CN115941807A - Efficient data compression method for park security system - Google Patents
Efficient data compression method for park security system Download PDFInfo
- Publication number
- CN115941807A CN115941807A CN202211657753.0A CN202211657753A CN115941807A CN 115941807 A CN115941807 A CN 115941807A CN 202211657753 A CN202211657753 A CN 202211657753A CN 115941807 A CN115941807 A CN 115941807A
- Authority
- CN
- China
- Prior art keywords
- data
- data point
- coordinate system
- sensor
- abnormal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000013144 data compression Methods 0.000 title claims abstract description 17
- 230000002159 abnormal effect Effects 0.000 claims abstract description 165
- 230000002776 aggregation Effects 0.000 claims abstract description 34
- 238000004220 aggregation Methods 0.000 claims abstract description 34
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 230000005856 abnormality Effects 0.000 description 13
- 230000011218 segmentation Effects 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 238000007726 management method Methods 0.000 description 5
- 238000012216 screening Methods 0.000 description 5
- 238000012502 risk assessment Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000007906 compression Methods 0.000 description 3
- 230000006835 compression Effects 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Alarm Systems (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention relates to the technical field of data compression, in particular to a high-efficiency data compression method for a park security system. The method comprises the following steps: constructing a three-dimensional coordinate system corresponding to each type of sensor based on data in the garden acquired by different types of sensors, and acquiring the category of the area where each sensor is located; obtaining the distribution aggregation degree of each data point based on the category, and further determining the corresponding neighborhood distance; obtaining the abnormal degree of each data point based on the data value of each data point and the data value of the data point in the neighborhood distance of each data point; marking the pixel points with the abnormal degree larger than the abnormal degree threshold value, acquiring data points to be corrected, correcting the abnormal degree of each data point to be corrected, acquiring a normal data point and an abnormal data point, and compressing and storing the corresponding data based on the normal data point and the abnormal data point. The invention improves the efficiency of data compression on the basis of ensuring that the important data of the security system of the park is not lost.
Description
Technical Field
The invention relates to the technical field of data compression, in particular to a high-efficiency data compression method for a garden security system.
Background
An important task of intelligent campus management is to manage the security and protection operations of the campus. The intelligent security system of the garden is through applying the internet of things technology, so that the interconnection and intercommunication of all the sub security systems can extract and analyze data of the garden in real time, emergency treatment is timely carried out on the garden, and the function of real-time prevention is realized. In the operation management of the intelligent security system of the park, various sensor devices are arranged in the park, and data acquired by the sensors are transmitted to the intelligent park security system through the technology of the Internet of things for scientific analysis and decision-making.
However, because the number of sensors arranged in the campus is large, and the data of the sensors are various and are continuously updated in time series, the amount of data collected by the sensors is large, and further, the storage amount of the data is large. Since the network transmission bandwidth and the storage space are limited, if all the acquired data are stored, the equipment cost needs to be increased. The existing method usually adopts a lossy compression mode to compress data collected by a sensor, so that part of information is lost, the risk of accurately analyzing a park cannot be guaranteed, and further, greater potential safety hazard exists. Therefore, how to efficiently compress the data of the security system of the park and ensure that important data are not lost is a problem to be solved.
Disclosure of Invention
In order to solve the problem that the data of the garden security system cannot be efficiently compressed on the basis of ensuring that important data are not lost in the prior art, the invention aims to provide an efficient data compression method for the garden security system, and the adopted technical scheme is as follows:
the invention provides a high-efficiency data compression method for a garden security system, which comprises the following steps:
acquiring data in a park in real time by using different types of sensors;
constructing a three-dimensional coordinate system corresponding to each type of sensor based on data in the campus acquired by each type of sensor, wherein the three-dimensional coordinate system comprises at least two data points; obtaining the corresponding category of the area where each sensor is located based on the park plan and the trained neural network; obtaining the distribution aggregation degree corresponding to each data point according to the category corresponding to the area where each sensor is located and the position of each data point in the three-dimensional coordinate system;
determining a neighborhood distance corresponding to each data point in the three-dimensional coordinate system based on the distribution aggregation degree and the total number of data points corresponding to the regions belonging to the same category and corresponding to the regions corresponding to the data points in the three-dimensional coordinate system; obtaining the abnormal degree of each data point based on the data value of each data point and the data value of the data point in the neighborhood distance of each data point; marking the pixel points with the abnormal degree larger than the abnormal degree threshold value, acquiring data points to be corrected according to the marked data points and the unmarked data points, and correcting the abnormal degree of each data point to be corrected to acquire the corrected abnormal degree;
and acquiring a normal data point and an abnormal data point based on the abnormal degree of each data point and the abnormal degree corrected by each data point to be corrected, and compressing and storing corresponding data based on the normal data point and the abnormal data point.
Preferably, the acquiring the data point to be corrected according to the marked data point and the non-marked data point includes:
for either type of sensor: calculating the ratio of the number of the marked data points in the three-dimensional coordinate system corresponding to the type of sensor to the total number of the data points in the three-dimensional coordinate system corresponding to the type of sensor, and taking the ratio as the proportion of the abnormal data points in the three-dimensional coordinate system corresponding to the type of sensor;
marking the sensor with the largest proportion of abnormal data points in the three-dimensional coordinate system as a reference type sensor; recording a three-dimensional coordinate system corresponding to other types of sensors except the reference type of sensor as a coordinate system to be analyzed;
for the qth coordinate system to be analyzed:
and recording an area corresponding to the nth non-mark data point in the coordinate system to be analyzed as a target area, judging whether the area corresponding to the mark data point exists in the three-dimensional coordinate system corresponding to the sensor of the reference type as the target area, and recording the nth non-mark data point in the coordinate system to be analyzed as a data point to be corrected if the area corresponding to the mark data point exists in the three-dimensional coordinate system corresponding to the sensor of the reference type.
Preferably, the correcting the abnormal degree of each data point to be corrected to obtain the corrected abnormal degree includes:
marking a mark data point in a target area which is a corresponding area in a three-dimensional coordinate system corresponding to the sensor of the reference type as a reference data point; and calculating the abnormal degree of the data point to be corrected according to the Euclidean distance between the sensor for collecting the data value of the data point to be corrected and the sensor for collecting the data value of each reference data point and the data value of the data point to be corrected.
