public double[] GetLogPsd()
{
var psd = MatrixTools.GetColumnAverages(this.Data);
var logPsd = DataTools.LogValues(psd);
return(logPsd);
}
public void GetPsd(string path)
{
var psd = MatrixTools.GetColumnAverages(this.Data);
FileTools.WriteArray2File(psd, path + ".csv");
GraphsAndCharts.DrawGraph(psd, "Title", new FileInfo(path));
//GraphsAndCharts.DrawGraph("Title", psd, width, height, 4 new FileInfo(path));
//image.Save(path);
}
public void DrawLogPsd(string path)
{
var psd = MatrixTools.GetColumnAverages(this.Data);
var logPsd = DataTools.LogValues(psd);
FileTools.WriteArray2File(logPsd, path + ".csv");
GraphsAndCharts.DrawGraph(logPsd, "log PSD", new FileInfo(path));
//GraphsAndCharts.DrawGraph("Title", psd, width, height, 4 new FileInfo(path));
//image.Save(path, ImageFormat.Png);
}
public static Dictionary <string, double[]> AverageIndicesOverMinutes(Dictionary <string, double[, ]> allIndices, int startRowId, int endRowId)
{
var opIndices = new Dictionary <string, double[]>();
var keys = allIndices.Keys;
foreach (string key in keys)
{
var success = allIndices.TryGetValue(key, out double[,] matrix);
if (success)
{
var colCount = matrix.GetLength(1);
var subMatrix = MatrixTools.Submatrix(matrix, startRowId, 0, endRowId, colCount - 1);
opIndices.Add(key, MatrixTools.GetColumnAverages(subMatrix));
}
}
return(opIndices);
}
/// <summary>
/// THE KEY ANALYSIS METHOD
/// </summary>
/// <param name="recording">
/// The segment Of Source File.
/// </param>
/// <param name="configDict">
/// The config Dict.
/// </param>
/// <param name="value"></param>
/// <returns>
/// The <see cref="LimnodynastesConvexResults"/>.
/// </returns>
internal static LimnodynastesConvexResults Analysis(
Dictionary <string, double[, ]> dictionaryOfHiResSpectralIndices,
AudioRecording recording,
Dictionary <string, string> configDict,
AnalysisSettings analysisSettings,
SegmentSettingsBase segmentSettings)
{
// for Limnodynastes convex, in the D.Stewart CD, there are peaks close to:
//1. 1950 Hz
//2. 1460 hz
//3. 970 hz These are 490 Hz apart.
// for Limnodynastes convex, in the JCU recording, there are peaks close to:
//1. 1780 Hz
//2. 1330 hz
//3. 880 hz These are 450 Hz apart.
// So strategy is to look for three peaks separated by same amount and in the vicinity of the above,
// starting with highest power (the top peak) and working down to lowest power (bottom peak).
var outputDir = segmentSettings.SegmentOutputDirectory;
TimeSpan segmentStartOffset = segmentSettings.SegmentStartOffset;
//KeyValuePair<string, double[,]> kvp = dictionaryOfHiResSpectralIndices.First();
var spg = dictionaryOfHiResSpectralIndices["RHZ"];
int rhzRowCount = spg.GetLength(0);
int rhzColCount = spg.GetLength(1);
int sampleRate = recording.SampleRate;
double herzPerBin = sampleRate / 2 / (double)rhzRowCount;
double scoreThreshold = (double?)double.Parse(configDict["EventThreshold"]) ?? 3.0;
int minimumFrequency = (int?)int.Parse(configDict["MinHz"]) ?? 850;
int dominantFrequency = (int?)int.Parse(configDict["DominantFrequency"]) ?? 1850;
// # The Limnodynastes call has three major peaks. The dominant peak is at 1850 or as set above.
// # The second and third peak are at equal gaps below. DominantFreq-gap and DominantFreq-(2*gap);
// # Set the gap in the Config file. Should typically be in range 880 to 970
int peakGapInHerz = (int?)int.Parse(configDict["PeakGap"]) ?? 470;
int F1AndF2Gap = (int)Math.Round(peakGapInHerz / herzPerBin);
//int F1AndF2Gap = 10; // 10 = number of freq bins
int F1AndF3Gap = 2 * F1AndF2Gap;
//int F1AndF3Gap = 20;
int hzBuffer = 250;
int bottomBin = 5;
int dominantBin = (int)Math.Round(dominantFrequency / herzPerBin);
int binBuffer = (int)Math.Round(hzBuffer / herzPerBin);;
int dominantBinMin = dominantBin - binBuffer;
int dominantBinMax = dominantBin + binBuffer;
// freqBin + rowID = binCount - 1;
// therefore: rowID = binCount - freqBin - 1;
int minRowID = rhzRowCount - dominantBinMax - 1;
int maxRowID = rhzRowCount - dominantBinMin - 1;
int bottomRow = rhzRowCount - bottomBin - 1;
var list = new List <Point>();
// loop through all spectra/columns of the hi-res spectrogram.
for (int c = 1; c < rhzColCount - 1; c++)
{
double maxAmplitude = -double.MaxValue;
int idOfRowWithMaxAmplitude = 0;
for (int r = minRowID; r <= bottomRow; r++)
{
if (spg[r, c] > maxAmplitude)
{
maxAmplitude = spg[r, c];
idOfRowWithMaxAmplitude = r;
}
}
if (idOfRowWithMaxAmplitude < minRowID)
{
continue;
}
if (idOfRowWithMaxAmplitude > maxRowID)
{
continue;
}
// want a spectral peak.
if (spg[idOfRowWithMaxAmplitude, c] < spg[idOfRowWithMaxAmplitude, c - 1])
{
continue;
}
if (spg[idOfRowWithMaxAmplitude, c] < spg[idOfRowWithMaxAmplitude, c + 1])
{
continue;
}
// peak should exceed thresold amplitude
if (spg[idOfRowWithMaxAmplitude, c] < 3.0)
{
continue;
}
// convert row ID to freq bin ID
int freqBinID = rhzRowCount - idOfRowWithMaxAmplitude - 1;
list.Add(new Point(c, freqBinID));
// we now have a list of potential hits for LimCon. This needs to be filtered.
