Design of a Wearable Sensor Badge for Smart Kindergarten

1
Design of a Wearable Sensor Badge for Smart
Kindergarten

• Sung Park, Ivo Locher, Andreas Savvides, Mani B.
  Srivastava, Alvin Chen, Richard Muntz, Spencer
  Yuen
• University of California, Los Angeles
• ISWC, October 10, 2002

2
Wireless Networking and Computing Technology

• So far focus on richer person - person and
  person - computer interaction
• Cellular telephony
• Personal communications
• Wireless internet access to web services
• Future communication between people and their
  physical environment
• Mark Weisers vision
• Allow users to query, sense, and manipulate the
  state of the physical world
• Add a sense of real world to user interaction
  with computer systems
• Context-aware applications that exploit computing
  and networking infrastructure melded into the
  environment

3
Smart Kindergarten (SmartKG)

• Wireless networked sensors densely embedded in a
  kindergarten room
• create a problem solving environment that can is
  continually sensed in detail
• kids, toys, blocks, playthings, classroom
  woodwork
• Background computing data management
  infrastructure for on-line and off-line sensor
  data processing and mining
• Sensor information used for
• assessment of student learning
• problem solving tasks that are adaptive and
  reactive
• services beneficial to teacher and students

4
Smart Kindergarten (SmartKG) System Architecture
and iBadge
iBadge Speech Processing Wireless
Communication Localization Orientation
Sensing Environment Sensing
Networked Toys
5
Smart Kindergarten (SmartKG) System Architecture

• Sensing Infrastructure-
• A Suite of sensors that collects the context
  information in SmartKG
• video camera, microphone, motion detectors, and
  iBadge
• Middleware Infrastructure Sylph
• provides various services that process, store,
  fuse, manage, and present the data collected from
  Sensing Infrastructure
• manages the interaction between applications and
  other higher-level services such as speech
  recognition, sensor data storage and sensor data
  browsing

6
iBadge Wearable Sensor Badge System

• Wearable Design worn by kindergarten children
  to monitor the context information of the student
• Sensors - Ultrasound Transceiver, Accelerometer,
  Magnetometer, Temperature, Humidity, Light,
  Atmospheric Pressure

7
iBadge Architecture

• ATMega128L, Wireless Communication Unit, Speech
  Processing Unit, Power Management and Tracking
  Unit, Localization Unit, Orientation and Tilt
  Sensing Unit, Environment Sensing Unit

8
iBadge Functional Units

• Main Processing Unit
• ATMega128L Microcontroller from Atmel
• Responsible for power management, localization,
  and interfaces different functional units
• Localization Unit
• Relative and absolute positioning
• responsible for obtaining precise 3D location of
  iBadge in the classroom
• estimates its 3D location using an ad-hoc
  localization process
• Speech Processing Unit
• Consists of TI DSP and CODEC
• Performs speech codec and front end processing of
  the real time speech of the children
• Two modes (Simple Coding or Front End Processing)
  of operation based on power requirements and user
  request.

9
iBadge Functional Units (Continued)

• Power Management/Tracking Unit
• Battery Monitors (DS2438) keep track of energy
  usage of various functional units
• CMOS switches provides control to turn on/off
  different part of the circuits
• Orientation/Tilt Sensing Unit
• Accelerometer combined with magnetometer provides
  the orientation of the children with earths
  magnetic field
• Environment Sensing Unit
• Temperature, Humidity, Atmospheric Pressure, and
  Light Intensity

10
The Sylph Middleware
11
The Sylph Middleware

• Modular, Layered Design
• Sensor module
• Service discovery module
• Proxy core
• Query Language
• READ temperature EVERY 30 seconds FOR 1 hour
• Sensor Stream Processing

12
Sylph Components

• Sensor Module
• Strong Abstraction Barrier
• Derived from IEEE 1451 Transducer Electronic Data
  Sheet (TEDS)
• Metadata - name, manufacturer, etc.
• Attributes - device status, sampling interval,
  etc.
• Data available data, return types
• Service Discovery Module
• Device Proxy
• Common Service Discovery Mechanisms (e.g., Jini)

13
Sylph Components (Continued)

• Proxy Core
• Device Manager
• Sensor Proxy
• Service discovery
• Layered functionality (e.g., buffering)
• Query Processor
• Query parsing
• Directed graph of stream operators
• Query optimization
• Query Distribution - Gateways

14
Localization Subsystem

• iBadges equipped with a 40KHz ultrasonic receiver
  circuit
• Allows high precision distance measurements to
  other devices in its immediate environment
• Ad-Hoc Flavor
• Many devices can collaborate
• together to solve a problem
• that none of the devices can
• solve individually
• When distance measurements
• are available, track the iBadge
• using dead-reckoning

15
Localization Process

• Atomic Multilateration
• Collaborative Multilateration
• iBadges and other nodes collaborate with each
  other to form a non-linear optimization problem
  and solve it efficiently in a fully distributed
  manner

Known Location
Unknown Location
16
Distributed Computation

• Use a distributed approximation to estimate node
  locations
• Nodes organize themselves in to groups that
  provide well-constrained configurations
  collaborative subtrees
• Use known beacon information to obtain an initial
  estimate of location
• Refine initial estimates using iterative least
  squares
• Each node performs a multilateration using only
  next-hop neighbor information in the context of a
  collaborative subtree
• Much less computation, similar result, fully
  distributed operation

17
Distributed Computation
1. Obtain initial estimates 2. for each
unknown 2.1 Perform Atomic Multilateration
if the neighbor is beacon use
beacon location else use current
position estimate 2.2 Broadcast new
location estimate 3. Repeat step 2 every time a
new position estimate is received until
the convergence criteria are met
The unknown nodes need to perform their atomic
multilateration in the same order, driven by a
Distributed Depth First Search algorithm gt
local computations, follow a global gradient
18
Convergence Process

• From SensorSim
• simulation
• 40 nodes, 4 beacons
• IEEE 802.11 MAC
• 10Kbps radio
• Average 6 neighbors
• per node

19
Gains in Computation Overhead

• Computation cost based on MATLAB FLOPS outputs
• Result difference between centralized and
  distributed is very small
• Mean 0.015 mm, Standard Deviation 0.0054mm
• A group of nodes can collectively solve a
  non-linear optimization problem than none of the
  nodes can solve individually.

20
Summary

• SmartKG constructs the context information of the
  classroom based on information from sensing
  infrastructure (iBadge) and middleware
  infrastructure (Sylph)
• iBadges wearable platform provides detailed
  information about the wearer
• Precise localization is one key research challenge

21
Conclusions

• Node development completed, finishing firmware
  integration
• Still a lot of things to be learned from
  programming and using the system
• Success defined by proving the usefulness of such
  a system to educators
• Lots of privacy issues are still pending
• For more information visit
• http//nesl.ee.ucla.edu/projects/smartkg
• Thank you!