CN113743488B - Vehicle monitoring method, device, equipment and storage medium based on parallel Internet of vehicles - Google Patents
Vehicle monitoring method, device, equipment and storage medium based on parallel Internet of vehicles Download PDFInfo
- Publication number
- CN113743488B CN113743488B CN202110976867.0A CN202110976867A CN113743488B CN 113743488 B CN113743488 B CN 113743488B CN 202110976867 A CN202110976867 A CN 202110976867A CN 113743488 B CN113743488 B CN 113743488B
- Authority
- CN
- China
- Prior art keywords
- vehicle
- vehicle monitoring
- tabu
- monitoring information
- preset
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 202
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 41
- 238000000605 extraction Methods 0.000 claims abstract description 41
- 230000006870 function Effects 0.000 claims description 27
- 238000004364 calculation method Methods 0.000 claims description 17
- 238000012545 processing Methods 0.000 claims description 13
- 238000012806 monitoring device Methods 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 230000006855 networking Effects 0.000 claims description 4
- 238000012958 reprocessing Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 description 8
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/10—Detection; Monitoring
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a vehicle monitoring method, device, equipment and storage medium based on parallel internet of vehicles, wherein the method comprises the following steps: acquiring the total quantity of vehicle monitoring samples, and calculating the extraction probability of the vehicle monitoring samples according to the total quantity of the vehicle monitoring samples; based on the vehicle monitoring information sample extraction probability, calculating to obtain vehicle monitoring information by using an Adaboost algorithm; acquiring a vehicle position sample set based on the vehicle monitoring information; and optimizing a Monte Carlo positioning algorithm by utilizing a tabu search strategy, and calculating the vehicle position sample set to obtain vehicle positioning monitoring information. Through the technical scheme of the embodiment, the accuracy of vehicle monitoring can be improved, and errors existing in vehicle monitoring can be well reduced.
Description
Technical Field
The invention relates to the field of vehicle monitoring, in particular to a vehicle monitoring method, device and equipment based on parallel internet of vehicles and a storage medium.
Background
Modern transportation is developed in an intelligent direction, and an intelligent management system for comprehensively and accurately monitoring traffic conditions is built by combining high-tech intelligent technologies such as artificial intelligence, electronic sensing, data communication and computer processing. The system plays a positive role in reducing urban traffic environmental pollution, improving traffic running efficiency, improving resident life quality and the like. Along with the wide application of intelligent traffic systems, the internet of vehicles technology for effectively grasping the transportation condition of vehicles has been developed. The internet of things is a technical foundation of the internet of vehicles, the internet of vehicles uses individual vehicles as sources of internet of vehicles information, the technologies of vehicle mobile internet, inter-vehicle network and the like are jointly used, a traffic communication protocol and a data exchange protocol are preset, an information sharing mode among vehicles, roads and vehicles and the internet of vehicles is realized, a target vehicle is systematically managed, and transportation efficiency is optimized.
Parallel intelligence of car networking can be realized based on ACP, and the concrete mode is: first,: designing a software-defined artificial system (A), constructing artificial objects, artificial flows and artificial relations for different elements of the system, and fusing the learning, programming and other capabilities of the system to facilitate the recombination of system resources and structures; secondly, the data of the manual system are running data actually generated by the Internet of vehicles, a calculation experiment (C) is carried out according to the running data, the calculation experiment is unfolded in a game form, a large-scale data calculation result is obtained by synthesizing small-scale data, and the best execution plans in different occasions and situations are obtained after the calculation result is comprehensively evaluated; and finally, implementing an optimal plan by taking the manual system as a carrier through parallel execution (P), enabling the occurrence condition of the actual system to approach to the condition of the manual system, integrating the data of the actual system and the data of the manual system, and realizing the decision optimizing and parallel coordination of the Internet of vehicles system through interaction of the actual system and the manual system. However, the existing internet of vehicles system has a certain error in monitoring the vehicle, and cannot accurately monitor the vehicle.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems existing in the prior art.
Therefore, the vehicle monitoring method based on the parallel Internet of vehicles can improve the accuracy of vehicle monitoring and well reduce errors existing in vehicle monitoring.
The invention further provides a vehicle monitoring device based on the parallel Internet of vehicles, which is applied to the vehicle monitoring method based on the parallel Internet of vehicles.
The invention further provides vehicle monitoring equipment based on the parallel Internet of vehicles, which applies the vehicle monitoring method based on the parallel Internet of vehicles.
The invention also provides a computer readable storage medium applying the vehicle monitoring method based on the parallel Internet of vehicles.
According to an embodiment of the first aspect of the invention, a vehicle monitoring method for parallel internet of vehicles comprises the following steps:
acquiring the total quantity of vehicle monitoring samples, and calculating the extraction probability of the vehicle monitoring samples according to the total quantity of the vehicle monitoring samples;
based on the vehicle monitoring information sample extraction probability, calculating to obtain vehicle monitoring information by using an Adaboost algorithm;
acquiring a vehicle position sample set based on the vehicle monitoring information;
and optimizing a Monte Carlo positioning algorithm by utilizing a tabu search strategy, and calculating the vehicle position sample set to obtain vehicle positioning monitoring information.
