Environmental confidence assessment method and system based on DBSCAN
By combining the DBSCAN algorithm and the self-organizing algorithm, the problems of high computational cost and low prediction efficiency in environmental classification algorithms are solved, achieving efficient multi-class environmental classification with low computational cost, adapting to new environments and maintaining high prediction efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-12
- Publication Date
- 2026-04-03
AI Technical Summary
Existing environmental classification algorithms have high computational costs and low prediction efficiency over a long period of evolution, making it difficult to achieve rapid classification of multiple environmental categories.
We adopt a DBSCAN-based environmental confidence assessment method, which classifies multi-class environments by combining environmental labeling, normalization, clustering, cluster category judgment and frequency matrix update with historical prior probabilities. We also utilize a self-organizing algorithm to reduce computation and improve prediction efficiency.
It achieves efficient environment classification with low computational cost, can quickly adapt to new environments and maintain high predictive performance, and forms a higher-level data structure through a self-organizing algorithm, reducing the linearly growing computational cost and improving the algorithm's predictive performance.
Smart Images
Figure CN121784693A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of radar environment discrimination technology, and in particular to an environment confidence assessment method and system based on DBSCAN. Background Technology
[0002] Environmental classification involves dividing the external world of human survival and development into different categories based on various criteria, such as scope, nature, and elements, in order to more systematically study and address various environmental issues. Environmental classification is of great significance in daily life and scientific research. Because the environment is complex and ever-changing, environmental classification requires continuous learning in response to these changes.
[0003] In order to enable environmental classification algorithms to have the ability to learn and evolve over a long period of time, and to adapt to and learn new environments without deteriorating performance when evaluating historical data, it is necessary to invent an environmental classification algorithm with low computational cost and high algorithm prediction efficiency, so as to achieve rapid classification of multi-class environments. Summary of the Invention
[0004] The purpose of this invention is to provide a DBSCAN-based environmental confidence assessment method and system with low computational cost and high algorithm prediction efficiency.
[0005] The technical solution to achieve the purpose of this invention is: an environmental confidence assessment method based on DBSCAN, comprising the following steps:
[0006] Step 1: Use environmental labeling software to aggregate and extract radar echo features, and then label them;
[0007] Step 2: Normalize the environmental data features to eliminate the dimensional differences between different feature attributes;
[0008] Step 3: Based on the DBSCAN algorithm, cluster the environmental data features and establish environmental cluster centers. The distance between a sample and the cluster center represents the similarity between the sample and the category.
[0009] Step 4: Repeat the clustering calculation to obtain a batch of cluster centers formed after clustering, and determine the cluster category of the environmental data characteristics;
[0010] Step 5: Collect and analyze the clustered environmental marker information to form a frequency matrix;
[0011] Step 6: Update the frequency matrix when new environmental data is obtained;
[0012] Step 7: In the usage phase, historical prior probabilities are used to determine the confidence level of the environment, thereby achieving the classification of multiple types of environments.
[0013] Furthermore, in step 1, the radar echo features are aggregated and extracted using environmental labeling software and then labeled, as detailed below:
[0014] Using environmental labeling software, radar echo features were aggregated, extracted, and labeled. The labeled environmental data features were then... The environmental category is , .
[0015] Furthermore, the normalization of environmental data features described in step 2 is calculated using the following formula:
[0016]
[0017] In the formula, For the i-th environmental data feature, for The mean, for The standard deviation.
[0018] Furthermore, in step 3, the environmental data features are clustered using the DBSCAN algorithm to establish environmental cluster centers. The distance between a sample and a cluster center represents the similarity between the sample and the category, as detailed below:
[0019] Step 3.1: Set the cluster distance to [value]. The minimum number of samples that can be clustered is ;
[0020] Step 3.2: Index each environmental data feature in sequence and calculate the remaining environmental data features. and Manhattan distance :
[0021]
[0022] Step 3.3: Statistical distance is less than the set distance The number of environmental data features P, if P is less than Based on the characteristics of the current environmental data These are isolated noise points, and they are discarded. Conversely, the characteristics of the current environmental data are considered to be... Effective clusters have already formed nearby; the center of the features in this batch of environmental data is extracted as the cluster center:
[0023]
[0024] in, Indicates the first Cluster center.
[0025] Furthermore, the determination of the cluster category of environmental data characteristics in step 4 is as follows:
[0026] The method for determining the cluster category of environmental data features is as follows:
[0027]
[0028] in, Indicates to make The quantity that corresponds to the minimum value; This indicates the process of finding the minimum value of the following expression. The value of .
