Distributed farm bioaerosol simulation and health risk early warning method based on deep learning

Abstract

The invention discloses a distributed farm bioaerosol concentration simulation and health risk early warning method based on deep learning, and the method comprises the following steps: constructing and deploying a distributed sensor network, collecting and processing data, constructing a bioaerosol concentration distributed model and a health risk early warning model based on a deep learning method, and through a central processing control and 3D visualization unit, the simulation and prediction result of the bioaerosol concentration distributed model and the health risk level and early warning information generated by the health risk early warning model are used to generate a visual 3D graph. The risk of pathogen transmission is greatly reduced, the safety level of the farm environment is remarkably improved, and an intelligent and systematic solution is provided for guaranteeing the health of workers and animals.

Description

Technical Field

[0001] The present invention relates to the technical field of farm environment monitoring and health risk assessment, and in particular to a distributed farm bioaerosol simulation and health risk early warning method based on deep learning. Background Art

[0002] With the continuous increase in the scale and intensiveness of the aquaculture industry, the concentration of bioaerosols in farms and their surrounding environments has increased significantly. Bioaerosols are rich in a variety of microorganisms, including bacteria, fungi, viruses and allergens, which not only pose a potential threat to the air quality of farms and the public health of surrounding communities, but also affect the health of animals and cause human respiratory diseases, allergic reactions and other health problems. Therefore, it is particularly important to build an efficient monitoring and early warning system to timely evaluate the changes in bioaerosol concentrations and their impact on health.

[0003] Traditional monitoring methods mostly rely on regular sample collection and laboratory analysis, which is not only time-consuming and inefficient, but also unable to reflect the dynamic changes of bioaerosols in real time. To meet this challenge, it is urgent to conduct a systematic analysis of the sources, concentration changes and microbial components of bioaerosols, and dynamically update them according to actual conditions. This system will provide strong support for early warning and management of the impact of bioaerosols on air quality and public health, lay a scientific foundation for the sustainable development of the aquaculture industry, and help reduce resource waste, reduce corporate economic losses, and achieve more accurate local prevention and control measures. Summary of the invention

[0004] The purpose of the present invention is to provide a distributed farm bioaerosol simulation and health risk warning method based on deep learning to solve the problems in the above-mentioned background technology.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] A distributed farm bioaerosol concentration simulation and health risk warning method based on deep learning includes the following steps:

[0007] Build and deploy a distributed sensor network to collect real-time environmental data from multi-regional and multi-point farms, sample bioaerosol data, and obtain bioaerosol concentration data;

[0008] Standardize the collected data, form a structured data set from the standardized data and store it in a distributed database, preprocess the data set, and divide the data into a training set and a validation set;

[0009] A bioaerosol concentration distribution model is constructed based on a deep learning method, a training set is input into the bioaerosol concentration distribution model for training, and then the bioaerosol concentration distribution model is verified by a verification set. The verified model can simulate the concentration distribution of bioaerosols in farms in different regions and dynamically predict the diffusion behavior of bioaerosols in time and space dimensions;

[0010] A health risk warning model is constructed based on a deep learning method, the bioaerosol concentration in the data set is comprehensively analyzed, the health risk level is divided according to the analysis results, and the risk level threshold is set. The results of the simulation and prediction of the bioaerosol concentration distribution model are input into the health risk warning model to perform health risk analysis. If the result exceeds the threshold, a health risk warning is automatically triggered. If the prediction result is within the safety threshold, no alarm is triggered;

[0011] The simulation and prediction results of the bioaerosol concentration distribution model and the health risk level and warning information generated by the health risk warning model are combined into a visualized 3D graph through a central processing control and 3D visualization unit.

[0012] Furthermore, the standardized processing of the collected data includes removing outliers, normalization processing and unifying data types. The standardized data forms a structured data set and is stored in a distributed database to ensure the reliability of data storage and cross-regional sharing capabilities.

