1 / 13

Embedded Action Detector to Enhance Freedom from Care

Embedded Action Detector to Enhance Freedom from Care. Ritsumeikan University Graduate School of Computer Science Data Engineering Laboratory Kyohei Koyama. Tagged World. Service !. Alert !. Ubiquitous Facility. Leaving Without locking. Coordination. Pocket Assistant.

bairn
Télécharger la présentation

Embedded Action Detector to Enhance Freedom from Care

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. Embedded Action Detector to Enhance Freedom from Care Ritsumeikan University Graduate School of Computer Science Data Engineering Laboratory Kyohei Koyama

  2. Tagged World Service! Alert! Ubiquitous Facility Leaving Without locking Coordination Pocket Assistant Leaving something behind Detect you going out Leaving the stove on Access Log RFID Tag

  3. Main Subject of This Presentation • The Pocket Assistant is an embedded computer, thus it only has limited power resources • The load can be huge, because the Pocket Assistant inspects all logs for each every access to the objects • The new way to reduce the load, keeping the accuracy of human activity recognition

  4. Definitions of Human Activity • The human activity is composed of three elements • Act : A Minimum unit of human activity i.e. an access to an object • Action : A sequence of acts • Behavior : A set of actions

  5. Definitions of Human Activity Going out Turning off TV Putting on shoes Pushing the power button Taking the remote control Taking a shoehorn Putting on shoes Taking shoes Having baggage Opening the door Having a bag Unlocking the door Undoing the door chain Turning the knob Behavior Action Act

  6. Bayesian Network • Bayesian Network methodology is applied for inspecting the access logs Look Probability Variable is Changed Shoes Knob Chain Result (Going outside) Probability Propagation Door Key Shoehorn The probability of user going outside is 78%! Observed Value is Assigned

  7. Initial Approach Detect a Behavior!! Term Candidates Second Stage Sequence First Stage Act Bayesian Network time Access Log

  8. Experiment • “Going outside” behavior • Two kinds of cases are prepared True case : When the user go outside False case : When it looks like the user is going outside, but actually staying home • 324 cases have been sampled in total

  9. Ideas from Experiment (Threshold Value) True Cases Threshold Value False Cases

  10. Ideas from Experiment (Key Event) Shoes Shoehorn Shoes Lock Graph 2 Graph 1 Lock Key BN1 BN2 Shoes BN3 BN4 Graph 4 Graph 3

  11. Ideas from Experiment (Key Event) • The occurrence probability does not change dramatically when accesses other than the key event occur • It is reasonable to calculate the probability only when the Key Event occurs The Key Event is effective to reduce the number of calculation for the probability of the Bayesian Network

  12. Revised Approach Initial Approach Term Sequence Bayesian Network Detection of Key Event Detection of Key Event Trigger Trigger time Access Log Layoff (0.5~1.0sec) Layoff (0.5~1.0sec)

  13. Evaluation The revised approach reduces the number of calculation by 14.8% compared with the initial approach

More Related