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。

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

不需要将极大值与平均值进行比较，还可以将极大值与相邻的最小值进行比较，其中最小值仅定义在噪声阈值之上。 如果局部最大值是>的3倍(或其他置信因子)相邻的最小值，那么这个最大值就是一个峰值。 移动窗口越宽，峰值的确定越准确。 上面使用了以窗口中间为中心的计算， 顺便说一下，而不是在窗口结束时计算(== lag)。

请注意，最大值必须被视为信号之前的增加 之后下降。

c++实现

#include <iostream>
#include <vector>
#include <algorithm>
#include <unordered_map>
#include <cmath>
#include <iterator>
#include <numeric>

using namespace std;

typedef long double ld;
typedef unsigned int uint;
typedef std::vector<ld>::iterator vec_iter_ld;

/**
 * Overriding the ostream operator for pretty printing vectors.
 */
template<typename T>
std::ostream &operator<<(std::ostream &os, std::vector<T> vec) {
    os << "[";
    if (vec.size() != 0) {
        std::copy(vec.begin(), vec.end() - 1, std::ostream_iterator<T>(os, " "));
        os << vec.back();
    }
    os << "]";
    return os;
}

/**
 * This class calculates mean and standard deviation of a subvector.
 * This is basically stats computation of a subvector of a window size qual to "lag".
 */
class VectorStats {
public:
    /**
     * Constructor for VectorStats class.
     *
     * @param start - This is the iterator position of the start of the window,
     * @param end   - This is the iterator position of the end of the window,
     */
    VectorStats(vec_iter_ld start, vec_iter_ld end) {
        this->start = start;
        this->end = end;
        this->compute();
    }

    /**
     * This method calculates the mean and standard deviation using STL function.
     * This is the Two-Pass implementation of the Mean & Variance calculation.
     */
    void compute() {
        ld sum = std::accumulate(start, end, 0.0);
        uint slice_size = std::distance(start, end);
        ld mean = sum / slice_size;
        std::vector<ld> diff(slice_size);
        std::transform(start, end, diff.begin(), [mean](ld x) { return x - mean; });
        ld sq_sum = std::inner_product(diff.begin(), diff.end(), diff.begin(), 0.0);
        ld std_dev = std::sqrt(sq_sum / slice_size);

        this->m1 = mean;
        this->m2 = std_dev;
    }

    ld mean() {
        return m1;
    }

    ld standard_deviation() {
        return m2;
    }

private:
    vec_iter_ld start;
    vec_iter_ld end;
    ld m1;
    ld m2;
};

/**
 * This is the implementation of the Smoothed Z-Score Algorithm.
 * This is direction translation of https://stackoverflow.com/a/22640362/1461896.
 *
 * @param input - input signal
 * @param lag - the lag of the moving window
 * @param threshold - the z-score at which the algorithm signals
 * @param influence - the influence (between 0 and 1) of new signals on the mean and standard deviation
 * @return a hashmap containing the filtered signal and corresponding mean and standard deviation.
 */
unordered_map<string, vector<ld>> z_score_thresholding(vector<ld> input, int lag, ld threshold, ld influence) {
    unordered_map<string, vector<ld>> output;

    uint n = (uint) input.size();
    vector<ld> signals(input.size());
    vector<ld> filtered_input(input.begin(), input.end());
    vector<ld> filtered_mean(input.size());
    vector<ld> filtered_stddev(input.size());

    VectorStats lag_subvector_stats(input.begin(), input.begin() + lag);
    filtered_mean[lag - 1] = lag_subvector_stats.mean();
    filtered_stddev[lag - 1] = lag_subvector_stats.standard_deviation();

    for (int i = lag; i < n; i++) {
        if (abs(input[i] - filtered_mean[i - 1]) > threshold * filtered_stddev[i - 1]) {
            signals[i] = (input[i] > filtered_mean[i - 1]) ? 1.0 : -1.0;
            filtered_input[i] = influence * input[i] + (1 - influence) * filtered_input[i - 1];
        } else {
            signals[i] = 0.0;
            filtered_input[i] = input[i];
        }
        VectorStats lag_subvector_stats(filtered_input.begin() + (i - lag), filtered_input.begin() + i);
        filtered_mean[i] = lag_subvector_stats.mean();
        filtered_stddev[i] = lag_subvector_stats.standard_deviation();
    }

    output["signals"] = signals;
    output["filtered_mean"] = filtered_mean;
    output["filtered_stddev"] = filtered_stddev;

    return output;
};

int main() {
    vector<ld> input = {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;
    ld threshold = 5.0;
    ld influence = 0.0;
    unordered_map<string, vector<ld>> output = z_score_thresholding(input, lag, threshold, influence);
    cout << output["signals"] << endl;
}