[0029] Furthermore, in step 5, the clustered environmental marker information is statistically analyzed to form a frequency matrix. The formula is as follows:
[0030]
[0032] Furthermore, in step 7, during the usage phase, historical prior probabilities are used to determine the confidence level of the environment. The formula is as follows:
[0033]
[0035] A DBSCAN-based environmental confidence assessment system is provided. This system implements the DBSCAN-based environmental confidence assessment method. The system includes a labeling module, a normalization module, a clustering module, a cluster category determination module, a statistics module, an update module, and a classification module, wherein:
[0036] The tagging module uses environmental tagging software to aggregate and extract radar echo features and then tag them.
[0037] The normalization module normalizes environmental data features, eliminating dimensional differences between different feature attributes.
[0038] The clustering module, based on the DBSCAN algorithm, clusters environmental data features and establishes environmental cluster centers. The distance between a sample and a cluster center represents the similarity between the sample and the category.
[0039] The cluster category determination module performs clustering calculations in a loop to obtain a batch of cluster centers formed after clustering, and determines the cluster category of environmental data characteristics;
[0040] The statistics module collects and aggregates environmental marker information into clusters, forming a frequency matrix.
[0041] The update module updates the frequency matrix when new environmental data is obtained;
[0042] The classification module, during the usage phase, uses historical prior probabilities to determine the confidence level of the environment, thereby achieving classification of multiple environmental categories.
[0043] A mobile terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, it implements the DBSCAN-based environmental confidence assessment method.
[0044] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the DBSCAN-based environmental confidence assessment method.
[0045] Compared with the prior art, the present invention has the following significant advantages: (1) By statistically analyzing and iterating the frequency of occurrence of the environment in history, the algorithm is dynamically updated and the rapid classification of multi-category environments is achieved based on the self-organizing method; (2) The statistics adopt the frequency of features to different labels and the self-organizing algorithm is used to improve the efficiency of the algorithm; (3) The K-means algorithm is used to re-cluster the cluster center results to form a higher-level data structure. The number of levels is determined by the number of internal clusters, which can ultimately reduce the linearly growing computational load and improve the algorithm's prediction efficiency. Attached Figure Description
[0046] Figure 1 This is a flowchart illustrating an environmental confidence assessment method based on DBSCAN according to the present invention. Detailed Implementation
[0047] The present invention will now be described in further detail with reference to the accompanying drawings and specific embodiments.
[0048] like Figure 1 As shown, this invention discloses an environmental confidence assessment method based on DBSCAN. This method improves algorithm performance by employing a self-organizing algorithm. Essentially, this self-organizing algorithm re-clusters the cluster center results using the K-means algorithm, thereby forming a higher-level data structure and significantly improving the algorithm's prediction performance. The method includes the following steps:
[0049] Step 1: Use environmental labeling software to aggregate and extract radar echo features, and then label them;
[0050] Step 2: Normalize the environmental data features to eliminate the dimensional differences between different feature attributes;
[0051] Step 3: Based on the DBSCAN algorithm, cluster the environmental data features and establish environmental cluster centers. The distance between a sample and the cluster center represents the similarity between the sample and the category.
[0052] Step 4: Repeat the clustering calculation to obtain a batch of cluster centers formed after clustering, and determine the cluster category of the environmental data characteristics;
[0053] Step 5: Collect and analyze the clustered environmental marker information to form a frequency matrix;
[0054] Step 6: Update the frequency matrix when new environmental data is obtained;
[0055] Step 7: In the usage phase, historical prior probabilities are used to determine the confidence level of the environment, thereby achieving the classification of multiple types of environments.
[0056] As a specific example, step 1 involves using environmental labeling software to aggregate and extract radar echo features, and then labeling them, as detailed below:
[0057] Using environmental labeling software, radar echo features were aggregated, extracted, and labeled. The labeled environmental data features were then... The environmental category is , .
[0058] As a specific example, the normalization of environmental data features described in step 2 is calculated using the following formula:
[0059]
[0060] In the formula, For the i-th environmental data feature, for The mean, for The standard deviation.