The vehicle monitoring method of the parallel Internet of vehicles, provided by the embodiment of the invention, has at least the following beneficial effects: firstly, acquiring the total quantity of vehicle monitoring samples, and calculating to obtain the extraction probability of the vehicle monitoring samples according to the total quantity of the vehicle monitoring samples; then, based on the extraction probability of the vehicle monitoring information sample, the vehicle monitoring information can be calculated by using an Adaboost algorithm, a data base is provided for the subsequent vehicle transportation positioning monitoring, and the vehicle preliminary monitoring is realized; then, based on vehicle monitoring information, obtaining a vehicle position sample set, and finally, optimizing a Monte Carlo positioning algorithm by utilizing a tabu search strategy to calculate the vehicle position sample set, so as to obtain vehicle positioning monitoring information; the Monte Carlo positioning algorithm is optimized, a tabu search strategy is introduced in filtering and relieving, the Monte Carlo algorithm is effectively prevented from falling into a local extremum, more excellent elements are expanded, the optimized value is prevented from being omitted, the accuracy of the positioning algorithm is improved, the accuracy of vehicle monitoring is improved, and errors existing in the vehicle monitoring are well reduced.
According to some embodiments of the invention, the calculating the vehicle monitoring information by using Adaboost algorithm based on the probability of extracting the vehicle monitoring information sample includes:
based on the vehicle monitoring information sample extraction probability, processing the obtained vehicle monitoring data and calculating a minimum error value of a classifier;
comparing the minimum error value of the classifier with a preset threshold value;
if the minimum error value of the classifier is smaller than the preset threshold value, reprocessing the obtained vehicle monitoring data; if the minimum error value of the classifier is not smaller than the preset threshold value, calculating to obtain a vehicle information weight;
calculating to obtain a total probability value of a vehicle monitoring extraction sample and an initial classifier weighted sum based on the vehicle information weight;
and obtaining the vehicle monitoring information based on the weighted sum of the initial classifiers.
According to some embodiments of the present invention, the calculating the vehicle position sample set by using a tabu search strategy to optimize a monte carlo positioning algorithm to obtain vehicle positioning monitoring information includes:
taking the elements of the vehicle position sample set as initial solutions and defining a tabu table as empty;
calculating a field element set corresponding to the vehicle position sample set by using a field function based on the vehicle position sample set;
judging and comparing the field element set with a preset element privilege standard;
if the field element set accords with the preset element privilege standard, outputting the corresponding field element set as an optimized element value; if the field element set does not accord with the preset element privilege standard, taking the element with the largest weight in the corresponding field element set as a new tabu element;
judging and comparing the tabu element with a preset termination standard;
if the tabu element accords with the preset termination standard, outputting the tabu element as the optimized element value; if the tabu element does not accord with the preset termination standard, re-using the domain function to calculate a new domain element set until the domain element set accords with the preset element special privilege standard or the tabu element accords with the preset termination standard;
and calculating the vehicle positioning monitoring information by using a standardized importance sampling function based on the optimized element value.
According to some embodiments of the invention, if the minimum error value of the classifier is not less than the preset threshold value, a vehicle information weight is calculated, where a calculation formula for calculating the vehicle information weight may be expressed as follows:
α 1 ＝log[(1-ε)/ε]
wherein epsilon is the minimum error value of the classifier, alpha 1 Is the weight of the vehicle information.
According to a second aspect of the present invention, a vehicle monitoring device based on parallel internet of vehicles includes:
the first unit is used for acquiring the total quantity of the vehicle monitoring samples and calculating the extraction probability of the vehicle monitoring samples according to the total quantity of the vehicle monitoring samples;
the second unit is used for extracting probability based on the vehicle monitoring information sample and calculating to obtain vehicle monitoring information by using an Adaboost algorithm;
a third unit for acquiring a vehicle position sample set based on the vehicle monitoring information;
and the fourth unit is used for optimizing the Monte Carlo positioning algorithm by utilizing the tabu search strategy to calculate and process the vehicle position sample set so as to obtain vehicle positioning monitoring information.
According to some embodiments of the invention, the second unit comprises:
a fifth unit for processing the obtained vehicle monitoring data and calculating a classifier minimum error value based on the vehicle monitoring information sample extraction probability;
a sixth unit, configured to compare the minimum error value of the classifier with a preset threshold;
a seventh unit, configured to reprocess the obtained vehicle monitoring data if the minimum error value of the classifier is smaller than the preset threshold; if the minimum error value of the classifier is not smaller than the preset threshold value, calculating to obtain a vehicle information weight;
an eighth unit, configured to calculate, based on the vehicle information weight, a total probability value of the vehicle monitoring extraction sample and a weighted sum of the initial classifier;
and a ninth unit, configured to obtain the vehicle monitoring information based on the weighted sum of the initial classifiers.
According to some embodiments of the invention, the fourth unit comprises:
a tenth unit configured to take an element of the vehicle position sample set as an initial solution and define a tabu table as empty;
an eleventh unit configured to calculate, based on the vehicle position sample set, a field element set corresponding to the vehicle position sample set using a field function;
a twelfth unit, configured to judge and compare the domain element set with a preset element privilege standard;
a thirteenth unit, configured to output, if the domain element set meets the preset element privilege standard, the corresponding domain element set as an optimized element value; if the field element set does not accord with the preset element privilege standard, taking the element with the largest weight in the corresponding field element set as a new tabu element;
a fourteenth unit, configured to judge and compare the tabu element with a preset termination criterion;
a fifteenth unit, configured to output the tabu element as the optimized element value if the tabu element meets the preset termination criterion; if the tabu element does not accord with the preset termination standard, re-using the domain function to calculate a new domain element set until the domain element set accords with the preset element special privilege standard or the tabu element accords with the preset termination standard;
and a sixteenth unit for calculating the vehicle positioning monitoring information by using a standardized importance sampling function based on the optimized element value.