[0013] Furthermore, the preprocessing of the data set includes using a random forest algorithm combined with statistical methods to detect and process anomalies, accurately identifying and removing noise data by analyzing data characteristics and distribution patterns, and processing missing values ​​using interpolation, mean filling, or deep learning-based prediction completion methods.

[0014] Furthermore, the environmental data includes but is not limited to temperature, humidity, air pressure, atmospheric pollutant concentration and location information.

[0015] Furthermore, the risk threshold in the health risk warning model is set based on regulatory standards, industry specifications and historical risk data.

[0016] Furthermore, the distributed database can be updated periodically to optimize and adjust the bioaerosol concentration distribution model and the health risk warning model.

[0017] Furthermore, for the comprehensive analysis of bioaerosol concentrations in the data set, DNA / RNA is extracted from the samples in the data set by using automated extraction equipment, and sequence information is obtained by high-throughput sequencing methods. At the same time, the microscopic image processing module is used to collect sample images, and multi-dimensional feature extraction is performed on the images. The extracted DNA / RNA sequence and image feature data are then input into the health risk warning model together, and the pathogenic bacteria data are compared with the regional epidemic disease database to analyze the pathogenicity and evaluate the health risk level.

[0018] Furthermore, the health risk warning generates risk warning information and sends it to the manager's device to remind him to take countermeasures.

[0019] Furthermore, the visual 3D graph includes generating a dynamic heat map, a trend map and a risk level map.

[0020] Furthermore, the central processing control and 3D visualization unit can control the external information acquisition unit, store historical data and real-time environmental data, and record bioaerosol data.

[0021] Beneficial effects:

[0022] The present invention proposes a distributed farm bioaerosol simulation and health risk warning method based on deep learning. Through a distributed data acquisition network, the method can achieve real-time acquisition of bioaerosol data in multiple regions and complex environments, and comprehensively cover the key information of different farm environments. Through a distributed architecture, multi-point data is aggregated and input into a deep learning model for dynamic analysis and simulation, so as to more accurately evaluate the concentration distribution and propagation trend of bioaerosols. The present invention can combine deep learning technology to dynamically adjust the health risk assessment model, accurately identify potential threats, and optimize the emergency warning mechanism. When the risk exceeds the threshold, through real-time analysis and distributed control modules, the on-site equipment is linked to the scientifically regulated ventilation system to effectively inhibit the spread of pathogens. By providing early warning and scientific decision-making support to farm managers, the present invention greatly reduces the risk of pathogen transmission, significantly improves the environmental safety level of farms, and provides an intelligent and systematic solution to protect the health of staff and animals. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0024] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0025] Example

[0026] A distributed farm bioaerosol concentration simulation and health risk warning method based on deep learning, such as Figure 1 As shown, the following steps are included:

[0027] S1, build and deploy a distributed sensor network to collect real-time environmental data from multi-regional and multi-point farms, sample bioaerosol data, and obtain bioaerosol concentration data.

[0028] The environmental data include but are not limited to temperature, humidity, air pressure, atmospheric pollutant concentration (such as PM2.5, PM10, etc.) and location information. By building a distributed sensor network, data from each region can be collected and aggregated in real time at multiple points, fully covering the complexity of multi-regional and multi-environmental characteristics.

[0029] S2, standardize the collected data, form a structured data set from the standardized data and store it in a distributed database, preprocess the data set, and divide the data into a training set and a validation set.

[0030] The standardization of the collected data includes removing outliers, normalization and unifying data types. The standardized data forms a structured data set and is stored in a distributed database to ensure the reliability of data storage and cross-regional sharing capabilities. The preprocessing of the data set includes using a random forest algorithm combined with statistical methods to detect and process anomalies, accurately identifying and removing noise data by analyzing data characteristics and distribution patterns, and processing missing values ​​using interpolation, mean filling or deep learning-based prediction completion methods. Ensure the integrity and consistency of the data, thereby providing high-quality data input for subsequent model training and dynamic health risk assessment. Feature extraction is also required on the preprocessed data, and key feature variables such as temperature and humidity are used as input features of the model to provide highly correlated data for subsequent bioaerosol concentration distribution simulations.

