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.

下面是我尝试为“Smoothed z-score算法”创建一个Ruby解决方案:

module ThresholdingAlgoMixin
  def mean(array)
    array.reduce(&:+) / array.size.to_f
  end

  def stddev(array)
    array_mean = mean(array)
    Math.sqrt(array.reduce(0.0) { |a, b| a.to_f + ((b.to_f - array_mean) ** 2) } / array.size.to_f)
  end

  def thresholding_algo(lag: 5, threshold: 3.5, influence: 0.5)
    return nil if size < lag * 2
    Array.new(size, 0).tap do |signals|
      filtered = Array.new(self)

      initial_slice = take(lag)
      avg_filter = Array.new(lag - 1, 0.0) + [mean(initial_slice)]
      std_filter = Array.new(lag - 1, 0.0) + [stddev(initial_slice)]
      (lag..size-1).each do |idx|
        prev = idx - 1
        if (fetch(idx) - avg_filter[prev]).abs > threshold * std_filter[prev]
          signals[idx] = fetch(idx) > avg_filter[prev] ? 1 : -1
          filtered[idx] = (influence * fetch(idx)) + ((1-influence) * filtered[prev])
        end

        filtered_slice = filtered[idx-lag..prev]
        avg_filter[idx] = mean(filtered_slice)
        std_filter[idx] = stddev(filtered_slice)
      end
    end
  end
end

以及示例用法:

test_data = [
  1, 1, 1.1, 1, 0.9, 1, 1, 1.1, 1, 0.9, 1, 1.1, 1, 1, 0.9, 1,
  1, 1.1, 1, 1, 1, 1, 1.1, 0.9, 1, 1.1, 1, 1, 0.9, 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, 0.8, 4, 4, 2, 2.5, 1, 1, 1
].extend(ThresholdingAlgoMixin)

puts test_data.thresholding_algo.inspect

# Output: [
#   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,
#   0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, -1, 0, 0, 0,
#   0, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1,
#   1, 1, 0, 0, 0, -1, -1, 0, 0, 0, 0, 0, 0, 0, 0
# ]

下面是这个答案的平滑z-score算法的c++实现

std::vector<int> smoothedZScore(std::vector<float> input)
{   
    //lag 5 for the smoothing functions
    int lag = 5;
    //3.5 standard deviations for signal
    float threshold = 3.5;
    //between 0 and 1, where 1 is normal influence, 0.5 is half
    float influence = .5;

    if (input.size() <= lag + 2)
    {
        std::vector<int> emptyVec;
        return emptyVec;
    }

    //Initialise variables
    std::vector<int> signals(input.size(), 0.0);
    std::vector<float> filteredY(input.size(), 0.0);
    std::vector<float> avgFilter(input.size(), 0.0);
    std::vector<float> stdFilter(input.size(), 0.0);
    std::vector<float> subVecStart(input.begin(), input.begin() + lag);
    avgFilter[lag] = mean(subVecStart);
    stdFilter[lag] = stdDev(subVecStart);

    for (size_t i = lag + 1; i < input.size(); i++)
    {
        if (std::abs(input[i] - avgFilter[i - 1]) > threshold * stdFilter[i - 1])
        {
            if (input[i] > avgFilter[i - 1])
            {
                signals[i] = 1; //# Positive signal
            }
            else
            {
                signals[i] = -1; //# Negative signal
            }
            //Make influence lower
            filteredY[i] = influence* input[i] + (1 - influence) * filteredY[i - 1];
        }
        else
        {
            signals[i] = 0; //# No signal
            filteredY[i] = input[i];
        }
        //Adjust the filters
        std::vector<float> subVec(filteredY.begin() + i - lag, filteredY.begin() + i);
        avgFilter[i] = mean(subVec);
        stdFilter[i] = stdDev(subVec);
    }
    return signals;
}

下面是平滑z-score算法的Groovy (Java)实现(见上面的答案)。

/**
 * "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)
 */

public HashMap<String, List<Object>> thresholdingAlgo(List<Double> y, Long lag, Double threshold, Double influence) {
    //init stats instance
    SummaryStatistics stats = new SummaryStatistics()