According to some embodiments of the invention, if the minimum error value of the classifier is not less than the preset threshold value, a vehicle information weight is calculated, where a calculation formula for calculating the vehicle information weight may be expressed as follows:
α 1 ＝log[(1-ε)/ε]
wherein epsilon is the minimum error value of the classifier, alpha 1 Is the weight of the vehicle information.
According to an embodiment of the third aspect of the invention, the vehicle monitoring device based on parallel driving networking comprises: the system comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the vehicle monitoring method based on the parallel internet of vehicles when executing the computer program.
A computer-readable storage medium according to an embodiment of the fourth aspect of the present invention stores computer-executable instructions that, when executed by a control processor, implement the parallel internet of vehicles-based vehicle monitoring method as described above.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and may be better understood from the following description of embodiments taken in conjunction with the accompanying drawings in which:
FIG. 1 is a flow chart of a vehicle monitoring method based on parallel Internet of vehicles according to an embodiment of the present invention;
FIG. 2 is a flow chart of acquiring vehicle monitoring information according to a vehicle monitoring method based on parallel Internet of vehicles according to an embodiment of the present invention;
FIG. 3 is a flowchart of a method for acquiring vehicle positioning monitoring information according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a vehicle monitoring device based on parallel internet of vehicles according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a vehicle monitoring device based on parallel internet of vehicles according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative only and are not to be construed as limiting the invention.
In the description of the present invention, it should be understood that references to orientation descriptions such as upper, lower, front, rear, left, right, etc. are based on the orientation or positional relationship shown in the drawings, are merely for convenience of description of the present invention and to simplify the description, and do not indicate or imply that the apparatus or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention.
In the description of the present invention, a number means one or more, a number means two or more, and greater than, less than, exceeding, etc. are understood to not include the present number, and above, below, within, etc. are understood to include the present number. The description of the first and second is for the purpose of distinguishing between technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless explicitly defined otherwise, terms such as arrangement, installation, connection, etc. should be construed broadly and the specific meaning of the terms in the present invention can be reasonably determined by a person skilled in the art in combination with the specific contents of the technical scheme.
Referring to fig. 1, an embodiment according to the first aspect of the present invention provides a vehicle monitoring method based on parallel internet of vehicles, including but not limited to step S100, step S200, step S300 and step S400.
Step S100, acquiring the total quantity of vehicle monitoring samples, and calculating the extraction probability of the vehicle monitoring samples according to the total quantity of the vehicle monitoring samples;
step S200, based on the vehicle monitoring information sample extraction probability, calculating to obtain vehicle monitoring information by using an Adaboost algorithm;
step S300, acquiring a vehicle position sample set based on the vehicle monitoring information;
and step S400, calculating the vehicle position sample set by utilizing a tabu search strategy optimization Monte Carlo positioning algorithm to obtain vehicle positioning monitoring information.
In an embodiment, the embodiment of the invention firstly obtains the total quantity of the vehicle monitoring sample, and calculates the extraction probability of the vehicle monitoring sample according to the total quantity of the vehicle monitoring sample; then, based on the extraction probability of the vehicle monitoring information sample, the vehicle monitoring information can be calculated by using an Adaboost algorithm, a data base is provided for the subsequent vehicle transportation positioning monitoring, and the vehicle preliminary monitoring is realized; then, based on vehicle monitoring information, obtaining a vehicle position sample set, and finally, optimizing a Monte Carlo positioning algorithm by utilizing a tabu search strategy to calculate the vehicle position sample set, so as to obtain vehicle positioning monitoring information; the Monte Carlo positioning algorithm is optimized, a tabu search strategy is introduced in filtering and relieving, the Monte Carlo algorithm is effectively prevented from falling into a local extremum, more excellent elements are expanded, the optimized value is prevented from being omitted, the accuracy of the positioning algorithm is improved, the accuracy of vehicle monitoring is improved, and errors existing in the vehicle monitoring are well reduced.
The internet of things has the property of internet of things and is a comprehensive and typical network structure. The Internet of vehicles comprises three key layers of a vehicle-mounted end, a communication layer and a cloud management layer: the main functions of the vehicle-mounted terminal are to collect traffic perception information and provide data for other layers; valuable vehicle transportation information is transmitted through the communication layer; the analysis, operation and model construction of the vehicle transportation data are completed by the cloud pipe layer, and the vehicle transportation data are background supports of the vehicle-mounted end.
It should be noted that the Adaboost algorithm, which is collectively referred to as adaptive Boosting (Adaptive Boosting), is a classifier that constructs a strong classifier from a linear combination of weak classifiers. The performance of weak classifiers is not too good and only needs to be stronger than random guesses by which a very accurate strong classifier can be constructed.
When the positioning information of the large logistics transportation vehicle is filtered based on a Monte Carlo (MCL) positioning algorithm, the iteration times are high, the solution is easy to fall into a local optimal solution, and the possibility solution cannot be searched comprehensively. Therefore, a tabu search strategy (TS) is adopted to optimize a Monte Carlo positioning algorithm, and a TS-MCL vehicle positioning monitoring algorithm is obtained; the tabu search strategy optimized filtering can reduce the data iteration times, a new positioning path is opened up based on the temporarily locked local extremum, the vehicle monitoring and positioning monitoring efficiency is effectively improved, and the positioning accuracy is optimized. The TS-MCL vehicle positioning monitoring algorithm is a Monte Carlo positioning algorithm optimized by a tabu search strategy. The Monte Carlo positioning algorithm is optimized by the Monte Carlo positioning algorithm optimized by the tabu search strategy, the tabu search strategy is introduced in filtering alleviation, the Monte Carlo algorithm is effectively prevented from being trapped in a local extremum, more excellent elements are expanded, optimized values are avoided from being omitted, and the accuracy of the positioning algorithm is improved.
