blob: e66c66c164acc80708c1b5fd6a707e7207648c03 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
|
// SPDX-License-Identifier: GPL-3.0-or-later
#include "KMeans.h"
#include <dlib/clustering.h>
void KMeans::train(SamplesBuffer &SB, size_t MaxIterations) {
std::vector<DSample> Samples = SB.preprocess();
MinDist = std::numeric_limits<CalculatedNumber>::max();
MaxDist = std::numeric_limits<CalculatedNumber>::min();
{
std::lock_guard<std::mutex> Lock(Mutex);
ClusterCenters.clear();
dlib::pick_initial_centers(NumClusters, ClusterCenters, Samples);
dlib::find_clusters_using_kmeans(Samples, ClusterCenters, MaxIterations);
for (const auto &S : Samples) {
CalculatedNumber MeanDist = 0.0;
for (const auto &KMCenter : ClusterCenters)
MeanDist += dlib::length(KMCenter - S);
MeanDist /= NumClusters;
if (MeanDist < MinDist)
MinDist = MeanDist;
if (MeanDist > MaxDist)
MaxDist = MeanDist;
}
}
}
CalculatedNumber KMeans::anomalyScore(SamplesBuffer &SB) {
std::vector<DSample> DSamples = SB.preprocess();
std::unique_lock<std::mutex> Lock(Mutex, std::defer_lock);
if (!Lock.try_lock())
return std::numeric_limits<CalculatedNumber>::quiet_NaN();
CalculatedNumber MeanDist = 0.0;
for (const auto &CC: ClusterCenters)
MeanDist += dlib::length(CC - DSamples.back());
MeanDist /= NumClusters;
if (MaxDist == MinDist)
return 0.0;
CalculatedNumber AnomalyScore = 100.0 * std::abs((MeanDist - MinDist) / (MaxDist - MinDist));
return (AnomalyScore > 100.0) ? 100.0 : AnomalyScore;
}
|