// Console.WriteLine("Col {0}, Bin {1} ", c, freqBinID);
}
// DEBUG ONLY // ################################ TEMPORARY ################################
// superimpose point on RHZ HiRes spectrogram for debug purposes
bool drawOnHiResSpectrogram = true;
//string filePath = @"G:\SensorNetworks\Output\Frogs\TestOfHiResIndices-2016July\Test\Towsey.HiResIndices\SpectrogramImages\3mile_creek_dam_-_Herveys_Range_1076_248366_20130305_001700_30_0min.CombinedGreyScale.png";
var fileName = Path.GetFileNameWithoutExtension(segmentSettings.SegmentAudioFile.Name);
string filePath = outputDir.FullName + @"\SpectrogramImages\" + fileName + ".CombinedGreyScale.png";
var debugImage = new FileInfo(filePath);
if (!debugImage.Exists)
{
drawOnHiResSpectrogram = false;
}
if (drawOnHiResSpectrogram)
{
// put red dot where max is
Bitmap bmp = new Bitmap(filePath);
foreach (Point point in list)
{
bmp.SetPixel(point.X + 70, 1911 - point.Y, Color.Red);
}
// mark off every tenth frequency bin
for (int r = 0; r < 26; r++)
{
bmp.SetPixel(68, 1911 - (r * 10), Color.Blue);
bmp.SetPixel(69, 1911 - (r * 10), Color.Blue);
}
// mark off upper bound and lower frequency bound
bmp.SetPixel(69, 1911 - dominantBinMin, Color.Lime);
bmp.SetPixel(69, 1911 - dominantBinMax, Color.Lime);
//bmp.SetPixel(69, 1911 - maxRowID, Color.Lime);
string opFilePath = outputDir.FullName + @"\SpectrogramImages\" + fileName + ".CombinedGreyScaleAnnotated.png";
bmp.Save(opFilePath);
}
// END DEBUG ################################ TEMPORARY ################################
// now construct the standard decibel spectrogram WITHOUT noise removal, and look for LimConvex
// get frame parameters for the analysis
double epsilon = Math.Pow(0.5, recording.BitsPerSample - 1);
int frameSize = rhzRowCount * 2;
int frameStep = frameSize; // this default = zero overlap
double frameDurationInSeconds = frameSize / (double)sampleRate;
double frameStepInSeconds = frameStep / (double)sampleRate;
double framesPerSec = 1 / frameStepInSeconds;
//var dspOutput = DSP_Frames.ExtractEnvelopeAndFFTs(recording, frameSize, frameStep);
//// Generate deciBel spectrogram
//double[,] deciBelSpectrogram = MFCCStuff.DecibelSpectra(dspOutput.amplitudeSpectrogram, dspOutput.WindowPower, sampleRate, epsilon);
// i: Init SONOGRAM config
var sonoConfig = new SonogramConfig
{
SourceFName = recording.BaseName,
WindowSize = frameSize,
WindowOverlap = 0.0,
NoiseReductionType = NoiseReductionType.None,
};
// init sonogram
BaseSonogram sonogram = new SpectrogramStandard(sonoConfig, recording.WavReader);
// remove the DC row of the spectrogram
sonogram.Data = MatrixTools.Submatrix(sonogram.Data, 0, 1, sonogram.Data.GetLength(0) - 1, sonogram.Data.GetLength(1) - 1);
//scores.Add(new Plot("Decibels", DataTools.NormaliseMatrixValues(dBArray), ActivityAndCover.DefaultActivityThresholdDb));
//scores.Add(new Plot("Active Frames", DataTools.Bool2Binary(activity.activeFrames), 0.0));
// convert spectral peaks to frequency
//var tuple_DecibelPeaks = SpectrogramTools.HistogramOfSpectralPeaks(deciBelSpectrogram);
//int[] peaksBins = tuple_DecibelPeaks.Item2;
//double[] freqPeaks = new double[peaksBins.Length];
//int binCount = sonogram.Data.GetLength(1);
//for (int i = 1; i < peaksBins.Length; i++) freqPeaks[i] = (lowerBinBound + peaksBins[i]) / (double)nyquistBin;
//scores.Add(new Plot("Max Frequency", freqPeaks, 0.0)); // location of peaks for spectral images
// create new list of LimCon hits in the standard spectrogram.
double timeSpanOfFrameInSeconds = frameSize / (double)sampleRate;
var newList = new List <int[]>();
int lastFrameID = sonogram.Data.GetLength(0) - 1;
int lastBinID = sonogram.Data.GetLength(1) - 1;
foreach (Point point in list)
{
double secondsFromStartOfSegment = (point.X * 0.1) + 0.05; // convert point.Y to center of time-block.
int framesFromStartOfSegment = (int)Math.Round(secondsFromStartOfSegment / timeSpanOfFrameInSeconds);
// location of max point is uncertain, so search in neighbourhood.
