1 / 13

Location and Activity Tracking with the Cloud

Location and Activity Tracking with the Cloud. Taj Morton, Alex Weeks, Samuel House, Patrick Chiang, and Chris Scaffidi School of Electrical Engineering and Computer Science Oregon State University. Aging in place. Do the math Nursing home ~ $250/day per person

ryo
Télécharger la présentation

Location and Activity Tracking with the Cloud

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Location and Activity Tracking with the Cloud Taj Morton, Alex Weeks, Samuel House, Patrick Chiang, and Chris Scaffidi School of Electrical Engineering and Computer Science Oregon State University

  2. Aging in place • Do the math • Nursing home ~ $250/day per person • Assisted living communities ~ $115/day • In-home health aides ~ $20/day • Objective: help people live at home as long as possible • Summon health aides when needed Introduction Contribution  Discussion

  3. But how can we detect when home aides are needed? • Much work exists on monitoring health with sensors • E.g., monitoring gait to detect… • Decline in cognitive ability • Decline in proprioception • Increase in risk of falls • Decrease in general fitness level • Decrease in cardiovascular health • Increase in risk of depression (… as well as monitoring with other sensors) Introduction Contribution  Discussion

  4. Prior work: High-accuracy gait monitoring with IMU+RFID • Attach inertial monitoring unit (IMU) to shoe • IMU monitors gait using accelerometer • Obtains fiducial updates from nearby RFIDs (e.g., RFIDs placed on doorways) • Excellent capabilities • Accuracy of 47 cm • Cost of $100 • Size of 4cm Introduction Contribution  Discussion

  5. Advantages of IMU+RFID sensor over existing technology Introduction Contribution  Discussion

  6. Challenge and approach • Needed: a means for the IMU+RFID sensor to send data out of the home • Other gait sensing technologies also require a similar means of transmitting data to facilitate remote monitoring • Approach: • Transmit data from sensor to a cell phone via bluetooth • Transmit data from cell phone to cloud via wireless Introduction  Contribution Discussion

  7. Overall system architecture Introduction  Contribution Discussion

  8. Software architecture Cloud-based servers Amazon SimpleDB Data processor (stores data) Data upload client (cell phone app) Data storage and access objects Location analysis (and gait if needed) Web browser Visualizer service Other applications Data sharing service Introduction  Contribution Discussion

  9. Visualization currently supported Introduction  Contribution Discussion

  10. Low-latency (< 2 seconds) up to ~ 2.1k data samples per second • ~ 300 samples per second (gyro+accel, total) for high-resolution tracking • Lower-resolution tracking requires lower sampling rates Introduction  Contribution Discussion

  11. Key design advantages • Cell phone app as well as most of our software components on the cloud are “sensor-agnostic” • Can forward and store any data that we send to it • Modular design to facilitate adding new analyses • In contrast to existing systems on the cloud that can only store data for you (so you need to compute elsewhere) • Full parallelization among users • Number of users is directly proportional to the number of servers allocated (linear scalability) Introduction  Contribution  Discussion

  12. Future directions • The sensor • Improved accuracy (using an environment model) • Reduced power consumption and size (integrated circuit) • Integrate with other wearable sensors • The cloud • Improve scalability by further optimizing algorithms • Provide additional analyses and visualizations • Integrate protection for security and privacy • Applications • Test reliability with long-term field study • Use system as a tool for health monitoring studies Introduction  Contribution  Discussion

  13. Thank you… • To EMBC for this opportunity • To you for your interest Questions? Introduction  Contribution  Discussion

More Related