[0031] S3, construct a bioaerosol concentration distribution model based on deep learning method, input the training set into the bioaerosol concentration distribution model for training, and then verify the bioaerosol concentration distribution model through the verification set. The verified model can simulate the concentration distribution of bioaerosols in farms in different regions and dynamically predict the diffusion behavior of bioaerosols in time and space dimensions.

[0032] The bioaerosol concentration distribution simulation is realized through the bioaerosol concentration distributed model, multi-source and multi-dimensional data are processed, spatial information is fully utilized, and the accuracy and scalability of concentration simulation are improved. Specifically, the model conducts in-depth analysis of the collected data to calculate the spatiotemporal distribution of bioaerosol concentration and its dynamic change law. All data and analysis results are stored in the dynamic basic database, and combined with the regular collection and feedback mechanism of the distributed architecture to ensure real-time update and efficient synchronization of data. Distributed processing not only improves the adaptability to complex environments in multiple regions, but also significantly enhances the efficiency of data calculation and feedback, laying a solid foundation for health risk management of farms and providing strong technical support for accurate early warning and automated control.

[0033] When verifying the distributed model of bioaerosol concentration, cross-regional and multi-scenario verification is carried out through distributed data sets. The model accuracy and prediction effect are evaluated based on multiple evaluation indicators such as mean square error and mean absolute error. The verified model is used to predict the spatial distribution of bioaerosol concentration at each point in the distributed farms in real time or periodically.

[0034] S4, build a health risk warning model based on deep learning methods, comprehensively analyze the bioaerosol concentration in the data set, divide the health risk level according to the analysis results, set the risk level threshold, input the simulation and prediction results of the bioaerosol concentration distribution model into the health risk warning model for health risk analysis, and automatically trigger a health risk warning if the result exceeds the threshold. If the prediction result is within the safety threshold, no alarm is triggered. The health risk warning model dynamically adjusts the parameters of the model through a deep learning algorithm to adapt to the complexity of the farm environment in different regions and improve the accuracy and applicability of the prediction.

[0035] The health risk level is generated through comprehensive calculations using a deep learning algorithm. Health risks are dynamically quantified based on multi-point monitoring data, diffusion model results, and real-time environmental parameters. Dynamic warning thresholds are set using health risk assessments. When the health risk level exceeds the warning threshold, the system automatically triggers a health risk warning. The early warning system generates risk warning information in real time and sends it to the manager's device, reminding them to take countermeasures, such as increasing ventilation and improving protective equipment, to effectively reduce potential health risks. If the system simulates that the bioaerosol concentration is within the safety threshold, the interface displays a safe state, and the system continues to dynamically monitor changes in bioaerosol concentrations and environmental parameters in the air, but does not trigger an alarm.

[0036] S5, generating a visualized 3D graph by combining the simulation and prediction results of the bioaerosol concentration distribution model with the health risk level and warning information generated by the health risk warning model through a central processing control and 3D visualization unit.

[0037] Among them, the central processing control and 3D visualization analysis unit can control the external information acquisition unit, combine the simulation results of bioaerosol concentration with the environmental layout of farms in different regions, and generate dynamic heat maps, trend maps and risk level maps based on 3D visualization. Users can view the diffusion path and risk hotspots of bioaerosols in real time through the interactive interface, and adjust the prevention and control measures in combination with the early warning information. In addition, historical data and real-time environmental data can also be stored, and bioaerosol data can be recorded. Through the 3D visualization unit, key data such as bioaerosol concentration and health risk warning are intuitively displayed to help users fully grasp the dynamic information of air quality and health risks. The system uses a variety of 3D visualization forms such as heat maps, trend maps and risk grading maps to show the spatial distribution, concentration change trend and health risk level of bioaerosols in the air of farms in different regions. The heat map intuitively presents the concentration distribution of bioaerosols in different regions to help identify high-risk areas; the trend map shows the time change trend of bioaerosol concentration, supporting risk trend prediction and early prevention. The risk grading map compares the real-time health risk index with the safety threshold, so that users can clearly understand the current health risk level. When the detected or simulated concentration level exceeds the warning threshold, the system will immediately display the warning information in the interface and make response suggestions, such as increasing ventilation, to help users respond quickly.

