Three-dimensional atmospheric pollution monitoring system based on big data analysis

Abstract

The invention discloses an atmospheric pollution three-dimensional monitoring system based on big data analysis. The atmospheric pollution three-dimensional monitoring system comprises a data acquisition module, a data preprocessing module, a sub-cluster generation module, an optimal cluster center number selection module, a cluster optimization module and an atmospheric pollution three-dimensional monitoring module. The invention belongs to the technical field of atmospheric pollution monitoring, and particularly relates to an atmospheric pollution three-dimensional monitoring system based on big data analysis, according to the scheme, setting of a threshold value and a judgment distance is introduced, and a point pair similarity matrix is selectively formed; the data storage space and the calculation amount are reduced; the convergence effect is accelerated; introducing a core data point; selecting an optimal clustering center based on the core data points and the contour coefficients; a search space is established based on clustering hyper-parameters, different movement strategies are made for individuals based on individual positions and optimized individual positions, and the convergence speed and search efficiency of the algorithm are improved; the three individuals with the lowest fitness values are reinitialized; and realizing atmospheric pollution three-dimensional monitoring based on clustering optimization.

Description

Technical Field

[0001] The present invention relates to the technical field of air pollution monitoring, and in particular to a three-dimensional air pollution monitoring system based on big data analysis. Background Art

[0002] The air pollution monitoring system is a system used to continuously monitor, analyze and report the concentration of pollutants in the atmospheric environment. It provides important information support for environmental protection, public health and policy making by collecting and processing environmental data. The main purpose of the system is to assess air quality, identify pollution sources, warn of pollution events, and help formulate and evaluate air quality improvement measures. However, the general air pollution monitoring system has problems such as excessive calculation due to large data sets and poor adaptability to data sets during clustering, resulting in poor clustering effect and low accuracy of air pollution monitoring results; the general air pollution monitoring system has problems such as improper selection of clustering centers during clustering, resulting in unstable clustering results, and ultimately poor detection results; the general air pollution monitoring system has problems such as improper selection of parameters during clustering, resulting in low accuracy of clustering results, which in turn leads to weak monitoring performance. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides a three-dimensional air pollution monitoring system based on big data analysis. In view of the problems that the general air pollution monitoring system has too large a data set resulting in excessive calculation and poor adaptability to the data set during clustering resulting in poor clustering effect, and low accuracy of air pollution monitoring results, this solution introduces the setting of thresholds and judgment distances, selectively forms a point pair similarity matrix, and ensures that only one nearest point is selected each time when allocating data points; so as to reduce data storage space and calculation amount; and accelerate the convergence effect; in view of the problem that the general air pollution monitoring system has improper selection of clustering centers during clustering resulting in unstable clustering results, which ultimately leads to poor detection effect, this solution introduces a kernel The proposed method can reduce the amount of data calculation and make the clustering results more reasonable and flexible. In view of the problem that improper parameter selection during clustering in general air pollution monitoring systems leads to low accuracy of clustering results, which in turn leads to weak monitoring performance, this scheme establishes a search space based on clustering hyperparameters, formulates different movement strategies for individuals based on individual positions and preferred individual positions, improves the convergence speed and search efficiency of the algorithm, and reinitializes the three individuals with the lowest fitness values. It can maintain the diversity of the population during the search process, avoid falling into the local optimal solution, and improve the global search ability of the algorithm. It realizes air pollution monitoring based on clustering optimization.

