Data fusion system for water quality and aquatic organism monitoring based on internet of things

Abstract

The application discloses a water quality and aquatic organism monitoring data fusion system based on the Internet of Things, relates to the technical field of lake monitoring, and analyzes the gray correlation degree between fluctuating water quality parameters and aquatic organisms when the water quality parameters fluctuate, clusters all sub-regions after calculating the aquatic organism similarity features between the sub-regions, and analyzes the gray correlation degree in each category as a whole, wherein the attention sorting module combines the clustering results and the historical changes of the water quality parameters, finds the influence indexes of all water quality parameters on the lake, generates a water quality parameter attention degree sorting table, and sends the table to a lake management platform. The fusion system calculates the aquatic organism similarity features between the sub-regions, clusters the sub-regions based on the features, divides the ecologically similar lake areas, improves the pertinence of lake management, can quickly identify the affected aquatic organisms, and provides a scientific basis for ecological protection and pollution control.

Description

Technical Field

[0001] This invention relates to the field of lake monitoring technology, and more specifically to a data fusion system for water quality and aquatic life monitoring based on the Internet of Things. Background Technology

[0002] Traditional water quality monitoring mainly relies on manual sampling and laboratory analysis, which suffers from problems such as poor timeliness and insufficient spatial coverage. The water quality and aquatic life monitoring data fusion system based on the Internet of Things (IoT) uses sensor networks, wireless communication, big data analysis and artificial intelligence technologies to achieve real-time and accurate monitoring of the aquatic environment and biological ecology, providing a scientific basis for water environment protection and ecological restoration.

[0003] The existing technology has the following drawbacks:

[0004] 1. Existing water quality monitoring systems mainly focus on abnormal changes in water quality parameters themselves (such as pH, dissolved oxygen, ammonia nitrogen concentration, etc.), but lack direct observation and impact assessment of aquatic biological communities. They have failed to establish a quantitative relationship between water quality parameters and aquatic biological population dynamics. Water quality changes often produce complex chain reactions on lake ecosystems. For example, changes in certain water quality factors may affect the reproduction of phytoplankton, thereby affecting the survival of fish communities.

[0005] 2. As complex ecosystems, lakes exhibit significant differences in hydrodynamic conditions, aquatic biological communities, and pollution source distribution across different regions, resulting in marked spatial heterogeneity in water quality changes. Existing monitoring systems often lack systematic analysis of the aquatic ecological characteristics of different lake areas, making it difficult to tailor management measures to local conditions. For example, some areas may be more prone to eutrophication, while others may be more sensitive to pollution. However, due to the lack of sub-regional division and cluster analysis, managers find it difficult to formulate refined control strategies.

[0006] Based on this, the present invention proposes a data fusion system for water quality and aquatic organism monitoring based on the Internet of Things. By calculating the similarity characteristics of aquatic organisms between sub-regions and clustering the sub-regions based on these characteristics, ecologically similar lake areas are divided, which improves the targeting of lake management, can quickly identify affected aquatic organisms, and provides a scientific basis for ecological protection and pollution control. Summary of the Invention

[0007] The purpose of this invention is to provide a data fusion system for water quality and aquatic organism monitoring based on the Internet of Things (IoT) to address the shortcomings of the prior art.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a data fusion system for water quality and aquatic organism monitoring based on the Internet of Things, comprising a data acquisition module, a monitoring module, an analysis module, and a focus ranking module;

[0009] Data acquisition module: Acquires lake information based on the lake management platform and divides the lake into several sub-regions according to the lake area;

[0010] Monitoring module: Monitors changes in water quality parameters in each sub-area in real time through IoT sensing devices;

[0011] Analysis module: When water quality parameters fluctuate, the gray relational degree between fluctuating water quality parameters and aquatic organisms is analyzed. After calculating the aquatic organism similarity characteristics between sub-regions, all sub-regions are clustered, and the gray relational degree in each category is analyzed holistically.

[0012] Attention Ranking Module: Combining clustering results with historical changes in water quality parameters, this module finds the impact index of all water quality parameters relative to the lake, generates a water quality parameter attention ranking table, and sends it to the lake management platform.

[0013] In a preferred embodiment, the analysis module calculates the grey relational degree between water quality parameters and aquatic organisms based on water quality parameter values ​​and influence indices, expressed as: In the formula, For gray relational degree, For the number of time points, For the first Grey relational coefficients at each time point.