[0038] Preferably, the risk threshold in the health risk warning model is set based on regulatory standards, industry specifications and historical risk data. The air quality threshold system is set according to environmental regulations and health standards to provide a benchmark for subsequent air quality judgments.

[0039] Preferably, the distributed database can be updated periodically to optimize and adjust the bioaerosol concentration distribution model and the health risk warning model.

[0040] Preferably, for the comprehensive analysis of bioaerosol concentrations in the data set, DNA / RNA is extracted from the samples in the data set using automated extraction equipment, and sequence information is obtained using a high-throughput sequencing method. At the same time, the sample image is collected using a microscopic image processing module, and multi-dimensional feature extraction is performed on the image, including morphological features and fluorescence features, etc. The extracted DNA / RNA sequence and image feature data are then input into the health risk early warning model together, and the pathogenic bacteria data are compared with the regional epidemic disease database to analyze pathogenicity and assess the health risk level.

[0041] Based on the health risk warning model, bioaerosol data samples and environmental data are input into the model at the same time. The model calculates the health risk level through pre-training, generates a health risk report and triggers an emergency response. When the risk value exceeds the set threshold, a real-time warning is triggered and a health risk prompt is sent to the user, supporting the expansion needs of large-scale multi-point monitoring.

[0042] The distributed farm bioaerosol concentration simulation and health risk warning method based on deep learning in this embodiment is based on the environmental information data of farms in different regions. Through distributed collection and processing, multi-dimensional input is provided for the model, and two core models, namely, the bioaerosol concentration distributed model and the health risk warning model, are constructed using a deep learning method. Among them, the bioaerosol concentration distributed model simulates the concentration distribution of bioaerosols in farms in different regions by integrating meteorological data, regional characteristics and monitoring data obtained by a distributed sensor network, and dynamically predicts its diffusion behavior in time and space dimensions. The health risk warning model comprehensively analyzes the bioaerosol concentration and biological characteristic data to assess its potential health risks to farm workers and animals. Distributed applications enable data from each region to be gathered and processed in real time, thereby more comprehensively describing the diffusion laws and health risks of aerosols in complex environments. When the risk level exceeds the set threshold, the wind speed and direction can be dynamically adjusted by linking the ventilation equipment distributed in the farm to accurately control the diffusion path of pollutants. Through periodic database updates, the latest monitoring data collected in a distributed manner is continuously introduced to optimize model parameters and prediction accuracy, forming a closed-loop management mechanism from data collection, model optimization to risk feedback. The distributed architecture not only enhances the response speed and prediction reliability, but also can flexibly adapt to the needs of farms in multiple scenarios and scales, providing modern farms with efficient and intelligent risk warning and control solutions, and comprehensively improving the level of health management. In addition, the 3D visualization analysis unit is used to generate real-time updated bioaerosol concentration distribution maps and risk propagation path maps, which intuitively display high-risk areas and their diffusion trends for users, and provide scientific decision-making basis. The 3D visualization unit has built-in socio-economic impact analysis tools to comprehensively evaluate factors such as environmental governance costs, health maintenance costs, and production losses, calculate the social and economic benefits of current management measures, and generate evaluation reports. The report will be stored for a long time to provide a reference for future management optimization, help managers to more scientifically allocate resources and optimize solutions, and achieve an effective balance between economic benefits and health and safety.

[0043] Although the embodiments of the present invention are described in the specification, these embodiments are only for reference and should not limit the protection scope of the present invention. Various omissions, substitutions and changes within the scope of the present invention should be included in the protection scope of the present invention.

