CN108055154A - A kind of car networking anomaly data detection system and method based on mist operating structure - Google Patents
A kind of car networking anomaly data detection system and method based on mist operating structure Download PDFInfo
- Publication number
- CN108055154A CN108055154A CN201711347035.2A CN201711347035A CN108055154A CN 108055154 A CN108055154 A CN 108055154A CN 201711347035 A CN201711347035 A CN 201711347035A CN 108055154 A CN108055154 A CN 108055154A
- Authority
- CN
- China
- Prior art keywords
- data
- model
- abnormal data
- fog
- central server
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0631—Management of faults, events, alarms or notifications using root cause analysis; using analysis of correlation between notifications, alarms or events based on decision criteria, e.g. hierarchy, tree or time analysis
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/142—Network analysis or design using statistical or mathematical methods
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W24/00—Supervisory, monitoring or testing arrangements
- H04W24/06—Testing, supervising or monitoring using simulated traffic
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Algebra (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Probability & Statistics with Applications (AREA)
- Pure & Applied Mathematics (AREA)
- Traffic Control Systems (AREA)
- Alarm Systems (AREA)
Abstract
The present invention relates to a kind of car networking anomaly data detection system and method based on mist operating structure, which includes：Data perception unit, mist arithmetic element and central server unit.Traffic data is obtained by data perception unit, and by these data and then mist arithmetic element is transferred to handle.Mist arithmetic element carries out the abnormal data Preliminary detection based on Density Estimator, and result is uploaded to central server unit.Central server unit summarizes the testing result of mist arithmetic element, and nuclear density model is constantly adjusted according to result and is handed down to mist arithmetic element, to ensure the accurate of testing result.A kind of car networking anomaly data detection system and method based on mist operating structure proposed by the invention, characteristic that intelligent terminal can be made full use of widely distributed and it is increasingly enhanced computing capability, delete the abnormal data occurred during traffic data collection, ensure the quality of data, improve the accuracy of follow-up car networking decision-making.
Description
Technical Field
The invention relates to a system and a method for detecting abnormal data of a vehicle networking based on a fog operation structure.
Background
With the rapid development of economy and science and technology, the quantity of automobile reserves of residents in China is continuously increased, the problems of road congestion and safety are gradually serious, and the intelligent traffic system is in the process of operation, and the Internet of vehicles is an important means of the intelligent traffic system. The car networking system senses, calculates and analyzes a series of factors such as traffic facilities and road conditions by utilizing advanced technologies such as information, communication, sensing and control, and finally provides a series of services such as accurate travel suggestions and front road traffic conditions for drivers, and plays roles in improving traffic travel efficiency, avoiding traffic risks, improving road conditions and the like.
The traditional abnormal data detection mostly adopts a centralized processing model based on cloud computing. And all the data collected by the data collection nodes are uploaded to the cloud server, and the cloud server judges and deletes abnormal data according to a uniform detection model to generate an available data set. The algorithm can not process data sources which continuously generate new data, and can not be applied to the scene that the data sources of the Internet of vehicles are widely distributed; and the cloud computing model has the defects of high time delay and high data throughput, the computing capacity of the data terminal cannot be exerted, the computing task of the cloud server is too heavy, and the real-time requirement of the Internet of vehicles cannot be met. The cloud computing method introduces a concept of the fog computing to make up the deficiency of the cloud computing, adds the fog computing layer composed of equipment with certain computing capacity between the data sensing layer and the server, reduces the computing load of the cloud server, reduces the processing time delay, reduces the network bandwidth pressure, and helps the Internet of vehicles system to make traffic decisions more quickly. Therefore, it is very meaningful to combine the fog operation with the internet of vehicles and research a method capable of quickly and accurately detecting abnormal data of the internet of vehicles.
The method is characterized in that a statistical detection method is one of the most commonly used abnormal data judgment standards in the traditional vehicle networking abnormal data detection algorithm, the core of the method is to apply a statistical theory to determine a confidence upper limit, and if the error of traffic data exceeds the upper limit, the abnormal data is judged. The method can achieve high detection performance theoretically, but the abnormal detection is carried out on the premise that the data are subjected to normal distribution, and in real life, due to randomness of driving behaviors and vehicle performance, the vehicle networking data are not necessarily subjected to normal distribution, so that the actual detection performance of the method in the vehicle networking application is far lower than the theoretical performance.
