CN111858712A - In-situ water quality inspection data time-space analysis and anomaly detection method and system - Google Patents
In-situ water quality inspection data time-space analysis and anomaly detection method and system Download PDFInfo
- Publication number
- CN111858712A CN111858712A CN202010699357.9A CN202010699357A CN111858712A CN 111858712 A CN111858712 A CN 111858712A CN 202010699357 A CN202010699357 A CN 202010699357A CN 111858712 A CN111858712 A CN 111858712A
- Authority
- CN
- China
- Prior art keywords
- time
- space
- point
- water quality
- neighborhood
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2474—Sequence data queries, e.g. querying versioned data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Probability & Statistics with Applications (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Fuzzy Systems (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The method and the system for the time-space analysis and the abnormality detection of the in-situ water quality inspection data comprise the following steps: s1, acquiring space-time sequence data and performing time sequence abnormity detection and judgment; s2, dividing a neighborhood space according to the abnormal data points of the time sequence to obtain a neighborhood point set and a time neighborhood of a moment; s3, acquiring a time series change trend feature vector; and S4, calculating vector similarity, and judging whether the data points are space-time abnormal data points or time abnormal data points according to the similarity. The invention combines various anomaly detection technologies to detect the time sequence anomaly of water quality data, integrates a Thiessen polygon algorithm and a clustering algorithm to divide a space neighborhood, performs piecewise linear representation on time sequence data to fit the time sequence change trend characteristic of a period of time window, detects the anomaly data of space dimensions by combining the space neighborhood and the time sequence characteristic, and can trigger the handheld inspection water quality control optimization through anomaly detection.
Description
Technical Field
The invention relates to the technical field of water quality monitoring, in particular to a method and a system for time-space analysis and anomaly detection of in-situ water quality inspection data.
Background
The handheld in-situ water quality monitor can solve the problems of low efficiency, data reliability and water quality property change when a water sample is conveyed to a room from a site. Compared with the traditional modes of extraction, station house detection and the like, the in-situ detection can assist more water quality monitoring and river growth scenes such as pollution tracing, river network routing inspection and the like due to the characteristics of flexibility and convenience, and can also be used for on-line water quality monitoring in the fields of factories, municipal water supply, pipe networks, swimming pools, landscape fountains and the like. However, the data generated by in-situ detection scenarios is more abundant and variable than fixed sampling, and therefore presents new challenges for data analysis thereof.
Data generated by a detection scene has space-time characteristics, a detection technology needs to detect in a time dimension and a space dimension at the same time, at present, a plurality of single algorithms for anomaly detection in a space sequence or a time sequence exist, the space-time anomaly detection refers to a data object with special attributes obviously deviating from a space-time adjacent domain, and the space-time anomaly is represented as space anomaly at the moment and also represented as anomaly in the time sequence.
Therefore, it is necessary to perform fusion anomaly analysis on the time sequence and the space sequence aiming at the time-space water quality data to form an anomaly detection technology based on the time-space sequence, and to comprehensively detect multi-dimensional data such as time, location coordinates, water depth, water quality detection results and the like to find the anomaly of the in-situ detection water quality inspection data.
Disclosure of Invention
The invention aims to provide an in-situ water quality inspection data space-time analysis and anomaly detection method and system.