[0004] The technical solution adopted by the present invention is as follows: the three-dimensional air pollution monitoring system based on big data analysis provided by the present invention includes a data acquisition module, a data preprocessing module, a sub-clustering generation module, an optimal cluster center number selection module, a clustering optimization module and an air pollution three-dimensional monitoring module;

[0005] The data acquisition module monitors historical data and real-time data;

[0006] The data preprocessing module performs data cleaning, data conversion and standardization on the collected data;

[0007] The sub-cluster generation module introduces the setting of threshold and judgment distance, selectively forms a point pair similarity matrix, and ensures that only one nearest point is selected each time when allocating data points, thereby obtaining sub-clusters;

[0008] The optimal cluster center number selection module introduces core data points; selects the optimal cluster center based on the core data points and the silhouette coefficient;

[0009] The cluster optimization module establishes a search space based on cluster hyperparameters, formulates different movement strategies for individuals based on individual positions and preferred individual positions, and reinitializes the three individuals with the lowest fitness values ​​to achieve cluster optimization;

[0010] The air pollution stereoscopic monitoring module performs air pollution stereoscopic monitoring on the real-time monitoring data based on the optimized clustering result.

[0011] Furthermore, in the data acquisition module, the historical monitoring data and the real-time monitoring data both include pollutant concentration data, meteorological data, auxiliary data and geographic information data; the pollutant concentration data include particulate matter concentration data, air pollutant concentration data and organic matter concentration data; the meteorological data include temperature, humidity, wind speed, wind direction and atmospheric pressure; the auxiliary data include traffic flow data and industrial production data; the geographic information data include population density, topography and land use; the historical monitoring data also includes atmospheric pollution levels.

[0012] Furthermore, in the data preprocessing module, the data cleaning is to process missing values, duplicate values ​​and outliers; the data conversion is to convert the data into a vector form; and the standardization processing is to standardize the data based on maximum and minimum normalization to obtain the original data set.

[0013] Furthermore, the sub-cluster generation module specifically includes the following contents:

[0014] Initial point pair similarity matrix forming unit, with a pre-set distance threshold ; For each pair of data points p in the dataset i and p j, calculate the similarity of data points based on Euclidean distance d ij If d ij No more than , then add the point pairs and corresponding similarities to the point pair similarity matrix;

[0015] Data clustering unit, selects the maximum distance from the initial point similarity matrix As the judgment distance, randomly initialize the first cluster center;

[0016] Data point allocation unit, find the closest to the current cluster center and the distance is no greater than , add it to the current cluster; ensure that only one nearest point is selected each time; when there is no point that meets the conditions, go to the update cluster center unit;

[0017] Update the cluster center unit. If there are unassigned data points, select the data point with a distance greater than The data points are used as the new generation clustering centers and transferred to the data point allocation unit; otherwise, they are transferred to the iteration unit;

[0018] Iteration unit, if the maximum number of iterations is not reached or the clustering does not converge, As the distance threshold, the point pair similarity matrix is ​​updated, the center point of the current cluster is selected as the new cluster center, and it is transferred to the data point allocation unit; if the maximum number of iterations is reached, the first cluster center is reinitialized; otherwise, the sub-cluster generation is terminated.

[0019] Furthermore, the optimal cluster center number selection module specifically includes the following contents:

[0020] The core data set generation unit initializes the core data set to be empty; for each sub-cluster, selects the data point closest to the center point of the sub-cluster, the point closest to other sub-clusters in the sub-cluster, and the point with the maximum density in the sub-cluster as the core data point; adds the core data points of all sub-clusters to the core data set;

[0021] A core similarity matrix generation unit calculates the Euclidean distance between all data points in the core data set to obtain a core similarity matrix;

[0022] Multiple clustering units, select different numbers of cluster centers and corresponding judgment distances to perform clustering based on the core similarity matrix, randomly initialize the first cluster center, and the clustering process is the same as the data point allocation unit to the iteration unit; when the clustering converges, the clustering results of different numbers of cluster centers are evaluated based on the silhouette coefficient, and the number of cluster centers corresponding to the cluster result with the largest evaluation value is selected as the optimal number of cluster centers;

[0023] The final clustering unit clusters the original data set based on the optimal number of cluster centers. Specifically, a data point is randomly selected from the core data set as the first cluster center to be initialized, and the data point with the farthest distance from the current cluster center is selected as the cluster center each time until the optimal number of cluster centers is reached. The data points are allocated based on the data point allocation unit. When the cluster center is updated, the center point of the cluster is selected as the new generation cluster center. If the clustering converges, the final clustering is completed. If the maximum number of iterations is reached, the first cluster center is reinitialized. Otherwise, clustering continues to be iterated.