Claims

1. A distributed farm bioaerosol concentration simulation and health risk warning method based on deep learning, characterized in that: The following steps are involved: Build and deploy a distributed sensor network to collect real-time environmental data from multi-regional and multi-point farms, sample bioaerosol data, and obtain bioaerosol concentration data; Standardize the collected data, form a structured data set from the standardized data and store it in a distributed database, preprocess the data set, and divide the data into a training set and a validation set; A bioaerosol concentration distribution model is constructed based on a deep learning method, a training set is input into the bioaerosol concentration distribution model for training, and then the bioaerosol concentration distribution model is verified by a verification set. The verified model can simulate the concentration distribution of bioaerosols in farms in different regions and dynamically predict the diffusion behavior of bioaerosols in time and space dimensions; A health risk warning model is constructed based on a deep learning method, the bioaerosol concentration in the data set is comprehensively analyzed, the health risk level is divided according to the analysis results, and the risk level threshold is set. The results of the simulation and prediction of the bioaerosol concentration distribution model are input into the health risk warning model to perform health risk analysis. If the result exceeds the threshold, a health risk warning is automatically triggered. If the prediction result is within the safety threshold, no alarm is triggered; The simulation and prediction results of the bioaerosol concentration distribution model and the health risk level and warning information generated by the health risk warning model are combined into a visualized 3D graph through a central processing control and 3D visualization unit.

2. The distributed farm bioaerosol concentration simulation and health risk early warning method based on deep learning according to claim 1 is characterized in that: The standardized processing of the collected data includes removing outliers, normalization processing and unifying data types. The standardized data forms a structured data set and is stored in a distributed database to ensure the reliability of data storage and cross-regional sharing capabilities.

3. The distributed farm bioaerosol concentration simulation and health risk early warning method based on deep learning according to claim 1 is characterized in that: The preprocessing of the data set includes using a random forest algorithm combined with statistical methods to detect and process anomalies, accurately identifying and removing noise data by analyzing data characteristics and distribution patterns, and processing missing values ​​using interpolation, mean filling, or deep learning-based prediction completion methods.

4. The distributed farm bioaerosol concentration simulation and health risk early warning method based on deep learning according to claim 1 is characterized in that: The environmental data includes but is not limited to temperature, humidity, air pressure, atmospheric pollutant concentration and location information.

5. The distributed farm bioaerosol concentration simulation and health risk early warning method based on deep learning according to claim 1 is characterized in that: The risk thresholds in the health risk early warning model are set based on regulatory standards, industry specifications and historical risk data.

6. The distributed farm bioaerosol concentration simulation and health risk early warning method based on deep learning according to claim 1 is characterized in that: The distributed database can be updated periodically to optimize and adjust the bioaerosol concentration distribution model and the health risk warning model.

7. The distributed farm bioaerosol concentration simulation and health risk early warning method based on deep learning according to claim 1 is characterized in that: For the comprehensive analysis of bioaerosol concentrations in the data set, DNA / RNA is extracted from the samples in the data set by using automated extraction equipment, and sequence information is obtained through high-throughput sequencing methods. At the same time, the microscopic image processing module is used to collect sample images, and multi-dimensional features are extracted from the images. The extracted DNA / RNA sequences and image feature data are then input into the health risk warning model together, and the pathogenic bacteria data are compared with the regional epidemic disease database to analyze the pathogenicity and evaluate the health risk level.

8. The method for distributed farm bioaerosol concentration simulation and health risk early warning based on deep learning according to claim 1 is characterized in that: The health risk warning generates risk warning information and sends it to the manager's device to remind him to take countermeasures.

9. The distributed farm bioaerosol concentration simulation and health risk early warning method based on deep learning according to claim 1 is characterized in that: The visual 3D graph includes a dynamic heat map, a trend map and a risk level map.

10. The method for simulating bioaerosol concentration and warning health risks in distributed farms based on deep learning according to any one of claims 1 to 9, characterized in that: The central processing control and 3D visualization unit is capable of controlling the external information acquisition unit, storing historical data and real-time environmental data, and recording bioaerosol data.

Images