In order to achieve the purpose, the invention adopts the following technical scheme:
the in-situ water quality inspection data space-time analysis and anomaly detection method comprises the following steps:
s1, acquiring space-time sequence data and performing time sequence abnormity detection and judgment;
s2, dividing a neighborhood space according to the abnormal data points of the time sequence to obtain a neighborhood point set and a time neighborhood of a moment;
s3, acquiring a time series change trend feature vector;
s4, calculating vector similarity, and judging whether the vector similarity is a space-time abnormal data point or a time abnormal data point according to the similarity;
correspondingly, in step S1, the collision result of four statistical distribution anomaly detection algorithms of IForest, PCA, HBOS, and KNN and the scoring result of time series anomaly modeling are used for fusion determination, and all dimensions are modeled separately, and the result can obtain the dimension determined as anomaly;
Correspondingly, in step S2, after the time series abnormality is determined, the coordinate position information of the data point that has been determined to be time series abnormality is divided into spatial neighborhoods by a taison polygon and a K-means clustering algorithm, so as to obtain a neighborhood point set SNi of the observation point, where { S1, S2,. gtn | i, j < n }, and a d-time neighborhood TNt of the time t is determined as { Tt-d,. gtn.,. Tt,. gtt + d };
correspondingly, the steps of establishing the Thiessen polygon are as follows:
a) constructing a Delaunay triangulation network through discrete points, numbering the discrete points and the formed triangles, and recording which three discrete points each triangle consists of;
b) finding and recording the numbers of all triangles adjacent to each discrete point, and finding out all triangles with one same vertex in the constructed triangulation network;
c) sorting triangles adjacent to each discrete point in a clockwise or counterclockwise direction so as to be connected to generate a Thiessen polygon;
d) calculating and recording the circle center of a circumscribed circle of each triangle;
e) connecting the centers of circumscribed circles of the adjacent triangles according to the adjacent triangles of each discrete point to obtain a Thiessen polygon;
correspondingly, in the step c), the discrete point is set as o, a triangle with o as a vertex is found, and the triangle is set as A; taking another vertex of the triangle A except o as a, finding out the third vertex as f; the next triangle must be bounded by of, which is triangle F; if the other vertex of triangle F is e, the next triangle is with oe as the side, and the process is repeated until the oa side is reached;
Correspondingly, in the step e), for the Thiessen polygon at the edge of the triangular net, a vertical bisector can be crossed with the outline to form the Thiessen polygon together with the outline;
correspondingly, in step S3, for all point locations in the neighborhood space that have been determined as time series abnormal data points, obtaining sequence data of the abnormal dimension in the d time domain at time t, fitting the sequence data through a time series piecewise linear representation algorithm, and obtaining a slope value of each segment, extracting the variation trend features of the sequence data as a corresponding pattern set, so as to obtain a variation trend feature vector;
correspondingly, fitting sequence data by using a bottom-up time sequence piecewise linear representation algorithm, and obtaining a slope value of each segment by using a least square method;
correspondingly, the bottom-up time series piecewise linear representation algorithm is specifically as follows:
dividing the time sequence into short sequences of adjacent points, connecting a first point with a second point at the moment, enabling an original point to fall on a line segment, connecting two adjacent line segments, enabling each line segment to comprise three original points, calculating the fitting error of a middle point, finding out a segment with the minimum error and the error smaller than a threshold value R after obtaining the fitting error result of the middle point in all the line segments of the three points, on the basis, connecting the first segment with the adjacent line segments, calculating the fitting error of each segment, finding out the segment with the minimum error and the error smaller than the threshold value R as a second segment, circulating in this way until the fitting errors of all the segments are smaller than the threshold value R, and ending the segmentation;
Correspondingly, in step S4, the cosine distance is used to calculate the similarity between the point location and the neighborhood point location;
correspondingly, in step S4, if the similarity does not exceed 90%, the point is determined to be a spatial anomaly, and a time-space anomaly data point is obtained, and if the similarity does not exceed 90%, the point is determined to be a time anomaly, and a time anomaly data point is obtained.