[0024] Furthermore, the clustering optimization module specifically includes the following contents:

[0025] Initialization unit, establishes search space based on distance threshold, initial first cluster center of sub-cluster, judgment distance corresponding to different number of cluster centers in multi-cluster and initial first cluster center; randomly initializes search population position, takes average silhouette coefficient of clusters iterated k times based on individual position clustering as individual fitness value;

[0026] The position update unit selects the three individuals with the highest fitness values ​​as the preferred individuals, represented by a, b and c respectively; the position of the individuals is updated, and the formula used is as follows:

[0027] ;

[0028] ;

[0029] In the formula, X i (·) is the position of the i-th individual except the preferred individual, t is the number of iterations; X a (·)、X b (·) and X c (·) is the position of the preferred individual; Fa, Fb and Fc are the fitness values ​​corresponding to the preferred individuals; i∈a, i∈b and i∈c respectively indicate that the i-th individual is closest to a, b and c; Y(·) is the position of the preferred individual; T is the maximum number of iterations; is the average position of the preferred individuals; is a smoothing term;

[0030] Reinitialize the unit and initialize the three individuals with the lowest fitness values. The formula used is as follows:

[0031] ;

[0032] Where newX d (·) and X d (·) are the positions of the three individuals with the lowest fitness before and after initialization, respectively. d and U dare the upper and lower limits of the search space in the dth dimension respectively;

[0033] The search judgment unit is pre-set with a fitness threshold. When there is an individual fitness value higher than the fitness threshold, the data set is clustered based on the individual position to obtain the optimized final clustering result; if the maximum number of iterations is reached, the population position is reinitialized; otherwise, the preferred individual is reselected to continue the iterative search.

[0034] Furthermore, the atmospheric pollution stereoscopic monitoring module selects the label with the largest number of historical data as the cluster label based on the optimized final clustering result; and outputs the cluster label to which the real-time data belongs as the final monitoring result of the real-time data.

[0035] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0036] (1) In view of the problems of excessive computational effort caused by large data sets in general air pollution monitoring systems and poor adaptability to data sets during clustering, which leads to poor clustering effect and low accuracy of air pollution monitoring results, this scheme introduces the setting of thresholds and judgment distances, selectively forms a point pair similarity matrix, and ensures that only one nearest point is selected each time when allocating data points, thereby reducing data storage space and computational effort and accelerating convergence.

[0037] (2) In order to solve the problem that improper selection of cluster centers leads to unstable clustering results and ultimately poor detection effects in general air pollution monitoring systems, this scheme introduces core data points; selects the best cluster center based on core data points and silhouette coefficients; reduces the amount of data calculation and makes the clustering results more reasonable and flexible.

[0038] (3) In order to address the problem that improper parameter selection during clustering in general air pollution monitoring systems leads to low clustering result accuracy, which in turn leads to poor monitoring performance, this scheme establishes a search space based on clustering hyperparameters, formulates different movement strategies for individuals based on individual positions and preferred individual positions, thereby improving the convergence speed and search efficiency of the algorithm; and reinitializes the three individuals with the lowest fitness values; it can maintain the diversity of the population during the search process, avoid falling into local optimal solutions, and improve the global search capability of the algorithm; and realize air pollution monitoring based on clustering optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 A schematic diagram of the process of the three-dimensional air pollution monitoring system based on big data analysis provided by the present invention;

[0040] Figure 2 Schematic diagram of the process of generating modules for sub-clustering;

[0041] Figure 3Schematic diagram of the process of selecting a module for the optimal number of cluster centers.