Preferably, the abnormal degree after the nth data point to be corrected in the qth coordinate system to be analyzed is calculated by the following formula:
wherein, beta ′ qn The abnormal degree of the nth data point to be corrected in the qth coordinate system to be analyzed is obtained, W is the number of the reference data points, d n,w For the Euclidean distance between the sensor for collecting the data value of the nth data point to be corrected and the sensor for collecting the data value of the w reference data point in the q coordinate system to be analyzed, exp () is an exponential function with a natural constant as a base number, and beta qn The abnormal degree of the nth data point to be corrected in the qth coordinate system to be analyzed.
Preferably, the obtaining the distribution aggregation degree corresponding to each data point according to the category corresponding to the area where each sensor is located and the position of each data point in the three-dimensional coordinate system includes:
for the ith data point in the three-dimensional coordinate system corresponding to any type of sensor:
calculating the mean value of Euclidean distances between the ith data point and all data points corresponding to the regions, corresponding to the ith data point, of the same class in the three-dimensional coordinate system corresponding to the sensor of the type, and recording the mean value as a first mean value; the area corresponding to the ith data point is the area where the sensor is located when the data value of the ith data point is acquired;
and taking a natural constant as a base number, and taking a value of an exponential function taking the negative first mean value as an index as the distribution aggregation degree corresponding to the ith data point.
Preferably, the determining a neighborhood distance corresponding to each data point in the three-dimensional coordinate system based on the distribution aggregation degree and the total number of data points corresponding to regions in the three-dimensional coordinate system, where the regions corresponding to the data points belong to the same category, includes:
for the ith data point in the three-dimensional coordinate system corresponding to any type of sensor: calculating the product of the total number of data points corresponding to the regions corresponding to the ith data point and belonging to the same category in the three-dimensional coordinate system corresponding to the sensor of the type and the distribution aggregation degree corresponding to the ith data point, and recording the product as a first product; rounding the first product downwards, and recording the result of rounding downwards as a first distance; and taking the sum of the first distance and the initial neighborhood distance as the neighborhood distance corresponding to the ith data point.
Preferably, the obtaining the abnormal degree of each data point based on the data value of each data point and the data value of the data point in the neighborhood distance of each data point includes:
for the ith data point in the three-dimensional coordinate system corresponding to any type of sensor:
obtaining the local distribution degree of the ith data point according to the difference between the data value of the ith data point and the data value of each data point within the neighborhood distance of the ith data point and the data value of the ith data point;
and taking the ratio of the average value of the local distribution degrees of all the data points in the neighborhood distance of the ith data point to the local distribution degree of the ith data point as the abnormal degree of the ith data point.
Preferably, the acquiring normal data points and abnormal data points based on the abnormal degree of each data point and the abnormal degree after each data point to be corrected, and performing compression storage on corresponding data based on the normal data points and the abnormal data points includes:
taking the corrected data points to be corrected with the abnormal degree larger than the abnormal degree threshold value as abnormal data points, taking all data points except the data points to be corrected as abnormal data points, and taking all data points except the abnormal data points in all three-dimensional coordinate systems as normal data points;
and respectively coding the data value of the normal data point and the data value of the abnormal data point by adopting run length coding, and storing the coded data.
The invention has at least the following beneficial effects:
1. the method comprises the steps of firstly establishing a three-dimensional coordinate system corresponding to each type of sensor based on data in a garden obtained by each type of sensor, considering that certain relevance exists between data collected by the same type of sensor arranged in similar areas in the garden, obtaining a category corresponding to each area in a plane graph of the garden by using a neural network, calculating the distribution aggregation degree corresponding to each data point according to the category corresponding to the area where each sensor is located in the garden and the position of each data point in the three-dimensional coordinate system, representing the relevance between the data collected by the sensors, further determining the neighborhood distance corresponding to each data point, effectively avoiding the interference of inappropriate neighborhood size setting on the accuracy of a calculation result when the abnormal degree of each data point is calculated subsequently, further enabling the screening result of subsequent data to be more accurate, respectively compressing the normal data and the abnormal data to different degrees, and improving the efficiency and reliability of data compression on the basis of ensuring that important data of a security system is not lost.
2. When the abnormal degree of each data point is calculated, the abnormal degree of each data point is obtained based on the data value of each data point and the data value of the data point in the neighborhood distance of each data point, and the pixel points with the abnormal degree larger than the abnormal degree threshold value are marked; considering that the marked data points and the non-marked data points have different presented characteristics, the abnormal degree of the marked pixel points is larger, and attention should be paid to the marked pixel points, so that the data points to be corrected are obtained according to the marked data points and the non-marked data points.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flowchart of a method for efficiently compressing data of a security system of a park according to the present invention.
Detailed Description
To further illustrate the technical means and effects of the present invention for achieving the predetermined objects, the following detailed description of a method for efficiently compressing data of a security system of a campus according to the present invention is provided with reference to the accompanying drawings and preferred embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following describes a specific scheme of the efficient data compression method for the park security system provided by the invention in detail with reference to the accompanying drawings.
An embodiment of a method for efficiently compressing data of a park security system comprises the following steps:
as shown in fig. 1, the method for efficiently compressing the data of the campus security system of this embodiment includes the following steps:
and S1, acquiring data in the park in real time by using different types of sensors.
At garden security protection system in the management process, the inside data information in garden is gathered to the installation multiple sensor in the garden to data transmission to the management system in through internet of things with gathering. However, the acquired data volume is huge, and part of the data acquired by the sensors does not contain or only contains a small amount of important information, so that a large space is occupied and the equipment cost is increased if all the data acquired by the sensors are transmitted and stored, so that the data acquired by the sensors are screened, the data which contain more information and influence the risk analysis of the security system of the park are selected, and the redundancy of the data is reduced as much as possible.
In this embodiment, a plurality of types of sensor devices are arranged in the campus, and are used for acquiring data information in the campus in real time, and the types of the sensor devices include: infrared ray sensor, fire smoke sensor, gas leakage sensor, temperature sensor, humidity sensor, etc.; setting the sampling frequency and the acquisition time of all the sensors to be the same, and setting all the sensors to acquire data once per second in the embodiment; the installation position of each sensor can be planned according to the distribution situation in the garden, and the implementer of the specific model and type of the sensor selects according to the specific situation.
