-- TomasCap - 25 Aug 2017 Here I'll put the presentation for MSU Meeting

Start presentation

Slide 1: Look for the best variable using MC

  • An analysis was done in order to seen which variables are the best when all variable in the HAWC data stream were used.

Ranking Using MC

Slide 2: Choose the best variable

  • The first plot show the variables that have at least one ranking point with a value less or equal to 2. The second is the same but it has a value less or equal to 4.
Variable that have at least one ranking point with a value less 3 Variable that have at least one ranking point with a value less 5

Slide 3: New Network Training using Real Data

Three networks were trained using Real Data:
  • Using 15 inputs:

  • Using 4 inputs:
    • Compactness
    • rec.PINC
    • rec.LDFAmp
    • rec.LDFChi2

  • Using 6 inputs:
    • Compactness
    • rec.PINC
    • rec.LDFAmp
    • rec.LDFChi2
    • rec.SFCFChi2
    • rec.gammaleLLH

Slide 4: Conditions

  • Real data were used to training and verification.
    • /data/scratch/userspace/pretz/scrappy-platypus-optimization/

  • Both stages were applied the following cuts:
    • rec.coreFideScale < 100 [Events are inside of the HAWC ].
    • rec.CxPE40 > 0.

  • Crab maps were made using the month: January and February 2017
    • /data/archive/hawcroot/data/hawc/reconstructed/hawcprod/v2.02.02/config-38125/reco_xcdf/

Slide 5: Real data vs MC

In the training stage, I should apply a cut in Energy

Comparative of the NN training with 15 inputs when MC and Real data were used Comparative of the NN training with 15 inputs when MC and Real data were used -- NN/SC

Slide 6: Look the maps in Bin 0

Significance maps of Crab nebula using the Networks trained

Slide 7: Ranking using real data

  • I don't know why rec.nTankAvail have a good ranking. Maybe it has different value in both files (MC as signal and Real data as Bkg)
Variable that have at least one ranking point with a value less 3 using real data

Slide 8: Weekly goals

  • Work on the version 2 of disMax
  • Read information about BDT
  • Train a BDT with 15 inputs
  • Research why don't have a better result when I use real data (Maybe I have a better result if I apply one cut in Energy)

Topic attachments
I Attachment Action Size Date Who Comment
15MCAndRDCom.pngpng 15MCAndRDCom.png manage 56.5 K 28 Aug 2017 - 17:20 TomasCap Comparative of the NN training with 15 inputs when MC and Real data were used -- NN/SC
15MCAndRDCom_MaxSig.pngpng 15MCAndRDCom_MaxSig.png manage 57.1 K 28 Aug 2017 - 17:21 TomasCap Comparative of the NN training with 15 inputs when MC and Real data were used
SignificanceMapsComparation.pngpng SignificanceMapsComparation.png manage 1327.2 K 28 Aug 2017 - 17:22 TomasCap Significance maps of Crab nebula using the Networks trained
allvariable.pngpng allvariable.png manage 147.9 K 28 Aug 2017 - 16:36 TomasCap RankingUsingMC
thebest2.pngpng thebest2.png manage 44.2 K 28 Aug 2017 - 16:40 TomasCap Variable that have at least one ranking point with a value less 3
thebest2RD.pngpng thebest2RD.png manage 65.8 K 28 Aug 2017 - 18:32 TomasCap Variable that have at least one ranking point with a value less 3 using Real data
thebest4.pngpng thebest4.png manage 55.0 K 28 Aug 2017 - 16:42 TomasCap Variable that have at least one ranking point with a value less 5
Topic revision: r3 - 28 Aug 2017, TomasCap
 

This site is powered by FoswikiCopyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding Foswiki? Send feedback