[0042] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0044] In the description of the present invention, it should be understood that terms such as “upper”, “lower”, “front”, “back”, “left”, “right”, “top”, “bottom”, “inside” and “outside” indicating directions or positional relationships are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore should not be understood as limiting the present invention.

[0045] Example 1, see Figure 1 The present invention provides a three-dimensional air pollution monitoring system based on big data analysis, comprising a data acquisition module, a data preprocessing module, a sub-clustering generation module, an optimal cluster center number selection module, a clustering optimization module and an air pollution three-dimensional monitoring module;

[0046] The data acquisition module monitors historical data and real-time data and sends the data to the data preprocessing module;

[0047] The data preprocessing module receives the data sent by the data acquisition module; performs data cleaning, data conversion and standardization on the collected data; and sends the data to the sub-clustering generation module;

[0048] The sub-cluster generation module receives the data sent by the data pre-processing module; introduces the setting of threshold and judgment distance, selectively forms a point pair similarity matrix, and ensures that only one nearest point is selected each time when allocating data points; thereby obtaining sub-clusters; and sending the data to the optimal cluster center number selection module;

[0049] The optimal cluster center number selection module receives data sent by the sub-cluster generation module; introduces core data points; selects the optimal cluster center based on the core data points and the silhouette coefficient; and sends the data to the cluster optimization module;

[0050] The cluster optimization module receives data sent by the optimal cluster center number selection module; establishes a search space based on cluster hyperparameters, formulates different movement strategies for individuals based on individual positions and preferred individual positions; and reinitializes the three individuals with the lowest fitness values ​​to achieve cluster optimization; and sends the data to the atmospheric pollution three-dimensional monitoring module;

[0051] The air pollution stereoscopic monitoring module receives the data sent by the clustering optimization module; and performs air pollution stereoscopic monitoring on the real-time monitoring data based on the optimized clustering results.

[0052] Example 2, see Figure 1 This embodiment is based on the above embodiment. In the data acquisition module, both historical monitoring data and real-time monitoring data include pollutant concentration data, meteorological data, auxiliary data and geographic information data; pollutant concentration data include particulate matter concentration data, air pollutant concentration data and organic matter concentration data; meteorological data include temperature, humidity, wind speed, wind direction and atmospheric pressure; auxiliary data include traffic flow data and industrial production data; geographic information data include population density, topography and land use; historical monitoring data also include atmospheric pollution levels.

[0053] Example 3, see Figure 1 This embodiment is based on the above embodiment. In the data preprocessing module, data cleaning is to process missing values, duplicate values ​​and abnormal values; the data conversion is to convert the data into a vector form; the standardization processing is to standardize the data based on maximum and minimum normalization to obtain the original data set.

[0054] Example 4, see Figure 1 and Figure 2 This embodiment is based on the above embodiment, and the sub-cluster generation module specifically includes the following contents:

[0055] Initial point pair similarity matrix forming unit, with a pre-set distance threshold ; For each pair of data points p in the dataset i and p j , calculate the similarity of data points based on Euclidean distance d ij If d ij No more than , then add the point pairs and corresponding similarities to the point pair similarity matrix;

[0056] Data clustering unit, selects the maximum distance from the initial point similarity matrix As the judgment distance, randomly initialize the first cluster center;

[0057] Data point allocation unit, find the closest to the current cluster center and the distance is no greater than , add it to the current cluster; ensure that only one nearest point is selected each time; when there is no point that meets the conditions, go to the update cluster center unit;

[0058] Update the cluster center unit. If there are unassigned data points, select the data point with a distance greater than The data points are used as the new generation clustering centers and transferred to the data point allocation unit; otherwise, they are transferred to the iteration unit;

[0059] Iteration unit, if the maximum number of iterations is not reached or the clustering does not converge, As the distance threshold, the point pair similarity matrix is ​​updated, the center point of the current cluster is selected as the new cluster center, and it is transferred to the data point allocation unit; if the maximum number of iterations is reached, the first cluster center is reinitialized; otherwise, the sub-cluster generation is terminated.

