Xiaofan Jiang, Chieh-Jan Mike Liang, Kaifei Chen, Ben
Zhang, Jeff Hsu
Jie Liu, Bin Cao, and Feng Zhao
Microsoft Research Asia
20120730-Neight
Outline









MOTIVATION
PROXIMITY ZONE
Empirical Definition
EVALUATION OF EXISTING TECHNOLOGIES
LIVESYNERGY PLATFORM
EVALUATION OF LIVESYNERGY
APPLICATION DEPLOYMENT
CONCLUSIONS
Motivation

 To make applications intuitive to human users, the
discovered objects in the environment must be
within the personal interaction sphere
 Computer automatically wake up
 Refrigerator change its user interface
 Many typical low power communication
technologies, (Bluetooth, ZigBee) have difficulties
maintaining robust communication zones
Contributions

 propose methodologies and systematically compare
the proximity zones created by various wireless
technologies(BLE, ZigBee, and RFID reader)
 Design, Implement, and Evaluate a magneticinduction based wireless proximity sensing platform
 Deploying LiveSynergy in an real-world application
PROXIMITY ZONE

 Boundary sharpness:
boundary of proximity zone should be binary
 Boundary consistency:
detection should be consistent over time
PROXIMITY ZONE

 Obstacle penetration:
Beaconing node and listening node can be mobile
and against obstructions
 Additional metrics:
1. Range and geometric shape of zones
2. Beaconing frequency achievable
3. Power consumption
4. Form-Factor of the mobile tag
5. Cost of overall system
Classification of Points

 Broadcasts at fixed frequency f (α packets ∈ (𝑡, 𝑡′) )
 P = a point in space at a distance of (𝑃𝑥 , 𝑃𝑦 , 𝑃𝑧 ) from
the beacon
Classification of Zones

 white/grey boundary:
{P | Color(P, t, t’) = white}
{P | Color(P, t, t’) = grey}
𝑓𝑤 𝑥 > 0 if x∈ 𝑃𝑤 , 𝑓𝑤 𝑥′ < 0 if x’∈ 𝑃𝑔
𝑔
𝑔
𝑓𝑤 𝑥 = 0 represents the decision boundary
𝑔
 grey/black boundary:
𝑓𝑔 𝑥 > 0 if x∈ 𝑃𝑔 , 𝑓𝑔 𝑥′ < 0 if x’∈ 𝑃𝑏
𝑏
𝑏
Three proximity zones

Proximity Zones

Questions?
Classifier

 Use support vector machines (SVM) as the classifier
seeks maximum-margin hyperplane to separate two
classes
 w and b are the parameters to define the hyperplane
to separate the two classes.
Classifier

 Two user-definable parameters:
 Error tolerance:
- Smooth boundary vs. non-smooth boundary
- Tradeoff between training loss and regularization
- Cost parameter C
 Strictness:
-Expect the white zone and the black zone contain no
grey points
-Related to error tolerance but non-symmetry
Classifier

• Cost parameter
C: the cost of false positive
C’: the cost of false negative C’
• Strictness parameter:
Kernel Trick

 RBF kernel as the kernel function
 Classifier:
 𝜑 𝑥 is the feature mapping function for RBF kernel
Matrix

 Size:
Size of the white and grey zone, which can be computed
numerically based on the boundaries.
 Boundary sharpness:
 Fitness:
How well the zone boundaries fit the data, or a confidence
measure of the proximity zone classification.
Classifier

Questions?
Boundary Sharpness
and Consistency

 Hardware setup:
• TI CC2540 BLE dev boards (transmitting on 2.4 GHz
at 0 dBm),
• A pair of TelosB motes with 802.15.4-compliant TI
CC24240 radio(transmitting on 2.4 GHz at 0 dBm)
• A Impinj Speedway R1000 RFID reader (transmitting
on 902 MHz at 8 dBm)
Boundary Sharpness
and Consistency

 Parameters:
• packet reception data is collected over a period of
200 seconds
• WPRR using a windows size of 3 seconds and 𝜀 = 0
• Strictness parameter = 0.99
 Results:
Boundary Sharpness
and Consistency

Human Obstacle
Penetration

 The user carries the receiver in the right pants pocket
- calculate PRR from 500 packets as the user changes
the body orientation by 90° each round at each distance
Additional Metrics

 Signal propagation and geometry:
RFID antennas usually have a radiation angle less than
180 degrees
 Form Factor and Costs:
RFID can produce a more consistent and smaller grey
zone
802.15.4 and BLE have advantages in both form factor
and costs.
Evaluation

Questions?
LIVESYNERGY
PLATFORM

 Pulse Transmitter: (use AC power)
Four primary hardware
 microcontroller (MCU) and radio
 magnetic transmitter tuned at 125kHz
 Energy metering
 mechanical relay for actuation.
LIVESYNERGY
PLATFORM

 Link Receiver: ( battery-powered)
Three primary hardware
9.2cm ×5.8cm × 2.3cm enclosure
• MCU and radio
• 3D magnetic coil
• wake up chip
Boundary Sharpness
and Consistency

Body orientation vs. distance

 human body has very little impact on the MI signal
propagation
Additional Metrics

 Geometry:
two dimensions extends to all directions, covering 360◦
 Range:
maximum range (i.e., radius) is around 5m
APPLICATION DEPLOYMENT

Diners enter the cafeteria from the entrance at the lower left corner at different times
Experment

 Each diner takes a different route and visits various
food counters on the way
 Recorded a video as the customers walk around the
cafeteria purchasing food.
- Use video timestamps
Result

Summary

 Values:
1. Propose methodologies and systematically compare
the proximity zones
2. Deploying LiveSynergy in an real-world application
 Future?
1. MI still can implement in mobile phone…