[0061] As a specific example, step 3, based on the DBSCAN algorithm, clusters environmental data features to establish environmental cluster centers. The distance between a sample and the cluster center represents the similarity between the sample and the category, as detailed below:
[0062] Step 3.1: Set the cluster distance to [value]. The minimum number of samples that can be clustered is ;
[0063] Step 3.2: Index each environmental data feature in sequence and calculate the remaining environmental data features. and Manhattan distance :
[0064]
[0065] Step 3.3: Statistical distance is less than the set distance The number of environmental data features P, if P is less than Based on the characteristics of the current environmental data These are isolated noise points, and they are discarded. Conversely, the characteristics of the current environmental data are considered to be... Effective clusters have already formed nearby; the center of the features in this batch of environmental data is extracted as the cluster center:
[0066]
[0067] in, Indicates the first Cluster center.
[0068] As a specific example, the determination of the cluster category of environmental data characteristics in step 4 is as follows:
[0069] The method for determining the cluster category of environmental data features is as follows:
[0070]
[0071] in, Indicates to make The quantity that corresponds to the minimum value; This indicates the process of finding the minimum value of the following expression. The value of .
[0072] As a specific example, in step 5, the clustered environmental marker information is statistically analyzed to form a frequency matrix. The formula is as follows:
[0073]
[0075] As a specific example, in step 7, during the usage phase, historical prior probabilities are used to determine the confidence level of the environment. The formula is as follows:
[0076]
[0078] This invention is based on the DBSCAN environmental confidence assessment method, which statistically analyzes environmental features and their labels to achieve a probability mapping from features to labels. To enable dynamic evolution and updates of the algorithm, the statistics use the frequency of features to different labels. A self-organizing algorithm is proposed to improve algorithm performance. This self-organizing algorithm essentially re-clusters the cluster center results using the K-means algorithm, thereby forming a higher-level data structure. The number of levels is determined by the number of internal clusters, ultimately reducing the linearly increasing computational load and significantly improving the algorithm's prediction performance.
[0079] In one specific embodiment, the present invention provides an environment confidence assessment system based on DBSCAN. This system is used to implement the aforementioned DBSCAN-based environment confidence assessment method. The system includes a labeling module, a normalization module, a clustering module, a cluster category determination module, a statistics module, an update module, and a classification module, wherein:
[0080] The tagging module uses environmental tagging software to aggregate and extract radar echo features and then tag them.
[0081] The normalization module normalizes environmental data features, eliminating dimensional differences between different feature attributes.
[0082] The clustering module, based on the DBSCAN algorithm, clusters environmental data features and establishes environmental cluster centers. The distance between a sample and a cluster center represents the similarity between the sample and the category.
[0083] The cluster category determination module performs clustering calculations in a loop to obtain a batch of cluster centers formed after clustering, and determines the cluster category of environmental data characteristics;
[0084] The statistics module collects and aggregates environmental marker information into clusters, forming a frequency matrix.
[0085] The update module updates the frequency matrix when new environmental data is obtained;
[0086] The classification module, during the usage phase, uses historical prior probabilities to determine the confidence level of the environment, thereby achieving classification of multiple environmental categories.
[0087] It should be noted that the DBSCAN-based environmental confidence assessment system provided in this embodiment of the invention is used to execute all the process steps of the DBSCAN-based environmental confidence assessment method described in the above embodiment. The working principles and beneficial effects of the two are one-to-one, and therefore will not be repeated.
[0088] This invention also provides a mobile terminal. The mobile terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor, such as a DBSCAN-based environmental confidence assessment method program. When the processor executes the computer program, it implements the steps in the various DBSCAN-based environmental confidence assessment method embodiments described above. Alternatively, when the processor executes the computer program, it implements the functions of each module in the various system embodiments described above.
[0089] In one specific embodiment, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the DBSCAN-based environmental confidence assessment method.
[0090] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the electronic device.
[0091] The mobile terminal can be a computing device such as a desktop computer, laptop, PDA, or smart tablet. The mobile terminal may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above components are merely examples of electronic devices and do not constitute a limitation on the mobile terminal. It may include more or fewer components than described above, or a combination of certain components, or different components. For example, the mobile terminal may also include input / output devices, network access devices, buses, etc.
[0092] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the electronic device, connecting all parts of the electronic device via various interfaces and lines.
[0093] The memory can be used to store the computer programs and / or modules. The processor implements various functions of the electronic device by running or executing the computer programs and / or modules stored in the memory and by calling data stored in the memory. The memory may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, phonebook, etc.). In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other volatile solid-state storage device.
[0094] Wherein, if the modules / units integrated in the mobile terminal are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, it can implement the steps of the various method embodiments described above. Wherein, the computer program includes computer program code, which can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content contained in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.