Therefore, the data in the campus at each acquisition time are acquired by using different types of sensors.
S2, constructing a three-dimensional coordinate system corresponding to each type of sensor based on data in the garden acquired by each type of sensor, wherein the three-dimensional coordinate system comprises at least two data points; obtaining the corresponding category of the area where each sensor is located based on the park plan and the trained neural network; and obtaining the distribution aggregation degree corresponding to each data point according to the category corresponding to the area where each sensor is located and the position of each data point in the three-dimensional coordinate system.
Because the data collected by the sensors contains data which does not contain or only contains a small amount of important information, the data has a small effect on the security risk analysis of the park, namely, the data contains less information which is beneficial to the security risk analysis of the park. Therefore, the abnormal degree of each data is calculated by the embodiment and used for representing the information quantity which is contained in each data and is beneficial to the security risk analysis of the park, and then the data are screened, so that the redundancy of the data is reduced as much as possible, and favorable conditions are provided for the compression of the data.
In order to facilitate analysis of the abnormal degree of each piece of data collected by the sensor, the data collected by the sensor is converted into data points by constructing a three-dimensional data coordinate system, and the abnormal degree of the corresponding data is determined by analyzing the abnormal degree of each three-dimensional data point. In this embodiment, a three-dimensional coordinate system is constructed for data acquired by each type of sensor, and data in the three-dimensional coordinate system is continuously updated along with update of acquired data, that is, is continuously changed along with change of acquisition time, specifically, for a gas leakage sensor: acquiring a two-dimensional coordinate of each gas leakage sensor in a park plan, and constructing a three-dimensional coordinate system corresponding to each gas leakage sensor at any acquisition time according to the two-dimensional coordinate of each gas leakage sensor in the park plan and a data value acquired by each gas leakage sensor at the acquisition time, wherein an X axis and a Y axis in the three-dimensional coordinate system represent coordinate values of data points, and a Z axis represents the data value of the data points; since the heights of the same type of sensor installation generally do not differ much, the present embodiment does not consider the height coordinates of the sensors. By adopting the method, the three-dimensional coordinate system corresponding to each type of sensor at each acquisition time can be obtained, and data points in the three-dimensional coordinate system are data values acquired by the corresponding type of sensor at the corresponding acquisition time.
Since all data points in each three-dimensional data coordinate system are data in the campus acquired by all the sensors of each type at the corresponding acquisition time, the present embodiment obtains the distribution characteristics of each data point by analyzing the distribution relationship of the data points in the three-dimensional coordinate system corresponding to each type of sensor, and further determines the abnormal distribution characteristics corresponding to the abnormal data points, and calculates the abnormal degree corresponding to the abnormal data points. Considering that the sensors are arranged at different positions of the campus and there is a correlation between data collected by the same type of sensors in similar areas in the campus, the present embodiment performs the degree of abnormality analysis on the collected different types of data using the LOF algorithm (adaptive local abnormality factor detection algorithm) based on this characteristic.
For either type of sensor:
since the data values of the data points in the three-dimensional coordinate system may change with the change of the acquisition time, this embodiment will be described with one acquisition time as an example, and this embodiment will calculate, based on all the data points in the three-dimensional coordinate system corresponding to the type of sensor, the distribution aggregation degrees corresponding to all the data points in the three-dimensional coordinate system corresponding to the type of sensor, where it is to be described that the distribution aggregation degrees corresponding to the data points refer to the distribution aggregation degrees of the positions of the sensors that acquire the data values of the data points, that is, the coordinates of the X axis and the coordinates of the Y axis of all the data points in the corresponding three-dimensional coordinate system, and are used to subsequently acquire the neighborhood distances corresponding to the data points with different distribution characteristics in the LOF algorithm.
The method includes the steps that firstly, positions of all sensors arranged in a park need to be classified, and then relevance among the positions of the sensors is obtained, and the purpose is to obtain distribution and aggregation degrees among the sensors in the same type of area in the park.
Because the mounted position of sensor is relevant with the distribution of garden building, consequently the process of classifying all sensor positions is realized through classifying the garden plan, and concrete process is: the method comprises the following steps of firstly, acquiring a park plan by using a camera, and then analyzing the park plan based on a neural network, wherein the neural network in the embodiment selects a semantic segmentation network, the semantic segmentation network aims at classification, and the training process of the semantic segmentation network comprises the following steps: the training data set is a sample plan of a plurality of parks; marking different areas in a sample plane graph of the park in a manual marking mode, marking a grassland area as 0, manually marking a building area as 1, manually marking a road area as 2 and the like; the loss function of the semantic segmentation network is a cross entropy function; in a specific application, a implementer of the labeling condition of each area in the sample plan of the park can set according to the specific condition; the training process of the semantic segmentation network is the prior art, and redundant description is not repeated here; inputting the park plan into a trained semantic segmentation network, and outputting the park plan into categories corresponding to all areas in the park plan; the method includes the steps of obtaining a park plan after semantic segmentation, namely analyzing connected domains of the park plan, obtaining a plurality of connected domains in the park plan, taking each connected domain as a region, wherein each region in the park plan corresponds to a category, and obtaining the category corresponding to the region where each sensor is located based on the position of each sensor and the category corresponding to each region in the park plan, for example: if a certain sensor is located in a building area, the type corresponding to the area where the sensor is located is a building area type. At this point, the method is adopted to obtain the categories corresponding to the areas where all the sensors in the park are located.
In the above steps, the area where the sensor is located is classified, and then the distribution aggregation degree corresponding to each data point is calculated based on the classification result, that is, the distribution aggregation degree of the sensor is calculated, so as to obtain the neighborhood distance of each data point. The Euclidean distance between data points in a three-dimensional coordinate system corresponding to a certain type of sensor can represent the distribution condition of the sensors in a garden; the more data collected in the same type of area by using a certain type of sensor, the more the number of data points in the three-dimensional coordinate system corresponding to the type of sensor is, which indicates that the more the number of the sensors arranged in the same type of area in the campus is; considering that the coordinates of the data points in the three-dimensional coordinate system can represent the distribution positions of the sensors, the present embodiment determines the distribution aggregation degree corresponding to each data point according to the category corresponding to the area where each sensor is located and the position of each data point in the three-dimensional coordinate system, that is, calculates the distribution aggregation degree corresponding to each data point according to the category of the area corresponding to each data point in the three-dimensional coordinate system and the position of each data point.