// NOTE: sonogram.data matrix is time*freqBin
double maxValue = -double.MaxValue;
int idOfTMax = framesFromStartOfSegment;
int idOfFMax = point.Y;
for (int deltaT = -4; deltaT <= 4; deltaT++)
{
for (int deltaF = -1; deltaF <= 1; deltaF++)
{
int newT = framesFromStartOfSegment + deltaT;
if (newT < 0)
{
newT = 0;
}
else if (newT > lastFrameID)
{
newT = lastFrameID;
}
double value = sonogram.Data[newT, point.Y + deltaF];
if (value > maxValue)
{
maxValue = value;
idOfTMax = framesFromStartOfSegment + deltaT;
idOfFMax = point.Y + deltaF;
}
}
}
// newList.Add(new Point(frameSpan, point.Y));
int[] array = new int[2];
array[0] = idOfTMax;
array[1] = idOfFMax;
newList.Add(array);
}
// Now obtain more of spectrogram to see if have peaks at two other places characteristic of Limnodynastes convex.
// In the D.Stewart CD, there are peaks close to:
//1. 1950 Hz
//2. 1460 hz
//3. 970 hz These are 490 Hz apart.
// For Limnodynastes convex, in the JCU recording, there are peaks close to:
//1. 1780 Hz
//2. 1330 hz
//3. 880 hz These are 450 Hz apart.
// So strategy is to look for three peaks separated by same amount and in the vicinity of the above,
// starting with highest power (the top peak) and working down to lowest power (bottom peak).
//We have found top/highest peak - now find the other two.
int secondDominantFrequency = 1380;
int secondDominantBin = (int)Math.Round(secondDominantFrequency / herzPerBin);
int thirdDominantFrequency = 900;
int thirdDominantBin = (int)Math.Round(thirdDominantFrequency / herzPerBin);
var acousticEvents = new List <AcousticEvent>();
int Tbuffer = 2;
// First extract a sub-matrix.
foreach (int[] array in newList)
{
// NOTE: sonogram.data matrix is time*freqBin
int Tframe = array[0];
int F1bin = array[1];
double[,] subMatrix = MatrixTools.Submatrix(sonogram.Data, Tframe - Tbuffer, 0, Tframe + Tbuffer, F1bin);
double F1power = subMatrix[Tbuffer, F1bin];
// convert to vector
var spectrum = MatrixTools.GetColumnAverages(subMatrix);
// use the following code to get estimate of background noise
double[,] powerMatrix = MatrixTools.Submatrix(sonogram.Data, Tframe - 3, 10, Tframe + 3, F1bin);
double averagePower = (MatrixTools.GetRowAverages(powerMatrix)).Average();
double score = F1power - averagePower;
// debug - checking what the spectrum looks like.
//for (int i = 0; i < 18; i++)
// spectrum[i] = -100.0;
//DataTools.writeBarGraph(spectrum);
// locate the peaks in lower frequency bands, F2 and F3
bool[] peaks = DataTools.GetPeaks(spectrum);
int F2bin = 0;
double F2power = -200.0; // dB
for (int i = -3; i <= 2; i++)
{
int bin = F1bin - F1AndF2Gap + i;
if ((peaks[bin]) && (F2power < subMatrix[1, bin]))
{
F2bin = bin;
F2power = subMatrix[1, bin];
}
}
if (F2bin == 0)
{
continue;
}
if (F2power == -200.0)
{
continue;
}
score += (F2power - averagePower);
int F3bin = 0;
double F3power = -200.0;
for (int i = -5; i <= 2; i++)
{
int bin = F1bin - F1AndF3Gap + i;
if ((peaks[bin]) && (F3power < subMatrix[1, bin]))
{
F3bin = bin;
F3power = subMatrix[1, bin];
}
}
if (F3bin == 0)
{
continue;
}
if (F3power == -200.0)
{
continue;
}
score += (F3power - averagePower);
score /= 3;
// ignore events where SNR < decibel threshold
if (score < scoreThreshold)
{
continue;
}
// ignore events with wrong power distribution. A good LimnoConvex call has strongest F1 power
if ((F3power > F1power) || (F2power > F1power))
{
continue;
}
//freq Bin ID must be converted back to Matrix row ID
// freqBin + rowID = binCount - 1;
// therefore: rowID = binCount - freqBin - 1;
minRowID = rhzRowCount - F1bin - 2;
maxRowID = rhzRowCount - F3bin - 1;
int F1RowID = rhzRowCount - F1bin - 1;
int F2RowID = rhzRowCount - F2bin - 1;
int F3RowID = rhzRowCount - F3bin - 1;
int maxfreq = dominantFrequency + hzBuffer;
int topBin = (int)Math.Round(maxfreq / herzPerBin);
int frameCount = 4;
double duration = frameCount * frameStepInSeconds;
double startTimeWrtSegment = (Tframe - 2) * frameStepInSeconds;
// Got to here so start initialising an acoustic event
var ae = new AcousticEvent(segmentStartOffset, startTimeWrtSegment, duration, minimumFrequency, maxfreq);
ae.SetTimeAndFreqScales(framesPerSec, herzPerBin);
//var ae = new AcousticEvent(oblong, recording.Nyquist, binCount, frameDurationInSeconds, frameStepInSeconds, frameCount);
//ae.StartOffset = TimeSpan.FromSeconds(Tframe * frameStepInSeconds);
var pointF1 = new Point(2, topBin - F1bin);
var pointF2 = new Point(2, topBin - F2bin);
var pointF3 = new Point(2, topBin - F3bin);
ae.Points = new List <Point>();
ae.Points.Add(pointF1);
ae.Points.Add(pointF2);
ae.Points.Add(pointF3);
//tried using HitElements but did not do what I wanted later on.
