In the paper Figure 7, we claimed:

1
In the paper Figure 7, we claimed the best
value for R depends on the amount of training
data available. Here are the results for
Gun-Point Dataset and another dataset, Two_ Pat,
which we randomly pick half size instances
repeatedly. The observation is that with fewer
objects in the dataset, the accuracy decreases
and peaks at larger window size.
Gun Point
Two_Pat
2
In the paper Table 4, we list the datasets used
in the paper, here we present additional datasets
and show all the experiments that could not fit
in the paper due the limit of space.
Name class features instances Evaluation Data type
JF 2 2 20,000 2,000/18,000 real
Letter 26 16 20,000 5,000/15,000 mixed
Pen Digits 10 16 10,992 7,494/3,498 real
Forest Cover Type 7 54 581,012 11,340/569,672 real
Iris 3 4 150 10-fold CV real
Ionosphere 2 34 351 10-fold CV real
Voting Records 2 16 435 10-fold CV Boolean
Australian Credit 2 14 690 10-fold CV 6 numerial/8 categorical
German Credit 2 24 1,000 10-fold CV real
Leaf 6 150 442 200/242 time series
Two_Pat 4 128 5,000 1,000/4,000 time series
Face 16 131 2,231 1,113/1,118 time series
3
JF, 2 classed, 20,000 instances, 2,000/18,000
4
Letter, 26 classes, 20,000 instances, 5,000/15,000
5
Pen digits, 10 classed, 10,992 instances,
7,494/3,498
6
Forest Cover Type, 7 classes, 581,012 instances,
11,340/569,672
7
100
90
80
70
accuracy()
RandomTrain
RandomTest
SimpleRankTrain
60
SimpleRankTest
DROP1
DROP2
50
DROP3
40
0
100
200
300
400
500
600
Number of instances seen before interruption, S
data instances
Australian Credit, 2 classes, 690 instances,
10-fold Cross Validation
8
100
90
80
accuracy()
70
60
50
0
50
100
150
200
250
300
Number of instances seen before interruption, S
100
100
90
90
80
80
accuracy()
70
Random Test
70
accuracy()
60
SimpleRank Test
RandomTrain
RandomTest
50
60
SimpleRankTrain
SimpleRankTest
0
50
100
150
200
250
300
DROP1
Number of instances seen before interruption, S
50
DROP2
DROP3
40
0
50
100
150
200
250
300
data instances
Ionosphere, 2 classes, 351 instances, 10-fold
Cross Validation
9
100
90
100
80
accuracy()
90
70
60
80
50
accuracy()
70
0
50
100
150
200
250
300
RandomTrain
RandomTest
Number of instances seen before interruption, S
60
SimpleRankTrain
SimpleRankTest
DROP1
50
DROP2
DROP3
100
40
0
20
40
60
80
100
120
90
data instances
80
accuracy()
70
Random Test
60
SimpleRank Test
50
0
50
100
150
200
250
300
Number of instances seen before interruption, S
Iris, 3 classes, 150 instances, 10-fold Cross
Validation
10
Voting records
100
accuracy()
90
0
50
100
150
200
250
300
350
Number of instances seen before interruption, S
100
90
80
70
accuracy()
RandomTrain
RandomTest
60
SimpleRankTrain
SimpleRankTest
DROP1
50
DROP2
DROP3
40
0
50
100
150
200
250
300
350
data instances
11
100
90
80
70
accuracy()
RandomTrain
60
RandomTest
SimpleRankTrain
SimpleRankTest
DROP1
50
DROP2
DROP3
40
0
100
200
300
400
500
600
700
800
900
data instances
German Credit, 2 classes, 1,000 instances,
10-fold Cross Validation
12
Two_Pat, 4 classes, 5,000 instances, 1,000/4,000
split
13
Leaf Dataset, 6 classes, 442 instances
14
Face dataset, 16 classes, 2,231 instances,
1,113/1,118 split