使用实时流的Python版本(不会在每个新数据点到达时重新计算所有数据点)。您可能想要调整类函数返回的内容—对于我的目的，我只需要信号。

import numpy as np


class real_time_peak_detection():
    def __init__(self, array, lag, threshold, influence):
        self.y = list(array)
        self.length = len(self.y)
        self.lag = lag
        self.threshold = threshold
        self.influence = influence
        self.signals = [0] * len(self.y)
        self.filteredY = np.array(self.y).tolist()
        self.avgFilter = [0] * len(self.y)
        self.stdFilter = [0] * len(self.y)
        self.avgFilter[self.lag - 1] = np.mean(self.y[0:self.lag]).tolist()
        self.stdFilter[self.lag - 1] = np.std(self.y[0:self.lag]).tolist()

    def thresholding_algo(self, new_value):
        self.y.append(new_value)
        i = len(self.y) - 1
        self.length = len(self.y)
        if i < self.lag:
            return 0
        elif i == self.lag:
            self.signals = [0] * len(self.y)
            self.filteredY = np.array(self.y).tolist()
            self.avgFilter = [0] * len(self.y)
            self.stdFilter = [0] * len(self.y)
            self.avgFilter[self.lag] = np.mean(self.y[0:self.lag]).tolist()
            self.stdFilter[self.lag] = np.std(self.y[0:self.lag]).tolist()
            return 0

        self.signals += [0]
        self.filteredY += [0]
        self.avgFilter += [0]
        self.stdFilter += [0]

        if abs(self.y[i] - self.avgFilter[i - 1]) > (self.threshold * self.stdFilter[i - 1]):

            if self.y[i] > self.avgFilter[i - 1]:
                self.signals[i] = 1
            else:
                self.signals[i] = -1

            self.filteredY[i] = self.influence * self.y[i] + \
                (1 - self.influence) * self.filteredY[i - 1]
            self.avgFilter[i] = np.mean(self.filteredY[(i - self.lag):i])
            self.stdFilter[i] = np.std(self.filteredY[(i - self.lag):i])
        else:
            self.signals[i] = 0
            self.filteredY[i] = self.y[i]
            self.avgFilter[i] = np.mean(self.filteredY[(i - self.lag):i])
            self.stdFilter[i] = np.std(self.filteredY[(i - self.lag):i])

        return self.signals[i]

在Palshikar(2009)中发现了另一个算法:

Palshikar, G.(2009)。时间序列中峰值检测的简单算法。在Proc. 1st Int。高级数据分析，商业分析和智能(卷122)。

论文可以从这里下载。

算法是这样的:

algorithm peak1 // one peak detection algorithms that uses peak function S1 

input T = x1, x2, …, xN, N // input time-series of N points 
input k // window size around the peak 
input h // typically 1 <= h <= 3 
output O // set of peaks detected in T 

begin 
O = empty set // initially empty 

    for (i = 1; i < n; i++) do
        // compute peak function value for each of the N points in T 
        a[i] = S1(k,i,xi,T); 
    end for 

    Compute the mean m' and standard deviation s' of all positive values in array a; 

    for (i = 1; i < n; i++) do // remove local peaks which are “small” in global context 
        if (a[i] > 0 && (a[i] – m') >( h * s')) then O = O + {xi}; 
        end if 
    end for 

    Order peaks in O in terms of increasing index in T 

    // retain only one peak out of any set of peaks within distance k of each other 

    for every adjacent pair of peaks xi and xj in O do 
        if |j – i| <= k then remove the smaller value of {xi, xj} from O 
        end if 
    end for 
end

优势

本文提出了5种不同的峰值检测算法 算法在原始时间序列数据上工作(不需要平滑)

缺点

很难事先确定k和h 峰不能是平的(就像我测试数据中的第三个峰)

例子:

我在我的机器人项目中需要这样的东西。我想我可以归还Kotlin实现。

/**
* Smoothed zero-score alogrithm shamelessly copied from https://stackoverflow.com/a/22640362/6029703
* Uses a rolling mean and a rolling deviation (separate) to identify peaks in a vector
*
* @param y - The input vector to analyze
* @param lag - The lag of the moving window (i.e. how big the window is)
* @param threshold - The z-score at which the algorithm signals (i.e. how many standard deviations away from the moving mean a peak (or signal) is)
* @param influence - The influence (between 0 and 1) of new signals on the mean and standard deviation (how much a peak (or signal) should affect other values near it)
* @return - The calculated averages (avgFilter) and deviations (stdFilter), and the signals (signals)
*/
fun smoothedZScore(y: List<Double>, lag: Int, threshold: Double, influence: Double): Triple<List<Int>, List<Double>, List<Double>> {
    val stats = SummaryStatistics()
    // the results (peaks, 1 or -1) of our algorithm
    val signals = MutableList<Int>(y.size, { 0 })
    // filter out the signals (peaks) from our original list (using influence arg)
    val filteredY = ArrayList<Double>(y)
    // the current average of the rolling window
    val avgFilter = MutableList<Double>(y.size, { 0.0 })
    // the current standard deviation of the rolling window
    val stdFilter = MutableList<Double>(y.size, { 0.0 })
    // init avgFilter and stdFilter
    y.take(lag).forEach { s -> stats.addValue(s) }
    avgFilter[lag - 1] = stats.mean
    stdFilter[lag - 1] = Math.sqrt(stats.populationVariance) // getStandardDeviation() uses sample variance (not what we want)
    stats.clear()
    //loop input starting at end of rolling window
    (lag..y.size - 1).forEach { i ->
        //if the distance between the current value and average is enough standard deviations (threshold) away
        if (Math.abs(y[i] - avgFilter[i - 1]) > threshold * stdFilter[i - 1]) {
            //this is a signal (i.e. peak), determine if it is a positive or negative signal
            signals[i] = if (y[i] > avgFilter[i - 1]) 1 else -1
            //filter this signal out using influence
            filteredY[i] = (influence * y[i]) + ((1 - influence) * filteredY[i - 1])
        } else {
            //ensure this signal remains a zero
            signals[i] = 0
            //ensure this value is not filtered
            filteredY[i] = y[i]
        }
        //update rolling average and deviation
        (i - lag..i - 1).forEach { stats.addValue(filteredY[it]) }
        avgFilter[i] = stats.getMean()
        stdFilter[i] = Math.sqrt(stats.getPopulationVariance()) //getStandardDeviation() uses sample variance (not what we want)
        stats.clear()
    }
    return Triple(signals, avgFilter, stdFilter)
}

带有验证图的示例项目可以在github上找到。

以下是平滑z-score算法的Scala版本(非惯用):

/**
  * Smoothed zero-score alogrithm shamelessly copied from https://stackoverflow.com/a/22640362/6029703
  * Uses a rolling mean and a rolling deviation (separate) to identify peaks in a vector
  *
  * @param y - The input vector to analyze
  * @param lag - The lag of the moving window (i.e. how big the window is)
  * @param threshold - The z-score at which the algorithm signals (i.e. how many standard deviations away from the moving mean a peak (or signal) is)
  * @param influence - The influence (between 0 and 1) of new signals on the mean and standard deviation (how much a peak (or signal) should affect other values near it)
  * @return - The calculated averages (avgFilter) and deviations (stdFilter), and the signals (signals)
  */
private def smoothedZScore(y: Seq[Double], lag: Int, threshold: Double, influence: Double): Seq[Int] = {
  val stats = new SummaryStatistics()

  // the results (peaks, 1 or -1) of our algorithm
  val signals = mutable.ArrayBuffer.fill(y.length)(0)

  // filter out the signals (peaks) from our original list (using influence arg)
  val filteredY = y.to[mutable.ArrayBuffer]