Disclosure of Invention
The invention aims to provide a system and a method for detecting abnormal data of a vehicle networking based on a fog operation structure, which are used for overcoming the defects in the prior art.
In order to achieve the purpose, the technical scheme of the invention is as follows: the utility model provides a car networking abnormal data detecting system based on fog operation structure, includes: the system comprises a data sensing unit, a fog operation unit and a central server unit;
the data sensing unit comprises a data acquisition module which is arranged at the mobile terminal of the driver and is used for acquiring traffic data;
the fog operation unit comprises a mobile terminal carrying a nuclear density model issued by the central server unit, and the mobile terminal detects abnormal data of the traffic data through the nuclear density model and feeds back the detection result of the abnormal data to the central server unit; the mobile terminal periodically detects the effectiveness of the nuclear density model and feeds back a model detection result to the central server unit;
and the central server unit receives the abnormal data detection result and the model detection result uploaded by the fog operation unit, performs model updating operation according to the model detection result, and sends the updated model to the fog operation unit.
The method comprises a model initialization stage, an abnormal data detection stage and a model updating stage;
the model initialization phase: taking traffic data acquired by a data sensing unit in the driving process of a vehicle as initialization data; when the acquired initialization data reach the preset data volume, the acquired initialization data are uploaded to a central server unit through a fog operation unit; the central server unit acquires an initial nuclear density model according to the uploaded initialization data and sends the initial nuclear density model to the fog operation unit;
the abnormal data detection stage comprises: after the fog operation unit acquires the initial nuclear density model, the solution confidence coefficient operation is carried out on the traffic data subsequently acquired by the data sensing unit according to the initial nuclear density model, whether the traffic data is abnormal data or not is detected, and the abnormal data detection result is uploaded to the central server unit to be stored;
the model updating stage comprises the following steps: when the central server unit receives the abnormal data detection result uploaded by the fog operation unit, counting the number of terminals corresponding to the fog element operation unit which uploads the abnormal data detection result; if the number of the terminals does not exceed the preset proportion of the total number, the initial nuclear density model is not updated; otherwise, entering a model updating stage; and the central server unit acquires a new nuclear density model through the collected normal data, and sends the new nuclear density model as an adjustment result to the fog operation unit for abnormal data detection in the next abnormal data detection stage.
In an embodiment of the present invention, the fog operation unit includes a handheld smart phone and a tablet computer; the data sensing unit comprises a speed sensor, an acceleration sensor, a three-axis acceleration sensor and a GPS which are arranged on the fog computing unit.
In one embodiment of the invention, the model is initializedIn the conversion stage, the central server unit obtains the initial nuclear density model according to the uploaded initialization data in the following mode
Where n is the sample volume, h is the window width, K (-) is the kernel function, X i The value is taken for the ith sample.
In an embodiment of the present invention, the kernel function is a gaussian kernel function:
wherein u is an independent variable.
In an embodiment of the present invention, in the abnormal data detection stage, the confidence is solved as follows
Degree r (x) operation:
wherein f (x) is a preset probability density model, alpha is a confidence probability, and data with the confidence degree smaller than 0 is judged as abnormal data.
In one embodiment of the invention, in the abnormal data detection stage, every preset period, the fog operation unit evaluates the change degree of the data probability density of the acquired traffic data, and judges the effectiveness of the original probability density model; and if the change degree exceeds a preset threshold value, uploading the result to the central service unit, and performing model updating operation through the central service unit. In an embodiment of the present invention, the degree of change of the data probability density of the collected traffic data is evaluated by:
therein, Ψ JS Evaluating a standard JS-Scattering value for the degree of change; p is a radical of i And q is i Probability density models corresponding to two adjacent periods before and after are respectively provided, and omega is a value set of the traffic data x.
In an embodiment of the present invention, the preset period is 5min, and the preset threshold is 0.5.
In an embodiment of the invention, in the model updating stage, the total number is preset to be 50%.
Compared with the prior art, the invention has the following beneficial effects:
(1) The method can make full use of the characteristics of wide distribution of the intelligent terminals and increasingly enhanced computing power, delete abnormal data generated in the traffic data acquisition process, ensure the data quality and improve the accuracy of subsequent vehicle networking decisions.