    //the results (peaks, 1 or -1) of our algorithm
    List<Integer> signals = new ArrayList<Integer>(Collections.nCopies(y.size(), 0))
    //filter out the signals (peaks) from our original list (using influence arg)
    List<Double> filteredY = new ArrayList<Double>(y)
    //the current average of the rolling window
    List<Double> avgFilter = new ArrayList<Double>(Collections.nCopies(y.size(), 0.0d))
    //the current standard deviation of the rolling window
    List<Double> stdFilter = new ArrayList<Double>(Collections.nCopies(y.size(), 0.0d))
    //init avgFilter and stdFilter
    (0..lag-1).each { stats.addValue(y[it as int]) }
    avgFilter[lag - 1 as int] = stats.getMean()
    stdFilter[lag - 1 as int] = Math.sqrt(stats.getPopulationVariance()) //getStandardDeviation() uses sample variance (not what we want)
    stats.clear()
    //loop input starting at end of rolling window
    (lag..y.size()-1).each { i ->
        //if the distance between the current value and average is enough standard deviations (threshold) away
        if (Math.abs((y[i as int] - avgFilter[i - 1 as int]) as Double) > threshold * stdFilter[i - 1 as int]) {
            //this is a signal (i.e. peak), determine if it is a positive or negative signal
            signals[i as int] = (y[i as int] > avgFilter[i - 1 as int]) ? 1 : -1
            //filter this signal out using influence
            filteredY[i as int] = (influence * y[i as int]) + ((1-influence) * filteredY[i - 1 as int])
        } else {
            //ensure this signal remains a zero
            signals[i as int] = 0
            //ensure this value is not filtered
            filteredY[i as int] = y[i as int]
        }
        //update rolling average and deviation
        (i - lag..i-1).each { stats.addValue(filteredY[it as int] as Double) }
        avgFilter[i as int] = stats.getMean()
        stdFilter[i as int] = Math.sqrt(stats.getPopulationVariance()) //getStandardDeviation() uses sample variance (not what we want)
        stats.clear()
    }

    return [
        signals  : signals,
        avgFilter: avgFilter,
        stdFilter: stdFilter
    ]
}

下面是同一个数据集上的测试，其结果与上面的Python / numpy实现相同。

    // Data
    def y = [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]

    // Settings
    def lag = 30
    def threshold = 5
    def influence = 0


    def thresholdingResults = thresholdingAlgo((List<Double>) y, (Long) lag, (Double) threshold, (Double) influence)

    println y.size()
    println thresholdingResults.signals.size()
    println thresholdingResults.signals

    thresholdingResults.signals.eachWithIndex { x, idx ->
        if (x) {
            println y[idx]
        }
    }

下面是@Jean-Paul为Arduino微控制器设计的平滑z分数的C语言实现，用于获取加速度计读数，并判断撞击的方向是来自左边还是右边。这表现得非常好，因为这个设备返回一个反弹信号。这是设备对峰值检测算法的输入-显示了来自右边的冲击，然后是来自左边的冲击。你可以看到最初的峰值然后传感器的振荡。

#include <stdio.h>
#include <math.h>
#include <string.h>


#define SAMPLE_LENGTH 1000

float stddev(float data[], int len);
float mean(float data[], int len);
void thresholding(float y[], int signals[], int lag, float threshold, float influence);


void thresholding(float y[], int signals[], int lag, float threshold, float influence) {
    memset(signals, 0, sizeof(int) * SAMPLE_LENGTH);
    float filteredY[SAMPLE_LENGTH];
    memcpy(filteredY, y, sizeof(float) * SAMPLE_LENGTH);
    float avgFilter[SAMPLE_LENGTH];
    float stdFilter[SAMPLE_LENGTH];

    avgFilter[lag - 1] = mean(y, lag);
    stdFilter[lag - 1] = stddev(y, lag);

    for (int i = lag; i < SAMPLE_LENGTH; i++) {
        if (fabsf(y[i] - avgFilter[i-1]) > threshold * stdFilter[i-1]) {
            if (y[i] > avgFilter[i-1]) {
                signals[i] = 1;
            } else {
                signals[i] = -1;
            }
            filteredY[i] = influence * y[i] + (1 - influence) * filteredY[i-1];
        } else {
            signals[i] = 0;
        }
        avgFilter[i] = mean(filteredY + i-lag, lag);
        stdFilter[i] = stddev(filteredY + i-lag, lag);
    }
}

float mean(float data[], int len) {
    float sum = 0.0, mean = 0.0;

    int i;
    for(i=0; i<len; ++i) {
        sum += data[i];
    }

    mean = sum/len;
    return mean;