Referring to fig. 2, the acquiring of the vehicle monitoring information in step S200 includes, but is not limited to, step S210, step S220, step S230, step S240, and step S250.
Step S210, based on the vehicle monitoring information sample extraction probability, processing the obtained vehicle monitoring data and calculating a minimum error value of the classifier;
step S220, comparing the minimum error value of the classifier with a preset threshold value;
step S230, if the minimum error value of the classifier is smaller than a preset threshold value, reprocessing the obtained vehicle monitoring data; if the minimum error value of the classifier is not smaller than the preset threshold value, calculating to obtain a vehicle information weight;
step S240, calculating and obtaining a total probability value of a vehicle monitoring extraction sample and an initial classifier weighted sum based on the vehicle information weight;
step S250, obtaining vehicle monitoring information based on the weighted sum of the initial classifiers.
The method comprises the steps of processing acquired vehicle monitoring data and calculating a minimum error value of a classifier based on the extraction probability of a vehicle monitoring information sample; comparing the minimum error value of the classifier with a preset threshold value; if the minimum error value of the classifier is smaller than a preset threshold value, reprocessing the obtained vehicle monitoring data; if the minimum error value of the classifier is not smaller than the preset threshold value, calculating to obtain a vehicle information weight; then, based on the weight of the vehicle information, calculating to obtain a total probability value of the vehicle monitoring extraction sample and an initial classifier weighted sum; and finally, obtaining the vehicle monitoring information based on the weighted sum of the initial classifiers.
Notably, an exemplary scenario for acquiring vehicle monitoring information may be as follows:
training set based on Adaboost extraction algorithm is composed of uniformly distributed parallel Internet of vehicles data subsets, definition B t (i) The training failure sample distribution weight is the probability of training the ith vehicle monitoring sample in the sample, and the probability of training is increased by the vehicle monitoring data; continuously learning in the process of extracting the vehicle monitoring information, iterating the vehicle monitoring information, and then obtaining a weak base classifier by using h 1 ,h 2 ,…,h t The representation, wherein, the weight of the vehicle information is alpha 1 Indicating that its size is h 1 The magnitude of the vehicle information weight depends on the effect of the classifier. The original primary classifier is weighted to obtain the data finally used for vehicle information positioning, data extraction is realized, and the method comprises the following steps of:
the formula describing the initial classifier weights is as follows:
B 1 (i)＝1/M i＝1,2,…,M
wherein B is 1 (i) The probability is the vehicle monitoring information sample extraction probability, and M is the total vehicle monitoring information sample amount. The formula for processing the vehicle monitoring data is as follows:
B 1 (i)＝t/T t＝1,2,…,T
wherein T and T are the number of the vehicle monitoring information and the total amount of the monitoring information respectively.
When the vehicle data iterates, a classifier h with the smallest error is obtained 1 Definition of y i ＝h 1 (x i ) The following formula exists:
where ε is the classifier minimum error, y i And x i Classification data and vehicle monitoring information features, respectively. Defining epsilon to be less than 0.5, ending the iteration of the vehicle monitoring information when the better data characteristics are obtained, and otherwise, continuing the data iteration.
Description of Primary classifier h 1 The formula of the information weight of (2) is as follows:
α 1 ＝log[(1-ε)/ε]
wherein alpha is 1 The information weight is monitored for the vehicle.
The formula for updating the monitoring information data of the large logistics transportation vehicle to obtain the sample weight is as follows:
B t+1 (i)＝{B 1 (i)exp[-α 1 y 1 h 1 (x)]}/Z t
wherein B is t+1 (i) Is the total probability value of the vehicle monitoring information extraction sample, Z t And monitoring the weight of the information sample for the vehicle. H (x) is a weighted sum of the primary classifiers, and vehicle monitoring information extraction is achieved based on the data.
According to the logistics transportation monitoring demand, the related information in the vehicle driving process is obtained based on the mode, and the preliminary monitoring of the vehicle is completed. In order to prevent the vehicles from being out of connection and enhance the tight connection among logistics vehicles, the positioning information of the vehicles needs to be further acquired, so that the accurate monitoring of the vehicles is realized.
Referring to fig. 3, the acquiring of the vehicle positioning monitoring information in the above-mentioned step S400 includes, but is not limited to, step S410, step S420, step S430, step S440, step S450, step S460 and step S470.
Step S410, taking elements of a vehicle position sample set as initial solutions and defining a tabu table as empty;
step S420, calculating a field element set corresponding to the vehicle position sample set by using a field function based on the vehicle position sample set;
step S430, judging and comparing the domain element set with a preset element privilege standard;
step S440, if the field element set accords with the preset element privilege standard, outputting the corresponding field element set as an optimized element value; if the field element set does not accord with the preset element privilege standard, taking the element with the largest weight in the corresponding field element set as a new tabu element;
step S450, judging and comparing the tabu element with a preset termination standard;
step S460, outputting the tabu element as an optimized element value if the tabu element accords with a preset termination standard; if the tabu element does not accord with the preset termination standard, the domain function is reused to calculate a new domain element set until the domain element set accords with the preset element privilege standard or the tabu element accords with the preset termination standard;
step S470, calculating to obtain the vehicle positioning monitoring information by using the standardized importance sampling function based on the optimized element value.
It should be noted that, based on the tabu search strategy, the position points where the low-probability vehicle is located are obtained through optimized filtering and removed, and the rest samples are the approximate optimal estimated position sample set of the vehicle. The field element set is built according to the field function in the sample set data, the problem of local optimum of vehicle position searching is effectively solved by building the tabu table, and elements with better performance are forbidden and added into the position sample set, so that global optimal positioning of the vehicle is facilitated to be completed.
