Skip to main content

Table 5 The total accuracy and Kappa index obtained from two Naïve Bayes models on 13 datasets (FCdb and 12 datasets that obtained from attribute weighting models)

From: Prediction of lung tumor types based on protein attributes by machine learning algorithms

Data Base

Bayes Kernel Accuracy

Naive Bayes Accuracy

Bayes Kernel Kappa

Naive Bayes Kappa

Rule

57.93%

48.03%

13.54%

25.30%

SVM

66.97%

77.35%

42.20%

63.30%

Uncertainty

58.21%

55.45%

14.33%

32.65%

Relief

66.74%

72.65%

42.94%

55.55%

PCA

54.39%

44.02%

19.52%

11.38%

Info Gain Ratio

61.24%

61.14%

25.22%

41.00%

Info Gain

69.32%

70.23%

44.63%

54.66%

Gini Index

65.68%

66.74%

38.20%

48.97%

Deviation

54.39%

44.02%

19.52%

11.38%

Chi Squared

63.18%

64.09%

37.20%

42.02%

FCdb

58.21%

14.30%

42.20%

32.60%

MR

70.00%

77.20%

50.84%

63.60%

SAM

61.20%

62.95%

26.95%

39.75%