(2) Removing abnormal traffic data: compared with the traditional statistical detection method, the method has the advantages that the characteristics of data distribution can be directly solved by using the kernel density model on the premise of no prior knowledge, abnormal values in traffic data are effectively detected and eliminated, and the data quality is improved.
(3) Ease of use of the platform: at present, the intelligent terminal is provided with a built-in sensor with comprehensive functions, strong terminal computing power, high popularization rate and wide network coverage, and can easily realize the functions of a data sensing layer and a fog operation layer. Compared with the scheme that the traditional abnormal data detection system of the Internet of vehicles collects all data to the central server in a unified mode, the system can fully utilize the computing power of the terminal to perform parallel operation, and the detection time is greatly shortened.
Drawings
Fig. 1 is an architecture diagram of an abnormal data detection system based on a fog operation structure according to an embodiment of the present invention.
FIG. 2 is a flowchart illustrating an abnormal data detection method based on a fog operation structure according to an embodiment of the present invention.
Fig. 3 is a diagram illustrating an effect verification result according to an embodiment of the invention.
Detailed Description
The technical scheme of the invention is specifically explained below with reference to the accompanying drawings.
The invention provides a system and a method for detecting abnormal data of a vehicle networking based on a fog operation structure, as shown in figure 1, the system comprises: the system comprises a data perception layer, a fog operation layer and a central server.
The data perception layer is composed of built-in sensors of the intelligent terminal carried by the driver, and the built-in sensors include but are not limited to a GPS (global positioning system), a three-axis acceleration sensor and the like. Through carrying on the APP that is used for data acquisition on intelligent terminal, will acquire traffic data and save from the sensor.
The fog operation layer is composed of an intelligent terminal carried by a driver, and comprises but is not limited to a smart phone, a tablet computer and the like. For convenience of description, the following embodiments are collectively referred to as a mist device. And the fog equipment performs abnormal data detection on the collected traffic data according to a nuclear density model issued by the central server and feeds back a detection result to the central server. In addition, the effectiveness of the nuclear density model is detected at a certain period, and the model detection result is fed back to the central server.
The central server is composed of servers with high hardware configuration and strong computing power. The central server establishes an initial nuclear density model according to the collected initial traffic data and issues the initial nuclear density model to each fog device, then collects abnormal data detection results and model validity detection results of the fog devices, makes a judgment on whether the nuclear density model needs to be updated or not, and issues the latest nuclear density model to each fog device.
Further, the method comprises: model initialization, abnormal data detection and model updating, and the flow chart is shown in fig. 2.
Model initialization phase: each fog device collects a large amount of traffic data as initialization data in the vehicle running process through a data collection APP and a built-in sensor. When the initialized data reach a certain scale, the fog equipment uploads the initialized data to a central server, the central server samples the data and then calculates an initial nuclear density model according to the formula (1)And issued to each mist device.
Where n is the sample volume, h is the window width, K (-) is the kernel function, X i And taking the value of the ith sample.
Preferably, the kernel function K (·) may use a gaussian kernel function as in equation (2):
abnormal data detection stage: after the fog equipment receives the initial nuclear density model, the confidence coefficient r (x) is solved according to the model and the traffic data collected next according to the formula (3), whether the traffic data is abnormal data or not is detected, and judgment is carried out
And uploading the other results to a central server for storage.
Wherein f (x) is a preset probability density model, alpha is a confidence probability, and data with the confidence degree smaller than 0 is judged as abnormal data.
Further, every certain period, the fog equipment can evaluate the change degree of the data probability density and judge the effectiveness of the original probability density model; if the change degree is obvious, the result is reported to the central server, and the central server performs subsequent model adjustment work. Preferably, every 5 minutes, the fog device evaluates the change degree of the data probability density, judges the effectiveness of the original probability density model, and evaluates the evaluation standard to be JS-divergence, as shown in formula (4), and the judgment threshold is 0.5.
The evaluation criteria are as follows:
therein, Ψ JS Evaluating a standard JS-Scattering value for the degree of change; p is a radical of i 、q i Probability density models which are respectively corresponding to the front and the back adjacent periods and participate in the judgment; the degree of change in the probability density of the data was evaluated every 5 minutes by the fogger device, p i 、q i Probability density models which are respectively corresponding to two adjacent periods of 5 minutes before and after and participate in the judgment; Ω is the value set of the traffic data x. In this embodiment, let 5min be the period for judging the validity of the model, let Ψ be JS >, 0.5 as a threshold with a significant degree of variation.