Notably, an exemplary scenario for obtaining vehicle positioning monitoring information may be as follows:
defining the sampling time as t and the sample set as G t The optimized filtering step based on the tabu search strategy is as follows:
step 1, definitionIs extracted into a vehicle position sample set G t Is marked as a 'best so far' state, defines a tabu table as empty and has a length of 2.
Step 2, obtaining elements only by domain functionElement set of->And the value of j is 1 and 2 respectively. Domain function expression:
wherein N (0, 1) is a normal random number, which means that the mean and variance are 0,1, respectively. When the element in the element tabu list is consistent with the new element, the new element needs to be regenerated until no repeated element exists. As can be seen from the above formula, the element field category corresponding to the large weight and the small weight is small and large, so that the obtained element set has stronger reliability.
Step 3, defining element privilege standardDetermine->If the rule is met, the step 4 is not met, otherwise, the element is adopted to replace the 'best so far' state element, and the step 6 is entered.
Step 4: at the position ofThe contraindication element with the largest weight value is adopted to replace the previous contraindication element.
Step 5: step 6 is performed when the element meets the termination criteria of the following formula, whereas step 2 is performed.
Wherein K (0, 1) is a random number and is uniformly arranged in [0,1 ].
Step 6, when the termination standard of the above formula is met, the element is addedAs an optimized output result; otherwise, the 'best so far' state element is used as an optimized output result. P (g) of t moment, which is the result obtained by tabu search strategy optimizing filtering algorithm t |o t ) Values.
And realizing importance sampling of the position sampling values of the vehicle monitoring nodes based on a standardized importance sampling function pi, fusing and adjusting weights of the independent position sampling values of the vehicle nodes, and completing posterior probability distribution estimation of the possible positions of the vehicle based on the adjusted weights. The process uses the importance function shown below:
π(g t |o 0 ,o 1 ,o 2 ,…,o t ) Andrespectively representing the prediction and update time of the vehicle movement position, p (g) k |g k-1 ) By means of vehicle position prediction, the vehicle position filtering is optimized to obtain p (g t |o t ) Further calculate +.>Normalization of weights based on the above formula>Acquisition->
And calculating the expected position of the vehicle of the sample set by adopting the mode described by the following formula, completing the position estimation of the vehicle and realizing the positioning monitoring of the large logistics transportation vehicle.
Wherein,,and->A desired location of the vehicle for the sample set.
In an embodiment, if the minimum error value of the classifier is not less than the preset threshold, the vehicle information weight is calculated, where the calculation formula for calculating the vehicle information weight may be expressed as follows:
wherein epsilon is the minimum error value of the classifier, alpha 1 Is the weight of the vehicle information.
Referring to fig. 4, there is provided a vehicle monitoring device 1000 based on parallel internet of vehicles according to an embodiment of a second aspect of the present invention, including:
a first unit 1100, configured to obtain a total amount of vehicle monitoring samples, and calculate a vehicle monitoring sample extraction probability according to the total amount of vehicle monitoring samples;
a second unit 1200, configured to calculate, based on the probability of extraction of the vehicle monitoring information sample, the vehicle monitoring information by using an Adaboost algorithm;
a third unit 1300 for acquiring a vehicle location sample set based on the vehicle monitoring information;
and a fourth unit 1400, configured to optimize a monte carlo positioning algorithm by using a tabu search strategy to perform calculation processing on the vehicle position sample set, so as to obtain vehicle positioning monitoring information.
In an embodiment, the second unit 1200 includes:
a fifth unit 1210 for processing the acquired vehicle monitoring data and calculating a classifier minimum error value based on the vehicle monitoring information sample extraction probability;
a sixth unit 1220, configured to compare the minimum error value of the classifier with a preset threshold;
a seventh unit 1230, configured to reprocess the obtained vehicle monitoring data if the minimum error value of the classifier is less than the preset threshold; if the minimum error value of the classifier is not smaller than the preset threshold value, calculating to obtain a vehicle information weight;
an eighth unit 1240, configured to calculate, based on the vehicle information weight, a total probability value of the vehicle monitoring extraction sample and a weighted sum of the initial classifiers;
a ninth unit 1250 for obtaining vehicle monitoring information based on the initial classifier weighted sum.
In one embodiment, the fourth unit 1400 includes:
a tenth unit 1410, configured to use an element of the vehicle position sample set as an initial solution and define a tabu table as empty;
an eleventh unit 1420 for calculating a field element set corresponding to the vehicle position sample set using a field function based on the vehicle position sample set;
a twelfth unit 1430 for comparing the domain element set with a predetermined element privilege standard;
a thirteenth unit 1440, configured to output, if the domain element set meets a preset element privilege standard, the corresponding domain element set as an optimized element value; if the field element set does not accord with the preset element privilege standard, taking the element with the largest weight in the corresponding field element set as a new tabu element;
a fourteenth unit 1450 for comparing the tabu element with a predetermined termination criterion;
fifteenth unit 1460, configured to output a tabu element as an optimized element value if the tabu element meets a preset termination criterion; if the tabu element does not accord with the preset termination standard, the domain function is reused to calculate a new domain element set until the domain element set accords with the preset element privilege standard or the tabu element accords with the preset termination standard;
sixteenth unit 1470 calculates the vehicle positioning monitoring information using the normalized importance sampling function based on the optimized element value.