[0014] In a preferred embodiment, the expression for calculating the grey relational coefficient is:

[0015] In the formula, The grey relational coefficient is... For water quality parameters and the first Aquatic organisms at all times The absolute difference, and , For water quality parameters at time The value, For the first Aquatic organisms at all times Influence factors Represents the double minimum operator. Represents the doubly maximum operator. Let be the resolution coefficient, and .

[0016] In a preferred embodiment, after the analysis module obtains the aquatic organism species in all sub-regions, it calculates the aquatic organism similarity characteristics between each sub-region and other sub-regions.

[0017] After obtaining the aquatic organism similarity features between each sub-region and other sub-regions, a correlation matrix is ​​constructed based on the aquatic organism similarity features;

[0018] The similarity features of aquatic organisms among all sub-regions are compared with a preset feature threshold. The feature threshold is used to determine whether a sub-region can be classified into a cluster. All sub-regions with aquatic organism similarity features greater than the feature threshold are classified into a cluster.

[0019] In a preferred embodiment, the correlation matrix is ​​expressed as follows:

[0020] In the formula, This is a correlation matrix. This represents the number of sub-regions.

[0021] In a preferred embodiment, the aquatic organism similarity characteristics between each sub-region and other sub-regions are calculated, expressed as: In the formula, sub-region sub-region Similarities in aquatic organisms , They are sub-regions sub-region The mean population size of aquatic organisms. sub-region The Middle aquatic organism density sub-region The Middle Aquatic organism density.

[0022] In a preferred embodiment, the attention ranking module obtains the mean grey relational degree of each cluster and the historical frequency of fluctuations in the water quality parameters that have fluctuated. Based on the mean grey relational degree and the historical frequency of fluctuations, an influence index is calculated, expressed as: In the formula, To influence the index, The mean of the grey relational degree. For the frequency of historical fluctuations, , These are the weighting coefficients, and ;

[0023] After obtaining the impact index of all water quality parameters, sort all water quality parameters from largest to smallest according to the impact index to generate a ranking table of attention.

[0024] In a preferred embodiment, when the analysis module analyzes the fluctuations in water quality parameters, it obtains the density decline rate and mortality rate of aquatic organisms, normalizes the density decline rate and mortality rate so that the value range of the density decline rate and mortality rate is mapped to [0,1], and sums the normalized density decline rate and mortality rate to obtain the influencing factor.

[0025] In a preferred embodiment, the analysis module compares the real-time monitored water quality parameters with the corresponding parameter thresholds. The difference is obtained by subtracting the corresponding parameter threshold from the real-time monitored water quality parameter value. The absolute value of the difference is taken as the deviation value of the water quality parameter. If the deviation value of the water quality parameter is greater than a preset deviation threshold, the analysis indicates that the water quality parameter has fluctuated.

[0026] In a preferred embodiment, the monitoring module detects the acidity or alkalinity of the water using a pH sensor, monitors the oxygen content in the water using a dissolved oxygen sensor, monitors the ammonia nitrogen, total phosphorus, and total nitrogen content in the water using ammonia nitrogen, total phosphorus, and total nitrogen sensors, monitors the water transparency using a turbidity sensor, monitors the water temperature using a temperature sensor, and detects the water conductivity using a conductivity sensor.

[0027] The technical effects and advantages provided by the present invention in the above technical solution are as follows:

[0028] This invention divides a lake into several sub-regions based on its area using a data acquisition module. When water quality parameters fluctuate, the analysis module analyzes the grey relational degree between these fluctuating parameters and aquatic organisms. After calculating the aquatic organism similarity characteristics between sub-regions, all sub-regions are clustered, and the grey relational degree within each category is analyzed holistically. The attention ranking module combines the clustering results with historical changes in water quality parameters to find the impact index of all water quality parameters relative to the lake, generating a water quality parameter attention ranking table and sending it to the lake management platform. This fusion system calculates the aquatic organism similarity characteristics between sub-regions and clusters them based on these characteristics, classifying ecologically similar lake areas. This improves the targeting of lake management, enables rapid identification of affected aquatic organisms, and provides a scientific basis for ecological protection and pollution control. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in this invention. For those skilled in the art, other drawings can be obtained based on these drawings.

