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;
}

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.

用现代c++实现的面向对象版z-score算法

template<typename T>
class FindPeaks{
private:
    std::vector<T> m_input_signal;                      // stores input vector
    std::vector<T> m_array_peak_positive;               
    std::vector<T> m_array_peak_negative;               

public:
    FindPeaks(const std::vector<T>& t_input_signal): m_input_signal{t_input_signal}{ }

    void estimate(){
        int lag{5};
        T threshold{ 5 };                                                                                       // set a threshold
        T influence{ 0.5 };                                                                                    // value between 0 to 1, 1 is normal influence and 0.5 is half the influence

        std::vector<T> filtered_signal(m_input_signal.size(), 0.0);                                             // placeholdered for smooth signal, initialie with all zeros
        std::vector<int> signal(m_input_signal.size(), 0);                                                          // vector that stores where the negative and positive located
        std::vector<T> avg_filtered(m_input_signal.size(), 0.0);                                                // moving averages
        std::vector<T> std_filtered(m_input_signal.size(), 0.0);                                                // moving standard deviation

        avg_filtered[lag] = findMean(m_input_signal.begin(), m_input_signal.begin() + lag);                         // pass the iteartor to vector
        std_filtered[lag] = findStandardDeviation(m_input_signal.begin(), m_input_signal.begin() + lag);

        for (size_t iLag = lag + 1; iLag < m_input_signal.size(); ++iLag) {                                         // start index frm 
            if (std::abs(m_input_signal[iLag] - avg_filtered[iLag - 1]) > threshold * std_filtered[iLag - 1]) {     // check if value is above threhold             
                if ((m_input_signal[iLag]) > avg_filtered[iLag - 1]) {
                    signal[iLag] = 1;                                                                               // assign positive signal
                }
                else {
                    signal[iLag] = -1;                                                                                  // assign negative signal
                }
                filtered_signal[iLag] = influence * m_input_signal[iLag] + (1 - influence) * filtered_signal[iLag - 1];        // exponential smoothing
            }
            else {
                signal[iLag] = 0;                                                                                         // no signal
                filtered_signal[iLag] = m_input_signal[iLag];
            }

            avg_filtered[iLag] = findMean(filtered_signal.begin() + (iLag - lag), filtered_signal.begin() + iLag);
            std_filtered[iLag] = findStandardDeviation(filtered_signal.begin() + (iLag - lag), filtered_signal.begin() + iLag);

        }

        for (size_t iSignal = 0; iSignal < m_input_signal.size(); ++iSignal) {
            if (signal[iSignal] == 1) {
                m_array_peak_positive.emplace_back(m_input_signal[iSignal]);                                        // store the positive peaks
            }
            else if (signal[iSignal] == -1) {
                m_array_peak_negative.emplace_back(m_input_signal[iSignal]);                                         // store the negative peaks
            }
        }
        printVoltagePeaks(signal, m_input_signal);

    }

    std::pair< std::vector<T>, std::vector<T> > get_peaks()
    {
        return std::make_pair(m_array_peak_negative, m_array_peak_negative);
    }

};


template<typename T1, typename T2 >
void printVoltagePeaks(std::vector<T1>& m_signal, std::vector<T2>& m_input_signal) {
    std::ofstream output_file("./voltage_peak.csv");
    std::ostream_iterator<T2> output_iterator_voltage(output_file, ",");
    std::ostream_iterator<T1> output_iterator_signal(output_file, ",");
    std::copy(m_input_signal.begin(), m_input_signal.end(), output_iterator_voltage);
    output_file << "\n";
    std::copy(m_signal.begin(), m_signal.end(), output_iterator_signal);
}

template<typename iterator_type>
typename std::iterator_traits<iterator_type>::value_type findMean(iterator_type it, iterator_type end)
{
    /* function that receives iterator to*/
    typename std::iterator_traits<iterator_type>::value_type sum{ 0.0 };
    int counter = 0;
    while (it != end) {
        sum += *(it++);
        counter++;
    }
    return sum / counter;
}

template<typename iterator_type>
typename std::iterator_traits<iterator_type>::value_type findStandardDeviation(iterator_type it, iterator_type end)
{
    auto mean = findMean(it, end);
    typename std::iterator_traits<iterator_type>::value_type sum_squared_error{ 0.0 };
    int counter{ 0 };
    while (it != end) {
        sum_squared_error += std::pow((*(it++) - mean), 2);
        counter++;
    }
    auto standard_deviation = std::sqrt(sum_squared_error / (counter - 1));
    return standard_deviation;
}

这是一个修改后的Fortran版本的z-score算法。 它是专门针对频率空间中传递函数的峰值(共振)检测进行修改的(每个更改在代码中都有一个小注释)。

如果在输入向量的下界附近存在共振，则第一个修改会向用户发出警告，该共振由高于某个阈值的标准偏差表示(在本例中为10%)。这仅仅意味着信号不够平坦，不足以使检测正确地初始化滤波器。