For the ith data point in the three-dimensional coordinate system corresponding to any type of sensor:
calculating the distribution aggregation degree corresponding to the data point according to the category of the area corresponding to the data point and the position of the data point, namely:
wherein alpha is i The distribution aggregation degree, J, corresponding to the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type i The total number of data points corresponding to the region, corresponding to the ith data point, belonging to the same class in the three-dimensional coordinate system corresponding to the sensor of the type, d (i, j) is the Euclidean distance between the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type and the jth data point corresponding to the region, corresponding to the ith data point, belonging to the same class in the three-dimensional coordinate system corresponding to the sensor of the type, and exp () is an exponential function with a natural constant as a base number; the area corresponding to the ith data point is an area where the sensor is located when the data value of the ith data point is acquired; the d (i, j) is obtained based on the coordinates of the data points in the three-dimensional coordinate system on the X axis and the Y axis, namely the Euclidean distance between the positions of the two sensors for collecting the data values of the two data points.
If the total number of data points corresponding to the areas, corresponding to the ith data point, belonging to the same category in the three-dimensional coordinate system corresponding to the sensors of the type is more, the more the number of the sensors of the type arranged in the corresponding area in the garden is; if the Euclidean distance between the ith data point and each data point corresponding to the region, corresponding to the ith data point, of the three-dimensional coordinate system corresponding to the sensor of the type, wherein the region corresponding to the ith data point belongs to the same category, the closer the data points are distributed around the ith data point in the three-dimensional coordinate system;
the ith data point is represented, and the area corresponding to the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type belongs to the same areaThe mean value of the euclidean distances between all data points corresponding to the regions of the category indicates that, when the mean value is larger, the data points around the ith data point are distributed more sparsely, that is, the distribution aggregation degree corresponding to the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type is smaller; when the mean value is smaller, the distribution of data points around the ith data point is denser, that is, the distribution corresponding to the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type is more aggregated.
By adopting the method, the distribution aggregation degree corresponding to each data point in each three-dimensional coordinate system can be obtained.
S3, determining a neighborhood distance corresponding to each data point in the three-dimensional coordinate system based on the distribution aggregation degree and the total number of data points corresponding to the regions belonging to the same category with the region corresponding to each data point in the three-dimensional coordinate system; obtaining the abnormal degree of each data point based on the data value of each data point and the data value of the data point in the neighborhood distance of each data point; marking the pixel points with the abnormal degree larger than the abnormal degree threshold value, acquiring data points to be corrected according to the marked data points and the unmarked data points, and correcting the abnormal degree of each data point to be corrected to acquire the corrected abnormal degree.
The method calculates the abnormal degree corresponding to each data point based on the idea of an LOF algorithm, wherein the main idea of the LOF algorithm is to judge whether each point is an abnormal point or not by comparing the density of each point with the density of points in the neighborhood of each point, and if the density of a certain point is lower, the point is more likely to be considered as an abnormal point; the present embodiment calculates the degree of abnormality for each data point based on the correlation between data collected by the same type of sensors located in similar areas within the campus. In the embodiment, a semantic segmentation and LOF algorithm combination mode is adopted for analysis, namely, a semantic segmentation network is utilized to acquire the category corresponding to each area in a park planogram, the data acquired by the sensors arranged in the areas of the same category are analyzed, the distribution aggregation degree corresponding to each data point is calculated, the distribution aggregation degree is used for representing the relevance between the data acquired by the sensors of the same type in the areas of the same category, the neighborhood size of each data point in a three-dimensional coordinate system in the LOF algorithm is further acquired, the interference of the sensor acquired data of different types on the judgment of the abnormal degree of the data point when the abnormal degree of the data point is calculated based on the LOF algorithm is eliminated, the calculated abnormal degree of the data point is more accurate, and the subsequent data screening result is further ensured to be more accurate.
Considering that when the abnormal degree of each data point is calculated, the neighborhood data point of each data point needs to be analyzed, if the neighborhood distance is not set properly, the accuracy of the result is directly affected, and if the neighborhood distance is set too small or too large, the calculation result of the abnormal degree is not accurate, so that the neighborhood distance corresponding to each data point is determined first, and the abnormal degree of each data point is analyzed based on the data points in the neighborhood distance. When the distribution density degree corresponding to the data points in the three-dimensional coordinate system is larger, the distribution density of the data points around the data points is more dense, and when the data points are analyzed, the neighborhood distance is set to be larger in order to improve the accuracy; based on the method, the neighborhood distance corresponding to each data point is determined according to the distribution aggregation degree corresponding to each data point in the three-dimensional coordinate system and the total number of the data points corresponding to the regions of the same category corresponding to the data points in the three-dimensional coordinate system.
For the ith data point in the three-dimensional coordinate system corresponding to any type of sensor, the corresponding neighborhood distance is as follows:
wherein k is i Is the neighborhood distance, alpha, corresponding to the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type i Is the distribution aggregation degree, k, corresponding to the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type 0 Is the initial neighborhood distance and is the distance of the initial neighborhood,
to round down. This example arrangementInitial neighborhood distance k 0 The value of (2) is a unit of pixel point, and in specific application, an implementer can set the value according to specific conditions.
When the distribution aggregation degree corresponding to the ith data point in the three-dimensional coordinate system is larger, and the number of data points corresponding to the region, which belongs to the same category, of the region corresponding to the ith data point in the three-dimensional coordinate system is larger, it is described that the number of data points of the same category around the ith data point is larger, the number of neighborhood data points referred to when the abnormality degree of the data point is calculated is larger, that is, the neighborhood distance corresponding to the data point is larger.
