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
# ]

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;
}

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)

在计算拓扑学中，持久同调的思想导致一个有效的 -快如排序数字-解决方案。它不仅检测峰值，还以一种自然的方式量化峰值的“重要性”，使您能够选择对您重要的峰值。

算法的总结。 在一维设置(时间序列，实值信号)中，算法可以简单地描述为下图:

Think of the function graph (or its sub-level set) as a landscape and consider a decreasing water level starting at level infinity (or 1.8 in this picture). While the level decreases, at local maxima islands pop up. At local minima these islands merge together. One detail in this idea is that the island that appeared later in time is merged into the island that is older. The "persistence" of an island is its birth time minus its death time. The lengths of the blue bars depict the persistence, which is the above mentioned "significance" of a peak.

效率。 在对函数值进行排序之后，找到一个在线性时间内运行的实现并不难——实际上它是一个单一的、简单的循环。因此，这种实现在实践中应该是快速的，也很容易实现。

参考文献 一篇关于整个故事的文章和对持久同调(计算代数拓扑中的一个领域)动机的引用可以在这里找到: https://www.sthu.org/blog/13-perstopology-peakdetection/index.html

函数scipy.signal。Find_peaks，顾名思义，在这方面很有用。但是要得到好的峰值提取，必须了解其参数宽度、阈值、距离和突出度。

根据我的测试和文档，突出的概念是“有用的概念”，可以保留好的峰值，丢弃噪声峰值。

什么是(地形)突出?它是“从山顶下降到任何更高地形所需的最低高度”，如下图所示:

这个想法是:

突出位置越高，山峰就越“重要”。