In an embodiment, if the minimum error value of the classifier is not less than the preset threshold, the vehicle information weight is calculated, where the calculation formula for calculating the vehicle information weight may be expressed as follows:
α 1 ＝log[(1-ε)/ε]
wherein epsilon is the minimum error value of the classifier, alpha 1 Is the weight of the vehicle information.
It should be noted that, since the vehicle monitoring device 1000 based on the parallel internet of vehicles in the present embodiment and the vehicle monitoring method based on the parallel internet of vehicles in the above embodiment are based on the same inventive concept, the corresponding content in the method embodiment is also applicable to the system embodiment, and will not be described in detail herein.
Referring to fig. 5, an embodiment according to a third aspect of the present invention provides a vehicle monitoring device based on parallel internet of vehicles, including: the memory 700, the processor 600 and the computer program stored on the memory 700 and executable on the processor 600, the processor 600 implements the above-described method steps S100 to S400 in fig. 1, method steps S210 to S250 in fig. 2 and method steps S410 to S470 in fig. 3 when executing the computer program.
According to an embodiment of the fourth aspect of the present invention, there is provided a computer-readable storage medium storing computer-executable instructions that when executed by a control processor implement the parallel internet of vehicles-based vehicle monitoring method in the above embodiment. For example, the above-described method steps S100 to S400 in fig. 1, method steps S210 to S250 in fig. 2, and method steps S410 to S470 in fig. 3 are performed.
It should be noted that, since the computer readable storage medium in the present embodiment is based on the same inventive concept as the vehicle monitoring method based on parallel internet of vehicles in the above embodiment, the corresponding content in the method embodiment is also applicable to the system embodiment, and will not be described in detail herein.
Those of ordinary skill in the art will appreciate that all or some of the steps, systems, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically include computer readable instructions, data structures, program modules, or other data in a modulated data signal, such as a carrier wave or other transport mechanism, and may include any information delivery media.
In the description of the present specification, reference to the terms "one embodiment," "some embodiments," "illustrative embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that: many changes, modifications, substitutions and variations may be made to the embodiments without departing from the spirit and principles of the invention, the scope of which is defined by the claims and their equivalents.
Claims (9)
1. A vehicle monitoring method based on parallel internet of vehicles, the method comprising:
acquiring the total quantity of vehicle monitoring samples, and calculating the extraction probability of the vehicle monitoring samples according to the total quantity of the vehicle monitoring samples;
based on the vehicle monitoring information sample extraction probability, calculating to obtain vehicle monitoring information by using an Adaboost algorithm;
acquiring a vehicle position sample set based on the vehicle monitoring information;
optimizing a Monte Carlo positioning algorithm by utilizing a tabu search strategy to calculate the vehicle position sample set so as to obtain vehicle positioning monitoring information;
the method for optimizing the Monte Carlo positioning algorithm by utilizing the tabu search strategy carries out calculation processing on the vehicle position sample set to obtain vehicle positioning monitoring information, and comprises the following steps:
taking the elements of the vehicle position sample set as initial solutions and defining a tabu table as empty;
calculating a field element set corresponding to the vehicle position sample set by using a field function based on the vehicle position sample set;
judging and comparing the field element set with a preset element privilege standard;
if the field element set accords with the preset element privilege standard, outputting the corresponding field element set as an optimized element value; if the field element set does not accord with the preset element privilege standard, taking the element with the largest weight in the corresponding field element set as a new tabu element;
judging and comparing the tabu element with a preset termination standard;
if the tabu element accords with the preset termination standard, outputting the tabu element as the optimized element value; if the tabu element does not accord with the preset termination standard, re-using the domain function to calculate a new domain element set until the domain element set accords with the preset element special privilege standard or the tabu element accords with the preset termination standard;
calculating to obtain the vehicle positioning monitoring information by using a standardized importance sampling function based on the optimized element value;
the calculation formula of the vehicle monitoring sample extraction probability is expressed as follows:
B 1 (i)＝1/M i＝1,2,L,M
B 1 (i) Representing the vehicle monitoring sample extraction probability, M representing the total vehicle monitoring sample amount;
wherein the vehicle monitoring information is determined based on a weighted sum of the primary classifiers; the calculation formula of the weighted sum of the primary classifier is expressed as follows:
B t+1 (i)＝{B 1 (i)exp[-α 1 y 1 h 1 (x)]}/Z t
wherein B is t+1 (i) A probability sum value Z representing the extraction probability of the vehicle monitoring sample t Representing the weight of a sample of vehicle monitoring information, H (x) representing the weighted sum of the primary classifiers, alpha 1 Indicating the weight value of the vehicle monitoring information, h 1 Classifier with minimal representation error, y 1 And x 1 The characteristics of the classified data and the vehicle monitoring information are respectively, and T and T are respectively the quantity of the vehicle monitoring information and the total quantity of the monitoring information.
2. The vehicle monitoring method based on the parallel internet of vehicles according to claim 1, wherein the vehicle monitoring information is calculated by using an Adaboost algorithm based on the probability of extraction of the vehicle monitoring information sample, and comprises:
based on the vehicle monitoring information sample extraction probability, processing the obtained vehicle monitoring data and calculating a minimum error value of a classifier;
comparing the minimum error value of the classifier with a preset threshold value;
if the minimum error value of the classifier is smaller than the preset threshold value, reprocessing the obtained vehicle monitoring data; if the minimum error value of the classifier is not smaller than the preset threshold value, calculating to obtain a vehicle information weight;
calculating to obtain a total probability value of a vehicle monitoring extraction sample and an initial classifier weighted sum based on the vehicle information weight;
and obtaining the vehicle monitoring information based on the weighted sum of the initial classifiers.
