Table 7: Relative accuracy by algorithm based on the number of WAPs when training with border locations (part III).

#WAPsRandom
Tree
REP
Tree
SVMNN
NBC

4091.50
± 
3.76
92.50
± 
3.59
98.00
± 
1.00
97.00
± 
1.63
87.17
± 
1.83

588.33
± 
1.29
82.50
± 
4.17
68.17
± 
1.74
80.00
± 
2.98
80.50
± 
1.07

887.83
± 
1.83
92.17
± 
2.89
87.50
± 
2.71
86.33
± 
1.94
81.17
± 
1.07

1097.33
±  
1.53
93.33
±  
3.07
98.17
±  
0.50
92.17
±  
1.30
97.00
±  
0.67

1695.67
± 
3.00
92.83
± 
3.66
98.33
± 
0.75
95.17
± 
1.89
96.67
± 
1.05

2093.83
± 
3.66
93.83
± 
3.95
97.50
± 
0.83
94.67
± 
1.63
95.50
± 
1.30

3295.83
± 
4.43
92.83
± 
3.66
99.33
± 
0.82
98.50
± 
0.90
87.50
± 
1.54