[0060] By performing the above operations, this scheme introduces the setting of thresholds and judgment distances to selectively form a point pair similarity matrix, and ensures that only one nearest point is selected each time when allocating data points, so as to reduce data storage space and calculation amount, and accelerate the convergence effect.

[0061] Example 5, see Figure 1 and Figure 3 Based on the above embodiment, this embodiment includes the following contents:

[0062] The core data set generation unit initializes the core data set to be empty; for each sub-cluster, selects the data point closest to the center point of the sub-cluster, the point closest to other sub-clusters in the sub-cluster, and the point with the maximum density in the sub-cluster as the core data point; adds the core data points of all sub-clusters to the core data set;

[0063] A core similarity matrix generation unit calculates the Euclidean distance between all data points in the core data set to obtain a core similarity matrix;

[0064] Multiple clustering units, select different numbers of cluster centers and corresponding judgment distances to perform clustering based on the core similarity matrix, randomly initialize the first cluster center, and the clustering process is the same as the data point allocation unit to the iteration unit; when the clustering converges, the clustering results of different numbers of cluster centers are evaluated based on the silhouette coefficient, and the number of cluster centers corresponding to the cluster result with the largest evaluation value is selected as the optimal number of cluster centers;

[0065] The final clustering unit clusters the original data set based on the optimal number of cluster centers. Specifically, a data point is randomly selected from the core data set as the first cluster center to be initialized, and the data point with the farthest distance from the current cluster center is selected as the cluster center each time until the optimal number of cluster centers is reached. The data points are allocated based on the data point allocation unit. When the cluster center is updated, the center point of the cluster is selected as the new generation cluster center. If the clustering converges, the final clustering is completed. If the maximum number of iterations is reached, the first cluster center is reinitialized. Otherwise, clustering continues to be iterated.

[0066] By performing the above operations, this solution introduces core data points to address the problem that improper selection of clustering centers leads to unstable clustering results and ultimately poor detection effects in general air pollution monitoring systems. The solution selects the best clustering center based on core data points and silhouette coefficients, reduces the amount of data calculation, and makes clustering results more reasonable and flexible.

[0067] Example 6, see Figure 1 This embodiment is based on the above embodiment, and the clustering optimization module specifically includes the following contents:

[0068] Initialization unit, establishes search space based on distance threshold, initial first cluster center of sub-cluster, judgment distance corresponding to different number of cluster centers in multi-cluster and initial first cluster center; randomly initializes search population position, takes average silhouette coefficient of clusters iterated k times based on individual position clustering as individual fitness value;

[0069] The position update unit selects the three individuals with the highest fitness values ​​as the preferred individuals, represented by a, b and c respectively; the position of the individuals is updated, and the formula used is as follows:

[0070] ;

[0071] ;

[0072] In the formula, X i (·) is the position of the i-th individual except the preferred individual, t is the number of iterations; X a (·)、X b (·) and X c (·) is the position of the preferred individual; Fa, Fb and Fc are the fitness values ​​corresponding to the preferred individuals; i∈a, i∈b and i∈c respectively indicate that the i-th individual is closest to a, b and c; Y(·) is the position of the preferred individual; T is the maximum number of iterations; is the average position of the preferred individuals; is a smoothing term;

[0073] Reinitialize the unit and initialize the three individuals with the lowest fitness values. The formula used is as follows:

[0074] ;

[0075] Where newX d (·) and X d (·) are the positions of the three individuals with the lowest fitness before and after initialization, respectively. d and U d are the upper and lower limits of the search space in the dth dimension respectively;

[0076] The search judgment unit is pre-set with a fitness threshold. When there is an individual fitness value higher than the fitness threshold, the data set is clustered based on the individual position to obtain the optimized final clustering result; if the maximum number of iterations is reached, the population position is reinitialized; otherwise, the preferred individual is reselected to continue the iterative search.