3. The vehicle monitoring method based on the parallel internet of vehicles according to claim 2, wherein if the minimum error value of the classifier is not less than the preset threshold value, a vehicle information weight is calculated, and a calculation formula of the vehicle information weight is calculated as follows:
α 1 ＝log[(1-ε)/ε]
wherein epsilon is the minimum error value of the classifier, alpha 1 Is the weight of the vehicle information.
4. Vehicle monitoring device based on parallel car networking, characterized by, include:
the first unit is used for acquiring the total quantity of the vehicle monitoring samples and calculating the extraction probability of the vehicle monitoring samples according to the total quantity of the vehicle monitoring samples;
the second unit is used for extracting probability based on the vehicle monitoring information sample and calculating to obtain vehicle monitoring information by using an Adaboost algorithm;
a third unit for acquiring a vehicle position sample set based on the vehicle monitoring information;
the fourth unit is used for optimizing a Monte Carlo positioning algorithm by utilizing a tabu search strategy to calculate and process the vehicle position sample set so as to obtain vehicle positioning monitoring information;
the method for optimizing the Monte Carlo positioning algorithm by utilizing the tabu search strategy carries out calculation processing on the vehicle position sample set to obtain vehicle positioning monitoring information, and comprises the following steps:
taking the elements of the vehicle position sample set as initial solutions and defining a tabu table as empty;
calculating a field element set corresponding to the vehicle position sample set by using a field function based on the vehicle position sample set;
judging and comparing the field element set with a preset element privilege standard;
if the field element set accords with the preset element privilege standard, outputting the corresponding field element set as an optimized element value; if the field element set does not accord with the preset element privilege standard, taking the element with the largest weight in the corresponding field element set as a new tabu element;
judging and comparing the tabu element with a preset termination standard;
if the tabu element accords with the preset termination standard, outputting the tabu element as the optimized element value; if the tabu element does not accord with the preset termination standard, re-using the domain function to calculate a new domain element set until the domain element set accords with the preset element special privilege standard or the tabu element accords with the preset termination standard;
calculating to obtain the vehicle positioning monitoring information by using a standardized importance sampling function based on the optimized element value;
the calculation formula of the vehicle monitoring sample extraction probability is expressed as follows:
B 1 (i)＝1/M i＝1,2,L,M
B 1 (i) Representing the vehicle monitoring sample extraction probability, M representing the total vehicle monitoring sample amount;
wherein the vehicle monitoring information is determined based on a weighted sum of the primary classifiers; the calculation formula of the weighted sum of the primary classifier is expressed as follows:
B t+1 (i)＝{B 1 (i)exp[-α 1 y 1 h 1 (x)]}/Z t
wherein B is t+1 (i) A probability sum value Z representing the extraction probability of the vehicle monitoring sample t Representing the weight of a sample of vehicle monitoring information, H (x) representing the weighted sum of the primary classifiers, alpha 1 Indicating the weight value of the vehicle monitoring information, h 1 Classifier with minimal representation error, y 1 And x 1 The characteristics of the classified data and the vehicle monitoring information are respectively, and T and T are respectively the quantity of the vehicle monitoring information and the total quantity of the monitoring information.
5. The parallel internet of vehicles-based vehicle monitoring device of claim 4, wherein the second unit comprises:
a fifth unit for processing the obtained vehicle monitoring data and calculating a classifier minimum error value based on the vehicle monitoring information sample extraction probability;
a sixth unit, configured to compare the minimum error value of the classifier with a preset threshold;
a seventh unit, configured to reprocess the obtained vehicle monitoring data if the minimum error value of the classifier is smaller than the preset threshold; if the minimum error value of the classifier is not smaller than the preset threshold value, calculating to obtain a vehicle information weight;
an eighth unit, configured to calculate, based on the vehicle information weight, a total probability value of the vehicle monitoring extraction sample and a weighted sum of the initial classifier;
and a ninth unit, configured to obtain the vehicle monitoring information based on the weighted sum of the initial classifiers.
6. The parallel internet of vehicles-based vehicle monitoring device of claim 4, wherein the fourth unit comprises:
a tenth unit configured to take an element of the vehicle position sample set as an initial solution and define a tabu table as empty;
an eleventh unit configured to calculate, based on the vehicle position sample set, a field element set corresponding to the vehicle position sample set using a field function;
a twelfth unit, configured to judge and compare the domain element set with a preset element privilege standard;
a thirteenth unit, configured to output, if the domain element set meets the preset element privilege standard, the corresponding domain element set as an optimized element value; if the field element set does not accord with the preset element privilege standard, taking the element with the largest weight in the corresponding field element set as a new tabu element;
a fourteenth unit, configured to judge and compare the tabu element with a preset termination criterion;
a fifteenth unit, configured to output the tabu element as the optimized element value if the tabu element meets the preset termination criterion; if the tabu element does not accord with the preset termination standard, re-using the domain function to calculate a new domain element set until the domain element set accords with the preset element special privilege standard or the tabu element accords with the preset termination standard;
and a sixteenth unit for calculating the vehicle positioning monitoring information by using a standardized importance sampling function based on the optimized element value.
7. The vehicle monitoring device based on parallel internet of vehicles according to claim 5, wherein if the minimum error value of the classifier is not less than the preset threshold value, a vehicle information weight is calculated, wherein a calculation formula of the vehicle information weight is calculated as follows:
α 1 ＝log[(1-ε)/ε]
wherein epsilon is the minimum error value of the classifier, alpha 1 Is the weight of the vehicle information.
8. Vehicle monitoring equipment based on parallel car networking, characterized by, include: a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the parallel internet of vehicles-based vehicle monitoring method according to any one of claims 1 to 3 when executing the computer program.
