workshop on smart object systems dietary-aware dining table – tracking what and how much you eat...
DESCRIPTION
Workshop on Smart Object Systems The food tracking table Track food consumption of multiple users over a table by –Identify food items by RFID-tagged containers –Track food transfers by monitoring weight changes over a weighting surfaceTRANSCRIPT
Workshop on Smart Object Systems
Dietary-Aware Dining Table –Tracking What and How Much
You EatKeng-hao Chang, Shih-yen Liu,
Jr-ben Tian, Hao-hua Chu, Cheryl Chen
National Taiwan University
Workshop on Smart Object Systems
Why Dietary-Aware Dining Table
• We are what we eat.– Our everyday food choices affect our long-term
and short-term health.
Workshop on Smart Object Systems
The food tracking table• Track food consumption of multiple users
over a table by– Identify food items by RFID-tagged containers– Track food transfers by monitoring weight
changes over a weighting surface
Workshop on Smart Object Systems
Related work• Lancaster’s load sensing table
– Objective: track object’s location over the table– Method: track the object by its center of weight
• Dietary-aware dining table– Objective: monitor food consumptions over the
table– Method: monitor the food path by weight
transfer detection
Workshop on Smart Object Systems
How does the magic surface work?
Two examples
Workshop on Smart Object Systems
Example Scenario 1 (1/2)
Pour tea?•Weight increases w2.
• Bob pours tea from the tea pot to personal cup, and drinks it
Pick up tea pot.• RFID tag disappears• Weight decreases w1
Put on tea pot.Pour tea!• RFID tag appears• Weight increases w1-w2
Workshop on Smart Object Systems
Example Scenario 1 (1/2)• Bob pours tea from the tea pot to personal
cup, and drinks it
Pick up cup.• RFID tag disappears.• Weight decreases w1.
Put on cup.Drink tea? (only if no match)• RFID tag appears.• Weight increases w2.
Workshop on Smart Object Systems
Example Scenario 2 (1/2)• Bob pours tea & Alice cuts cake
Pour tea?Cut cake? • Weight change w
Pour tea• Weight increases w1
Cut cake• Weight decreases w2
Workshop on Smart Object Systems
Example Scenario 2 (2/2)• Multiple, concurrent person-object
interactions– The larger the cell, the higher possibility of
concurrent interactions over a cell– Cell size ≈ average size of container– Reduce the possibility of concurrent
interactions over one cell
Workshop on Smart Object Systems
System Archietecture• Bottom-up event triggered inference, JESS
• Cake transfer from share plate to personal plate
• Share plate weight decrease w• Personal plate weight increase w
• Share plate on cell j1• cell j1 weight decrease w • personal plate on cell j2• cell j2 weight increase w
Workshop on Smart Object Systems
Conclusion & Future work• Simple prototype automatically tracks what
and how much each individual eats.• Identify users other than by the personal
plates• The reliability of the system
– Weight matching method– Weight increase from the world outside of the table
• Cross cell problem• Further reliable way to infer food path • Build LEGO like component
Workshop on Smart Object Systems
Thank you• Any question?
• If you have further question, please email me: Keng-hao Chang ([email protected])