And (3) updating the model: when the central server receives the distribution change notification uploaded by part of the fog devices, the number of the fog devices which report changes is counted firstly, and if the number does not exceed 50% of the total number, the original kernel density model is not adjusted. Otherwise, entering a model updating stage, and the central server utilizes the collected normal data to obtain a new nuclear density model, and sends the new nuclear density model as an adjustment result to all fog devices as a basis for detecting the next abnormal data.
Further, in order to make those skilled in the art further understand the technical solution proposed by the present invention, the following description is made with reference to a specific operation method of each module.
In this embodiment, the specific working steps of the mist device are as follows:
step 1) collecting initialization data, uploading the data to a central server, and waiting for the central server to issue an initial model;
step 2) if the initial model is not received, repeating the step 1); otherwise, receiving and storing the initial model;
step 3) carrying out abnormal data detection based on kernel density estimation on the next collected data by using the initial model, and uploading the abnormal data detection result to a central server;
step 4) if the time reaches the detection period of 5 minutes, evaluating the change degree of the probability density model, and if the time exceeds a change threshold value, uploading a change detection result to a central server; otherwise, repeating the step 3);
step 5) waiting for a notice from the central server after uploading, if the central server issues an update notice, saving the new model, and returning to the step 3); otherwise, continuing to use the original model and returning to the step 3).
In this embodiment, the specific working steps of the central server are as follows:
step 1) receiving and storing initial data uploaded from various fog devices;
step 2), when the data volume reaches a preset requirement, solving an initial nuclear density model, otherwise, repeating the step 1);
step 3), the model is issued to each fog device, and an updating request and a detection result from the fog device are waited;
step 4) collecting detection results of the fog devices, counting the number of the fog devices with obviously changed probability density, starting a kernel density model updating step if the number exceeds 50%, and entering step 5), otherwise, informing each fog device to continue using the original kernel density model;
and 5) recalculating the nuclear density model by using the initial data and the normal data returned by the fog equipment, taking the nuclear density model as an updated new model, and returning to the step 3.
Further, the above examples were subjected to effect verification, and the results shown in fig. 3 were obtained. As can be seen from FIG. 3, the vehicle networking abnormal data detection algorithm based on the fog operation structure provided by the invention can obtain a relatively good detection effect in practice, and the detection accuracy is about 87%. And with the increase of the proportion of error data, the detection accuracy rate is only reduced a little, and relatively stable detection performance is reflected.
The above are preferred embodiments of the present invention, and all changes made according to the technical scheme of the present invention that produce functional effects do not exceed the scope of the technical scheme of the present invention belong to the protection scope of the present invention.
Claims (10)
1. The utility model provides a car networking abnormal data detecting system based on fog operation structure which characterized in that includes: the system comprises a data sensing unit, a fog operation unit and a central server unit;
the data sensing unit comprises a data acquisition module which is arranged at the mobile terminal of the driver and is used for acquiring traffic data;
the fog operation unit comprises a mobile terminal loaded with a nuclear density model issued by the central server unit, and the mobile terminal performs abnormal data detection on the traffic data through the nuclear density model and feeds back an abnormal data detection result to the central server unit; the mobile terminal periodically detects the effectiveness of the nuclear density model and feeds back a model detection result to the central server unit;
and the central server unit receives the abnormal data detection result and the model detection result uploaded by the fog operation unit, performs model updating operation according to the model detection result, and sends the updated model to the fog operation unit.
2. A fog operation structure-based abnormal data detection method for the Internet of vehicles is characterized by comprising a model initialization stage, an abnormal data detection stage and a model updating stage;
the initialization stage of the model: taking traffic data acquired by a data sensing unit in the driving process of a vehicle as initialization data; when the acquired initialization data reach the preset data volume, the acquired initialization data are uploaded to a central server unit through a fog operation unit; the central server unit acquires an initial nuclear density model according to the uploaded initialization data and sends the initial nuclear density model to the fog operation unit;
the abnormal data detection stage comprises: after the fog operation unit acquires the initial nuclear density model, the solution confidence coefficient operation is carried out on the traffic data subsequently acquired by the data sensing unit according to the initial nuclear density model, whether the traffic data is abnormal data or not is detected, and the abnormal data detection result is uploaded to the central server unit to be stored;
the model updating stage comprises the following steps: when the central server unit receives the abnormal data detection result uploaded by the fog operation unit, counting the number of terminals corresponding to the fog element operation unit which uploads the abnormal data detection result; if the number of the terminals does not exceed the preset proportion of the total number, the initial kernel density model is not updated; otherwise, updating the initial nuclear density model; and the central server unit acquires a new nuclear density model through the collected normal data, and sends the new nuclear density model as an adjustment result to the fog operation unit for abnormal data detection in the next abnormal data detection stage.