9. A computer-readable storage medium storing computer-executable instructions which, when executed by a control processor, implement the parallel internet of vehicles-based vehicle monitoring method of any one of claims 1 to 3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110976867.0A CN113743488B (en) | 2021-08-24 | 2021-08-24 | Vehicle monitoring method, device, equipment and storage medium based on parallel Internet of vehicles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110976867.0A CN113743488B (en) | 2021-08-24 | 2021-08-24 | Vehicle monitoring method, device, equipment and storage medium based on parallel Internet of vehicles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113743488A CN113743488A (en) | 2021-12-03 |
| CN113743488B true CN113743488B (en) | 2023-09-19 |
Family
ID=78732586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110976867.0A Active CN113743488B (en) | 2021-08-24 | 2021-08-24 | Vehicle monitoring method, device, equipment and storage medium based on parallel Internet of vehicles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113743488B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138987A (en) * | 2015-08-26 | 2015-12-09 | 电子科技大学 | Vehicle detection method based on aggregation channel characteristic and motion estimation |
| CN105631440A (en) * | 2016-02-22 | 2016-06-01 | 清华大学 | Vulnerable road user joint detection method |
| CN110956093A (en) * | 2019-11-08 | 2020-04-03 | 武汉东湖大数据交易中心股份有限公司 | Big data-based model identification method, device, equipment and medium |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7519201B2 (en) * | 2005-10-28 | 2009-04-14 | Honda Motor Co., Ltd. | Detecting humans via their pose |
| US12046040B2 (en) * | 2015-07-17 | 2024-07-23 | Origin Research Wireless, Inc. | Method, apparatus, and system for people counting and recognition based on rhythmic motion monitoring |
-
2021
- 2021-08-24 CN CN202110976867.0A patent/CN113743488B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105138987A (en) * | 2015-08-26 | 2015-12-09 | 电子科技大学 | Vehicle detection method based on aggregation channel characteristic and motion estimation |
| CN105631440A (en) * | 2016-02-22 | 2016-06-01 | 清华大学 | Vulnerable road user joint detection method |
| CN110956093A (en) * | 2019-11-08 | 2020-04-03 | 武汉东湖大数据交易中心股份有限公司 | Big data-based model identification method, device, equipment and medium |
Non-Patent Citations (7)
| Title |
|---|
| A Fast Video Vehicle Detection Approach Based on Improved Adaboost Classifier;Tao Jiang;《 Advances in Swarm Intelligence 》;第10386卷;387–394 * |
| Xiaona Song.The AdaBoost algorithm for vehicle detection based on CNN features.《ICIMCS '15》.2019,1–5. * |
| 交通卡口车辆检测与自动识别技术研究;顾人舒;《中国优秀硕士学位论文全文数据库信息科技辑》(第03期);I138-2169 * |
| 基于快速检测和AdaBoost的车辆检测;何松华;章阳;;计算机工程与设计(第01期);212-216 * |
| 基于禁忌搜索的车联网蒙特卡洛定位算法;孙友伟;王辰寰;张晶;;计算机测量与控制(06);250-253 * |
| 复杂交通监控场景下运动目标检测与跟踪方法研究;薛茹;《中国博士学位论文全文数据库信息科技辑》(第12期);I138-51 * |
| 高速路的车道检测与车辆跟踪;刘金清;陈存弟;;计算机系统应用(第02期);191-201 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113743488A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112862093B (en) | Graphic neural network training method and device | |
| CN110458324B (en) | Method and device for calculating risk probability and computer equipment | |
| CN110555989B (en) | Xgboost algorithm-based traffic prediction method | |
| CN111368887B (en) | Training method of thunderstorm weather prediction model and thunderstorm weather prediction method | |
| CN110794308B (en) | Method and device for predicting train battery capacity | |
| CN111126654A (en) | Shared vehicle ride-back probability and loss probability prediction method and device | |
| CN111626338B (en) | Cloud environment matching method, device, equipment and medium based on fusion classification model | |
| Wang et al. | Fusing heterogeneous traffic data by Kalman filters and Gaussian mixture models | |
| CN108596204B (en) | Improved SCDAE-based semi-supervised modulation mode classification model method | |
| CN113139570A (en) | Dam safety monitoring data completion method based on optimal hybrid valuation | |
| CN117523218A (en) | Label generation, training of image classification model and image classification method and device | |
| CN116311880A (en) | Traffic flow prediction method and equipment based on local-global space-time feature fusion | |
| US11410020B2 (en) | Machine learning models for predicting time in traffic | |
| CN113682302B (en) | Driving state estimation method and device, electronic equipment and storage medium | |
| EP4220495A1 (en) | Task learning system and method, and related device | |
| CN104217296A (en) | Listed company performance comprehensive evaluation method | |
| CN113743488B (en) | Vehicle monitoring method, device, equipment and storage medium based on parallel Internet of vehicles | |
| CN116703682B (en) | Government affair data platform based on deep learning | |
| Huang et al. | Designing importance samplers to simulate machine learning predictors via optimization | |
| CN115691140B (en) | Analysis and prediction method for space-time distribution of automobile charging demand | |
| CN116579789A (en) | Power battery performance analysis-based secondary vehicle estimation method and system | |
| CN112784008A (en) | Case similarity determining method and device, storage medium and terminal | |
| CN116186565A (en) | Automatic driving control method and track searching and index constructing method and device | |
| CN108985526B (en) | Transportation capacity prediction method and device, computer readable storage medium and terminal | |
| CN114595764A (en) | Method and system for acquiring influence degree of urban factors on inland inundation disaster loss |
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 |