第二种修改是只将峰值的最大值添加到已找到的峰值中。这是通过将每个发现的峰值与其(滞后)前辈及其(滞后)后继者的大小进行比较来达到的。

第三个变化是尊重共振峰通常在共振频率周围表现出某种形式的对称性。因此，围绕当前数据点对称地计算平均值和std是很自然的(而不仅仅是针对之前的数据点)。这将导致更好的峰值检测行为。

这些修改的效果是，整个信号必须事先被函数知道，这是共振检测的通常情况(类似于Jean-Paul的Matlab示例，其中数据点是动态生成的，这是行不通的)。

function PeakDetect(y,lag,threshold, influence)
    implicit none
    ! Declaring part
    real, dimension(:), intent(in) :: y
    integer, dimension(size(y)) :: PeakDetect
    real, dimension(size(y)) :: filteredY, avgFilter, stdFilter
    integer :: lag, ii
    real :: threshold, influence

    ! Executing part
    PeakDetect = 0
    filteredY = 0.0
    filteredY(1:lag+1) = y(1:lag+1)
    avgFilter = 0.0
    avgFilter(lag+1) = mean(y(1:2*lag+1))
    stdFilter = 0.0
    stdFilter(lag+1) = std(y(1:2*lag+1))

    if (stdFilter(lag+1)/avgFilter(lag+1)>0.1) then ! If the coefficient of variation exceeds 10%, the signal is too uneven at the start, possibly because of a peak.
        write(unit=*,fmt=1001)
1001        format(1X,'Warning: Peak detection might have failed, as there may be a peak at the edge of the frequency range.',/)
    end if
    do ii = lag+2, size(y)
        if (abs(y(ii) - avgFilter(ii-1)) > threshold * stdFilter(ii-1)) then
            ! Find only the largest outstanding value which is only the one greater than its predecessor and its successor
            if (y(ii) > avgFilter(ii-1) .AND. y(ii) > y(ii-1) .AND. y(ii) > y(ii+1)) then
                PeakDetect(ii) = 1
            end if
            filteredY(ii) = influence * y(ii) + (1 - influence) * filteredY(ii-1)
        else
            filteredY(ii) = y(ii)
        end if
        ! Modified with respect to the original code. Mean and standard deviation are calculted symmetrically around the current point
        avgFilter(ii) = mean(filteredY(ii-lag:ii+lag))
        stdFilter(ii) = std(filteredY(ii-lag:ii+lag))
    end do
end function PeakDetect

real function mean(y)
    !> @brief Calculates the mean of vector y
    implicit none
    ! Declaring part
    real, dimension(:), intent(in) :: y
    integer :: N
    ! Executing part
    N = max(1,size(y))
    mean = sum(y)/N
end function mean

real function std(y)
    !> @brief Calculates the standard deviation of vector y
    implicit none
    ! Declaring part
    real, dimension(:), intent(in) :: y
    integer :: N
    ! Executing part
    N = max(1,size(y))
    std = sqrt((N*dot_product(y,y) - sum(y)**2) / (N*(N-1)))
end function std

对于我的应用程序，算法的工作就像一个魅力!

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。

一个python/numpy的迭代版本的答案https://stackoverflow.com/a/22640362/6029703在这里。对于大数据(100000+)，此代码比计算平均和标准偏差的速度更快。

def peak_detection_smoothed_zscore_v2(x, lag, threshold, influence):
    '''
    iterative smoothed z-score algorithm
    Implementation of algorithm from https://stackoverflow.com/a/22640362/6029703
    '''
    import numpy as np
    labels = np.zeros(len(x))
    filtered_y = np.array(x)
    avg_filter = np.zeros(len(x))
    std_filter = np.zeros(len(x))
    var_filter = np.zeros(len(x))

    avg_filter[lag - 1] = np.mean(x[0:lag])
    std_filter[lag - 1] = np.std(x[0:lag])
    var_filter[lag - 1] = np.var(x[0:lag])
    for i in range(lag, len(x)):
        if abs(x[i] - avg_filter[i - 1]) > threshold * std_filter[i - 1]:
            if x[i] > avg_filter[i - 1]:
                labels[i] = 1
            else:
                labels[i] = -1
            filtered_y[i] = influence * x[i] + (1 - influence) * filtered_y[i - 1]
        else:
            labels[i] = 0
            filtered_y[i] = x[i]
        # update avg, var, std
        avg_filter[i] = avg_filter[i - 1] + 1. / lag * (filtered_y[i] - filtered_y[i - lag])
        var_filter[i] = var_filter[i - 1] + 1. / lag * ((filtered_y[i] - avg_filter[i - 1]) ** 2 - (
            filtered_y[i - lag] - avg_filter[i - 1]) ** 2 - (filtered_y[i] - filtered_y[i - lag]) ** 2 / lag)
        std_filter[i] = np.sqrt(var_filter[i])

    return dict(signals=labels,
                avgFilter=avg_filter,
                stdFilter=std_filter)