[0030] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0031] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] Example

[0033] Please see Figure 1 As shown in this embodiment, the data fusion system for water quality and aquatic organism monitoring based on the Internet of Things includes a data acquisition module, a monitoring module, an analysis module, and a focus ranking module.

[0034] Data acquisition module: Based on the lake management platform, it acquires basic information about the lake, including lake area, location, historical water quality data and aquatic species. The lake is divided into several sub-regions according to its area, and the sub-regions are sent to the analysis module and the monitoring module.

[0035] The data acquisition module is primarily responsible for obtaining basic information about the lakes from the lake management platform and dividing the lakes into sub-regions based on their area. The data from these sub-regions will then be sent to the analysis and monitoring modules to support subsequent water quality monitoring and ecological analysis. The specific workflow of this module is as follows:

[0036] Extract basic information related to lake ecological monitoring from the lake management platform, including but not limited to:

[0037] Lake area (used for regional division);

[0038] Lake geographic location (for location and GIS analysis);

[0039] Historical water quality data (used for trend analysis and water quality change assessment);

[0040] Information on aquatic organism species and distribution (for biological similarity analysis);

[0041] Based on the total area of ​​the lake, and considering factors such as hydrodynamic characteristics, pollution source distribution, and aquatic habitats, the lake is divided into multiple sub-regions. The following methods can be used for this division:

[0042] Grid division: Divide the lake into equally sized grid cells, each cell serving as a sub-region.

[0043] Natural zoning: Based on the topographic features of the lake, the location of its inflow and outflow points, and the distribution characteristics of aquatic organisms, natural sub-regions are delineated.

[0044] Dynamic adjustment: Based on historical water quality data and aquatic organism monitoring results, the boundaries of sub-regions are adjusted to make the regional division more in line with ecological characteristics.

[0045] Each sub-region should include the following basic attribute information:

[0046] Area code (unique identifier);

[0047] Latitude and longitude range (for easy GIS analysis);

[0048] Area size (used for subsequent data normalization processing);

[0049] Historical water quality characteristics (summarizing the trend of water quality changes in the region based on past data);

[0050] Distribution of aquatic organisms (major species, population density, etc.);

[0051] Sub-region information is transmitted to the analysis module for subsequent processing:

[0052] Grey relational analysis of water quality parameters and aquatic organisms;

[0053] Calculation of aquatic organism similarity between sub-regions;

[0054] Assessment of the impact of water quality parameters on lake ecology;

[0055] Information from sub-regions is transmitted to the monitoring module, enabling the deployment of IoT sensors in each sub-region for real-time water quality monitoring. The monitoring module dynamically allocates monitoring devices, optimizes sensor layout, adjusts monitoring frequency based on sub-region water quality characteristics, acquires real-time water quality data, and feeds it back to the data fusion system.

[0056] The main function of the data acquisition module is to integrate basic information from the lake management platform, scientifically divide the lake into sub-regions, and provide data support to the analysis and monitoring modules. Reasonable regional division can improve the accuracy of water quality monitoring and provide foundational data for subsequent aquatic ecosystem analysis.

[0057] Monitoring module: Monitors the changes in water quality parameters in each sub-area in real time through IoT sensing devices, and sends the changes in water quality parameters to the analysis module;

[0058] The monitoring module detects the acidity or alkalinity of the water using a pH sensor, the oxygen content in the water using a dissolved oxygen (DO) sensor, the ammonia nitrogen, total phosphorus, and total nitrogen content in the water using ammonia nitrogen, total phosphorus, and total nitrogen sensors, the water transparency using a turbidity sensor, the water temperature using a temperature sensor, and the water conductivity using a conductivity sensor.

[0059] To ensure comprehensive monitoring of the lake's ecological environment, it is necessary to deploy various types of water quality sensing equipment. Each sensor is responsible for monitoring different water quality parameters, including:

[0060] pH sensor: Used to detect the acidity or alkalinity of water. Changes in pH value may be related to factors such as pollutant discharge and algae growth.

[0061] Dissolved oxygen (DO) sensor: used to monitor the oxygen content in water. Dissolved oxygen level is a key indicator of the living environment of aquatic organisms. Low oxygen may lead to fish death or eutrophication of water bodies.

[0062] Ammonia nitrogen, total phosphorus, and total nitrogen sensors: These parameters are core indicators for measuring the degree of water pollution. When they exceed the standards, they may lead to algal blooms and affect the survival of aquatic organisms.