  // the current average of the rolling window
  val avgFilter = mutable.ArrayBuffer.fill(y.length)(0d)

  // the current standard deviation of the rolling window
  val stdFilter = mutable.ArrayBuffer.fill(y.length)(0d)

  // init avgFilter and stdFilter
  y.take(lag).foreach(s => stats.addValue(s))

  avgFilter(lag - 1) = stats.getMean
  stdFilter(lag - 1) = Math.sqrt(stats.getPopulationVariance) // getStandardDeviation() uses sample variance (not what we want)

  // loop input starting at end of rolling window
  y.zipWithIndex.slice(lag, y.length - 1).foreach {
    case (s: Double, i: Int) =>
      // if the distance between the current value and average is enough standard deviations (threshold) away
      if (Math.abs(s - avgFilter(i - 1)) > threshold * stdFilter(i - 1)) {
        // this is a signal (i.e. peak), determine if it is a positive or negative signal
        signals(i) = if (s > avgFilter(i - 1)) 1 else -1
        // filter this signal out using influence
        filteredY(i) = (influence * s) + ((1 - influence) * filteredY(i - 1))
      } else {
        // ensure this signal remains a zero
        signals(i) = 0
        // ensure this value is not filtered
        filteredY(i) = s
      }

      // update rolling average and deviation
      stats.clear()
      filteredY.slice(i - lag, i).foreach(s => stats.addValue(s))
      avgFilter(i) = stats.getMean
      stdFilter(i) = Math.sqrt(stats.getPopulationVariance) // getStandardDeviation() uses sample variance (not what we want)
  }

  println(y.length)
  println(signals.length)
  println(signals)

  signals.zipWithIndex.foreach {
    case(x: Int, idx: Int) =>
      if (x == 1) {
        println(idx + " " + y(idx))
      }
  }

  val data =
    y.zipWithIndex.map { case (s: Double, i: Int) => Map("x" -> i, "y" -> s, "name" -> "y", "row" -> "data") } ++
    avgFilter.zipWithIndex.map { case (s: Double, i: Int) => Map("x" -> i, "y" -> s, "name" -> "avgFilter", "row" -> "data") } ++
    avgFilter.zipWithIndex.map { case (s: Double, i: Int) => Map("x" -> i, "y" -> (s - threshold * stdFilter(i)), "name" -> "lower", "row" -> "data") } ++
    avgFilter.zipWithIndex.map { case (s: Double, i: Int) => Map("x" -> i, "y" -> (s + threshold * stdFilter(i)), "name" -> "upper", "row" -> "data") } ++
    signals.zipWithIndex.map { case (s: Int, i: Int) => Map("x" -> i, "y" -> s, "name" -> "signal", "row" -> "signal") }

  Vegas("Smoothed Z")
    .withData(data)
    .mark(Line)
    .encodeX("x", Quant)
    .encodeY("y", Quant)
    .encodeColor(
      field="name",
      dataType=Nominal
    )
    .encodeRow("row", Ordinal)
    .show

  return signals
}

下面是一个测试，返回与Python和Groovy版本相同的结果:

val y = List(1d, 1d, 1.1d, 1d, 0.9d, 1d, 1d, 1.1d, 1d, 0.9d, 1d, 1.1d, 1d, 1d, 0.9d, 1d, 1d, 1.1d, 1d, 1d,
  1d, 1d, 1.1d, 0.9d, 1d, 1.1d, 1d, 1d, 0.9d, 1d, 1.1d, 1d, 1d, 1.1d, 1d, 0.8d, 0.9d, 1d, 1.2d, 0.9d, 1d,
  1d, 1.1d, 1.2d, 1d, 1.5d, 1d, 3d, 2d, 5d, 3d, 2d, 1d, 1d, 1d, 0.9d, 1d,
  1d, 3d, 2.6d, 4d, 3d, 3.2d, 2d, 1d, 1d, 0.8d, 4d, 4d, 2d, 2.5d, 1d, 1d, 1d)

val lag = 30
val threshold = 5d
val influence = 0d

smoothedZScore(y, lag, threshold, influence)