//ae.HitElements = new HashSet<Point>();
//ae.HitElements = new SortedSet<Point>();
//ae.HitElements.Add(pointF1);
//ae.HitElements.Add(pointF2);
//ae.HitElements.Add(pointF3);
ae.Score = score;
//ae.MinFreq = Math.Round((topBin - F3bin - 5) * herzPerBin);
//ae.MaxFreq = Math.Round(topBin * herzPerBin);
acousticEvents.Add(ae);
}
// now add in extra common info to the acoustic events
acousticEvents.ForEach(ae =>
{
ae.SpeciesName = configDict[AnalysisKeys.SpeciesName];
ae.SegmentStartSeconds = segmentStartOffset.TotalSeconds;
ae.SegmentDurationSeconds = recording.Duration.TotalSeconds;
ae.Name = abbreviatedName;
ae.BorderColour = Color.Red;
ae.FileName = recording.BaseName;
});
double[] scores = new double[rhzColCount]; // predefinition of score array
double nomalisationConstant = scoreThreshold * 4; // four times the score threshold
double compressionFactor = rhzColCount / (double)sonogram.Data.GetLength(0);
foreach (AcousticEvent ae in acousticEvents)
{
ae.ScoreNormalised = ae.Score / nomalisationConstant;
if (ae.ScoreNormalised > 1.0)
{
ae.ScoreNormalised = 1.0;
}
int frameID = (int)Math.Round(ae.EventStartSeconds / frameDurationInSeconds);
int hiresFrameID = (int)Math.Floor(frameID * compressionFactor);
scores[hiresFrameID] = ae.ScoreNormalised;
}
var plot = new Plot(AnalysisName, scores, scoreThreshold);
// DEBUG ONLY ################################ TEMPORARY ################################
// Draw a standard spectrogram and mark of hites etc.
bool createStandardDebugSpectrogram = true;
var imageDir = new DirectoryInfo(outputDir.FullName + @"\SpectrogramImages");
if (!imageDir.Exists)
{
imageDir.Create();
}
if (createStandardDebugSpectrogram)
{
var fileName2 = Path.GetFileNameWithoutExtension(segmentSettings.SegmentAudioFile.Name);
string filePath2 = Path.Combine(imageDir.FullName, fileName + ".Spectrogram.png");
Bitmap sonoBmp = (Bitmap)sonogram.GetImage();
int height = sonoBmp.Height;
foreach (AcousticEvent ae in acousticEvents)
{
ae.DrawEvent(sonoBmp);
//g.DrawRectangle(pen, ob.ColumnLeft, ob.RowTop, ob.ColWidth-1, ob.RowWidth);
//ae.DrawPoint(sonoBmp, ae.HitElements.[0], Color.OrangeRed);
//ae.DrawPoint(sonoBmp, ae.HitElements[1], Color.Yellow);
//ae.DrawPoint(sonoBmp, ae.HitElements[2], Color.Green);
ae.DrawPoint(sonoBmp, ae.Points[0], Color.OrangeRed);
ae.DrawPoint(sonoBmp, ae.Points[1], Color.Yellow);
ae.DrawPoint(sonoBmp, ae.Points[2], Color.LimeGreen);
}
// draw the original hits on the standard sonogram
foreach (int[] array in newList)
{
sonoBmp.SetPixel(array[0], height - array[1], Color.Cyan);
}
// mark off every tenth frequency bin on the standard sonogram
for (int r = 0; r < 20; r++)
{
sonoBmp.SetPixel(0, height - (r * 10) - 1, Color.Blue);
sonoBmp.SetPixel(1, height - (r * 10) - 1, Color.Blue);
}
// mark off upper bound and lower frequency bound
sonoBmp.SetPixel(0, height - dominantBinMin, Color.Lime);
sonoBmp.SetPixel(0, height - dominantBinMax, Color.Lime);
sonoBmp.Save(filePath2);
}
// END DEBUG ################################ TEMPORARY ################################
return(new LimnodynastesConvexResults
{
Sonogram = sonogram,
Hits = null,
Plot = plot,
Events = acousticEvents,
RecordingDuration = recording.Duration,
});
} // Analysis()
/// <summary>
/// Calculate summary statistics for supplied temporal and spectral targets.
/// </summary>
/// <remarks>
/// The acoustic statistics calculated in this method are based on methods outlined in
/// "Acoustic classification of multiple simultaneous bird species: A multi-instance multi-label approach",
/// by Forrest Briggs, Balaji Lakshminarayanan, Lawrence Neal, Xiaoli Z.Fern, Raviv Raich, Sarah J.K.Hadley, Adam S. Hadley, Matthew G. Betts, et al.
/// The Journal of the Acoustical Society of America v131, pp4640 (2012); doi: http://dx.doi.org/10.1121/1.4707424
/// ..
/// The Briggs feature are calculated from the column (freq bin) and row (frame) sums of the extracted spectrogram.
/// 1. Gini Index for frame and bin sums. A measure of dispersion. Problem with gini is that its value is dependent on the row or column count.
/// We use entropy instead because value not dependent on row or column count because it is normalized.
/// For the following meausres of k-central moments, the freq and time values are normalized in 0,1 to width of the event.