}

float stddev(float data[], int len) {
    float the_mean = mean(data, len);
    float standardDeviation = 0.0;

    int i;
    for(i=0; i<len; ++i) {
        standardDeviation += pow(data[i] - the_mean, 2);
    }

    return sqrt(standardDeviation/len);
}

int main() {
    printf("Hello, World!\n");
    int lag = 100;
    float threshold = 5;
    float influence = 0;
    float y[]=  {1,1,1.1,1,0.9,1,1,1.1,1,0.9,1,1.1,1,1,0.9,1,1,1.1,1,1,1,1,1.1,0.9,1,1.1,1,1,0.9,
  ....
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,       2.6,4,3,3.2,2,1,1,0.8,4,4,2,2.5,1,1,1,1.2,1,1.5,1,3,2,5,3,2,1,1,1,0.9,1,1,3,
       2.6,4,3,3.2,2,1,1,0.8,4,4,2,2.5,1,1,1}

    int signal[SAMPLE_LENGTH];

    thresholding(y, signal,  lag, threshold, influence);

    return 0;
}

她的结果是影响= 0

不是很好，但这里的影响力= 1

这很好。

原文的附录1:Matlab和R翻译

Matlab代码

function [signals,avgFilter,stdFilter] = ThresholdingAlgo(y,lag,threshold,influence)
% Initialise signal results
signals = zeros(length(y),1);
% Initialise filtered series
filteredY = y(1:lag+1);
% Initialise filters
avgFilter(lag+1,1) = mean(y(1:lag+1));
stdFilter(lag+1,1) = std(y(1:lag+1));
% Loop over all datapoints y(lag+2),...,y(t)
for i=lag+2:length(y)
    % If new value is a specified number of deviations away
    if abs(y(i)-avgFilter(i-1)) > threshold*stdFilter(i-1)
        if y(i) > avgFilter(i-1)
            % Positive signal
            signals(i) = 1;
        else
            % Negative signal
            signals(i) = -1;
        end
        % Make influence lower
        filteredY(i) = influence*y(i)+(1-influence)*filteredY(i-1);
    else
        % No signal
        signals(i) = 0;
        filteredY(i) = y(i);
    end
    % Adjust the filters
    avgFilter(i) = mean(filteredY(i-lag:i));
    stdFilter(i) = std(filteredY(i-lag:i));
end
% Done, now return results
end

例子:

% Data
y = [1 1 1.1 1 0.9 1 1 1.1 1 0.9 1 1.1 1 1 0.9 1 1 1.1 1 1,...
    1 1 1.1 0.9 1 1.1 1 1 0.9 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 0.8 4 4 2 2.5 1 1 1];

% Settings
lag = 30;
threshold = 5;
influence = 0;

% Get results
[signals,avg,dev] = ThresholdingAlgo(y,lag,threshold,influence);

figure; subplot(2,1,1); hold on;
x = 1:length(y); ix = lag+1:length(y);
area(x(ix),avg(ix)+threshold*dev(ix),'FaceColor',[0.9 0.9 0.9],'EdgeColor','none');
area(x(ix),avg(ix)-threshold*dev(ix),'FaceColor',[1 1 1],'EdgeColor','none');
plot(x(ix),avg(ix),'LineWidth',1,'Color','cyan','LineWidth',1.5);
plot(x(ix),avg(ix)+threshold*dev(ix),'LineWidth',1,'Color','green','LineWidth',1.5);
plot(x(ix),avg(ix)-threshold*dev(ix),'LineWidth',1,'Color','green','LineWidth',1.5);
plot(1:length(y),y,'b');
subplot(2,1,2);
stairs(signals,'r','LineWidth',1.5); ylim([-1.5 1.5]);

R代码

ThresholdingAlgo <- function(y,lag,threshold,influence) {
  signals <- rep(0,length(y))
  filteredY <- y[0:lag]
  avgFilter <- NULL
  stdFilter <- NULL
  avgFilter[lag] <- mean(y[0:lag], na.rm=TRUE)
  stdFilter[lag] <- sd(y[0:lag], na.rm=TRUE)
  for (i in (lag+1):length(y)){
    if (abs(y[i]-avgFilter[i-1]) > threshold*stdFilter[i-1]) {
      if (y[i] > avgFilter[i-1]) {
        signals[i] <- 1;
      } else {
        signals[i] <- -1;
      }
      filteredY[i] <- influence*y[i]+(1-influence)*filteredY[i-1]
    } else {
      signals[i] <- 0
      filteredY[i] <- y[i]
    }
    avgFilter[i] <- mean(filteredY[(i-lag):i], na.rm=TRUE)
    stdFilter[i] <- sd(filteredY[(i-lag):i], na.rm=TRUE)
  }
  return(list("signals"=signals,"avgFilter"=avgFilter,"stdFilter"=stdFilter))
}

例子:

# Data
y <- c(1,1,1.1,1,0.9,1,1,1.1,1,0.9,1,1.1,1,1,0.9,1,1,1.1,1,1,1,1,1.1,0.9,1,1.1,1,1,0.9,
       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,
       2.6,4,3,3.2,2,1,1,0.8,4,4,2,2.5,1,1,1)

lag       <- 30
threshold <- 5
influence <- 0

# Run algo with lag = 30, threshold = 5, influence = 0
result <- ThresholdingAlgo(y,lag,threshold,influence)

# Plot result
par(mfrow = c(2,1),oma = c(2,2,0,0) + 0.1,mar = c(0,0,2,1) + 0.2)
plot(1:length(y),y,type="l",ylab="",xlab="") 
lines(1:length(y),result$avgFilter,type="l",col="cyan",lwd=2)
lines(1:length(y),result$avgFilter+threshold*result$stdFilter,type="l",col="green",lwd=2)
lines(1:length(y),result$avgFilter-threshold*result$stdFilter,type="l",col="green",lwd=2)
plot(result$signals,type="S",col="red",ylab="",xlab="",ylim=c(-1.5,1.5),lwd=2)

这段代码(两种语言)将为原始问题的数据产生以下结果:

附录2原答案:Matlab演示代码

(点击创建数据)

function [] = RobustThresholdingDemo()

%% SPECIFICATIONS
lag         = 5;       % lag for the smoothing
threshold   = 3.5;     % number of st.dev. away from the mean to signal
influence   = 0.3;     % when signal: how much influence for new data? (between 0 and 1)
                       % 1 is normal influence, 0.5 is half      
%% START DEMO
DemoScreen(30,lag,threshold,influence);

end

function [signals,avgFilter,stdFilter] = ThresholdingAlgo(y,lag,threshold,influence)
signals = zeros(length(y),1);
filteredY = y(1:lag+1);
avgFilter(lag+1,1) = mean(y(1:lag+1));
stdFilter(lag+1,1) = std(y(1:lag+1));
for i=lag+2:length(y)
    if abs(y(i)-avgFilter(i-1)) > threshold*stdFilter(i-1)
        if y(i) > avgFilter(i-1)
            signals(i) = 1;
        else
            signals(i) = -1;
        end
        filteredY(i) = influence*y(i)+(1-influence)*filteredY(i-1);
    else
        signals(i) = 0;
        filteredY(i) = y(i);
    end
    avgFilter(i) = mean(filteredY(i-lag:i));
    stdFilter(i) = std(filteredY(i-lag:i));
end
end

% Demo screen function
function [] = DemoScreen(n,lag,threshold,influence)
figure('Position',[200 100,1000,500]);
subplot(2,1,1);
title(sprintf(['Draw data points (%.0f max)      [settings: lag = %.0f, '...
    'threshold = %.2f, influence = %.2f]'],n,lag,threshold,influence));
ylim([0 5]); xlim([0 50]);
H = gca; subplot(2,1,1);
set(H, 'YLimMode', 'manual'); set(H, 'XLimMode', 'manual');
set(H, 'YLim', get(H,'YLim')); set(H, 'XLim', get(H,'XLim'));
xg = []; yg = [];
for i=1:n
    try
        [xi,yi] = ginput(1);
    catch
        return;
    end
    xg = [xg xi]; yg = [yg yi];
    if i == 1
        subplot(2,1,1); hold on;
        plot(H, xg(i),yg(i),'r.'); 
        text(xg(i),yg(i),num2str(i),'FontSize',7);
    end
    if length(xg) > lag
        [signals,avg,dev] = ...
            ThresholdingAlgo(yg,lag,threshold,influence);
        area(xg(lag+1:end),avg(lag+1:end)+threshold*dev(lag+1:end),...
            'FaceColor',[0.9 0.9 0.9],'EdgeColor','none');
        area(xg(lag+1:end),avg(lag+1:end)-threshold*dev(lag+1:end),...
            'FaceColor',[1 1 1],'EdgeColor','none');
        plot(xg(lag+1:end),avg(lag+1:end),'LineWidth',1,'Color','cyan');
        plot(xg(lag+1:end),avg(lag+1:end)+threshold*dev(lag+1:end),...
            'LineWidth',1,'Color','green');
        plot(xg(lag+1:end),avg(lag+1:end)-threshold*dev(lag+1:end),...
            'LineWidth',1,'Color','green');
        subplot(2,1,2); hold on; title('Signal output');
        stairs(xg(lag+1:end),signals(lag+1:end),'LineWidth',2,'Color','blue');
        ylim([-2 2]); xlim([0 50]); hold off;
    end
    subplot(2,1,1); hold on;
    for j=2:i
        plot(xg([j-1:j]),yg([j-1:j]),'r'); plot(H,xg(j),yg(j),'r.');
        text(xg(j),yg(j),num2str(j),'FontSize',7);
    end
end
end