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)

如果你的数据在一个数据库表中，这里是一个简单的z-score算法的SQL版本:

with data_with_zscore as (
    select
        date_time,
        value,
        value / (avg(value) over ()) as pct_of_mean,
        (value - avg(value) over ()) / (stdev(value) over ()) as z_score
    from {{tablename}}  where datetime > '2018-11-26' and datetime < '2018-12-03'
)


-- select all
select * from data_with_zscore 

-- select only points greater than a certain threshold
select * from data_with_zscore where z_score > abs(2)

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;
}

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>

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.

我允许自己创建一个javascript版本。也许会有帮助。javascript应该是上面给出的伪代码的直接转录。可用的npm包和github repo:

https://github.com/crux/smoothed-z-score @joe_six / smoothed-z-score-peak-signal-detection

Javascript的翻译:

// javascript port of: https://stackoverflow.com/questions/22583391/peak-signal-detection-in-realtime-timeseries-data/48895639#48895639

function sum(a) {
    return a.reduce((acc, val) => acc + val)
}

function mean(a) {
    return sum(a) / a.length
}

function stddev(arr) {
    const arr_mean = mean(arr)
    const r = function(acc, val) {
        return acc + ((val - arr_mean) * (val - arr_mean))
    }
    return Math.sqrt(arr.reduce(r, 0.0) / arr.length)
}

function smoothed_z_score(y, params) {
    var p = params || {}
    // init cooefficients
    const lag = p.lag || 5
    const threshold = p.threshold || 3.5
    const influence = p.influece || 0.5

    if (y === undefined || y.length < lag + 2) {
        throw ` ## y data array to short(${y.length}) for given lag of ${lag}`
    }
    //console.log(`lag, threshold, influence: ${lag}, ${threshold}, ${influence}`)

    // init variables
    var signals = Array(y.length).fill(0)
    var filteredY = y.slice(0)
    const lead_in = y.slice(0, lag)
    //console.log("1: " + lead_in.toString())

    var avgFilter = []
    avgFilter[lag - 1] = mean(lead_in)
    var stdFilter = []
    stdFilter[lag - 1] = stddev(lead_in)
    //console.log("2: " + stdFilter.toString())

    for (var i = lag; i < y.length; i++) {
        //console.log(`${y[i]}, ${avgFilter[i-1]}, ${threshold}, ${stdFilter[i-1]}`)
        if (Math.abs(y[i] - avgFilter[i - 1]) > (threshold * stdFilter[i - 1])) {
            if (y[i] > avgFilter[i - 1]) {
                signals[i] = +1 // positive signal
            } else {
                signals[i] = -1 // negative signal
            }
            // 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
        const y_lag = filteredY.slice(i - lag, i)
        avgFilter[i] = mean(y_lag)
        stdFilter[i] = stddev(y_lag)
    }

    return signals
}

module.exports = smoothed_z_score