Citron : Context Information Acquisition Framework on Personal Devices

Distributed Computing Laboratory Waseda University

Tetsuo Yamabe, Ayako Takagi, Tatsuo Nakajima

Outline

1.  Introduction 2.  Muffin 3.  Sensors on Muffin 4.  Context acquisition on Muffin 5.  Citron 6.  Sample application 7.  Experiments result 8.  Conclusion and future direction

Introduction

•  It is expected that personal devices acquire a perceptual ability and recognize a user’s context information. –  Why personal devices?

•  Tight partnership with a user •  Connectivity to a user and context-aware services

–  How they recognize? •  Incorporate sensors and analyze acquired values

"  What type of sensors are useful to acquire a user’s context ? "  What is required in the process of context acquisition ?

•  We have developed Muffin, which is a prototype of a sensory personal device, to investigate sensors’ characteristics and data processing process.

•  Also, we have developed a framework named Citron… –  to utilize the advantage of multiple sensory personal device. –  to implement context analysis modules on it.

•  By running context-aware application on top of Citron, we present… –  how Citron bring out Muffin’s capability –  possibilities of personal devices fabricated with multiple sensors

What is Muffin??

•  Muffin is a prototype of the future sensor device for research on ubiquitous computing area. –  Developed by a collaboration work with Nokia Research Center –  Sensing capability for context-awareness

•  15 kinds of sensors in a PDA size box –  Linux OS –  Wired / Wireless interface

•  Bluetooth, IrDA, WLAN •  USB, Serial port, PCMCIA slot

Sensors on Muffin

•  Sensors on Muffin are roughly divided into 4 categories.

Front camera RFID reader

Pulse sensor

Skin temperature sensor 3D Linear accelerometer

Grip sensor

GPS

Skin resistance sensor

Barometer Compass / Tilt sensor

Rear camera

Air temperature sensor Relative humidity sensor Alcohol gas sensor

Ultrasonic range finder

Microphone

•  Environmental sensors •  Physiological sensors •  Motion/Location sensors •  Other sensors

Context acquisition on Muffin

•  We performed some experiments about context acquisition on Muffin; and found that… "   Validity of sensor value and analysis algorithm changes

frequently according to a user’s taking style. "   Some sensors’ characteristics require long term data logging.

Muffin Waist-mounted Held Held User Not watching Not watching Watching Pulse invalid valid valid

Standing or not ? invalid invalid valid

Top side

"   Multiple sensors enable reliable context acquisition by analyzing information from multiple aspects of view.

"   We should reflect the already recognized context… –  to select an appropriate set of sensors and analysis algorithms –  by modeling relationships among other context → Middleware support should be offered to application

programmers.

Held or not

Under watch or not

Activity(1 - 5)

Walking or running or not

Accel Skin resistance Ultra range finder

Activity(1- 5)

Moving or stop

Citron: architecture overview

•  A framework for context acquisition on sensory personal devices –  Citron Worker

•  Context analysis module •  Work independently •  Enable parallel context processing

–  Citron Space •  Shared space for storing context •  Core module of a blackboard model

•  Citron supports … –  Hierarchical context abstraction –  Context analysis from multiple

aspects of view –  Switching analysis module

according to context

Citron Space Citron Worker

Citron API

Application

put

read

Sensor

Context

Input - Sensor data - Context

Output - Analyzed context

Sample application : StateTracer

•  StateTracer displays the track of walking route with user’s state in real time. –  Not only walking or not, but also walking speed and resting time –  No location systems or infrastructure

At rest Walking

Working modules on StateTracer

Top_side

Orientation

Walking (Threshold)

Orientation : “N”, “NW”, “W”, “SW”, “S”, “SE”, “E”, “EW” Walking_State : “walking”, “resting” Walking_Speed : “0”, “1”, “2”, “3”, “4”

Holding

Watching

accel_x, accel_y, accel_z skin resistance compass

Activity

Walking (FFT)

Walking (state, speed)

Citron worker

Sensor

Can detect speed, but time consuming

Can not detect speed, but responsive

Experimental result

Stop point

Walk fast

Walk slowly

Start and Goal

Case 1 Case 2 Case 3

•  Walk around a lot (50m x 100m) –  Change walking speed –  Two stop point

•  Change working analysis modules –  Case1 : Walking (threshold) worker only –  Case2 : Walking (FFT) worker only –  Case3 : Both workers

Conclusion and future direction

•  Coordination among analysis module with sharing context information is flexible and effective way to acquire context on Muffin. –  Bring out capability of Muffin and its perceptual ability –  Enable reliable context acquisition in practical usage

•  We continue to research on context acquisition on personal devices based on Muffin and Citron. –  Rearrange placement of sensors and reshape its form –  Distribute sensors as a wearable sensor device –  Coordination with remote resource over network

Cookie : Coin size wearable sensor

•  Size –  24mm x 22mm x 8~10mm –  Almost same size as 10 Yen coin.

•  Three stacked board structure –  Main board –  Sensor board –  Extension board

•  Running time –  About 1 hr (with 2032 size battery)

•  Sensor –  Compass –  Ambient Light Sensor –  Pulse sensor –  Skin temperature sensor –  GSR sensor –  UV sensor –  RGB color sensor –  3-Axis Linear Accelerometer –  Vibration motor