The in-situ water quality inspection data space-time analysis and anomaly detection system comprises a space-time sequence data acquisition and detection unit, a neighborhood point set and time neighborhood acquisition unit and a feature vector acquisition and calculation unit, the spatio-temporal sequence data acquisition detection unit acquires spatio-temporal sequence data and performs spatio-temporal sequence abnormality detection and determination, the time neighborhood acquisition unit of the neighborhood point set and the time divides the neighborhood space aiming at the abnormal data points of the time sequence to obtain the time neighborhood of the neighborhood point set and the time, the characteristic vector acquiring and calculating unit acquires the characteristic vector of the time series change trend and calculates the vector similarity, if the similarity does not exceed a set value, judging the point location to be space abnormal to obtain a space-time abnormal data point, and if the similarity does not exceed a set value, judging the point location to be time abnormal to obtain a time abnormal data point;
Correspondingly, after the time sequence abnormity is judged, the neighborhood point set and time neighborhood acquisition unit divides the spatial neighborhood according to the coordinate position information of the data point judged to be time sequence abnormity by the Tassen polygon and the K-means clustering algorithm to obtain the neighborhood point set SN of the observation pointi＝{S1，S2，...，SnI, j < n } and determining the d-time neighborhood TN at time tt＝{Tt-d，...，Tt，...，Tt+d}；
Correspondingly, the feature vector acquisition and calculation unit acquires sequence data of abnormal dimensions of the time sequence in the d time field at the moment t for all point positions in the neighborhood space which are judged to be time sequence abnormal data points, fits the sequence data through a bottom-up time sequence piecewise linear representation algorithm, obtains the slope value of each segment by using a least square method, extracts the variation trend features of the sequence data into a corresponding mode set, and obtains the variation trend feature vector;
correspondingly, the feature vector acquisition and calculation unit calculates the similarity between the point location and the neighborhood point location by using the cosine distance;
correspondingly, if the similarity does not exceed 90%, the point location is judged to be a space anomaly, and a space-time anomaly data point is obtained, and if the similarity does not exceed 90%, the point location is judged to be a time anomaly, and a time anomaly data point is obtained.
The invention has the beneficial effects that:
the method can be used for carrying out combined analysis on multi-dimensional water quality data, performing water quality data time sequence abnormity detection by combining various abnormity detection technologies, dividing a space neighborhood by combining a Thiessen polygon algorithm and a clustering algorithm, carrying out piecewise linear representation on time sequence data to fit a time sequence change trend characteristic of a period of time window, detecting abnormal data of space dimensions by combining the space neighborhood and the time sequence characteristic, and triggering handheld inspection water quality control optimization through abnormity detection.
Drawings
Fig. 1 is a schematic flow chart of a method for spatiotemporal analysis and anomaly detection of in-situ water quality inspection data according to an embodiment of the invention.
Detailed Description
As shown in fig. 1, in an embodiment of the present invention, the in-situ water quality inspection data spatio-temporal analysis and anomaly detection method includes the following steps:
1) acquiring space-time sequence data through a handheld in-situ detector;
2) detecting a time series abnormality; performing fusion judgment on the collision result of four statistical distribution anomaly detection algorithms of IForest, PCA, HBOS and KNN and the scoring result of time sequence anomaly modeling, and performing independent modeling on all dimensions to obtain the dimension judged to be abnormal;
3) Dividing a neighborhood space according to the abnormal data points of the time sequence to obtain a neighborhood point set; aiming at the coordinate position information of the data points judged to be abnormal in the time sequence, the space neighborhood is divided through the Tassen polygon and the K-means clustering algorithm to obtain a neighborhood point set SN of the observation pointsi＝{S1，S2，...，SnL i, j < n }; the method comprises the following steps of establishing a Thiessen polygon:
a) constructing a Delaunay triangulation network through discrete points, numbering the discrete points and the formed triangles, and recording which three discrete points each triangle consists of;
b) finding and recording the numbers of all triangles adjacent to each discrete point, and finding out all triangles with one same vertex in the constructed triangulation network;
c) sorting triangles adjacent to each discrete point in a clockwise or counterclockwise direction so as to be connected to generate a Thiessen polygon; for example, let the discrete point be o, find out a triangle with o as the vertex, and set it as a; taking another vertex of the triangle A except o as a, finding out the third vertex as f; the next triangle must be bounded by of, which is triangle F; if the other vertex of triangle F is e, the next triangle is with oe as the side, and the process is repeated until the oa side is reached;
d) Calculating and recording the circle center of a circumscribed circle of each triangle;