By adopting the method, the neighborhood distances corresponding to all data points in the three-dimensional coordinate system corresponding to different types of sensors can be obtained, all data points in the neighborhood distance corresponding to each data point are used as the neighborhood data points of each data point, the distribution condition of each data point is analyzed, the neighborhood data points of each data point are obtained, the interference of the unsuitability of neighborhood size setting on the accuracy of the calculation result when the abnormal degree of each data point is calculated in the follow-up process can be effectively avoided, and the screening result of the follow-up data is more accurate. In this embodiment, the data value of each data point in the three-dimensional coordinate system is used as a distribution metric in the LOF algorithm, and the abnormal degree of each data point is calculated by referring to the data value of the neighborhood data point within the neighborhood distance corresponding to each data point; the method includes the steps that the local distribution degree of each data point is obtained based on the numerical difference between each data point and other data points in the neighborhood distance and is used for measuring the distribution of the data values of the data points, the LOF algorithm has the main idea that whether each data point is an abnormal point or not is judged by comparing the density of each data point and the mean value of the density of the neighborhood of each data point, the ratio of the mean value of the local distribution degree of other data points in the neighborhood distance of each data point and the local distribution degree of each data point is used as the abnormal degree of each data point, and then whether each data point is an abnormal point or not is judged. Therefore, for the ith data point in the three-dimensional coordinate system corresponding to any type of sensor, the corresponding abnormal degree expression is as follows:
wherein epsilon i Is the local distribution degree, beta, of the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type i M (i) is the number of data points in the neighborhood distance of the ith data point in the three-dimensional coordinate system corresponding to the type of sensor, M is the mth data point in the neighborhood distance of the ith data point in the three-dimensional coordinate system corresponding to the type of sensor, Δ f (i, M) is the difference between the data value of the ith data point in the three-dimensional coordinate system corresponding to the type of sensor and the data value of the mth data point in the neighborhood distance thereof, and epsilon m The local distribution degree of the mth data point in the neighborhood distance of the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type is obtained; the process of acquiring the difference between the data value of the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type and the data value of the mth data point in the neighborhood distance is as follows: and taking the absolute value of the difference value between the data value of the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type and the data value of the mth data point in the neighborhood distance of the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type as the difference between the data value of the ith data point in the three-dimensional coordinate system corresponding to the sensor of the type and the data value of the mth data point in the neighborhood distance.
By adopting the method, the abnormal degree of each data point in the three-dimensional coordinate system corresponding to each type of sensor can be obtained. The method combines the idea of the LOF algorithm, measures the distribution of the data points by using the difference between the numerical values of each data point and other data points in the neighborhood, and represents the abnormal degree of each data point by using the difference between the local distribution degree of each data point and the mean value of the local distribution degrees of other data points in the neighborhood, namely, judges the abnormal degree of the data points based on the relevance of each data point and the surrounding data points, thereby avoiding the problem that the judgment result is inaccurate when the data points are judged to be abnormal only according to the difference between the data value and the manually set threshold value in the conventional abnormal detection algorithm.
When data in a certain area in a campus is abnormal at a certain time, in order to ensure the safety of the campus, data values of the area and its surrounding area at the certain time need to be obtained, so that in order to accurately analyze data change conditions of the surrounding area of the area where an abnormality occurs at some critical time (i.e., the time when the data abnormality occurs), the present embodiment corrects the abnormal degree of the obtained partial data points. When the abnormal degree of the data is analyzed, the data acquired at each moment are analyzed, and the data value of the data point in the three-dimensional coordinate system changes along with the change of time, so that the time t is taken as an example for explanation, and the method provided by the embodiment can be adopted for analysis at other moments; setting an abnormality degree threshold value beta T Taking the u-th type of sensor as an example, each number in the three-dimensional coordinate system corresponding to the type of sensor is determined separatelyData value of the data point and an abnormal degree threshold value beta T If the degree of abnormality of the p-th data point in the type is larger than beta T Then label the data point as 1; if the abnormality degree of the p-th data point in the type is less than or equal to beta T If so, the data point is not marked; it should be noted that, here, the description is given by taking the time t as an example, and therefore, the data collected by all the sensors in the u-th type sensor at the time t is divided into two types, one type is the abnormal degree greater than β T The data in the class is abnormal data, and the other class is abnormal degree less than or equal to beta T The data of (a); since the closer the value of the degree of abnormality is to 1 or less than 1, the more likely the corresponding data point is to be a normal sample point, β T The value of (b) needs to be greater than 1, and in the present embodiment, β is set T The value of (a) is 1.2, which can be set by the practitioner on a case-by-case basis in a particular application.
In the present embodiment, the abnormal degree of the data point in the three-dimensional coordinate system corresponding to one type of sensor is used to correct the abnormal degree of the data point of another type, specifically, for any type of sensor: counting the total number of data points in a three-dimensional coordinate system corresponding to the type of sensor, namely the number of the type of sensors in the whole park; for the time t, counting the number of the marked data points in the three-dimensional coordinate system corresponding to the type of sensor, namely acquiring the number of all abnormal data points collected by the type of sensor at the time t; calculating the ratio of the number of the marked data points in the three-dimensional coordinate system corresponding to the type of sensor to the total number of the data points in the three-dimensional coordinate system corresponding to the type of sensor, and taking the ratio as the proportion of the abnormal data points in the three-dimensional coordinate system corresponding to the type of sensor; by adopting the method, the proportion of abnormal data points in the three-dimensional coordinate system corresponding to each type of sensor can be obtained; the sensor with the largest proportion of abnormal data points in the three-dimensional coordinate system is marked as a reference type sensor and used for correcting the abnormal degree of the data points in the three-dimensional coordinate system corresponding to other types of sensors except the reference type sensor; recording a three-dimensional coordinate system corresponding to other types of sensors except the reference type sensor as a coordinate system to be analyzed, and for the q-th coordinate system to be analyzed: taking the nth non-labeled data point in the coordinate system to be analyzed as an example for explanation, marking an area corresponding to the nth non-labeled data point in the coordinate system to be analyzed as a target area, judging whether the area corresponding to the labeled data point exists in the three-dimensional coordinate system corresponding to the sensor of the reference type as the target area, if so, indicating that data in the target area is abnormal, and correcting the abnormal degree of the nth non-labeled data point in the coordinate system to be analyzed, marking the nth non-labeled data point in the coordinate system to be analyzed as a data point to be corrected, and marking the area corresponding to the three-dimensional coordinate system corresponding to the sensor of the reference type as a reference data point; if the data in the target area does not exist, the data in the target area does not exist abnormal, and the abnormal degree of the nth non-labeled data point in the coordinate system to be analyzed does not need to be corrected; and correcting the abnormal degree of the data point to be corrected based on the abnormal degree of the reference data point, wherein the more the data collected by the sensor which is closer to the position of the sensor for collecting the abnormal data point is concerned, so that the abnormal degree of the data point to be corrected is calculated according to the Euclidean distance between the sensor for collecting the data value of the data point to be corrected and the sensor for collecting the data value of each reference data point and the data value of the data point to be corrected, and the abnormal degree of the nth data point to be corrected in the qth coordinate system to be analyzed after correction is as follows:
wherein beta is ′ qn The abnormal degree of the nth data point to be corrected in the qth coordinate system to be analyzed is corrected, W is the number of the reference data points, d n,w Exp () is an exponential function with a natural constant as a base number, for a euclidean distance between a sensor for collecting a data value of an nth data point to be corrected and a sensor for collecting a data value of a w-th reference data point in a q-th coordinate system to be analyzed,β qn the abnormal degree of the nth data point to be corrected in the qth coordinate system to be analyzed; the euclidean distance between the sensor for collecting the data value of the nth data point to be corrected and the sensor for collecting the data value of the w-th reference data point in the q-th coordinate system to be analyzed is the position distance of the two sensors for collecting the data value of the nth data point to be corrected and the data value of the w-th reference data point on the circle, namely the euclidean distance between the X coordinate and the Y coordinate of the two data points in the three-dimensional coordinate system.