/// 2. freq-mean
/// 3. freq-variance
/// 4. freq-skew and kurtosis
/// 5. time-mean
/// 6. time-variance
/// 7. time-skew and kurtosis
/// 8. freq-max (normalized)
/// 9. time-max (normalized)
/// 10. Briggs et al also calculate a 16 value histogram of gradients for each event mask. We do not do that here although we could.
/// ...
/// NOTE 1: There are differences between our method of noise reduction and Briggs. Briggs does not convert to decibels
/// and instead works with power values. He obtains a noise profile from the 20% of frames having the lowest energy sum.
/// NOTE 2: To NormaliseMatrixValues for noise, they divide the actual energy by the noise value. This is equivalent to subtraction when working in decibels.
/// There are advantages and disadvantages to Briggs method versus ours. In our case, we hve to convert decibel values back to
/// energy values when calculating the statistics for the extracted acoustic event.
/// NOTE 3: We do not calculate the higher central moments of the time/frequency profiles, i.e. skew and kurtosis.
/// Ony mean and standard deviation.
/// ..
/// NOTE 4: This method assumes that the passed event occurs totally within the passed recording,
/// AND that the passed recording is of sufficient duration to obtain reliable BGN noise profile
/// BUT not so long as to cause memory constipation.
/// </remarks>
/// <param name="recording">as type AudioRecording which contains the event</param>
/// <param name="temporalTarget">Both start and end bounds - relative to the supplied recording</param>
/// <param name="spectralTarget">both bottom and top bounds in Hertz</param>
/// <param name="config">parameters that determine the outcome of the analysis</param>
/// <param name="segmentStartOffset">How long since the start of the recording this event occurred</param>
/// <returns>an instance of EventStatistics</returns>
public static EventStatistics AnalyzeAudioEvent(
AudioRecording recording,
Range <TimeSpan> temporalTarget,
Range <double> spectralTarget,
EventStatisticsConfiguration config,
TimeSpan segmentStartOffset)
{
var stats = new EventStatistics
{
EventStartSeconds = temporalTarget.Minimum.TotalSeconds,
EventEndSeconds = temporalTarget.Maximum.TotalSeconds,
LowFrequencyHertz = spectralTarget.Minimum,
HighFrequencyHertz = spectralTarget.Maximum,
SegmentDurationSeconds = recording.Duration.TotalSeconds,
SegmentStartSeconds = segmentStartOffset.TotalSeconds,
};
// temporal target is supplied relative to recording, but not the supplied audio segment
// shift coordinates relative to segment
var localTemporalTarget = temporalTarget.Shift(-segmentStartOffset);
if (!recording
.Duration
.AsRangeFromZero(Topology.Inclusive)
.Contains(localTemporalTarget))
{
stats.Error = true;
stats.ErrorMessage =
$"Audio not long enough ({recording.Duration}) to analyze target ({localTemporalTarget})";
return(stats);
}
// convert recording to spectrogram
int sampleRate = recording.SampleRate;
double epsilon = recording.Epsilon;
// extract the spectrogram
var dspOutput1 = DSP_Frames.ExtractEnvelopeAndFfts(recording, config.FrameSize, config.FrameStep);
double hertzBinWidth = dspOutput1.FreqBinWidth;
var stepDurationInSeconds = config.FrameStep / (double)sampleRate;
var startFrame = (int)Math.Ceiling(localTemporalTarget.Minimum.TotalSeconds / stepDurationInSeconds);
// subtract 1 frame because want to end before start of end point.
var endFrame = (int)Math.Floor(localTemporalTarget.Maximum.TotalSeconds / stepDurationInSeconds) - 1;
var bottomBin = (int)Math.Floor(spectralTarget.Minimum / hertzBinWidth);
var topBin = (int)Math.Ceiling(spectralTarget.Maximum / hertzBinWidth);
// Events can have their high value set to the nyquist.
// Since the submatrix call below uses an inclusive upper bound an index out of bounds exception occurs in
// these cases. So we just ask for the bin below.
if (topBin >= config.FrameSize / 2)
{
topBin = (config.FrameSize / 2) - 1;
}
// Convert amplitude spectrogram to deciBels and calculate the dB background noise profile
double[,] decibelSpectrogram = MFCCStuff.DecibelSpectra(dspOutput1.AmplitudeSpectrogram, dspOutput1.WindowPower, sampleRate, epsilon);
double[] spectralDecibelBgn = NoiseProfile.CalculateBackgroundNoise(decibelSpectrogram);
decibelSpectrogram = SNR.TruncateBgNoiseFromSpectrogram(decibelSpectrogram, spectralDecibelBgn);
decibelSpectrogram = SNR.RemoveNeighbourhoodBackgroundNoise(decibelSpectrogram, nhThreshold: 2.0);
// extract the required acoustic event
var eventMatrix = MatrixTools.Submatrix(decibelSpectrogram, startFrame, bottomBin, endFrame, topBin);
// Get the SNR of the event. This is just the max value in the matrix because noise reduced
MatrixTools.MinMax(eventMatrix, out _, out double max);
stats.SnrDecibels = max;
// Now need to convert event matrix back to energy values before calculating other statistics
eventMatrix = MatrixTools.Decibels2Power(eventMatrix);
var columnAverages = MatrixTools.GetColumnAverages(eventMatrix);
var rowAverages = MatrixTools.GetRowAverages(eventMatrix);
// calculate the mean and temporal standard deviation in decibels
NormalDist.AverageAndSD(rowAverages, out double mean, out double stddev);
stats.MeanDecibels = 10 * Math.Log10(mean);
stats.TemporalStdDevDecibels = 10 * Math.Log10(stddev);
// calculate the frequency standard deviation in decibels
NormalDist.AverageAndSD(columnAverages, out mean, out stddev);
stats.FreqBinStdDevDecibels = 10 * Math.Log10(stddev);
// calculate relative location of the temporal maximum
int maxRowId = DataTools.GetMaxIndex(rowAverages);
stats.TemporalMaxRelative = maxRowId / (double)rowAverages.Length;
// calculate the entropy dispersion/concentration indices
stats.TemporalEnergyDistribution = 1 - DataTools.EntropyNormalised(rowAverages);
stats.SpectralEnergyDistribution = 1 - DataTools.EntropyNormalised(columnAverages);
// calculate the spectral centroid and the dominant frequency
double binCentroid = CalculateSpectralCentroid(columnAverages);
stats.SpectralCentroid = (int)Math.Round(hertzBinWidth * binCentroid) + (int)spectralTarget.Minimum;
int maxColumnId = DataTools.GetMaxIndex(columnAverages);
stats.DominantFrequency = (int)Math.Round(hertzBinWidth * maxColumnId) + (int)spectralTarget.Minimum;
// remainder of this method is to produce debugging images. Can comment out when not debugging.