[0077] By performing the above operations, in order to solve the problem of low accuracy of clustering results caused by improper parameter selection during clustering in general air pollution monitoring systems, this scheme establishes a search space based on clustering hyperparameters, formulates different movement strategies for individuals based on individual positions and preferred individual positions, thereby improving the convergence speed and search efficiency of the algorithm; and reinitializes the three individuals with the lowest fitness values; it can maintain the diversity of the population during the search process, avoid falling into the local optimal solution, and improve the global search capability of the algorithm; and realizes air pollution monitoring based on clustering optimization.

[0078] Embodiment 7, see Figure 1 This embodiment is based on the above embodiment. The atmospheric pollution stereoscopic monitoring module selects the label with the largest number of historical data as the cluster label based on the optimized final clustering result; and outputs the cluster label to which the real-time data belongs as the final monitoring result of the real-time data.

[0079] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0080] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that many changes, modifications, substitutions and variations can be made to the embodiments without departing from the principles and spirit of the invention.

[0081] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. A three-dimensional air pollution monitoring system based on big data analysis, characterized by: The system includes a data acquisition module, a data preprocessing module, a sub-cluster generation module, an optimal cluster center number selection module, a cluster optimization module and an air pollution three-dimensional monitoring module; The data acquisition module monitors historical data and real-time data; The data preprocessing module performs data cleaning, data conversion and standardization on the collected data; The sub-cluster generation module introduces the setting of threshold and judgment distance, selectively forms a point pair similarity matrix, and ensures that only one nearest point is selected each time when allocating data points, thereby obtaining sub-clusters; The optimal cluster center number selection module introduces core data points; selects the optimal cluster center based on the core data points and the silhouette coefficient; The cluster optimization module establishes a search space based on cluster hyperparameters, formulates different movement strategies for individuals based on individual positions and preferred individual positions, and reinitializes the three individuals with the lowest fitness values ​​to achieve cluster optimization; The air pollution stereoscopic monitoring module performs air pollution stereoscopic monitoring on the real-time monitoring data based on the optimized clustering result.

2. The three-dimensional air pollution monitoring system based on big data analysis according to claim 1 is characterized in that: The sub-cluster generation module specifically includes the following contents: Initial point pair similarity matrix forming unit, with a pre-set distance threshold ; For each pair of data points p in the dataset i and p j , calculate the similarity of data points based on Euclidean distance d ij If d ij No more than , then add the point pairs and corresponding similarities to the point pair similarity matrix; Data clustering unit, selects the maximum distance from the initial point similarity matrix As the judgment distance, randomly initialize the first cluster center; The data point allocation unit is to find the closest cluster center with a distance no greater than , add it to the current cluster; Make sure to select only one nearest point each time; when there is no point that meets the conditions, go to the update cluster center unit; Update the cluster center unit. If there are unassigned data points, select the data point with a distance greater than The data points are used as the new generation clustering centers and transferred to the data point allocation unit; otherwise, they are transferred to the iteration unit; Iteration unit, if the maximum number of iterations is not reached or the clustering does not converge, Update the point pair similarity matrix as the distance threshold, select the center point of the current cluster as the new cluster center, and transfer to the data point allocation unit; If the maximum number of iterations is reached, the first cluster center is reinitialized; otherwise, sub-cluster generation ends.