The closer the data point in the coordinate system to be analyzed is to the reference data point, the closer the sensor of the type is to the sensor of the reference type, the greater the attention of the data point in the three-dimensional coordinate system corresponding to the sensor of the type should be, i.e., the greater the correction weight of the degree of abnormality of the data point in the three-dimensional coordinate system corresponding to the sensor of the type.
By analogy with the method, the abnormal degree of the data points to be corrected in all the coordinate systems to be analyzed can be corrected, and the corrected abnormal degree of all the data points to be corrected can be obtained. According to the embodiment, the relevance of distance distribution among the sensors of different types at the same moment is considered, and the obtained abnormal degree is corrected according to the relevance of the positions when the sensors of different types collect data, so that the safety management requirement of security of a park is met, and the screening precision of subsequent data can be effectively guaranteed.
And S4, acquiring normal data points and abnormal data points based on the abnormal degree of each data point and the abnormal degree of each data point to be corrected, and compressing and storing corresponding data based on the normal data points and the abnormal data points.
Correcting the abnormal degree of the data points to be corrected in the step S3 to obtain the abnormal degree of each data point to be corrected after correction, marking all the data points except the data point to be corrected as non-corrected data points, and also obtaining the abnormal degree of each non-data point to be corrected; the data points with larger abnormal degree should be focused, and the abnormal degree of the data points not to be corrected is larger than the abnormal degree threshold value beta T Each of them will beTaking the data point to be corrected as an abnormal data point, and comparing the abnormal degree of the corrected data point with an abnormal degree threshold value beta T The corrected abnormal degree is larger than the abnormal degree threshold value beta T The data points to be corrected are also used as abnormal data points, namely abnormal data points in all three-dimensional coordinate systems are obtained, all the data points except the abnormal data points in all the three-dimensional coordinate systems are used as normal data points, and the data points are analyzed based on a single acquisition moment when the data points are subjected to abnormal analysis, so that the data points acquired at each acquisition moment can be divided into two types, namely the normal data points and the abnormal data points.
Next, the collected data is compressed, and in order to ensure the integrity of the data, the embodiment needs to encode and store not only the data value of the abnormal data point, but also the data value of the normal data point. Specifically, the embodiment encodes the data collected in each time period, and encodes the data by using run-length encoded data, and for any time period: the time period may have normal data points and abnormal data points, and for the data values of the normal data points, the average value of the data values of the normal data points in the time period is used as data to be encoded, and run-length encoding is adopted for encoding; and for the data value of the abnormal data point, directly taking the data value of the abnormal data point as the data to be coded, and coding by adopting run-length coding. In the embodiment, the duration of each time period is set to be 1 minute, and in a specific application, an implementer can set the time period according to a specific situation; and the coded data is transmitted to a park security system server for storage, so that subsequent workers can check the data conveniently. Run-length coding is a well-known technique and will not be described in detail herein.
The method includes the steps that a three-dimensional coordinate system corresponding to each type of sensor is established based on data in a garden obtained by each type of sensor, a certain relevance exists between data collected by the same type of sensor arranged in similar areas in the garden, the category corresponding to each area in a garden plan is obtained by the aid of a neural network, distribution aggregation degrees corresponding to each data point are calculated according to the category corresponding to the area where each sensor is located in the garden and the position of each data point in the three-dimensional coordinate system, the relevance between the data collected by the sensors is represented, and accordingly a neighborhood distance corresponding to each data point is determined. In the embodiment, when the abnormal degree of each data point is calculated, the abnormal degree of each data point is obtained based on the data value of each data point and the data value of the data point in the neighborhood distance of each data point, and the pixel points of which the abnormal degree is greater than the threshold value of the abnormal degree are marked; considering that the marked data points and the non-marked data points have different presented characteristics, the abnormal degree of the marked pixel points is larger, and attention should be paid to the marked pixel points, so that the data points to be corrected are obtained according to the marked data points and the non-marked data points, the embodiment corrects the data points to be corrected to obtain the abnormal degree of the corrected data points to be corrected, all the data are divided into two types, namely normal data and abnormal data, and the data screening precision is improved.
Claims (8)
1. A high-efficiency data compression method for a park security system is characterized by comprising the following steps:
acquiring data in a park in real time by using different types of sensors;
constructing a three-dimensional coordinate system corresponding to each type of sensor based on data in the campus acquired by each type of sensor, wherein the three-dimensional coordinate system comprises at least two data points; obtaining the corresponding category of the area where each sensor is located based on the park plan and the trained neural network; obtaining the distribution aggregation degree corresponding to each data point according to the category corresponding to the area where each sensor is located and the position of each data point in the three-dimensional coordinate system;
determining the neighborhood distance corresponding to each data point in the three-dimensional coordinate system based on the distribution aggregation degree and the total number of data points corresponding to the regions belonging to the same category and corresponding to the regions corresponding to the data points in the three-dimensional coordinate system; obtaining the abnormal degree of each data point based on the data value of each data point and the data value of the data point in the neighborhood distance of each data point; marking the pixel points with the abnormal degree larger than the abnormal degree threshold value, acquiring data points to be corrected according to the marked data points and the unmarked data points, and correcting the abnormal degree of each data point to be corrected to acquire the corrected abnormal degree;
and acquiring normal data points and abnormal data points based on the abnormal degree of each data point and the abnormal degree of each data point to be corrected, and compressing and storing corresponding data based on the normal data points and the abnormal data points.