/*
* var normalisedIndex = DataTools.NormaliseMatrixValues(columnAverages);
* var image4 = GraphsAndCharts.DrawGraph("columnSums", normalisedIndex, 100);
* string path4 = @"C:\SensorNetworks\Output\Sonograms\UnitTestSonograms\columnSums.png";
* image4.Save(path4);
* normalisedIndex = DataTools.NormaliseMatrixValues(rowAverages);
* image4 = GraphsAndCharts.DrawGraph("rowSums", normalisedIndex, 100);
* path4 = @"C:\SensorNetworks\Output\Sonograms\UnitTestSonograms\rowSums.png";
* image4.Save(path4);
*/
return(stats);
}
/// <summary>
/// Remove events whose acoustic profile does not match that of a flying fox.
/// </summary>
/// <param name="events">unfiltered acoustic events.</param>
/// <param name="sonogram">includes matrix of spectrogram values.</param>
/// <returns>filtered acoustic events.</returns>
private static List <AcousticEvent> FilterEventsForSpectralProfile(List <AcousticEvent> events, BaseSonogram sonogram)
{
double[,] spectrogramData = sonogram.Data;
//int colCount = spectrogramData.GetLength(1);
// The following freq bins are used to demarcate freq bands for spectral tests below.
// The hertz values are hard coded but could be included in the config.yml file.
int maxBin = (int)Math.Round(8000 / sonogram.FBinWidth);
int fourKiloHzBin = (int)Math.Round(4000 / sonogram.FBinWidth);
int oneKiloHzBin = (int)Math.Round(1000 / sonogram.FBinWidth);
var filteredEvents = new List <AcousticEvent>();
foreach (AcousticEvent ae in events)
{
int startFrame = ae.Oblong.RowTop;
//int endFrame = ae.Oblong.RowBottom;
// get all the frames of the acoustic event
//var subMatrix = DataTools.Submatrix(spectrogramData, startFrame, 0, endFrame, colCount - 1);
// get only the frames from centre of the acoustic event
var subMatrix = DataTools.Submatrix(spectrogramData, startFrame + 1, 0, startFrame + 4, maxBin);
var spectrum = MatrixTools.GetColumnAverages(subMatrix);
var normalisedSpectrum = DataTools.normalise(spectrum);
normalisedSpectrum = DataTools.filterMovingAverageOdd(normalisedSpectrum, 11);
var maxId = DataTools.GetMaxIndex(normalisedSpectrum);
//var hzMax = (int)Math.Ceiling(maxId * sonogram.FBinWidth);
// Do TESTS to determine if event has spectrum matching a Flying fox.
// Test 1: Spectral maximum should be below 4 kHz.
bool passTest1 = maxId < fourKiloHzBin;
// Test 2: There should be little energy in 0-1 kHz band.
var subband1Khz = DataTools.Subarray(normalisedSpectrum, 0, oneKiloHzBin);
double bandArea1 = subband1Khz.Sum();
double energyRatio1 = bandArea1 / normalisedSpectrum.Sum();
// 0.125 = 1/8. i.e. test requires that energy in 0-1kHz band is less than average in all 8 kHz bands
// 0.0938 = 3/32. i.e. test requires that energy in 0-1kHz band is less than 3/4 average in all 8 kHz bands
// 0.0625 = 1/16. i.e. test requires that energy in 0-1kHz band is less than half average in all 8 kHz bands
bool passTest2 = !(energyRatio1 > 0.1);
// Test 3: There should be little energy in 4-5 kHz band.
var subband4Khz = DataTools.Subarray(normalisedSpectrum, fourKiloHzBin, oneKiloHzBin);
double bandArea2 = subband4Khz.Sum();
double energyRatio2 = bandArea2 / normalisedSpectrum.Sum();
bool passTest3 = !(energyRatio2 > 0.125);
// TODO write method to determine similarity of spectrum to a true flying fox spectrum.
// Problem: it is not certain how variable the FF spectra are.
// In ten minutes of recording used so far, which include 14-15 obvious calls, there appear to be two spectral types.
// One type has three peaks at around 1.5 kHz, 3 kHz and 6 kHz.
