CN110399537A - A kind of alert spatio-temporal prediction method based on artificial intelligence technology - Google Patents
A kind of alert spatio-temporal prediction method based on artificial intelligence technology Download PDFInfo
- Publication number
- CN110399537A CN110399537A CN201910660167.3A CN201910660167A CN110399537A CN 110399537 A CN110399537 A CN 110399537A CN 201910660167 A CN201910660167 A CN 201910660167A CN 110399537 A CN110399537 A CN 110399537A
- Authority
- CN
- China
- Prior art keywords
- alert
- prediction
- model
- data
- artificial intelligence
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of alert spatio-temporal prediction method based on artificial intelligence technology, method includes the following steps: Data Integration constructs the training sample of prediction model according to internet data resources such as alert data and weather；The random forests algorithm in artificial intelligence technology is called in feature extraction, extracts characteristic variable；Data modeling, calling logic regression algorithm carry out the modeling of alert prediction model；Model testing assessment, selects test sample to test assessment model；History alert time series in risk zones is established in time prediction, by autoregression quadrature moving average model(MA model) (ARIMA), predicts the time of origin of alert.The present invention uses intelligent algorithm, prediction model is established based on history alert data, alert is predicted according to newest characteristic element content, it can predict the net region of 50m*50m, prediction result is accurate to some region of a certain period, its prediction result is more objective, and estimation range is more accurate.
Description
Technical field
The present invention relates to alert electric powder predictions, and in particular to a kind of alert spatio-temporal prediction based on artificial intelligence technology
Method.
Background technique
The information technology of continuous development enables public security department to obtain more and more related (alert) data of committing a crime, such as
What designs a kind of effectively convenient and fast method, by analyzing these data, the mode and trend of crime data behind is excavated, to help
The police preferably carry out public security prevention and control and crime prevention, it has also become highly study the problem of, existing alert prediction side
Method, mostly based on the alert data that nearest a period of time has occurred, from time aggregation extent, the space clustering journey that alert has occurred
Spend come to following a period of time for example: tomorrow, next week, next month may the risk of alert assess.Currently, existing alert
Predicting means is predicted by artificial experience and Spatiotemporal Aggregation degree, and there are larger for forecasting accuracy
Uncertainty, such as: a period of time certain cell larceny case frequent occurrence recently can not illustrate to also occur that theft tomorrow
Case, from prediction result it is comprehensive for, there is also following deficiencies: prediction result can not be accurate to the period, such as: predict certain area
The risk of domain 3 ~ 6 points of generation alerts in afternoon is larger；Estimation range is relatively large, mostly using a street, local police station area under one's jurisdiction as object
Risk assessment is carried out, therefore, it is necessary to further progress improvement.
Summary of the invention
The purpose of the present invention is to provide a kind of alert spatio-temporal prediction method based on artificial intelligence technology, using artificial intelligence
Energy algorithm, establishes prediction model based on history alert data, finding out from historical law angle influences alert in different zones
Characteristic element, alert is predicted according to newest characteristic element content, meet alert prediction timeliness requirement,
Prediction result is more objective, and estimation range is more accurate, can predict the net region of 50m*50m, can be to alert high incidence period
It is predicted, prediction result is accurate to some region of a certain period, to solve the problems mentioned in the above background technology.
To achieve the above object, the invention provides the following technical scheme:
A kind of alert spatio-temporal prediction method based on artificial intelligence technology, method includes the following steps:
Step S1, Data Integration establish prediction model training data according to internet data resources such as alert data and weather
Collection and test data set sample, wherein range attenuation and time interval in sample data, be based on alert occur position and
Time is obtained using cuclear density interpolation technique by precomputation；
The random forests algorithm in artificial intelligence technology is called in step S2, feature extraction, extracts characteristic variable；
Step S3, data modeling, calling logic regression algorithm carry out the modeling of alert prediction model；
Step S4, model testing assessment, selects the sample of the test data set to test assessment model；
Step S5, time prediction, according to the history alert of the risk zones generation to prediction, with 24 hours for the period, with 3 hours
For interval, the time series of 8 periods is generated, by establishing autoregression quadrature moving average model(MA model) (ARIMA), acquisition most has
The time of alert may occur.
Further, using electronic map, police service area under one's jurisdiction is divided into the grid of several 50m*50m, each grid list
Member is exactly risk zones to be predicted, and alert data are integrated in convergence, constructs the training sample of prediction model, the training sample by
The training dataset and test data set are constituted.
Further, using random forests algorithm, characteristic variable is extracted, because the calculating time of random forest is long,
It is difficult to meet the timeliness requirement of alert prediction, so only extracting feature rather than modeling with random forest.
Further, logistic regression algorithm is selected, prediction model is automatically generated, it is contemplated that alert prediction is one typical
Two classification predictions, therefore agree with very much two sort features of logistic regression；Meanwhile because the output of logistic regression is a probability
Value, basic-level policemen are readily appreciated that and receive；More importantly because logistic regression allow for more training datas to be included in it is pre-
Model is surveyed, the dynamic that can meet alert prediction model well is upgraded demand.
Further, it tested, evaluated and optimized to prediction model using the sample of the test data set.
Further, according to the prediction model of building, the prediction model, development and application system, based on newly-increased number are called
According to the risk zones that prediction alert in future occurs.
Further, history alert time series in risk zones is established, autoregression quadrature moving average model(MA model) is passed through
(ARIMA), the time of origin of alert is predicted.
Further, the jamming countermeasure data that orientation patrol etc. frequently changes the training data is included in time to concentrate,
Realize that the dynamic of prediction model updates.
Compared with prior art, beneficial effects of the present invention are as follows:
1, using intelligent algorithm, prediction model is established based on history alert data, finds out not same district from historical law angle
The characteristic element that alert occurs is influenced in domain, and alert is predicted according to newest characteristic element content, it is pre- to meet alert
The timeliness requirement of survey；
2, prediction result of the present invention is more objective, and estimation range is more accurate, can predict the net region of 50m*50m, can be right
Alert high incidence period is predicted, prediction result is accurate to some region of a certain period, improves the accurate of alert prediction
Property.
Detailed description of the invention
Attached drawing is used to provide further understanding of the present invention, and constitutes part of specification, with tool of the invention
Body embodiment is used to explain the present invention together, is not construed as limiting the invention.
Fig. 1 is a kind of flow chart of alert spatio-temporal prediction method based on artificial intelligence technology of the invention；
Fig. 2 is a kind of refined flow chart of alert spatio-temporal prediction method based on artificial intelligence technology of the invention.
Specific embodiment
Below in conjunction with attached drawing to a preferred embodiment of the present invention will be described in detail, it should be understood that described herein excellent
Select embodiment only for the purpose of illustrating and explaining the present invention and is not intended to limit the present invention.
Key problem in technology point of the invention is by the way that using electronic map, police service area under one's jurisdiction is divided into several 50m*50m's
Grid, each grid cell are exactly risk zones to be predicted, call the random forests algorithm in artificial intelligence technology, are extracted
Characteristic variable establishes prediction model based on history alert data, selects logistic regression algorithm, automatically generate alert prediction model,
The characteristic element for influencing alert in different zones and occurring is found out from historical law angle, according to newest characteristic element content to police
Feelings are predicted.
Embodiment one:
As Figure 1-Figure 2, the present invention provides a kind of technical solution: a kind of alert spatio-temporal prediction side based on artificial intelligence technology
Method, method includes the following steps:
Step S1, Data Integration establish prediction model training data according to internet data resources such as alert data and weather
Collection and test data set sample, wherein range attenuation and time interval in sample data, be based on alert occur position and
Time is obtained using cuclear density interpolation technique by precomputation；
The random forests algorithm in artificial intelligence technology is called in step S2, feature extraction, extracts characteristic variable；
Step S3, data modeling, calling logic regression algorithm carry out the modeling of alert prediction model；
Step S4, model testing assessment, selects the sample of the test data set to test assessment model；
Step S5, time prediction, according to the history alert of the risk zones generation to prediction, with 24 hours for the period, with 3 hours
For interval, the time series of 8 periods is generated, by establishing autoregression quadrature moving average model(MA model) (ARIMA), acquisition most has
The time of alert may occur.
In the present embodiment, the specific steps of the step S1 are as follows: utilize electronic map, police service area under one's jurisdiction is divided into several
The grid of 50m*50m, each grid cell are exactly risk zones to be predicted；Alert data, building prediction mould are integrated in convergence
The training sample of type, the training sample are made of the training dataset and test data set.
In the present embodiment, in the step S2, using random forests algorithm, characteristic variable is extracted, because random forest
Calculate the time it is long, it is difficult to meet alert prediction timeliness requirement, so only with random forest extract feature rather than
Modeling.
In the present embodiment, in the step S3, logistic regression algorithm is selected, automatically generates prediction model, it is contemplated that alert
Prediction is a typical two classification prediction, therefore agrees with very much two sort features of logistic regression；Meanwhile because logistic regression
Output be a probability value, basic-level policemen is readily appreciated that and receives；More importantly because logistic regression allow will be more
Training data be included in prediction model, the dynamic that can meet alert prediction model well is upgraded demand.
In the present embodiment, in the step S4, is tested, commented to prediction model using the sample of the test data set
Estimate and optimize, according to the prediction model of building, calls the prediction model, development and application system, based on newly-increased data, prediction will
Carry out the risk zones of alert generation.
In the present embodiment, in the step S5, history alert time series in risk zones is established, autoregression quadrature is passed through
Moving average model(MA model) (ARIMA), predicts the time of origin of alert, and the jamming countermeasure data that orientation patrol etc. is frequently changed are timely
It is included in the training data to concentrate, realizes that the dynamic of prediction model updates.
Embodiment two:
As shown in Fig. 2, the present invention provides a kind of alert spatio-temporal prediction method based on artificial intelligence technology, the specific step of this method
Suddenly are as follows:
Police service area under one's jurisdiction is divided into the grid of several 50m*50m using electronic map by step A, each grid cell be exactly to
The risk zones of prediction；
Step B, convergence integrate alert data, construct the training sample of prediction model, the training sample is by the training data
Collection and test data set are constituted；
Step C extracts characteristic variable, because the calculating time of random forest is long, it is difficult to meet using random forests algorithm
The timeliness requirement of alert prediction, so only extracting feature rather than modeling with random forest；
Step D selects logistic regression algorithm, automatically generates prediction model, it is contemplated that alert prediction is typical two classification
Prediction, therefore agree with very much two sort features of logistic regression；Meanwhile because the output of logistic regression is a probability value, base
Layer people's police are readily appreciated that and receive；More importantly because logistic regression allows more training datas being included in prediction mould
Type, the dynamic that can meet alert prediction model well are upgraded demand；
Step E tests to prediction model using the sample of the test data set, evaluates and optimizes；
Step F calls the prediction model, development and application system, based on newly-increased data, prediction according to the prediction model of building
The risk zones that alert in future occurs；
Step G establishes history alert time series in risk zones, by autoregression quadrature moving average model(MA model) (ARIMA), in advance
Survey the time of origin of alert；
The jamming countermeasure data that orientation patrol etc. frequently changes are included in the training data in time and concentrated, realize prediction by step I
The dynamic of model updates.
In the present embodiment, by the prediction model of building, development and application system predicts alert in future based on newly-increased data
The risk zones of generation predict the time of origin of alert by autoregression quadrature moving average model(MA model) (ARIMA), by that will determine
The jamming countermeasure data frequently changed to patrol etc. are included in the training data in time and are concentrated, and realize the dynamic of prediction model more
Newly, the Various types of data of newest alert can be obtained, some region of a certain period in the accurate net region for predicting 50m*50m
Alert occurs.
The present invention is improved in a kind of alert spatio-temporal prediction method based on artificial intelligence technology of the invention, using artificial
Intelligent algorithm establishes prediction model based on history alert data, and finding out from historical law angle influences alert hair in different zones
Raw characteristic element predicts alert according to newest characteristic element content, meets the timeliness requirement of alert prediction,
Its prediction result is more objective, and estimation range is more accurate, can predict the net region of 50m*50m, when can be high-incidence to alert
Duan Jinhang prediction, is accurate to some region of a certain period for prediction result, improves the accuracy of alert prediction.
The foregoing is merely preferred embodiments of the invention, are not intended to restrict the invention, although referring to aforementioned implementation
Invention is explained in detail for example, for those skilled in the art, still can be to foregoing embodiments
Documented technical solution is modified or equivalent replacement of some of the technical features.It is all in spirit of the invention
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (8)
1. a kind of alert spatio-temporal prediction method based on artificial intelligence technology, which is characterized in that method includes the following steps:
Step S1, Data Integration establish prediction model training data according to internet data resources such as alert data and weather
Collection and test data set sample, wherein range attenuation and time interval in sample data, be based on alert occur position and
Time is obtained using cuclear density interpolation technique by precomputation；
The random forests algorithm in artificial intelligence technology is called in step S2, feature extraction, extracts characteristic variable；
Step S3, data modeling, calling logic regression algorithm carry out the modeling of alert prediction model；
Step S4, model testing assessment, selects the sample of the test data set to test assessment model；
Step S5, time prediction, according to the history alert of the risk zones generation to prediction, with 24 hours for the period, with 3 hours
For interval, the time series of 8 periods is generated, by establishing autoregression quadrature moving average model(MA model) (ARIMA), acquisition most has
The time of alert may occur.
2. a kind of alert spatio-temporal prediction method based on artificial intelligence technology according to claim 1, which is characterized in that institute
State the specific steps of step S1 are as follows:
Police service area under one's jurisdiction is divided into the grid of several 50m*50m using electronic map by step S11, each grid cell is exactly
Risk zones to be predicted；
Step S12, convergence integrate alert data, construct the training sample of prediction model, the training sample is by the trained number
It is constituted according to collection and test data set.
3. a kind of alert spatio-temporal prediction method based on artificial intelligence technology according to claim 1, which is characterized in that institute
It states in step S2, using random forests algorithm, characteristic variable is extracted, because the calculating time of random forest is long, it is difficult to full
The timeliness requirement of sufficient alert prediction, so only extracting feature rather than modeling with random forest.
4. a kind of alert spatio-temporal prediction method based on artificial intelligence technology according to claim 1, which is characterized in that institute
It states in step S3, selects logistic regression algorithm, automatically generate prediction model, it is contemplated that alert prediction is typical two classification
Prediction, therefore agree with very much two sort features of logistic regression；Meanwhile because the output of logistic regression is a probability value, base
Layer people's police are readily appreciated that and receive；More importantly because logistic regression allows more training datas being included in prediction mould
Type, the dynamic that can meet alert prediction model well are upgraded demand.
5. a kind of alert spatio-temporal prediction method based on artificial intelligence technology according to claim 1, which is characterized in that institute
It states in step S4, is tested, evaluated and optimized to prediction model using the sample of the test data set.
6. a kind of alert spatio-temporal prediction method based on artificial intelligence technology according to claim 4, which is characterized in that root
According to the prediction model of building, the prediction model is called, development and application system, based on newly-increased data, prediction alert in future occurs
Risk zones.
7. a kind of alert spatio-temporal prediction method based on artificial intelligence technology according to claim 1, which is characterized in that institute
It states in step S5, establishes history alert time series in risk zones, by autoregression quadrature moving average model(MA model) (ARIMA),
Predict the time of origin of alert.
8. a kind of alert spatio-temporal prediction method based on artificial intelligence technology according to claim 2, which is characterized in that will
The jamming countermeasure data that orientation patrol etc. frequently changes are included in the training data in time and are concentrated, and realize the dynamic of prediction model more
Newly.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910660167.3A CN110399537B (en) | 2019-07-22 | 2019-07-22 | Artificial intelligence technology-based warning situation space-time prediction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910660167.3A CN110399537B (en) | 2019-07-22 | 2019-07-22 | Artificial intelligence technology-based warning situation space-time prediction method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110399537A true CN110399537A (en) | 2019-11-01 |
| CN110399537B CN110399537B (en) | 2022-12-16 |
Family
ID=68324974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910660167.3A Active CN110399537B (en) | 2019-07-22 | 2019-07-22 | Artificial intelligence technology-based warning situation space-time prediction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110399537B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597461A (en) * | 2020-05-08 | 2020-08-28 | 北京百度网讯科技有限公司 | Target object aggregation prediction method and device and electronic equipment |
| CN113610309A (en) * | 2021-08-13 | 2021-11-05 | 清华大学 | Fire station site selection method and device based on big data and artificial intelligence |
| CN114898889A (en) * | 2021-12-15 | 2022-08-12 | 南京行者易智能交通科技有限公司 | Design method of aggregative risk control model based on big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007005975A2 (en) * | 2005-07-01 | 2007-01-11 | Valen Technologies, Inc. | Risk modeling system |
| CN108052528A (en) * | 2017-11-09 | 2018-05-18 | 华中科技大学 | A kind of storage device sequential classification method for early warning |
| CN108269000A (en) * | 2017-12-22 | 2018-07-10 | 武汉烽火众智数字技术有限责任公司 | Intelligent police deployment method and system based on alert big data space-time analysis |
| WO2018214060A1 (en) * | 2017-05-24 | 2018-11-29 | 北京质享科技有限公司 | Small-scale air quality index prediction method and system for city |
| CN109472419A (en) * | 2018-11-16 | 2019-03-15 | 中山大学 | Method for building up, device and the storage medium of alert prediction model based on space-time |
-
2019
- 2019-07-22 CN CN201910660167.3A patent/CN110399537B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2007005975A2 (en) * | 2005-07-01 | 2007-01-11 | Valen Technologies, Inc. | Risk modeling system |
| WO2018214060A1 (en) * | 2017-05-24 | 2018-11-29 | 北京质享科技有限公司 | Small-scale air quality index prediction method and system for city |
| CN108052528A (en) * | 2017-11-09 | 2018-05-18 | 华中科技大学 | A kind of storage device sequential classification method for early warning |
| CN108269000A (en) * | 2017-12-22 | 2018-07-10 | 武汉烽火众智数字技术有限责任公司 | Intelligent police deployment method and system based on alert big data space-time analysis |
| CN109472419A (en) * | 2018-11-16 | 2019-03-15 | 中山大学 | Method for building up, device and the storage medium of alert prediction model based on space-time |
Non-Patent Citations (1)
| Title |
|---|
| 梁慧玲等: "基于气象因子的随机森林算法在塔河地区林火预测中的应用", 《林业科学》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111597461A (en) * | 2020-05-08 | 2020-08-28 | 北京百度网讯科技有限公司 | Target object aggregation prediction method and device and electronic equipment |
| CN111597461B (en) * | 2020-05-08 | 2023-11-17 | 北京百度网讯科技有限公司 | Target object aggregation prediction method and device and electronic equipment |
| CN113610309A (en) * | 2021-08-13 | 2021-11-05 | 清华大学 | Fire station site selection method and device based on big data and artificial intelligence |
| CN114898889A (en) * | 2021-12-15 | 2022-08-12 | 南京行者易智能交通科技有限公司 | Design method of aggregative risk control model based on big data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110399537B (en) | 2022-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ali et al. | A data-driven approach for multi-scale GIS-based building energy modeling for analysis, planning and support decision making | |
| Straka et al. | Predicting popularity of electric vehicle charging infrastructure in urban context | |
| Corcoran et al. | Predicting the geo-temporal variations of crime and disorder | |
| CN105260795B (en) | A kind of emphasis personnel positions spatio-temporal prediction method based on condition random field | |
| Yu et al. | Crime forecasting using spatio-temporal pattern with ensemble learning | |
| Kim | Exploring the difference between ridership patterns of subway and taxi: Case study in Seoul | |
| Han et al. | Risk prediction of theft crimes in urban communities: An integrated model of LSTM and ST-GCN | |
| Van Patten et al. | A microspatial analysis of robbery: Prospective hot spotting in a small city | |
| CN110399537A (en) | A kind of alert spatio-temporal prediction method based on artificial intelligence technology | |
| CN109472419A (en) | Method for building up, device and the storage medium of alert prediction model based on space-time | |
| CN108256724B (en) | Power distribution network open capacity planning method based on dynamic industry coefficient | |
| CN103955804A (en) | Crime risk spatial-temporal pattern recognition method serving policing prevention and control district planning | |
| Borges et al. | Feature engineering for crime hotspot detection | |
| CN103699771A (en) | Cold load predication scene clustering method | |
| Xu et al. | Hybrid holiday traffic predictions in cellular networks | |
| Zhang et al. | Duplicate report detection in urban crowdsensing applications for smart city | |
| Hochstetler et al. | An optimal police patrol planning strategy for smart city safety | |
| Baqir et al. | Evaluating the performance of hierarchical clustering algorithms to detect spatio-temporal crime hot-spots | |
| Zahraie et al. | SST clustering for winter precipitation prediction in southeast of Iran: Comparison between modified K-means and genetic algorithm-based clustering methods | |
| CN112633636A (en) | Water disaster defense decision support system and method | |
| Ristea et al. | Geosocial Media Data as Predictors in a GWR Application to Forecast Crime Hotspots (Short Paper) | |
| CN111062547A (en) | Time-space region-based crime analysis method | |
| Luan et al. | An efficient target tracking approach through mobile crowdsensing | |
| Fior et al. | Estimating the incidence of adverse weather effects on road traffic safety using time series embeddings | |
| Yuan et al. | A novel learning approach for citywide crowd flow prediction |
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 |