Full-Band GSM Fingerprints for Indoor Localization Using a Machine Learning Approach
Table 1
Percentage of correct radio fingerprint classifications on the 4 carrier sets described in the text. Figures quoted are averages and standard deviations over 10 randomly selected validation sets. All classifiers achieve their best performance when all 488 carriers are included. The most effective classifier for this case is the linear SVM.
Fingerprint Type
Classifier
Current Top 7
Top 7/Memory
35 Best Overall
All 488
(7 carriers)
(36–40 carriers)
(35 carriers)
(488 carriers)
Linear SVM
71.3 ± 7.2
84.6 ± 3.6
90.4 ± 3.5
97.8 ± 1.5
Gauss. SVM
w/o PCA
72.2 ± 3.6
89.2 ± 2.9
93.2 ± 3.4
w/PCA
71.8 ± 3.2
85.6 ± 5.3
92.0 ± 3.0
96.4 ± 1.5
Linear Perceptron
66.9 ± 4.1
73.2 ± 5.1
79.7 ± 5.1
94.4 ± 2.6
MLP (one versus all)
w/o PCA
66.9 ± 7.1
87.2 ± 3.3
91.8 ± 3.4
w/PCA
68.1 ± 3.4
87.5 ± 4.5
89.6 ± 2.5
95.7 ± 2.1
MLP (multiclass) sigmoids
w/o PCA
56.8 ± 7.1
80.4 ± 12.9
92.6 ± 3.2
w/PCA
66.4 ± 5.7
85.1 ± 9.5
89.4 ± 3.6
96.1 ± 1.1
MLP (multiclass) softmax
w/o PCA
64.3 ± 7.5
85.7 15.8
91.2 4.2
w/PCA
67.7 ± 5.7
88.2 3.9
90.4 3.1
96.6 2.4
K-NN
5 59.33.5
26 85.13.0
20 93.32.1
20 94.91.9
1-NN
58.1 ± 5.2
74.7 ± 3.7
86.0 2.9
87.2 2.8
GP ( = 5 dB)
78.8 ± 3.7
—
SVM and K-NN can have < 7 carriers if some did not show up in the training set. Small training set size precludes training a nonlinear classifier due to Cover’s theorem [13]. Best result obtained using the first 4 principal components. Gaussian process is equivalent to 1-NN for fixed input vector length.