[0063] Turbidity sensor: Monitors the transparency of water bodies. High turbidity may be caused by silt, suspended particulate matter or microorganisms, which can affect aquatic ecosystems.

[0064] Temperature sensor: Water temperature affects the metabolism of aquatic organisms, dissolved oxygen content, and microbial activity.

[0065] Conductivity sensor: detects the electrical conductivity of water and can be used to determine changes in salinity, especially suitable for ecological monitoring in brackish water areas.

[0066] Equipment deployment should fully consider the lake's geographical features, hydrodynamic characteristics, pollution source distribution, and aquatic habitats to ensure the representativeness and accuracy of monitoring data. Key strategies include:

[0067] Uniform distribution: Suitable for lakes with small areas and relatively uniform ecological environment, where the same number of sensing devices are deployed in each sub-area.

[0068] Key monitoring areas: Increase sensor density and improve monitoring accuracy in key areas such as the vicinity of pollution sources and ecologically sensitive areas (such as fish spawning grounds).

[0069] Dynamic adjustment: By combining historical water quality data, the sensor deployment location is dynamically optimized to ensure that the equipment can effectively monitor key water quality change areas.

[0070] Sensor calibration: All devices must be precisely calibrated before going online to eliminate drift errors and ensure accurate measurement data.

[0071] Device connectivity test: Confirm the stability of the sensor and the data transmission network (such as LoRa, NB-IoT, 4G / 5G or satellite communication) to ensure that the monitoring data can be uploaded in real time.

[0072] Power management: For solar-powered or battery-powered equipment, conduct power consumption assessments to ensure that the equipment can operate for extended periods.

[0073] Self-checking mechanism: The equipment needs to perform self-checks regularly, including data acquisition accuracy, transmission signal strength, battery power, etc., to ensure stable system operation.

[0074] Standard sampling frequency: Under stable water quality conditions, data is collected every 5 minutes or 1 hour to ensure data continuity.

[0075] High-frequency sampling under abnormal conditions: When the system detects fluctuations in water quality parameters (such as a sudden drop in pH or a sharp decrease in dissolved oxygen), the sampling frequency is immediately increased (e.g., once per minute), and the changing trend of the area is continuously monitored.

[0076] Fixed-point sampling: The sensing devices in each sub-region periodically collect the current water quality parameters.

[0077] Mobile monitoring (optional): In some lake areas, unmanned boats or underwater robots carrying sensors can be used for mobile monitoring to overcome the limitations of fixed-point monitoring.

[0078] The data collected by the sensors includes water quality parameters, timestamps, device serial numbers, and geographical locations. A standardized data format is required to ensure compatibility and processing of data collected from different devices. Example data format:

[0079] {

[0080] "timestamp":"2025-03-07T10:30:00Z",

[0081] "device_id":"sensor_001",

[0082] "location":{"latitude":39.9042,"longitude":116.4074},

[0083] pH: 7.2,

[0084] "DO":6.5,

[0085] "NH3-N":0.3,

[0086] "turbidity": 12.0

[0087] }

[0088] Analysis module: When water quality parameters fluctuate, the gray relational degree between the fluctuating water quality parameters and aquatic organisms is analyzed. After calculating the aquatic organism similarity characteristics between sub-regions, all sub-regions are clustered, and the gray relational degree in each category is analyzed holistically. The clustering results are sent to the attention ranking module.

[0089] After sub-region clustering, holistic analysis can identify the main water quality parameters affecting the entire cluster, helping managers to adjust water quality management measures in a targeted manner. For example, if all sub-regions of a cluster are sensitive to dissolved oxygen fluctuations, dissolved oxygen can be monitored closely and measures can be taken in advance to prevent the deterioration of the aquatic ecosystem in the entire area.

[0090] The analysis module compares the real-time monitored water quality parameters with the corresponding parameter thresholds. It obtains the difference by subtracting the corresponding parameter threshold from the real-time monitored water quality parameter value, and takes the absolute value of the difference as the deviation value of the water quality parameter. If the deviation value of the water quality parameter is greater than the preset deviation threshold, the analysis indicates that the water quality parameter has fluctuated.

[0091] When water quality parameters fluctuate, the analysis module obtains the density decline rate and mortality rate of aquatic organisms, normalizes the density decline rate and mortality rate to map their values ​​to the range of [0,1], and sums the normalized density decline rate and mortality rate to obtain the influencing factor.