3. The Internet of vehicles abnormal data detection method based on the fog operation structure as claimed in claim 2, wherein the fog operation unit comprises a handheld smart phone and a tablet computer; the data sensing unit comprises a speed sensor, an acceleration sensor, a three-axis acceleration sensor and a GPS which are arranged on the fog computing unit.
4. The method for detecting abnormal data of the internet of vehicles based on the fog operation structure as claimed in claim 2, wherein in the model initialization phase, the central server unit obtains the initial kernel density model according to the uploaded initialization data in the following manner
Wherein the content of the first and second substances,n is sample capacity, h is window width, K (-) is kernel function, X i And taking the value of the ith sample.
5. The Internet of vehicles abnormal data detection method based on fog operation structure as claimed in claim 4, wherein the kernel function adopts Gaussian kernel function:
wherein u is an independent variable.
6. The method for detecting the abnormal data of the internet of vehicles based on the fog operation structure as claimed in claim 2, wherein in the abnormal data detection stage, the operation of solving the confidence r (x) is performed by:
wherein f (x) is a preset probability density model, alpha is a confidence probability, and data with the confidence degree smaller than 0 is judged as abnormal data.
7. The method for detecting the abnormal data of the Internet of vehicles based on the fog operation structure as claimed in claim 2, wherein in the abnormal data detection stage, every preset period, the fog operation unit evaluates the variation degree of the data probability density of the collected traffic data and judges the effectiveness of the original probability density model; and if the change degree exceeds a preset threshold value, uploading the result to the central service unit, and performing model updating operation through the central service unit.
8. The Internet of vehicles abnormal data detection method based on fog operation structure as claimed in claim 6,
evaluating a degree of change in a data probability density of the collected traffic data by:
therein, Ψ JS The standard JS-scatter values were evaluated for the degree of change; p is a radical of i And q is i Probability density models corresponding to two adjacent periods before and after are respectively provided, and omega is a value set of the traffic data x.
9. The method for detecting the abnormal data of the Internet of vehicles based on the fog operation structure as claimed in claim 7, wherein the preset period is 5min, and the preset threshold is 0.5.
10. The method for detecting abnormal data of the internet of vehicles based on the fog operation structure as claimed in claim 2, wherein the preset proportion of the total number is 50% in the model updating stage.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711347035.2A CN108055154B (en) | 2017-12-15 | 2017-12-15 | Car networking abnormal data detecting system based on fog operation structure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711347035.2A CN108055154B (en) | 2017-12-15 | 2017-12-15 | Car networking abnormal data detecting system based on fog operation structure |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108055154A true CN108055154A (en) | 2018-05-18 |
| CN108055154B CN108055154B (en) | 2020-11-03 |
Family
ID=62132474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711347035.2A Active CN108055154B (en) | 2017-12-15 | 2017-12-15 | Car networking abnormal data detecting system based on fog operation structure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108055154B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109347834A (en) * | 2018-10-24 | 2019-02-15 | 广东工业大学 | Detection method, device and the equipment of abnormal data in Internet of Things edge calculations environment |
| CN110599620A (en) * | 2019-07-26 | 2019-12-20 | 广州亚美信息科技有限公司 | Data processing method and device, computer equipment and readable storage medium |
| US20210390795A1 (en) * | 2020-06-10 | 2021-12-16 | Hitachi, Ltd. | Distributed System |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103916896A (en) * | 2014-03-26 | 2014-07-09 | 浙江农林大学 | Anomaly detection method based on multi-dimensional Epanechnikov kernel density estimation |
| CN107018031A (en) * | 2017-06-07 | 2017-08-04 | 济南浪潮高新科技投资发展有限公司 | A kind of car networking fast Optimization calculated based on mist |
