 Total of misses12416

21 Dietary Behavior# of times Recognition AccuracyWeight Accuracy Transfer dish A events %68.42% Transfer dish B events %78.75% Transfer dish C events %79.19% Transfer rice events %81.88% Transfer soup events %80.16% Eat events %91.23% Activity Recognition Accuracy in Scenario #4

22 Causes of Misses in Scenario #4 Causes of misses# of misses of transfer events # of misses of eat events Total Segmented weight-change events505 Eating before transferring food to personal containers 5510 Weight matching ambiguity707 Touching table325 Slow RFID sample rate303 Total of misses23730

23 Conclusion It is a smart object and a smart surface It supports natural user interface It supports fine-grained dietary tracking at individual level It is about human-centric computing Accuracy can be improved further

24 Future Work Improving recognition accuracy Removing constraints (assumptions) Persuasive computing –Encourage balanced diet –Encourage proper amount of diet

25 Questions & Answers Thank You