e) connecting the centers of the circumscribed circles of the adjacent triangles according to the adjacent triangles of each discrete point to obtain a Thiessen polygon, and making a perpendicular bisector of the Thiessen polygon at the edge of the triangular net intersect with the outline to form the Thiessen polygon together with the outline;
4) obtaining a time neighborhood of a moment; determining d time neighborhood TN at time t for all point locations in neighborhood space judged to be time sequence abnormal data pointst＝{Tt-d，...，Tt，...，Tt+d}，
5) Obtaining a time series change trend feature vector by using time series piecewise linear representation;
acquiring sequence data of abnormal dimensions of the time domain d at the moment t, fitting the sequence data through a bottom-up time sequence piecewise linear representation algorithm, obtaining a slope value of each segment by using a least square method, and extracting variation trend characteristics of the sequence data into a corresponding mode set to obtain a variation trend characteristic vector; the bottom-up time sequence piecewise linear representation algorithm is specifically as follows:
dividing the time sequence into short sequences of adjacent points, connecting a first point with a second point at the moment, enabling an original point to fall on a line segment, connecting two adjacent line segments, enabling each line segment to comprise three original points, calculating the fitting error of a middle point, finding out a segment with the minimum error and the error smaller than a threshold value R after obtaining the fitting error result of the middle point in all the line segments of the three points, on the basis, connecting the first segment with the adjacent line segments, calculating the fitting error of each segment, finding out the segment with the minimum error and the error smaller than the threshold value R as a second segment, circulating in this way until the fitting errors of all the segments are smaller than the threshold value R, and ending the segmentation;
6) Calculating the similarity of the vectors; calculating the similarity between the point location and the neighborhood point location by using the cosine distance;
7) if the similarity does not exceed 90%, the point location is judged to be space abnormal to obtain a space-time abnormal data point, and if the similarity does not exceed 90%, the point location is judged to be time abnormal to obtain a time abnormal data point.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (11)
1. The in-situ water quality inspection data space-time analysis and anomaly detection method is characterized by comprising the following steps of:
s1, acquiring space-time sequence data and performing time sequence abnormity detection and judgment;
s2, dividing a neighborhood space according to the abnormal data points of the time sequence to obtain a neighborhood point set and a time neighborhood of a moment;
s3, acquiring a time series change trend feature vector;
and S4, calculating vector similarity, and judging whether the data points are space-time abnormal data points or time abnormal data points according to the similarity.
2. The in-situ water quality inspection data space-time analysis and anomaly detection method according to claim 1, wherein in step S1, the collision results of four statistical distribution anomaly detection algorithms of IForest, PCA, HBOS and KNN and the scoring results of time series anomaly modeling are used for fusion judgment, all dimensions are modeled separately, and the results can obtain the dimensions judged to be anomalous.
3. The in-situ water quality inspection data space-time analysis and anomaly detection method according to claim 1, characterized in that in step S2, after time series anomaly determination is performed, space neighborhood division is performed through a Thiessen polygon and a K-means clustering algorithm according to coordinate position information of data points which are determined to be time series anomaly, and a neighborhood point set SN of observation points is obtainedi＝{S1，S2，...，SnI, j < n } and determining the d-time neighborhood TN at time tt＝{Tt-d，...，Tt，...，Tt+d}。
4. The in-situ water quality inspection data space-time analysis and anomaly detection method according to claim 3, wherein the step of establishing the Thiessen polygon is as follows:
a) constructing a Delaunay triangulation network through discrete points, numbering the discrete points and the formed triangles, and recording which three discrete points each triangle consists of;
b) Finding and recording the numbers of all triangles adjacent to each discrete point, and finding out all triangles with one same vertex in the constructed triangulation network;
c) sorting triangles adjacent to each discrete point in a clockwise or counterclockwise direction so as to be connected to generate a Thiessen polygon;
d) calculating and recording the circle center of a circumscribed circle of each triangle;
e) and connecting the centers of the circumscribed circles of the adjacent triangles according to the adjacent triangles of each discrete point to obtain the Thiessen polygon.
5. The in-situ water quality inspection data space-time analysis and anomaly detection method according to claim 4, wherein in the step c), a discrete point is set as o, and a triangle with o as a vertex is found and set as A; taking another vertex of the triangle A except o as a, finding out the third vertex as f; the next triangle must be bounded by of, which is triangle F; the other vertex of triangle F is e, then the next triangle is edged with oe, and so on until the oa edge is reached.