3. The three-dimensional air pollution monitoring system based on big data analysis according to claim 1 is characterized in that: The clustering optimization module specifically includes the following contents: Initialization unit, establishes search space based on distance threshold, initial first cluster center of sub-cluster, judgment distance corresponding to different number of cluster centers in multi-cluster and initial first cluster center; randomly initializes search population position, takes average silhouette coefficient of clusters iterated k times based on individual position clustering as individual fitness value; The position update unit selects the three individuals with the highest fitness values ​​as the preferred individuals, represented by a, b and c respectively; the position of the individuals is updated, and the formula used is as follows: ； ； Where, X i (·) is the position of the i-th individual except the preferred individual, t is the number of iterations; X a (·)、X b (·) and X c (·) is the position of the preferred individual; Fa, Fb and Fc are the fitness values ​​corresponding to the preferred individuals; i∈a, i∈b and i∈c respectively indicate that the i-th individual is closest to a, b and c; Y(·) is the position of the preferred individual; T is the maximum number of iterations; is the average position of the preferred individuals; is a smoothing term; Reinitialize the unit and initialize the three individuals with the lowest fitness values. The formula used is as follows: ； Where newX d (·) and X d (·) are the positions of the three individuals with the lowest fitness before and after initialization, respectively. d and U d are the upper and lower limits of the search space in the dth dimension respectively; The search judgment unit is pre-set with a fitness threshold. When there is an individual fitness value higher than the fitness threshold, the data set is clustered based on the individual position to obtain an optimized final clustering result; If the maximum number of iterations is reached, the population position is reinitialized; Otherwise, reselect the optimal individual and continue the iterative search.

4. The three-dimensional air pollution monitoring system based on big data analysis according to claim 1 is characterized in that: The optimal cluster center number selection module specifically includes the following contents: The core data set generation unit initializes the core data set to be empty; for each sub-cluster, selects the data point closest to the center point of the sub-cluster, the point closest to other sub-clusters in the sub-cluster, and the point with the maximum density in the sub-cluster as the core data point; adds the core data points of all sub-clusters to the core data set; A core similarity matrix generation unit calculates the Euclidean distance between all data points in the core data set to obtain a core similarity matrix; Multiple clustering units, select different numbers of cluster centers and corresponding judgment distances to perform clustering based on the core similarity matrix, randomly initialize the first cluster center, and the clustering process is the same as the data point allocation unit to the iteration unit; when the clustering converges, the clustering results of different numbers of cluster centers are evaluated based on the silhouette coefficient, and the number of cluster centers corresponding to the cluster result with the largest evaluation value is selected as the optimal number of cluster centers; The final clustering unit clusters the original data set based on the optimal number of cluster centers; Specifically, a data point is randomly selected from the core data set as the first cluster center to be initialized, and the data point with the farthest distance from the current cluster center is selected as the cluster center each time until the optimal number of cluster centers is reached; the data points are allocated based on the data point allocation unit; and when the cluster center is updated, the center point of the cluster is selected as the new generation cluster center; if the clustering converges, the final clustering is completed; if the maximum number of iterations is reached, the first cluster center is reinitialized; otherwise, the iterative clustering continues.

5. The three-dimensional air pollution monitoring system based on big data analysis according to claim 1 is characterized in that: In the data acquisition module, the historical monitoring data and real-time monitoring data both include pollutant concentration data, meteorological data, auxiliary data and geographic information data; the pollutant concentration data include particulate matter concentration data, air pollutant concentration data and organic matter concentration data; the meteorological data include temperature, humidity, wind speed, wind direction and atmospheric pressure; the auxiliary data include traffic flow data and industrial production data; the geographic information data include population density, topography and land use; the historical monitoring data also includes atmospheric pollution levels.

6. The three-dimensional air pollution monitoring system based on big data analysis according to claim 1 is characterized in that: The air pollution stereo monitoring module selects the label with the largest number of historical data as the cluster label based on the optimized final clustering result; and outputs the cluster label to which the real-time data belongs as the final monitoring result of the real-time data.

7. The three-dimensional air pollution monitoring system based on big data analysis according to claim 1 is characterized in that: In the data preprocessing module, the data cleaning is to process missing values, duplicate values ​​and outliers; the data conversion is to convert the data into vector form; the standardization processing is to standardize the data based on maximum and minimum normalization to obtain the original data set.

Images