public void train(List<Sample> samples) {
BLEBeacon.setBLEBeaconIdsToSamples(bleBeacons, samples);
List<List<Sample>> samplesList = Sample.samplesToConsecutiveSamplesList(samples);
if (doHyperParameterOptimize) {
doHyperParameterOptimize = false;
trainWithHyperParameters(samplesList);
}
List<Sample> samplesAvaragedTrain = Sample.meanTrimList(samplesList, minRssi);
this.trainByAveragedSamples(samplesAvaragedTrain);
}
boolean isSingleFloor(List<Sample> samples) {
Set<Double> floorSet = new HashSet<>();
for (Sample s : samples) {
Location loc = s.getLocation();
double z = loc.getZ();
floorSet.add(z);
}
if (floorSet.size() == 1) {
return true;
} else {
return false;
}
}
protected void trainWithHyperParameters(List<List<Sample>> samplesListTrainParent) {
List<Sample> samplesAvaragedTrain = Sample.meanTrimList(samplesListTrainParent, minRssi);
this.train(samplesAvaragedTrain);
// Update active beacon list about actually observed beacons
Sample samplesAllAverage = Sample.mean(samplesAvaragedTrain, minRssi);
List<Beacon> observedBeacons = samplesAllAverage.getBeacons();
this.setActiveBeaconList(ModelAdaptUtils.beaconsToActiveBeaconArray(observedBeacons));
double stdevTmp = stdev;
this.setStdev(0.0); // stdev is set to be zero before optimization of LDPL model
this.optimizeForLDPLModel();
this.setStdev(stdevTmp); // stdev must be updated before optimization of GP
this.optimizeForGPIsoScaleLOOMSE(); // optimize for lx(=ly) and stdev
this.optimizeEstimateSigmaN(
Sample.samplesListToSamples(samplesListTrainParent)); // estimate sigmaN
this.train(samplesAvaragedTrain);
}