[0092] The calculation logic for the density decline rate is as follows: when water quality parameters fluctuate, obtain the aquatic organism density at the moment when the water quality parameters fluctuate and the aquatic organism density at the current moment. Subtract the aquatic organism density at the moment when the water quality parameters fluctuate from the current moment to obtain the density decline value. Subtract the moment when the water quality parameters fluctuate from the current moment to obtain the monitoring duration. Divide the density decline value by the monitoring duration to obtain the density decline rate. The larger the density decline rate, the greater the impact of water quality parameters on aquatic organisms.

[0093] The logic for obtaining the mortality rate is as follows: after water quality parameters fluctuate for a period of time, the number of aquatic organisms that have perished (i.e. disappeared and died) is obtained. The number of perished organisms is divided by the duration of the fluctuation to obtain the mortality rate. The higher the mortality rate, the greater the impact of water quality parameters on aquatic organisms.

[0094] The expression for calculating the grey relational coefficient is as follows: In the formula, The grey relational coefficient is... For water quality parameters and the first Aquatic organisms at all times The absolute difference, and , For water quality parameters at time The value, For the first Aquatic organisms at all times Influence factors Represents the double minimum operator. Represents the doubly maximum operator. Let be the resolution coefficient, and .

[0095] In this application, the processing logic of the double minimum operator is as follows: first obtain the first... Find the absolute difference of the aquatic organisms at all times t. The minimum value, i.e. Then, the smallest of these minimum values ​​is taken, which represents the minimum absolute difference between all aquatic organisms and water quality parameters at all times, reflecting the minimum degree of difference between sequences.

[0096] The processing logic of the double maximum operator is as follows: first obtain the first... Find the absolute difference of the aquatic organisms at all times t. The maximum value, i.e. Then, the largest of these maximum values ​​is taken, which represents the maximum absolute difference between all aquatic organisms and water quality parameters at all times, reflecting the maximum degree of difference between sequences.

[0097] The analysis module calculates the grey relational degree between water quality parameters and aquatic organisms based on water quality parameter values ​​and influence indices. The expression is as follows: In the formula, For gray relational degree, For the number of time points, For the first Grey relational coefficients at each time point.

[0098] When water quality parameters change, the species distribution and abundance of aquatic organisms may be affected. To analyze lake ecosystems more comprehensively, the analysis module first calculates the similarity characteristics of aquatic organisms between sub-regions, and then clusters all sub-regions based on the similarity.

[0099] After calculating the aquatic organism similarity characteristics between sub-regions, the analysis module clusters all sub-regions and performs an overall analysis of the gray relational degree in each category. The clustering results are then sent to the attention ranking module.

[0100] The analysis module first obtains aquatic organism population information for each sub-region, mainly including:

[0101] Aquatic organisms (such as fish, plankton, benthic organisms, etc.);

[0102] Number of each species (individuals / L);

[0103] Biomass of each species (g / L or mg / L);

[0104] Species diversity indices (Shannon-Wiener index, Pielou evenness index, etc.);

[0105] Data sources include real-time monitoring data of aquatic organisms and historical data on aquatic organism distribution, so as to accurately measure the dynamic changes of biological communities when water quality parameters change.

[0106] After the analysis module obtains the aquatic organism species in all sub-regions, it calculates the aquatic organism similarity characteristics between each sub-region and other sub-regions, expressed as: In the formula, sub-region sub-region Similarities in aquatic organisms , They are sub-regions sub-region The mean population size of aquatic organisms. sub-region The Middle aquatic organism density sub-region The Middle Aquatic organism density.

[0107] After obtaining the aquatic organism similarity features between each sub-region and other sub-regions, a correlation matrix is ​​constructed based on the aquatic organism similarity features. The correlation matrix is ​​as follows:

[0108] In the formula, This is a correlation matrix. This represents the number of sub-regions.

[0109] The aquatic organism similarity features among all sub-regions are compared with a preset feature threshold. The feature threshold is used to determine whether a sub-region can be classified into a cluster. All sub-regions with aquatic organism similarity features greater than the feature threshold are classified into a cluster. If the aquatic organism similarity features of a sub-region are less than or equal to the feature threshold of all other sub-regions, then the sub-region is a separate cluster.