6. The in-situ water quality inspection data space-time analysis and anomaly detection method according to claim 4, wherein in the step e), for the Thiessen polygons at the edges of the triangulation network, perpendicular bisectors can be made to intersect with the outlines, and the Thiessen polygons are formed together with the outlines.
7. The in-situ water quality inspection data space-time analysis and anomaly detection method according to claim 1, characterized in that in step S3, for all point locations in a neighborhood space which are judged to be time-series abnormal data points, sequence data of abnormal dimensions in a d time field at time t are obtained, the sequence data are fitted through a time-series piecewise linear representation algorithm, a slope value of each segment is obtained, and a variation trend feature of the sequence data is extracted as a corresponding mode set to obtain a variation trend feature vector.
8. The in-situ water quality inspection data space-time analysis and anomaly detection method according to claim 7, wherein the sequence data is fitted using a bottom-up time series piecewise linear representation algorithm, and the slope value of each segment is found using a least squares method.
9. The in-situ water quality inspection data space-time analysis and anomaly detection method according to claim 8, wherein a bottom-up time series piecewise linear representation algorithm is specifically as follows:
dividing the time sequence into short sequences of adjacent points, connecting a first point with a second point, enabling an original point to fall on a line segment, connecting two adjacent line segments, enabling each line segment to comprise three original points, calculating the fitting error of a middle point, finding out a segment with the minimum error and the error smaller than a threshold value R after obtaining the fitting error result of the middle point in all the line segments of the three points, on the basis, connecting the first segment with the adjacent line segments, calculating the fitting error of each segment, finding out the segment with the minimum error and the error smaller than the threshold value R as a second segment, circulating in this way until the fitting errors of all the segments are smaller than the threshold value R, and ending the segmentation.
10. The in-situ water quality inspection data space-time analysis and anomaly detection method according to claim 1, wherein in step S4, the similarity between the point and the neighborhood point is calculated by using cosine distance.
11. The in-situ water quality inspection data space-time analysis and anomaly detection method according to claim 1, wherein in step S4, if the similarity does not exceed 90%, the point location is determined to be a space anomaly, a space-time anomaly data point is obtained, and if the similarity does not exceed 90%, the point location is determined to be a time anomaly, and a time anomaly data point is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010699357.9A CN111858712A (en) | 2020-07-20 | 2020-07-20 | In-situ water quality inspection data time-space analysis and anomaly detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010699357.9A CN111858712A (en) | 2020-07-20 | 2020-07-20 | In-situ water quality inspection data time-space analysis and anomaly detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111858712A true CN111858712A (en) | 2020-10-30 |
Family
ID=73000608
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010699357.9A Pending CN111858712A (en) | 2020-07-20 | 2020-07-20 | In-situ water quality inspection data time-space analysis and anomaly detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111858712A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112598797A (en) * | 2020-12-08 | 2021-04-02 | 中广核工程有限公司 | Method, system, medium and equipment for assimilating complex multi-source heterogeneous data of nuclear power plant |
| CN113255593A (en) * | 2021-06-25 | 2021-08-13 | 北京市水利自动化研究所 | Sensor information anomaly detection method facing space-time analysis model |
| CN113283003A (en) * | 2020-11-13 | 2021-08-20 | 西南交通大学 | High-speed train axle temperature anomaly detection method based on space-time fusion decision |
| CN113344059A (en) * | 2021-05-31 | 2021-09-03 | 武汉大学 | Spatial analysis anomaly detection method based on time sequence |
| CN114088128A (en) * | 2021-11-22 | 2022-02-25 | 中国联合网络通信集团有限公司 | Sensor determination method and device, storage medium and equipment |
| CN115271003A (en) * | 2022-09-30 | 2022-11-01 | 江苏云天新材料制造有限公司 | Abnormal data analysis method and system for automatic environment monitoring equipment |
| CN116308952A (en) * | 2023-03-08 | 2023-06-23 | 浪潮智慧科技有限公司 | Water quality monitoring method and device based on unmanned ship |
| CN118035774A (en) * | 2024-04-15 | 2024-05-14 | 四川能投云电科技有限公司 | Water level and pressure signal data safety control method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809205A (en) * | 2015-04-27 | 2015-07-29 | 河海大学 | Online detection method for time and space abnormal events by river network |
| CN107179525A (en) * | 2017-07-21 | 2017-09-19 | 南京邮电大学 | A kind of location fingerprint construction method of the Kriging regression based on Thiessen polygon |
| CN109325060A (en) * | 2018-07-27 | 2019-02-12 | 山东大学 | A kind of Model of Time Series Streaming method for fast searching based on data characteristics |
| CN109614576A (en) * | 2018-12-11 | 2019-04-12 | 福建工程学院 | Transformer exception detection method based on Multi-dimensional Gaussian distribution and trend segmentation |
| CN110018670A (en) * | 2019-03-28 | 2019-07-16 | 浙江大学 | A kind of industrial process unusual service condition prediction technique excavated based on dynamic association rules |
| CN110536307A (en) * | 2019-09-03 | 2019-12-03 | 南京华苏科技有限公司 | A kind of method and device of the adjacent section planning based on Thiessen polygon |
| CN110737874A (en) * | 2019-09-02 | 2020-01-31 | 中国科学院地理科学与资源研究所 | watershed water quality monitoring abnormal value detection method based on spatial relationship |
| CN110969556A (en) * | 2019-09-30 | 2020-04-07 | 上海仪电（集团）有限公司中央研究院 | Method and device for detecting river water quality abnormity by machine learning multi-dimension multi-model fusion |
-
2020
- 2020-07-20 CN CN202010699357.9A patent/CN111858712A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104809205A (en) * | 2015-04-27 | 2015-07-29 | 河海大学 | Online detection method for time and space abnormal events by river network |
| CN107179525A (en) * | 2017-07-21 | 2017-09-19 | 南京邮电大学 | A kind of location fingerprint construction method of the Kriging regression based on Thiessen polygon |
| CN109325060A (en) * | 2018-07-27 | 2019-02-12 | 山东大学 | A kind of Model of Time Series Streaming method for fast searching based on data characteristics |
| CN109614576A (en) * | 2018-12-11 | 2019-04-12 | 福建工程学院 | Transformer exception detection method based on Multi-dimensional Gaussian distribution and trend segmentation |
| CN110018670A (en) * | 2019-03-28 | 2019-07-16 | 浙江大学 | A kind of industrial process unusual service condition prediction technique excavated based on dynamic association rules |
| CN110737874A (en) * | 2019-09-02 | 2020-01-31 | 中国科学院地理科学与资源研究所 | watershed water quality monitoring abnormal value detection method based on spatial relationship |
| CN110536307A (en) * | 2019-09-03 | 2019-12-03 | 南京华苏科技有限公司 | A kind of method and device of the adjacent section planning based on Thiessen polygon |
| CN110969556A (en) * | 2019-09-30 | 2020-04-07 | 上海仪电（集团）有限公司中央研究院 | Method and device for detecting river water quality abnormity by machine learning multi-dimension multi-model fusion |
Non-Patent Citations (2)
| Title |
|---|
| 李光强;郑茂仪;邓敏;: "时空数据异常探测方法", 计算机工程 * |
| 邓敏;石岩;龚健雅;杨学习;: "时空异常探测方法研究综述", 地理与地理信息科学 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113283003A (en) * | 2020-11-13 | 2021-08-20 | 西南交通大学 | High-speed train axle temperature anomaly detection method based on space-time fusion decision |
| CN113283003B (en) * | 2020-11-13 | 2022-06-10 | 西南交通大学 | High-speed train axle temperature anomaly detection method based on space-time fusion decision |
| CN112598797A (en) * | 2020-12-08 | 2021-04-02 | 中广核工程有限公司 | Method, system, medium and equipment for assimilating complex multi-source heterogeneous data of nuclear power plant |
| CN112598797B (en) * | 2020-12-08 | 2024-03-12 | 中广核工程有限公司 | Method, system, medium and equipment for assimilating complex multi-source heterogeneous data of nuclear power plant |
| CN113344059B (en) * | 2021-05-31 | 2022-06-07 | 武汉大学 | Spatial analysis anomaly detection method based on time sequence |
| CN113344059A (en) * | 2021-05-31 | 2021-09-03 | 武汉大学 | Spatial analysis anomaly detection method based on time sequence |
| CN113255593B (en) * | 2021-06-25 | 2021-09-24 | 北京市水利自动化研究所 | Sensor information anomaly detection method facing space-time analysis model |
| CN113255593A (en) * | 2021-06-25 | 2021-08-13 | 北京市水利自动化研究所 | Sensor information anomaly detection method facing space-time analysis model |
| CN114088128A (en) * | 2021-11-22 | 2022-02-25 | 中国联合网络通信集团有限公司 | Sensor determination method and device, storage medium and equipment |
| CN114088128B (en) * | 2021-11-22 | 2023-11-17 | 中国联合网络通信集团有限公司 | Sensor determination method, device, storage medium and equipment |
| CN115271003A (en) * | 2022-09-30 | 2022-11-01 | 江苏云天新材料制造有限公司 | Abnormal data analysis method and system for automatic environment monitoring equipment |
| CN116308952A (en) * | 2023-03-08 | 2023-06-23 | 浪潮智慧科技有限公司 | Water quality monitoring method and device based on unmanned ship |
| CN116308952B (en) * | 2023-03-08 | 2023-09-22 | 浪潮智慧科技有限公司 | Water quality monitoring method and device based on unmanned ship |
| CN118035774A (en) * | 2024-04-15 | 2024-05-14 | 四川能投云电科技有限公司 | Water level and pressure signal data safety control method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111858712A (en) | In-situ water quality inspection data time-space analysis and anomaly detection method and system | |
| CN111462200B (en) | Cross-video pedestrian positioning and tracking method, system and equipment | |
| Hu et al. | Principal axis-based correspondence between multiple cameras for people tracking | |
| Rottensteiner et al. | Automated delineation of roof planes from lidar data | |
| CN109859226B (en) | Detection method of checkerboard corner sub-pixels for graph segmentation | |
| CN102243765A (en) | Multi-camera-based multi-objective positioning tracking method and system | |
| CN114022910B (en) | Swimming pool drowning prevention supervision method and device, computer equipment and storage medium | |
| Nurunnabi et al. | Robust segmentation for multiple planar surface extraction in laser scanning 3D point cloud data | |
| CN112862858A (en) | Multi-target tracking method based on scene motion information | |
| CN111192297A (en) | Multi-camera target association tracking method based on metric learning | |
| CN113469201A (en) | Image acquisition equipment offset detection method, image matching method, system and equipment | |
| CN111489416A (en) | Tunnel axis fitting method and application in calculation of over-under excavation square measure | |
| Ariyachandra et al. | Digital twinning of railway overhead line equipment from airborne lidar data | |
| CN110851978B (en) | Camera position optimization method based on visibility | |
| Landabaso et al. | Foreground regions extraction and characterization towards real-time object tracking | |
| CA2787856A1 (en) | Systems and methods for estimating the geographic location at which image data was captured | |
| Shi et al. | Investigating the performance of corridor and door detection algorithms in different environments | |
| CN114235815A (en) | Method for detecting surface defects of outdoor electrical equipment of converter station based on scene filtering | |
| Hussnain et al. | Automatic feature detection, description and matching from mobile laser scanning data and aerial imagery | |
| Yoon et al. | Landmark design and real-time landmark tracking for mobile robot localization | |
| CN112767476A (en) | Rapid positioning system, method and application | |
| Oberti et al. | Performance evaluation criterion for characterizing video-surveillance systems | |
| Sester et al. | Reconstruction of building ground plans from laser scanner data | |
| Duong et al. | Model-based robust lane detection for driver assistance | |
| CN112800828A (en) | Target track method for ground grid occupation probability |
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 |