2. The efficient data compression method for the campus security system according to claim 1, wherein the acquiring data points to be corrected according to the labeled data points and the non-labeled data points comprises:
for either type of sensor: calculating the ratio of the number of the marked data points in the three-dimensional coordinate system corresponding to the type of sensor to the total number of the data points in the three-dimensional coordinate system corresponding to the type of sensor, and taking the ratio as the proportion of the abnormal data points in the three-dimensional coordinate system corresponding to the type of sensor;
marking the sensor with the largest proportion of abnormal data points in the three-dimensional coordinate system as a reference type sensor; recording a three-dimensional coordinate system corresponding to other types of sensors except the reference type of sensor as a coordinate system to be analyzed;
for the qth coordinate system to be analyzed:
and recording an area corresponding to the nth non-mark data point in the coordinate system to be analyzed as a target area, judging whether the area corresponding to the mark data point exists in the three-dimensional coordinate system corresponding to the sensor of the reference type as the target area, and recording the nth non-mark data point in the coordinate system to be analyzed as a data point to be corrected if the area corresponding to the mark data point exists in the three-dimensional coordinate system corresponding to the sensor of the reference type.
3. The efficient data compression method for the campus security system according to claim 2, wherein the step of correcting the abnormal degree of each data point to be corrected to obtain the corrected abnormal degree comprises the steps of:
marking mark data points, which are in a target area, of an area corresponding to the reference type sensor in the three-dimensional coordinate system as reference data points; and calculating the abnormal degree of the data point to be corrected according to the Euclidean distance between the sensor for collecting the data value of the data point to be corrected and the sensor for collecting the data value of each reference data point and the data value of the data point to be corrected.
4. The efficient data compression method for the campus security system according to claim 3, wherein the abnormal degree after the nth data point to be corrected in the qth coordinate system to be analyzed is corrected is calculated by using the following formula:
wherein, beta ′ qn The abnormal degree of the nth data point to be corrected in the qth coordinate system to be analyzed is obtained, W is the number of the reference data points, d n,w For Euclidean distance between a sensor for collecting the data value of the nth data point to be corrected and a sensor for collecting the data value of the w-th reference data point in the q-th coordinate system to be analyzed, exp () is an exponential function with a natural constant as a base number, beta qn The abnormal degree of the nth data point to be corrected in the qth coordinate system to be analyzed.
5. The method according to claim 1, wherein the obtaining of the distribution and aggregation degree corresponding to each data point according to the category corresponding to the area where each sensor is located and the position of each data point in the three-dimensional coordinate system comprises:
for the ith data point in the three-dimensional coordinate system corresponding to any type of sensor:
calculating the mean value of Euclidean distances between the ith data point and all data points corresponding to the regions, corresponding to the ith data point, of the three-dimensional coordinate system corresponding to the sensor of the type, wherein the regions belong to the same category, and recording the mean value as a first mean value; the area corresponding to the ith data point is the area where the sensor is located when the data value of the ith data point is acquired;
and taking a natural constant as a base number, and taking a value of an exponential function taking the negative first mean value as an index as the distribution aggregation degree corresponding to the ith data point.
6. The method according to claim 1, wherein the determining the neighborhood distance corresponding to each data point in the three-dimensional coordinate system based on the distribution aggregation degree and the total number of data points corresponding to the regions of the three-dimensional coordinate system corresponding to the regions of the data points belonging to the same category comprises:
for the ith data point in the three-dimensional coordinate system corresponding to any type of sensor: calculating the product of the total number of data points corresponding to the regions, corresponding to the ith data point, of the regions belonging to the same category in the three-dimensional coordinate system corresponding to the sensor of the type and the distribution aggregation degree corresponding to the ith data point, and recording the product as a first product; rounding the first product downwards, and recording the result of rounding downwards as a first distance; and taking the sum of the first distance and the initial neighborhood distance as the neighborhood distance corresponding to the ith data point.
7. The efficient data compression method for the campus security system according to claim 1, wherein the obtaining the abnormal degree of each data point based on the data value of each data point and the data value of the data point within the neighborhood distance of each data point comprises:
for the ith data point in the three-dimensional coordinate system corresponding to any type of sensor:
obtaining the local distribution degree of the ith data point according to the difference between the data value of the ith data point and the data value of each data point within the neighborhood distance of the ith data point and the data value of the ith data point;
and taking the ratio of the average value of the local distribution degrees of all the data points in the neighborhood distance of the ith data point to the local distribution degree of the ith data point as the abnormal degree of the ith data point.
