SuperLectures.com

SPATIALLY-CORRELATED SENSOR DISCRIMINANT ANALYSIS

Classification and Pattern Recognition

Full Paper at IEEE Xplore

Presented by: Kush Varshney, Author(s): Kush Varshney, IBM T.J. Watson Research Center, United States

A study of generalization error in signal detection by multiple spatially-distributed and -correlated sensors is provided when the detection rule is learned from a finite number of training samples via the classical linear discriminant analysis formulation. Spatial correlation among sensors is modeled by a Gauss--Markov random field defined on a nearest neighbor graph according to inter-sensor spatial distance, where sensors are placed randomly on a growing bounded region of the plane. A fairly simple approximate expression for generalization error is derived involving few parameters. It is shown that generalization error is minimized not when there are an infinite number of sensors, but a number of sensors equal to half the number of samples in the training set. The minimum generalization error is related to a single parameter of the sensor spatial location distribution, derived based on weak laws of large numbers in geometric probability. The finite number of training samples acts like a budgeting variable, similar to a total communication power constraint.


  Speech Transcript

|

  Slides

Enlarge the slide | Show all slides in a pop-up window

0:00:16

  1. slide

0:00:27

  2. slide

0:01:12

  3. slide

0:03:01

  4. slide

0:03:43

  5. slide

0:04:59

  6. slide

0:05:59

  7. slide

0:07:00

  8. slide

0:08:14

  9. slide

0:09:15

 10. slide

0:10:31

 11. slide

0:11:28

     8. slide

0:11:41

    11. slide

0:12:03

 12. slide

0:13:24

 13. slide

0:15:02

 14. slide

0:16:07

 15. slide

0:16:23

    12. slide

0:16:30

    15. slide

0:17:29

 16. slide

0:17:42

 17. slide

0:18:19

 18. slide

0:18:52

 19. slide

0:20:24

    13. slide

  Comments

Please sign in to post your comment!

  Lecture Information

Recorded: 2011-05-25 16:15 - 16:35, Club B
Added: 22. 6. 2011 01:40
Number of views: 125
Video resolution: 1024x576 px, 512x288 px
Video length: 0:21:56
Audio track: MP3 [7.43 MB], 0:21:56