| CN107071033A (en) * | 2017-04-20 | 2017-08-18 | 济南浪潮高新科技投资发展有限公司 | A kind of car networking deployment system calculated based on mist |
-
2017
- 2017-12-15 CN CN201711347035.2A patent/CN108055154B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103916896A (en) * | 2014-03-26 | 2014-07-09 | 浙江农林大学 | Anomaly detection method based on multi-dimensional Epanechnikov kernel density estimation |
| CN107071033A (en) * | 2017-04-20 | 2017-08-18 | 济南浪潮高新科技投资发展有限公司 | A kind of car networking deployment system calculated based on mist |
| CN107018031A (en) * | 2017-06-07 | 2017-08-04 | 济南浪潮高新科技投资发展有限公司 | A kind of car networking fast Optimization calculated based on mist |
Non-Patent Citations (2)
| Title |
|---|
| XU YIWEN: "A New Outlier Detection Algorithm Based on Kernel Density Estimation for ITS", 《2016 IEEE INTERNATIONAL CONFERENCE ON INTERNET OF THINGS (ITHINGS) AND IEEE GREEN COMPUTING AND COMMUNICATIONS (GREENCOM) AND IEEE CYBER, PHYSICAL AND SOCIAL COMPUTING (CPSCOM) AND IEEE SMART DATA (SMARTDATA)》 * |
| 徐艺文: "面向群智感知车联网的异常数据检测方法", 《湖南大学学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109347834A (en) * | 2018-10-24 | 2019-02-15 | 广东工业大学 | Detection method, device and the equipment of abnormal data in Internet of Things edge calculations environment |
| CN109347834B (en) * | 2018-10-24 | 2021-03-16 | 广东工业大学 | Method, device and equipment for detecting abnormal data in Internet of things edge computing environment |
| CN110599620A (en) * | 2019-07-26 | 2019-12-20 | 广州亚美信息科技有限公司 | Data processing method and device, computer equipment and readable storage medium |
| CN110599620B (en) * | 2019-07-26 | 2021-12-24 | 广州亚美信息科技有限公司 | Data processing method and device, computer equipment and readable storage medium |
| US20210390795A1 (en) * | 2020-06-10 | 2021-12-16 | Hitachi, Ltd. | Distributed System |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108055154B (en) | 2020-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111452619B (en) | Online energy consumption prediction method and system for electric vehicle | |
| CN107818411B (en) | Bus dynamic scheduling system and method based on WiFi detection and GPS positioning | |
| CN108055154B (en) | Car networking abnormal data detecting system based on fog operation structure | |
| CN109697854B (en) | Multi-dimensional urban road traffic state evaluation method | |
| CN109767619B (en) | Intelligent networking pure electric vehicle running condition prediction method | |
| CN113335131B (en) | Vehicle endurance mileage prediction method, device, equipment and storage medium | |
| CN111882867A (en) | City wisdom traffic early warning system based on thing networking | |
| CN102944848A (en) | Real-time evaluation method for remaining capacity of power batteries and device thereof | |
| CN111948541A (en) | Vehicle battery overvoltage prediction method and device, server and storage medium | |
| CN112986492A (en) | Method and device for establishing gas concentration prediction model | |
| CN115396981B (en) | Intelligent monitoring system based on big data technology | |
| CN111210537A (en) | Oil consumption analysis method, device, equipment and storage medium | |
| CN103761870A (en) | System for counting bus loads | |
| CN105489010B (en) | A kind of through street journey time reliability monitoring analysis system and method | |
| Hung et al. | Model-driven traffic data acquisition in vehicular sensor networks | |
| CN110516923B (en) | Internet of vehicles information comprehensive evaluation method | |
| CN109677324B (en) | Parking vehicle collision alarm method based on NB-IoT technology | |
| CN111461094A (en) | Fake-licensed vehicle identification method and device based on monitoring video and computer equipment | |
| CN107466011A (en) | A kind of vehicle electronic device communication means | |
| CN111695735A (en) | Railway bow net real-time early warning method, system and device based on flow calculation | |
| Liu et al. | Pova: Traffic light sensing with probe vehicles | |
| CN202757625U (en) | Vehicle mile feedback device with vehicular satellite receiving terminal | |
| JP6551999B2 (en) | Device, program and method for estimating moving object of user | |
| CN107103756A (en) | Congestion in road degree judgment means and method based on the public transport operation time | |
| CN106740134A (en) | A kind of electric quantity of batteries of electric vehicle management system and its management method |
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 |