8. The efficient data compression method for the campus security system according to claim 1, wherein the step of obtaining normal data points and abnormal data points based on the abnormal degree of each data point and the abnormal degree after each data point to be corrected, and the step of compressing and storing corresponding data based on the normal data points and the abnormal data points comprises the steps of:
taking the corrected data points to be corrected with the abnormal degree larger than the abnormal degree threshold value as abnormal data points, taking all data points except the data points to be corrected as abnormal data points, and taking all data points except the abnormal data points in all three-dimensional coordinate systems as normal data points;
and respectively coding the data value of the normal data point and the data value of the abnormal data point by adopting run length coding, and storing the coded data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211657753.0A CN115941807B (en) | 2022-12-22 | 2022-12-22 | Efficient data compression method for park security system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211657753.0A CN115941807B (en) | 2022-12-22 | 2022-12-22 | Efficient data compression method for park security system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115941807A true CN115941807A (en) | 2023-04-07 |
| CN115941807B CN115941807B (en) | 2024-02-23 |
Family
ID=86652214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211657753.0A Active CN115941807B (en) | 2022-12-22 | 2022-12-22 | Efficient data compression method for park security system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115941807B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117078048A (en) * | 2023-10-17 | 2023-11-17 | 深圳市福山自动化科技有限公司 | Digital twinning-based intelligent city resource management method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070171050A1 (en) * | 2005-06-27 | 2007-07-26 | Nec Corporation | Method for managing data in a wireless sensor network |
| CN106878995A (en) * | 2017-04-27 | 2017-06-20 | 重庆邮电大学 | A kind of wireless sensor network Exception Type discrimination method based on perception data |
| CN110631624A (en) * | 2019-09-04 | 2019-12-31 | 精英数智科技股份有限公司 | Method, device and system for identifying abnormal operation data of mine sensor |
| CN112256686A (en) * | 2020-11-12 | 2021-01-22 | 北京理工大学 | MES-based fault data compression and prediction method and system |
| KR102321440B1 (en) * | 2020-09-10 | 2021-11-02 | 연세대학교 산학협력단 | Apparatus and Method for Anomaly Detection Using Multivariate Heterogeneous Time-Series Data |
| US20220026313A1 (en) * | 2020-07-21 | 2022-01-27 | Robert Bosch Gmbh | Method and device for detecting anomalies in sensor recordings of a technical system |
| CN114020811A (en) * | 2021-11-09 | 2022-02-08 | 中国工商银行股份有限公司 | Data anomaly detection method and device and electronic equipment |
| CN114492629A (en) * | 2022-01-25 | 2022-05-13 | 京东城市(北京)数字科技有限公司 | Abnormality detection method, abnormality detection device, electronic apparatus, and storage medium |
| CN114970621A (en) * | 2022-05-20 | 2022-08-30 | 京东城市(北京)数字科技有限公司 | Method and device for detecting abnormal aggregation event, electronic equipment and storage medium |
| CN115294409A (en) * | 2022-10-08 | 2022-11-04 | 南通商翼信息科技有限公司 | Video compression method, system and medium for security monitoring |
-
2022
- 2022-12-22 CN CN202211657753.0A patent/CN115941807B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070171050A1 (en) * | 2005-06-27 | 2007-07-26 | Nec Corporation | Method for managing data in a wireless sensor network |
| CN106878995A (en) * | 2017-04-27 | 2017-06-20 | 重庆邮电大学 | A kind of wireless sensor network Exception Type discrimination method based on perception data |
| CN110631624A (en) * | 2019-09-04 | 2019-12-31 | 精英数智科技股份有限公司 | Method, device and system for identifying abnormal operation data of mine sensor |
| US20220026313A1 (en) * | 2020-07-21 | 2022-01-27 | Robert Bosch Gmbh | Method and device for detecting anomalies in sensor recordings of a technical system |
| KR102321440B1 (en) * | 2020-09-10 | 2021-11-02 | 연세대학교 산학협력단 | Apparatus and Method for Anomaly Detection Using Multivariate Heterogeneous Time-Series Data |
| CN112256686A (en) * | 2020-11-12 | 2021-01-22 | 北京理工大学 | MES-based fault data compression and prediction method and system |
| CN114020811A (en) * | 2021-11-09 | 2022-02-08 | 中国工商银行股份有限公司 | Data anomaly detection method and device and electronic equipment |
| CN114492629A (en) * | 2022-01-25 | 2022-05-13 | 京东城市(北京)数字科技有限公司 | Abnormality detection method, abnormality detection device, electronic apparatus, and storage medium |
| CN114970621A (en) * | 2022-05-20 | 2022-08-30 | 京东城市(北京)数字科技有限公司 | Method and device for detecting abnormal aggregation event, electronic equipment and storage medium |
| CN115294409A (en) * | 2022-10-08 | 2022-11-04 | 南通商翼信息科技有限公司 | Video compression method, system and medium for security monitoring |
Non-Patent Citations (2)
| Title |
|---|
| 薛安荣;李明;: "无线传感器网络中异常读数检测算法研究", 计算机应用研究, no. 09, pages 3452 - 3455 * |
| 许欧阳;李光辉;: "萤火虫优化和随机森林的WSN异常数据检测", 计算机科学与探索, no. 10, pages 107 - 118 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117078048A (en) * | 2023-10-17 | 2023-11-17 | 深圳市福山自动化科技有限公司 | Digital twinning-based intelligent city resource management method and system |
| CN117078048B (en) * | 2023-10-17 | 2024-01-26 | 深圳市福山自动化科技有限公司 | Digital twinning-based intelligent city resource management method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115941807B (en) | 2024-02-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111176953B (en) | Abnormality detection and model training method, computer equipment and storage medium | |
| CN113328755B (en) | Compressed data transmission method facing edge calculation | |
| CN117421684B (en) | Abnormal data monitoring and analyzing method based on data mining and neural network | |
| CN116684878B (en) | 5G information transmission data safety monitoring system | |
| CN109597757B (en) | Method for measuring similarity between software networks based on multidimensional time series entropy | |
| CN113822366A (en) | Service index abnormality detection method and device, electronic equipment and storage medium | |
| CN117172509B (en) | Construction project distribution system based on decoration construction progress analysis | |
| CN115375522A (en) | Smart city carbon neutralization data analysis system | |
| CN117611015B (en) | Real-time monitoring system for quality of building engineering | |
| CN115941807A (en) | Efficient data compression method for park security system | |
| CN111709668A (en) | Power grid equipment parameter risk identification method and device based on data mining technology | |
| CN116150191A (en) | Data operation acceleration method and system for cloud data architecture | |
| CN116861331A (en) | Expert model decision-fused data identification method and system | |
| CN117828539B (en) | Intelligent data fusion analysis system and method | |
| CN117372144A (en) | Wind control strategy intelligent method and system applied to small sample scene | |
| CN113393169B (en) | Financial industry transaction system performance index analysis method based on big data technology | |
| CN114266483B (en) | Dangerous waste monitoring system based on Internet of things | |
| CN112765553B (en) | Engineering project management system based on big data | |
| CN114167837B (en) | Intelligent fault diagnosis method and system for railway signal system | |
| CN117294819B (en) | All-round surveillance camera head suitable for bank | |
| CN117035469B (en) | Method and device for measuring and calculating land indexes of public and railway intermodal transportation junction functional area construction | |
| CN117318053B (en) | Energy demand prediction method and system for energy storage power station | |
| CN116506205B (en) | Data processing method and system of intelligent medical platform | |
| CN116861204B (en) | Intelligent manufacturing equipment data management system based on digital twinning | |
| CN118094266A (en) | Intelligent terminal nuclear radiation detection analysis method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |