假设你的数据来自传感器(所以算法不可能知道未来的任何事情)，

我做了这个算法，它与我在自己的项目中获得的数据非常好。

该算法有2个参数:灵敏度和窗口。

最后，只需一行代码就可以得到你的结果:

detected=data.map((a, b, c) => (a > 0) ? c[b] ** 4 * c[b - 1] ** 3 : -0).map((a, b, c) => a > Math.max(...c.slice(2)) / sensitivity).map((a, b, c) => (b > dwindow) && c.slice(b - dwindow, b).indexOf(a) == -1);

因为我是程序员而不是数学家，所以我不能更好地解释它。但我相信有人可以。

sensitivity = 20; dwindow = 4; 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 > 0) ? c[b] ** 4 * c[b - 1] ** 3 : -0); var data2 = [{ name: 'filtered source', y: filtered }]; Plotly.newPlot('stage2', data2, { title: 'Filtered data<br>aₙ = aₙ⁴ * aₙ₋₁³', 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: 'Window 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: 'Window 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>

一种方法是根据以下观察来检测峰:

时间t是一个峰值(y (t) > y (t - 1)) & & ((t) > y (t + 1))

它通过等待上升趋势结束来避免误报。它并不完全是“实时”的，因为它会比峰值差一个dt。灵敏度可以通过要求比较的裕度来控制。在噪声检测和时延检测之间存在一种折衷。 您可以通过添加更多参数来丰富模型:

峰如果y (y (t) - (t-dt) > m) && (y (t) - y (t + dt) > m)

dt和m是控制灵敏度和延时的参数

这是你用上述算法得到的结果:

下面是在python中重现图的代码:

import numpy as np
import matplotlib.pyplot as plt
input = np.array([ 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. ])
signal = (input > np.roll(input,1)) & (input > np.roll(input,-1))
plt.plot(input)
plt.plot(signal.nonzero()[0], input[signal], 'ro')
plt.show()

通过设置m = 0.5，你可以得到一个更清晰的信号，只有一个假阳性:

在信号处理中，峰值检测通常采用小波变换。基本上就是对时间序列数据进行离散小波变换。返回的细节系数中的过零将对应于时间序列信号中的峰值。你会在不同的细节系数水平上检测到不同的峰值振幅，这给了你多层次的分辨率。

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

我们尝试在我们的数据集上使用平滑的z-score算法，这导致了过度敏感或不敏感(取决于参数如何调整)，几乎没有中间地带。在我们站点的交通信号中，我们观察到一个低频基线，它代表了每天的周期，即使有最好的可能参数(如下所示)，它仍然在第4天下降，特别是因为大多数数据点被认为是异常的。

在原始z-score算法的基础上，我们提出了一种通过反向滤波来解决这个问题的方法。改进后的算法及其在电视商业流量归因中的应用详见我们的团队博客。

我想把我的Julia算法实现提供给其他人。要点可以在这里找到

using Statistics
using Plots
function SmoothedZscoreAlgo(y, lag, threshold, influence)
    # Julia implimentation of http://stackoverflow.com/a/22640362/6029703
    n = length(y)
    signals = zeros(n) # init signal results
    filteredY = copy(y) # init filtered series
    avgFilter = zeros(n) # init average filter
    stdFilter = zeros(n) # init std filter
    avgFilter[lag - 1] = mean(y[1:lag]) # init first value
    stdFilter[lag - 1] = std(y[1:lag]) # init first value

    for i in range(lag, stop=n-1)
        if abs(y[i] - avgFilter[i-1]) > threshold*stdFilter[i-1]
            if y[i] > avgFilter[i-1]
                signals[i] += 1 # postive signal
            else
                signals[i] += -1 # negative signal
            end
            # Make influence lower
            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+1:i])
        stdFilter[i] = std(filteredY[i-lag+1:i])
    end
    return (signals = signals, avgFilter = avgFilter, stdFilter = stdFilter)
end


# 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
lag = 30
threshold = 5
influence = 0

results = SmoothedZscoreAlgo(y, lag, threshold, influence)
upper_bound = results[:avgFilter] + threshold * results[:stdFilter]
lower_bound = results[:avgFilter] - threshold * results[:stdFilter]
x = 1:length(y)

yplot = plot(x,y,color="blue", label="Y",legend=:topleft)
yplot = plot!(x,upper_bound, color="green", label="Upper Bound",legend=:topleft)
yplot = plot!(x,results[:avgFilter], color="cyan", label="Average Filter",legend=:topleft)
yplot = plot!(x,lower_bound, color="green", label="Lower Bound",legend=:topleft)
signalplot = plot(x,results[:signals],color="red",label="Signals",legend=:topleft)
plot(yplot,signalplot,layout=(2,1),legend=:topleft)