@Jean-Paul Smoothed Z Score算法的Dart版本:

class SmoothedZScore {
  int lag = 5;
  num threshold = 10;
  num influence = 0.5;

  num sum(List<num> a) {
    num s = 0;
    for (int i = 0; i < a.length; i++) s += a[i];
    return s;
  }

  num mean(List<num> a) {
    return sum(a) / a.length;
  }

  num stddev(List<num> arr) {
    num arrMean = mean(arr);
    num dev = 0;
    for (int i = 0; i < arr.length; i++) dev += (arr[i] - arrMean) * (arr[i] - arrMean);
    return sqrt(dev / arr.length);
  }

  List<int> smoothedZScore(List<num> y) {
    if (y.length < lag + 2) {
      throw 'y data array too short($y.length) for given lag of $lag';
    }

    // init variables
    List<int> signals = List.filled(y.length, 0);
    List<num> filteredY = List<num>.from(y);
    List<num> leadIn = y.sublist(0, lag);

    var avgFilter = List<num>.filled(y.length, 0);
    var stdFilter = List<num>.filled(y.length, 0);
    avgFilter[lag - 1] = mean(leadIn);
    stdFilter[lag - 1] = stddev(leadIn);

    for (var i = lag; i < y.length; i++) {
      if ((y[i] - avgFilter[i - 1]).abs() > (threshold * stdFilter[i - 1])) {
        signals[i] = y[i] > avgFilter[i - 1] ? 1 : -1;
        // make influence lower
        filteredY[i] = influence * y[i] + (1 - influence) * filteredY[i - 1];
      } else {
        signals[i] = 0; // no signal
        filteredY[i] = y[i];
      }

      // adjust the filters
      List<num> yLag = filteredY.sublist(i - lag, i);
      avgFilter[i] = mean(yLag);
      stdFilter[i] = stddev(yLag);
    }

    return signals;
  }
}

函数scipy.signal。Find_peaks，顾名思义，在这方面很有用。但是要得到好的峰值提取，必须了解其参数宽度、阈值、距离和突出度。

根据我的测试和文档，突出的概念是“有用的概念”，可以保留好的峰值，丢弃噪声峰值。

什么是(地形)突出?它是“从山顶下降到任何更高地形所需的最低高度”，如下图所示:

这个想法是:

突出位置越高，山峰就越“重要”。

在计算拓扑学中，持久同调的思想导致一个有效的 -快如排序数字-解决方案。它不仅检测峰值，还以一种自然的方式量化峰值的“重要性”，使您能够选择对您重要的峰值。

算法的总结。 在一维设置(时间序列，实值信号)中，算法可以简单地描述为下图:

Think of the function graph (or its sub-level set) as a landscape and consider a decreasing water level starting at level infinity (or 1.8 in this picture). While the level decreases, at local maxima islands pop up. At local minima these islands merge together. One detail in this idea is that the island that appeared later in time is merged into the island that is older. The "persistence" of an island is its birth time minus its death time. The lengths of the blue bars depict the persistence, which is the above mentioned "significance" of a peak.

效率。 在对函数值进行排序之后，找到一个在线性时间内运行的实现并不难——实际上它是一个单一的、简单的循环。因此，这种实现在实践中应该是快速的，也很容易实现。

参考文献 一篇关于整个故事的文章和对持久同调(计算代数拓扑中的一个领域)动机的引用可以在这里找到: https://www.sthu.org/blog/13-perstopology-peakdetection/index.html

如果边界值或其他标准取决于未来值，那么唯一的解决方案(没有时间机器，或其他关于未来值的知识)是推迟任何决定，直到有足够的未来值。如果你想要一个高于均值的水平，例如，20点，那么你必须等到你至少有19点才能做出任何峰值决策，否则下一个新点可能会完全超过你19点之前的阈值。

Added: If the statistical distribution of the peak heights could be heavy tailed, instead of Uniform or Gaussian, then you may need to wait until you see several thousand peaks before it starts to become unlikely that a hidden Pareto distribution won't produce a peak many times larger than any you currently have seen before or have in your current plot. Unless you somehow know in advance that the very next point can't be 1e20, it could appear, which after rescaling your plot's Y dimension, would be flat up until that point.