这里的要点

下面是在Golang中实现的Smoothed z-score算法(上图)。它假设一个[]int16 (PCM 16bit样本)的切片。你可以在这里找到要点。

/*
Settings (the ones below are examples: choose what is best for your data)
set lag to 5;          # lag 5 for the smoothing functions
set threshold to 3.5;  # 3.5 standard deviations for signal
set influence to 0.5;  # between 0 and 1, where 1 is normal influence, 0.5 is half
*/

// ZScore on 16bit WAV samples
func ZScore(samples []int16, lag int, threshold float64, influence float64) (signals []int16) {
    //lag := 20
    //threshold := 3.5
    //influence := 0.5

    signals = make([]int16, len(samples))
    filteredY := make([]int16, len(samples))
    for i, sample := range samples[0:lag] {
        filteredY[i] = sample
    }
    avgFilter := make([]int16, len(samples))
    stdFilter := make([]int16, len(samples))

    avgFilter[lag] = Average(samples[0:lag])
    stdFilter[lag] = Std(samples[0:lag])

    for i := lag + 1; i < len(samples); i++ {

        f := float64(samples[i])

        if float64(Abs(samples[i]-avgFilter[i-1])) > threshold*float64(stdFilter[i-1]) {
            if samples[i] > avgFilter[i-1] {
                signals[i] = 1
            } else {
                signals[i] = -1
            }
            filteredY[i] = int16(influence*f + (1-influence)*float64(filteredY[i-1]))
            avgFilter[i] = Average(filteredY[(i - lag):i])
            stdFilter[i] = Std(filteredY[(i - lag):i])
        } else {
            signals[i] = 0
            filteredY[i] = samples[i]
            avgFilter[i] = Average(filteredY[(i - lag):i])
            stdFilter[i] = Std(filteredY[(i - lag):i])
        }
    }

    return
}

// Average a chunk of values
func Average(chunk []int16) (avg int16) {
    var sum int64
    for _, sample := range chunk {
        if sample < 0 {
            sample *= -1
        }
        sum += int64(sample)
    }
    return int16(sum / int64(len(chunk)))
}

c++ (Qt)演示端口，交互式参数

我已经将这个算法的演示应用程序移植到c++ (Qt)上。

代码可以在GitHub上找到这里。带有安装程序的Windows(64位)构建在发布页面上。最后，我将添加一些文档和其他发布版本。

您不能绘制点，但可以从文本文件中导入它们(用空格分隔点——换行也算作空格)。您还可以调整算法参数，实时查看效果。这对于针对特定数据集调整算法以及探索参数如何影响结果非常有用。

上面的截图有些过时;从那以后，我添加了两个原始算法中没有的实验性选项:

反向处理数据集的选项(似乎至少改善了功率谱的结果)。 选项，为峰值设置硬性最小阈值。

我还在窗口中间添加了一个笨拙的缩放/平移条，只需用鼠标拖动它来缩放和平移。

模糊的构建指令:

在发布页面上有一个Windows安装程序(64位)，但如果你想从源代码构建它，要点是:

安装Qt的构建工具，然后将qmake && make放在与.pro文件相同的目录下，或者 安装Qt Creator，打开.pro文件，选择任何默认的构建配置，然后按下构建和/或运行按钮(Creator的左下角)。

我只测试过Qt5。我有91%的信心，如果你手动配置组件，Qt Creator安装程序会让你安装Qt5(如果你手动配置组件，你还需要确认是否安装了Qt Charts)。Qt6可能是一个流畅的构建，也可能不是。有一天，我将测试Qt4和Qt6，使这些文档更好。也许吧。