1 / 8

Class 1

Illustration of unbalanced data. Class 1. Attribute values which in reality define class 1. Class 2. Attribute values which very often arise in class 1, but does not define class 1. Attribute values which in reality define class 2.

jade-nunez
Download Presentation

Class 1

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. Illustrationofunbalanced data Class 1 Attributevalueswhich in realitydefineclass 1 Class 2 Attributevalueswhichveryoftenarise in class 1, butdoesnotdefineclass 1. Attributevalueswhich in realitydefineclass 2 This part is muchbigger in the test set and real life.

  2. Clusters K-means K=3 Cluster 2 Cluster 1 (185) (153) 27 135 76 48 50 1 Cluster 3 (160) 13 10 Classified As: Good, Guard Down 139 Good Bad

  3. By Victoria, October 20 Good: 141 Good, Guard Down: 171 Bad: 183 Total: 496 kicks

  4. By Svenn, November 9 Good: 12 Good, Guard Down: 26 Bad: 18 Total: 56 kicks

  5. By Victoria, November 8 Good: 15 Good, Guard Down: 10 Bad: 19 Total: 44 kicks

  6. Right shoulder, up-down, frame 1 1 Right shoulder, front-back, frame 1 2 Good Kick 3 Right shoulder, front-back, frame 6 Good Kick Guard Down 4 Attribute 250 Attribute 251 Bad Kick 163 Attribute 322 164 Attribute 323 LeftKnee, front-back, frame 6

  7. Sorry, this one’s not in original PP format, If you want to customize it I’d advise To edit the previous slide.

  8. Iteration 3 Generate models and test on Data set 2. Just MLP + Data set 1 AdaBoostM1 84% AdaBoostM1 + Data set 1 80% Just MLP + Data set 1 + Data set 3 + 89% AdaBoostM1 + Data set 1 + Data set 3 86%

More Related