// The other type have two peaks around 2.5 and 5.5 kHz.
//if (passTest1)
//if (true)
if (passTest1 && passTest2 && passTest3)
{
filteredEvents.Add(ae);
//DEBUG SPECTRAL PROFILES: UNCOMMENT following lines to get spectral profiles of the events.
/*
* double startSecond = ae.EventStartSeconds - ae.SegmentStartSeconds;
* string name = "CallSpectrum " + (ae.SegmentStartSeconds / 60) + "m" + (int)Math.Floor(startSecond) + "s hzMax" + hzMax;
* var bmp2 = GraphsAndCharts.DrawGraph(name, normalisedSpectrum, 100);
* bmp2.Save(Path.Combine(@"PATH\Towsey.PteropusSpecies", name + ".png"));
*/
}
}
return(filteredEvents);
}
public static void SimilarityIndex(double[] channelL, double[] channelR, double epsilon, int sampleRate,
out double similarityIndex, out double decibelIndex,
out double avDecibelBias, out double medianDecibelBias,
out double lowFreqDbBias, out double midFreqDbBias, out double hiFreqDbBias)
{
//var dspOutput1 = DSP_Frames.ExtractEnvelopeAndFFTs(subsegmentRecording, frameSize, frameStep);
int frameSize = 512;
int frameStep = 512;
frameSize *= 16; // take longer window to get low freq
frameStep *= 16;
var dspOutputL = DSP_Frames.ExtractEnvelopeAndAmplSpectrogram(channelL, sampleRate, epsilon, frameSize, frameStep);
var avSpectrumL = MatrixTools.GetColumnAverages(dspOutputL.AmplitudeSpectrogram);
//var medianSpectrumL = MatrixTools.GetColumnMedians(dspOutputL.amplitudeSpectrogram);
var dspOutputR = DSP_Frames.ExtractEnvelopeAndAmplSpectrogram(channelR, sampleRate, epsilon, frameSize, frameStep);
var avSpectrumR = MatrixTools.GetColumnAverages(dspOutputR.AmplitudeSpectrogram);
//var medianSpectrumR = MatrixTools.GetColumnMedians(dspOutputR.amplitudeSpectrogram);
similarityIndex = 0.0;
decibelIndex = 0.0;
for (int i = 0; i < avSpectrumR.Length; i++)
{
double min = Math.Min(avSpectrumL[i], avSpectrumR[i]);
double max = Math.Max(avSpectrumL[i], avSpectrumR[i]);
if (max <= 0.000001)
{
max = 0.000001; // to prevent division by zero.
}
// index = min / max;
double index = min * min / (max * max);
similarityIndex += index;
double dBmin = 20 * Math.Log10(min);
double dBmax = 20 * Math.Log10(max);
decibelIndex += dBmax - dBmin;
}
similarityIndex /= avSpectrumR.Length;
decibelIndex /= avSpectrumR.Length;
double medianLeft = Statistics.GetMedian(avSpectrumL);
double medianRight = Statistics.GetMedian(avSpectrumR);
medianDecibelBias = medianLeft - medianRight;
// init values
avDecibelBias = 0.0;
lowFreqDbBias = 0.0;
// calculate the freq band bounds for 2kHz and 7khz.
int lowBound = frameSize * 2000 / sampleRate;
int midBound = frameSize * 7000 / sampleRate;
for (int i = 0; i < lowBound; i++)
{
double dbLeft = 20 * Math.Log10(avSpectrumL[i]);
double dbRight = 20 * Math.Log10(avSpectrumR[i]);
avDecibelBias += dbLeft - dbRight;
lowFreqDbBias += dbLeft - dbRight;
}
midFreqDbBias = 0.0;
for (int i = lowBound; i < midBound; i++)
{
double dbLeft = 20 * Math.Log10(avSpectrumL[i]);
double dbRight = 20 * Math.Log10(avSpectrumR[i]);
avDecibelBias += dbLeft - dbRight;
midFreqDbBias += dbLeft - dbRight;
}
hiFreqDbBias = 0.0;
for (int i = midBound; i < avSpectrumR.Length; i++)
{
double dbLeft = 20 * Math.Log10(avSpectrumL[i]);
double dbRight = 20 * Math.Log10(avSpectrumR[i]);
avDecibelBias += dbLeft - dbRight;
hiFreqDbBias += dbLeft - dbRight;
}
avDecibelBias /= avSpectrumR.Length;
lowFreqDbBias /= lowBound;
midFreqDbBias /= midBound - lowBound;
hiFreqDbBias /= avSpectrumR.Length - midBound;
}
public void PowerSpectrumDensityTest()
{
var inputPath = @"C:\Users\kholghim\Mahnoosh\Liz\TrainSet\";
var resultPsdPath = @"C:\Users\kholghim\Mahnoosh\Liz\PowerSpectrumDensity\train_LogPSD.bmp";
var resultNoiseReducedPsdPath = @"C:\Users\kholghim\Mahnoosh\Liz\PowerSpectrumDensity\train_LogPSD_NoiseReduced.bmp";
//var inputPath =Path.Combine(inputDir, "TrainSet"); // directory of the one-min recordings of one day (21 and 23 Apr - Black Rail Data)
// check whether there is any file in the folder/subfolders
if (Directory.GetFiles(inputPath, "*", SearchOption.AllDirectories).Length == 0)
{
throw new ArgumentException("The folder of recordings is empty...");
}
// get the nyquist value from the first wav file in the folder of recordings
int nq = new AudioRecording(Directory.GetFiles(inputPath, "*.wav")[0]).Nyquist;