[0095] It should be noted that the embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.
[0096] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. In particular, it should be noted that any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention for those skilled in the art.
Claims
1. A method for assessing environmental confidence based on DBSCAN, characterized in that, Includes the following steps: Step 1: Use environmental labeling software to aggregate and extract radar echo features, and then label them; Step 2: Normalize the environmental data features to eliminate the dimensional differences between different feature attributes; Step 3: Based on the DBSCAN algorithm, cluster the environmental data features and establish environmental cluster centers. The distance between a sample and the cluster center represents the similarity between the sample and the category. Step 4: Repeat the clustering calculation to obtain a batch of cluster centers formed after clustering, and determine the cluster category of the environmental data characteristics; Step 5: Collect and analyze the clustered environmental marker information to form a frequency matrix; Step 6: Update the frequency matrix when new environmental data is obtained; Step 7: In the usage phase, historical prior probabilities are used to determine the confidence level of the environment, thereby achieving classification of multiple environmental categories.
2. The environmental confidence assessment method based on DBSCAN according to claim 1, characterized in that, Step 1 involves using environmental labeling software to aggregate and extract radar echo features, and then labeling them, as detailed below: Using environmental labeling software, radar echo features were aggregated, extracted, and labeled. The labeled environmental data features were then... The environmental category is , .
3. The DBSCAN-based environmental confidence assessment method according to claim 2, characterized in that, The normalization of environmental data features described in step 2 is calculated using the following formula: ； In the formula, For the i-th environmental data feature, for The mean, for The standard deviation.
4. The DBSCAN-based environmental confidence assessment method according to claim 3, characterized in that, Step 3 describes the use of the DBSCAN algorithm to cluster environmental data features and establish environmental cluster centers. The distance between a sample and a cluster center represents the similarity between the sample and the category, as detailed below: Step 3.1: Set the cluster distance to [value]. The minimum number of samples that can be clustered is ; Step 3.2: Index each environmental data feature in sequence and calculate the remaining environmental data features. and Manhattan distance : ； Step 3.3: Statistical distance is less than the set distance The number of environmental data features P, if P is less than Based on the characteristics of the current environmental data These are isolated noise points, and they are discarded. Conversely, the characteristics of the current environmental data are considered to be... Effective clusters have already formed nearby; the center of the features in this batch of environmental data is extracted as the cluster center: ； in, Indicates the first Cluster center.
5. The DBSCAN-based environmental confidence assessment method according to claim 4, characterized in that, The determination of the cluster category of environmental data characteristics in step 4 is as follows: The method for determining the cluster category of environmental data features is as follows: ； in, Indicates to make The quantity that corresponds to the minimum value; This indicates the process of finding the minimum value of the following expression. The value of .
6. The DBSCAN-based environmental confidence assessment method according to claim 5, characterized in that, In step 5, the environmental marker information that is clustered together is statistically analyzed to form a frequency matrix. The formula is as follows: 。 7. The DBSCAN-based environmental confidence assessment method according to claim 6, characterized in that, In step 7, during the usage phase, historical prior probabilities are used to determine the confidence level of the environment. The formula is as follows: 。 8. An environmental confidence assessment system based on DBSCAN, characterized in that, This system is used to implement the DBSCAN-based environmental confidence assessment method according to any one of claims 1 to 7. The system includes a labeling module, a normalization module, a clustering module, a cluster category determination module, a statistics module, an update module, and a classification module, wherein: The tagging module uses environmental tagging software to aggregate and extract radar echo features and then tag them. The normalization module normalizes environmental data features, eliminating dimensional differences between different feature attributes. The clustering module, based on the DBSCAN algorithm, clusters environmental data features and establishes environmental cluster centers. The distance between a sample and a cluster center represents the similarity between the sample and the category. The cluster category determination module performs clustering calculations in a loop to obtain a batch of cluster centers formed after clustering, and determines the cluster category of environmental data characteristics; The statistics module collects and aggregates environmental marker information into clusters, forming a frequency matrix. The update module updates the frequency matrix when new environmental data is obtained; The classification module, during the usage phase, uses historical prior probabilities to determine the confidence level of the environment, thereby achieving classification of multiple environmental categories.
9. A mobile terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the DBSCAN-based environmental confidence assessment method as described in any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the DBSCAN-based environmental confidence assessment method as described in any one of claims 1 to 7.