====== Profile MMSE - pomiar 2 ======

  * Dane: statystyki opisowe (6 cech) + charakteryzacja kształtów roskładu profili (4 cechy: średnia, odchylenie, skośność i kurtoza z gęstości)

[[projects:psycho:mmse_probe2_profiles|Wizualizacja profili MMSE]]

===== Płeć =====



===== Klasyfikacja 2 klasowa =====

  * KLasy: przeskalowane wyniki testu < 11.3
  * Testy: GM + std + 10x5CV - wszystko poniżej baserate

==== Wizualizacja QPC ====

  >> w2=qpctrain(xn,double(c2),'plot','qpc','display','short');
  procedure     = qpc
  dataname      = data
  vectors       = 43
  features      = 10
  OptMethod     = gd
  learningRate  = 0.100000
  prototypes    = 0
  proto lr      = 0.000000
  eps           = 0.001000
  start init.   = 10
  end init      = 3
  multistart    = yes
  maxIterations = 1000
  qpc function  = @(wx,p)qpcfunction(x,ci,wx,[],func)
  function      = @(x)f_gauss(x,parameters.beta)
  beta          = 0.100000
  Performing 10 initiations - Gradient based optimization (MultiStart)
  Sprawdzic dokladniej czy dobrze
  5 initiations was killed
  Finish N = 120   QPC = 0.208580 [1 ]
     -0.4560   -0.1730   -0.3320   -0.4411   -0.3017   -0.2253   -0.2223   -0.2117    0.3252   -0.3399
  
  Finish N = 125   QPC = 0.207879 [5 ]
     -0.3491   -0.1533   -0.3375   -0.4421   -0.4247   -0.2325   -0.4004   -0.1394    0.2099   -0.2951
  
  Finish N = 165   QPC = 0.207839 [2 ]
     -0.2781   -0.0500   -0.3092   -0.4222   -0.3757   -0.3861   -0.3210   -0.1927    0.2781   -0.3722
  
  Finish N = 175   QPC = 0.207835 [6 ]
     -0.2780   -0.1134   -0.3430   -0.4539   -0.3963   -0.3691   -0.3521   -0.1420    0.2542   -0.2902
  
  Finish N = 180   QPC = 0.207927 [7 ]
     -0.4938   -0.0749   -0.3447   -0.4402   -0.3056   -0.2249   -0.3799   -0.1363    0.2378   -0.2731
  
  Best:   0.208580     -0.4560  -0.1730  -0.3320  -0.4411  -0.3017  -0.2253  -0.2223  -0.2117  0.3252  -0.3399
  ---------------Sumary--------------------------
  Initialization  1 was the best
  N     QPC      W
  0  0.2086      -0.4560  -0.1730  -0.3320  -0.4411  -0.3017  -0.2253  -0.2223  -0.2117  0.3252  -0.3399
  -----------------------------------------------
  procedure     = qpc
  dataname      = data
  vectors       = 43
  features      = 10
  OptMethod     = gd
  learningRate  = 0.100000
  prototypes    = 0
  proto lr      = 0.000000
  eps           = 0.001000
  start init.   = 10
  end init      = 3
  multistart    = yes
  maxIterations = 1000
  qpc function  = @(wx,p)qpcfunction(x,ci,wx,[],func)
  function      = @(x)f_gauss(x,parameters.beta)
  beta          = 0.100000
  Performing 10 initiations - Gradient based optimization (MultiStart)
  Sprawdzic dokladniej czy dobrze
  7 initiations was killed
  Finish N = 205   QPC = 0.128676 [2 ]
     -0.2283   -0.0745    0.1508    0.0456   -0.2454   -0.5509   -0.3700    0.3563    0.1016    0.5288
  
  Finish N = 235   QPC = 0.128780 [7 ]
      0.1028    0.0219   -0.2325   -0.1533    0.1983    0.4898    0.2170   -0.4285   -0.1401   -0.6179
  
  Finish N = 520   QPC = 0.065417 [5 ]
     -0.2907    0.1032    0.2324   -0.4789   -0.3177   -0.1452    0.4339   -0.1645   -0.4864    0.2183
  
  Best:   0.128780     0.1028  0.0219  -0.2325  -0.1533  0.1983  0.4898  0.2170  -0.4285  -0.1401  -0.6179
  ---------------Sumary--------------------------
  Initialization  7 was the best
  N     QPC      W
  0  0.1288      0.1028  0.0219  -0.2325  -0.1533  0.1983  0.4898  0.2170  -0.4285  -0.1401  -0.6179
  -----------------------------------------------


  scaterplot(xn*w2',double(c2))

{{projects:psycho:150123:mmse2_scale_raven_c2_qpc_scatterplot.png?700|}}

  bar(abs(w2(1,:)))

{{projects:psycho:150123:mmse2_scale_raven_c2_w1.png|}}