int nyquist = nq; // 11025;
int frameSize = 1024;
int finalBinCount = 512; //256; //
int hertzInterval = 1000;
FreqScaleType scaleType = FreqScaleType.Linear;
//var freqScale = new FrequencyScale(scaleType, nyquist, frameSize, finalBinCount, hertzInterval);
//var fst = freqScale.ScaleType;
//var fst = FreqScaleType.Linear;
//var freqScale = new FrequencyScale(fst);
var settings = new SpectrogramSettings()
{
WindowSize = frameSize,
WindowOverlap = 0.1028,
//DoMelScale = (scaleType == FreqScaleType.Mel) ? true : false,
//MelBinCount = (scaleType == FreqScaleType.Mel) ? finalBinCount : frameSize / 2,
//DoMelScale = false,
MelBinCount = 256,
DoMelScale = (scaleType == FreqScaleType.Mel) ? true : false,
//MelBinCount = (scaleType == FreqScaleType.Mel) ? finalBinCount : frameSize / 2,
NoiseReductionType = NoiseReductionType.None,
NoiseReductionParameter = 0.0,
};
var attributes = new SpectrogramAttributes()
{
NyquistFrequency = nyquist,
Duration = TimeSpan.FromMinutes(1440),
};
List <double[]> psd = new List <double[]>();
foreach (string filePath in Directory.GetFiles(inputPath, "*.wav"))
{
FileInfo fileInfo = filePath.ToFileInfo();
// process the wav file if it is not empty
if (fileInfo.Length != 0)
{
var recording = new AudioRecording(filePath);
//var sonogram = new SpectrogramStandard(sonoConfig, recording.WavReader);
//var amplitudeSpectrogram = new AmplitudeSonogram(sonoConfig, recording.WavReader);
// save the matrix
// skip normalisation
// skip mel
settings.SourceFileName = recording.BaseName;
var spectrogram = new EnergySpectrogram(settings, recording.WavReader);
//var sonogram = new AmplitudeSpectrogram(settings, recording.WavReader);
//var energySpectrogram = new EnergySpectrogram(sonoConfig, amplitudeSpectrogram.Data);
//var energySpectrogram = new EnergySpectrogram(sonoConfig, recording.WavReader);
//var energySpectrogram = new EnergySpectrogram(settings, recording.WavReader);
// square the FFT coefficients to get an energy spectrogram
// double[,] energySpectrogram = PowerSpectrumDensity.GetEnergyValues(amplitudeSpectrogram.Data);
// RMS NORMALIZATION
//double[,] normalizedValues = SNR.RmsNormalization(energySpectro.Data);
//energySpectro.Data = SNR.RmsNormalization(energySpectro.Data);
// Median Noise Reduction
//spectrogram.Data = PcaWhitening.NoiseReduction(spectrogram.Data);
//spectrogram.Data = SNR.NoiseReduce_Standard(spectrogram.Data);
//double[] psd = PowerSpectralDensity.GetPowerSpectrum(noiseReducedValues);
//psd.Add(energySpectro.GetLogPsd());
psd.Add(MatrixTools.GetColumnAverages(spectrogram.Data));
//psd.Add(SpectrogramTools.CalculateAvgSpectrumFromEnergySpectrogram(normalizedValues));
//psd.Add(PowerSpectralDensity.GetPowerSpectrum(normalizedValues));
}
}
// writing psd matrix to csv file
//Csv.WriteMatrixToCsv(new FileInfo(@"C:\Users\kholghim\Mahnoosh\Liz\PowerSpectrumDensity\psd.csv"), psd.ToArray().ToMatrix());
//Image imagePsd = DecibelSpectrogram.DrawSpectrogramAnnotated(psd.ToArray().ToMatrix(), settings, attributes);
//imagePsd.Save(resultPsdPath, ImageFormat.Bmp);
var psdMatrix = psd.ToArray().ToMatrix();
// calculate the log of matrix
var logPsd = MatrixTools.Matrix2LogValues(psdMatrix);
Csv.WriteMatrixToCsv(new FileInfo(@"C:\Users\kholghim\Mahnoosh\Liz\PowerSpectrumDensity\logPsd.csv"), logPsd);
var image = DecibelSpectrogram.DrawSpectrogramAnnotated(logPsd, settings, attributes);
image.Save(resultPsdPath);
var noiseReducedLogPsd = PcaWhitening.NoiseReduction(logPsd); //SNR.NoiseReduce_Standard(logPsd); //SNR.NoiseReduce_Mean(logPsd, 0.0);//SNR.NoiseReduce_Median(logPsd, 0.0); //
Csv.WriteMatrixToCsv(new FileInfo(@"C:\Users\kholghim\Mahnoosh\Liz\PowerSpectrumDensity\logPsd_NoiseReduced.csv"), logPsd);
var image2 = DecibelSpectrogram.DrawSpectrogramAnnotated(noiseReducedLogPsd, settings, attributes);
image2.Save(resultNoiseReducedPsdPath);
//ImageTools.DrawMatrix(psd.ToArray().ToMatrix(), resultPath);
//ImageTools.DrawReversedMatrix(psd.ToArray().ToMatrix(), resultPath);
//var data = MatrixTools.Matrix2LogValues(psd.ToArray().ToMatrix());
//Image image = ImageTools.DrawReversedMatrixWithoutNormalisation(data);
//Image image = ImageTools.DrawReversedMatrixWithoutNormalisation(logPsd);
}