另外，这个算法对我来说也很好…

sensitivity = 4; dwindow = 4; k = dwindow; data = [1., 1., 1., 1., 1., 1., 1., 1.1, 1., 0.8, 0.9, 1., 1.2, 0.9, 1., 1., 1.1, 1.2, 1., 1.5, 1., 3., 2., 5., 3., 2., 1., 1., 1., 0.9, 1., 1., 3., 2.6, 4., 3., 3.2, 2., 1., 1., 1., 1., 1. ]; //data = data.concat(data); //data = data.concat(data); var data1 = [{ name: 'original source', y: data }]; Plotly.newPlot('stage1', data1, { title: 'Sensor data', yaxis: { title: 'signal' } }); filtered = data.map((a,b,c)=>a>=Math.max(...c.slice(b-k,b))?a**3:0); var data2 = [{ name: 'filtered source', y: filtered }]; Plotly.newPlot('stage2', data2, { title: 'Filtered data<br>aₙ = aₙ³', yaxis: { title: 'signal' } }); dwindow = 6; k = dwindow; detected = filtered.map((a,b,c)=>a>Math.max(...c.slice(2))/sensitivity).map((a,b,c)=>(b>k) && c.slice(b-k,b).indexOf(a)==-1 ); var data3 = [{ name: 'detected peaks', y: detected }]; Plotly.newPlot('stage3', data3, { title: 'Maximum in a window of 6', yaxis: { title: 'signal' } }); dwindow = 10; k = dwindow; detected = filtered.map((a, b, c) => a > Math.max(...c.slice(2)) / 20).map((a, b, c) => (b > k) && c.slice(b - k, b).indexOf(a) == -1) var data4 = [{ name: 'detected peaks', y: detected }]; Plotly.newPlot('stage4', data4, { title: 'Maximum in a window of 10', yaxis: { title: 'signal' } }); <script src="https://cdn.jsdelivr.net/npm/plotly.js@2.16.5/dist/plotly.min.js"></script> <div id="stage1"></div> <div id="stage2"></div> <div id="stage3"></div> <div id="stage4"></div>

根据@Jean-Paul提出的解决方案，我用c#实现了他的算法

public class ZScoreOutput
{
    public List<double> input;
    public List<int> signals;
    public List<double> avgFilter;
    public List<double> filtered_stddev;
}

public static class ZScore
{
    public static ZScoreOutput StartAlgo(List<double> input, int lag, double threshold, double influence)
    {
        // init variables!
        int[] signals = new int[input.Count];
        double[] filteredY = new List<double>(input).ToArray();
        double[] avgFilter = new double[input.Count];
        double[] stdFilter = new double[input.Count];

        var initialWindow = new List<double>(filteredY).Skip(0).Take(lag).ToList();

        avgFilter[lag - 1] = Mean(initialWindow);
        stdFilter[lag - 1] = StdDev(initialWindow);

        for (int i = lag; i < input.Count; i++)
        {
            if (Math.Abs(input[i] - avgFilter[i - 1]) > threshold * stdFilter[i - 1])
            {
                signals[i] = (input[i] > avgFilter[i - 1]) ? 1 : -1;
                filteredY[i] = influence * input[i] + (1 - influence) * filteredY[i - 1];
            }
            else
            {
                signals[i] = 0;
                filteredY[i] = input[i];
            }

            // Update rolling average and deviation
            var slidingWindow = new List<double>(filteredY).Skip(i - lag).Take(lag+1).ToList();

            var tmpMean = Mean(slidingWindow);
            var tmpStdDev = StdDev(slidingWindow);

            avgFilter[i] = Mean(slidingWindow);
            stdFilter[i] = StdDev(slidingWindow);
        }

        // Copy to convenience class 
        var result = new ZScoreOutput();
        result.input = input;
        result.avgFilter       = new List<double>(avgFilter);
        result.signals         = new List<int>(signals);
        result.filtered_stddev = new List<double>(stdFilter);

        return result;
    }

    private static double Mean(List<double> list)
    {
        // Simple helper function! 
        return list.Average();
    }

    private static double StdDev(List<double> values)
    {
        double ret = 0;
        if (values.Count() > 0)
        {
            double avg = values.Average();
            double sum = values.Sum(d => Math.Pow(d - avg, 2));
            ret = Math.Sqrt((sum) / (values.Count() - 1));
        }
        return ret;
    }
}

使用示例:

var input = new List<double> {1.0, 1.0, 1.1, 1.0, 0.9, 1.0, 1.0, 1.1, 1.0, 0.9, 1.0,
    1.1, 1.0, 1.0, 0.9, 1.0, 1.0, 1.1, 1.0, 1.0, 1.0, 1.0, 1.1, 0.9, 1.0, 1.1, 1.0, 1.0, 0.9,
    1.0, 1.1, 1.0, 1.0, 1.1, 1.0, 0.8, 0.9, 1.0, 1.2, 0.9, 1.0, 1.0, 1.1, 1.2, 1.0, 1.5, 1.0,
    3.0, 2.0, 5.0, 3.0, 2.0, 1.0, 1.0, 1.0, 0.9, 1.0, 1.0, 3.0, 2.6, 4.0, 3.0, 3.2, 2.0, 1.0,
    1.0, 0.8, 4.0, 4.0, 2.0, 2.5, 1.0, 1.0, 1.0};

int lag = 30;
double threshold = 5.0;
double influence = 0.0;

var output = ZScore.StartAlgo(input, lag, threshold, influence);