下面是一个基于Groovy回答的实际Java实现。(我知道已经发布了Groovy和Kotlin实现，但对于像我这样只做Java的人来说，弄清楚如何在其他语言和Java之间转换真的很麻烦)。

(结果与他人图表相匹配)

算法实现

import java.util.ArrayList;
import java.util.Collections;
import java.util.HashMap;
import java.util.List;

import org.apache.commons.math3.stat.descriptive.SummaryStatistics;

public class SignalDetector {

    public HashMap<String, List> analyzeDataForSignals(List<Double> data, int 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(data.size(), 0));

        // filter out the signals (peaks) from our original list (using influence arg)
        List<Double> filteredData = new ArrayList<Double>(data);

        // the current average of the rolling window
        List<Double> avgFilter = new ArrayList<Double>(Collections.nCopies(data.size(), 0.0d));

        // the current standard deviation of the rolling window
        List<Double> stdFilter = new ArrayList<Double>(Collections.nCopies(data.size(), 0.0d));

        // init avgFilter and stdFilter
        for (int i = 0; i < lag; i++) {
            stats.addValue(data.get(i));
        }
        avgFilter.set(lag - 1, stats.getMean());
        stdFilter.set(lag - 1, Math.sqrt(stats.getPopulationVariance())); // getStandardDeviation() uses sample variance
        stats.clear();

        // loop input starting at end of rolling window
        for (int i = lag; i < data.size(); i++) {

            // if the distance between the current value and average is enough standard deviations (threshold) away
            if (Math.abs((data.get(i) - avgFilter.get(i - 1))) > threshold * stdFilter.get(i - 1)) {

                // this is a signal (i.e. peak), determine if it is a positive or negative signal
                if (data.get(i) > avgFilter.get(i - 1)) {
                    signals.set(i, 1);
                } else {
                    signals.set(i, -1);
                }

                // filter this signal out using influence
                filteredData.set(i, (influence * data.get(i)) + ((1 - influence) * filteredData.get(i - 1)));
            } else {
                // ensure this signal remains a zero
                signals.set(i, 0);
                // ensure this value is not filtered
                filteredData.set(i, data.get(i));
            }

            // update rolling average and deviation
            for (int j = i - lag; j < i; j++) {
                stats.addValue(filteredData.get(j));
            }
            avgFilter.set(i, stats.getMean());
            stdFilter.set(i, Math.sqrt(stats.getPopulationVariance()));
            stats.clear();
        }

        HashMap<String, List> returnMap = new HashMap<String, List>();
        returnMap.put("signals", signals);
        returnMap.put("filteredData", filteredData);
        returnMap.put("avgFilter", avgFilter);
        returnMap.put("stdFilter", stdFilter);

        return returnMap;

    } // end
}

主要方法

import java.text.DecimalFormat;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.HashMap;
import java.util.List;

public class Main {

    public static void main(String[] args) throws Exception {
        DecimalFormat df = new DecimalFormat("#0.000");

        ArrayList<Double> data = new ArrayList<Double>(Arrays.asList(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));

        SignalDetector signalDetector = new SignalDetector();
        int lag = 30;
        double threshold = 5;
        double influence = 0;

        HashMap<String, List> resultsMap = signalDetector.analyzeDataForSignals(data, lag, threshold, influence);
        // print algorithm params
        System.out.println("lag: " + lag + "\t\tthreshold: " + threshold + "\t\tinfluence: " + influence);

        System.out.println("Data size: " + data.size());
        System.out.println("Signals size: " + resultsMap.get("signals").size());

        // print data
        System.out.print("Data:\t\t");
        for (double d : data) {
            System.out.print(df.format(d) + "\t");
        }
        System.out.println();

        // print signals
        System.out.print("Signals:\t");
        List<Integer> signalsList = resultsMap.get("signals");
        for (int i : signalsList) {
            System.out.print(df.format(i) + "\t");
        }
        System.out.println();