[0110] Assuming the feature threshold is 0.6 and the lake is divided into 3 sub-regions, the similarity features of aquatic organisms in each sub-region are calculated by the Pearson correlation coefficient and form a 3×3 correlation matrix;

[0111] Assuming the correlation is calculated based on the Pearson correlation coefficient, a 3×3 correlation matrix is ​​obtained as shown in Table 1 (example data):

[0112] Table 1 Correlation Matrix

[0113] subregion 1 2 3 1 1 0.75 0.40 2 0.75 1 0.55 3 0.40 0.55 1

[0114] Clustering is performed based on a feature threshold of 0.6. Sub-region 1 and sub-region 2 form a cluster because their similarity feature value is 0.75 > 0.6. The similarity feature values ​​of sub-region 3 are 0.40 and 0.55, respectively, both ≤ 0.6. Therefore, sub-region 3 forms a separate cluster.

[0115] Ultimately, the three sub-regions were divided into two clusters:

[0116] Cluster 1: {1,2};

[0117] Cluster 2: {3} (a separate sub-region).

[0118] After the analysis module clusters all sub-regions to obtain at least one cluster, it calculates the mean grey relational degree of each cluster. That is, it sums the grey relational degrees of all sub-regions in the cluster to obtain the total grey relational degree, and divides the total grey relational degree by the number of sub-regions in the cluster to obtain the mean grey relational degree.

[0119] Attention Ranking Module: Combining clustering results with historical changes in water quality parameters, the module finds the impact index of all water quality parameters relative to the lake, generates a water quality parameter attention ranking table, and sends it to the lake management platform.

[0120] The ranking module obtains the mean grey relational degree of each cluster and the historical frequency of fluctuations in water quality parameters. Based on the mean grey relational degree and the historical frequency of fluctuations, the influence index is calculated, expressed as: In the formula, To influence the index, The mean of the grey relational degree. For the frequency of historical fluctuations, , These are the weighting coefficients, and ;

[0121] The larger the impact index of a water quality parameter, the greater the impact of the change in that water quality parameter on aquatic organisms in the lake, the wider the scope of the impact, and the higher the frequency of historical fluctuations. Therefore, after obtaining the impact indices of all water quality parameters, all water quality parameters are sorted from largest to smallest according to their impact indices to generate a ranking table of attention.

[0122] This application uses a data acquisition module to divide a lake into several sub-regions based on its area. The analysis module analyzes the grey relational degree between fluctuating water quality parameters and aquatic organisms, calculates the aquatic organism similarity characteristics between sub-regions, clusters all sub-regions, and performs a comprehensive analysis of the grey relational degree within each category. The attention ranking module combines the clustering results with historical changes in water quality parameters to find the impact index of all water quality parameters relative to the lake, generates a water quality parameter attention ranking table, and sends it to the lake management platform. The fusion system calculates the aquatic organism similarity characteristics between sub-regions and clusters them based on these characteristics, classifying ecologically similar lake areas. This improves the targeting of lake management, enables rapid identification of affected aquatic organisms, and provides a scientific basis for ecological protection and pollution control.

[0123] The workflow of the fusion system is as follows:

[0124] The fusion system acquires basic information about lakes based on a lake management platform. This information includes lake area, location, historical water quality data, and aquatic species. The lake is divided into several sub-regions based on its area. The system monitors the changes in water quality parameters in each sub-region in real time using IoT sensors. When water quality parameters fluctuate, the system analyzes the grey relational degree between the fluctuating water quality parameters and aquatic species. After calculating the similarity characteristics of aquatic species between sub-regions, all sub-regions are clustered, and the grey relational degree in each category is analyzed holistically. Combining the clustering results with the historical changes in water quality parameters, the system finds the impact index of all water quality parameters relative to the lake, generates a water quality parameter attention ranking table, and sends it to the lake management platform.

[0125] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0126] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0127] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to any specific implementation. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. A data fusion system for water quality and aquatic organism monitoring based on the Internet of Things, characterized in that: It includes a data acquisition module, a monitoring module, an analysis module, and a focus ranking module; Data acquisition module: Acquires lake information based on the lake management platform and divides the lake into several sub-regions according to the lake area; Monitoring module: Monitors changes in water quality parameters in each sub-area in real time through IoT sensing devices; Analysis module: When water quality parameters fluctuate, the gray relational degree between fluctuating water quality parameters and aquatic organisms is analyzed. After calculating the aquatic organism similarity characteristics between sub-regions, all sub-regions are clustered, and the gray relational degree in each category is analyzed holistically. Attention Ranking Module: Combining clustering results with historical changes in water quality parameters, this module finds the impact index of all water quality parameters relative to the lake, generates a water quality parameter attention ranking table, and sends it to the lake management platform.