        // print filtered data
        System.out.print("Filtered Data:\t");
        List<Double> filteredDataList = resultsMap.get("filteredData");
        for (double d : filteredDataList) {
            System.out.print(df.format(d) + "\t");
        }
        System.out.println();

        // print running average
        System.out.print("Avg Filter:\t");
        List<Double> avgFilterList = resultsMap.get("avgFilter");
        for (double d : avgFilterList) {
            System.out.print(df.format(d) + "\t");
        }
        System.out.println();

        // print running std
        System.out.print("Std filter:\t");
        List<Double> stdFilterList = resultsMap.get("stdFilter");
        for (double d : stdFilterList) {
            System.out.print(df.format(d) + "\t");
        }
        System.out.println();

        System.out.println();
        for (int i = 0; i < signalsList.size(); i++) {
            if (signalsList.get(i) != 0) {
                System.out.println("Point " + i + " gave signal " + signalsList.get(i));
            }
        }
    }
}

结果

lag: 30     threshold: 5.0      influence: 0.0
Data size: 74
Signals size: 74
Data:           1.000   1.000   1.100   1.000   0.900   1.000   1.000   1.100   1.000   0.900   1.000   1.100   1.000   1.000   0.900   1.000   1.000   1.100   1.000   1.000   1.000   1.000   1.100   0.900   1.000   1.100   1.000   1.000   0.900   1.000   1.100   1.000   1.000   1.100   1.000   0.800   0.900   1.000   1.200   0.900   1.000   1.000   1.100   1.200   1.000   1.500   1.000   3.000   2.000   5.000   3.000   2.000   1.000   1.000   1.000   0.900   1.000   1.000   3.000   2.600   4.000   3.000   3.200   2.000   1.000   1.000   0.800   4.000   4.000   2.000   2.500   1.000   1.000   1.000   
Signals:        0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   1.000   0.000   1.000   1.000   1.000   1.000   1.000   0.000   0.000   0.000   0.000   0.000   0.000   1.000   1.000   1.000   1.000   1.000   1.000   0.000   0.000   0.000   1.000   1.000   1.000   1.000   0.000   0.000   0.000   
Filtered Data:  1.000   1.000   1.100   1.000   0.900   1.000   1.000   1.100   1.000   0.900   1.000   1.100   1.000   1.000   0.900   1.000   1.000   1.100   1.000   1.000   1.000   1.000   1.100   0.900   1.000   1.100   1.000   1.000   0.900   1.000   1.100   1.000   1.000   1.100   1.000   0.800   0.900   1.000   1.200   0.900   1.000   1.000   1.100   1.200   1.000   1.000   1.000   1.000   1.000   1.000   1.000   1.000   1.000   1.000   1.000   0.900   1.000   1.000   1.000   1.000   1.000   1.000   1.000   1.000   1.000   1.000   0.800   0.800   0.800   0.800   0.800   1.000   1.000   1.000   
Avg Filter:     0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   1.003   1.003   1.007   1.007   1.003   1.007   1.010   1.003   1.000   0.997   1.003   1.003   1.003   1.000   1.003   1.010   1.013   1.013   1.013   1.010   1.010   1.010   1.010   1.010   1.007   1.010   1.010   1.003   1.003   1.003   1.007   1.007   1.003   1.003   1.003   1.000   1.000   1.007   1.003   0.997   0.983   0.980   0.973   0.973   0.970   
Std filter:     0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.000   0.060   0.060   0.063   0.063   0.060   0.063   0.060   0.071   0.073   0.071   0.080   0.080   0.080   0.077   0.080   0.087   0.085   0.085   0.085   0.083   0.083   0.083   0.083   0.083   0.081   0.079   0.079   0.080   0.080   0.080   0.077   0.077   0.075   0.075   0.075   0.073   0.073   0.063   0.071   0.080   0.078   0.083   0.089   0.089   0.086   

Point 45 gave signal 1
Point 47 gave signal 1
Point 48 gave signal 1
Point 49 gave signal 1
Point 50 gave signal 1
Point 51 gave signal 1
Point 58 gave signal 1
Point 59 gave signal 1
Point 60 gave signal 1
Point 61 gave signal 1
Point 62 gave signal 1
Point 63 gave signal 1
Point 67 gave signal 1
Point 68 gave signal 1
Point 69 gave signal 1
Point 70 gave signal 1

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)))
}