2. The data fusion system for water quality and aquatic organism monitoring based on the Internet of Things as described in claim 1, characterized in that: The analysis module calculates the grey relational degree between water quality parameters and aquatic organisms based on water quality parameter values ​​and influence indices, expressed as: In the formula, For gray relational degree, For the number of time points, For the first Grey relational coefficients at each time point.

3. The data fusion system for water quality and aquatic organism monitoring based on the Internet of Things as described in claim 2, characterized in that: The expression for calculating the grey relational coefficient is as follows: In the formula, The grey relational coefficient is... For water quality parameters and the first Aquatic organisms at all times The absolute difference, and , For water quality parameters at time The value, For the first Aquatic organisms at all times Influence factors Represents the double minimum operator, This represents the doubly maximum operator. Let be the resolution coefficient, and .

4. The data fusion system for water quality and aquatic organism monitoring based on the Internet of Things as described in claim 3, characterized in that: After obtaining the aquatic organism species in all sub-regions, the analysis module calculates the aquatic organism similarity characteristics between each sub-region and other sub-regions. After obtaining the aquatic organism similarity features between each sub-region and other sub-regions, a correlation matrix is ​​constructed based on the aquatic organism similarity features; The similarity features of aquatic organisms among all sub-regions are compared with a preset feature threshold. The feature threshold is used to determine whether a sub-region can be classified into a cluster. All sub-regions with aquatic organism similarity features greater than the feature threshold are classified into a cluster.

5. The data fusion system for water quality and aquatic organism monitoring based on the Internet of Things according to claim 4, characterized in that: The expression for the correlation matrix is: In the formula, This is a correlation matrix. This represents the number of sub-regions.

6. The data fusion system for water quality and aquatic organism monitoring based on the Internet of Things as described in claim 5, characterized in that: The similarity characteristics of aquatic organisms between each sub-region and other sub-regions are calculated using the following expression: In the formula, sub-region sub-region Similarities in aquatic organisms , They are sub-regions sub-region The mean population size of aquatic organisms. sub-region The Middle aquatic organism density sub-region The Middle Aquatic organism density.

7. The data fusion system for water quality and aquatic organism monitoring based on the Internet of Things as described in claim 6, characterized in that: The attention ranking module obtains the mean grey relational degree of each cluster and the historical frequency of fluctuations in the water quality parameters. Based on the mean grey relational degree and the historical frequency of fluctuations, it calculates the influence index, expressed as: In the formula, To influence the index, The mean of the grey relational degree. The frequency of historical fluctuations , These are the weighting coefficients, and ; After obtaining the impact index of all water quality parameters, sort all water quality parameters from largest to smallest according to the impact index to generate a ranking table of attention.

8. The data fusion system for water quality and aquatic organism monitoring based on the Internet of Things according to claim 7, characterized in that: When water quality parameters fluctuate, the analysis module obtains the density decline rate and mortality rate of aquatic organisms, normalizes the density decline rate and mortality rate to map their values ​​to the range of [0,1], and sums the normalized density decline rate and mortality rate to obtain the influencing factor.

9. The data fusion system for water quality and aquatic organism monitoring based on the Internet of Things as described in claim 8, characterized in that: The analysis module compares the real-time monitored water quality parameters with the corresponding parameter thresholds. It obtains the difference by subtracting the corresponding parameter threshold from the real-time monitored water quality parameter value, and takes the absolute value of the difference as the deviation value of the water quality parameter. If the deviation value of the water quality parameter is greater than the preset deviation threshold, the analysis indicates that the water quality parameter has fluctuated.

10. The data fusion system for water quality and aquatic organism monitoring based on the Internet of Things according to claim 9, characterized in that: The monitoring module uses a pH sensor to detect the acidity or alkalinity of the water, a dissolved oxygen sensor to monitor the oxygen content in the water, ammonia nitrogen, total phosphorus, and total nitrogen sensors to monitor the ammonia nitrogen, total phosphorus, and total nitrogen content in the water, a turbidity sensor to monitor the water transparency, a temperature sensor to monitor the water temperature, and a conductivity sensor to detect the water conductivity.

Images