102 results about "Extreme gradient boosting" patented technology

The invention discloses a water quality time sequence prediction method of an SSA-VMD-LSTM-XGBoost hybrid model, and belongs to the technical field of water quality monitoring and prediction. Comprising the following steps: (1) data preparation and preprocessing; (2) optimizing the water quality time sequence decomposition of the VMD based on SSA: optimizing a penalty factor and a modal number of the VMD by adopting a sparrow search algorithm (SSA), and decomposing the water quality time sequence into a plurality of sub-components with high stability and low complexity by utilizing the optimized VMD; (3) construction and training of an LSTM-XGBoost hybrid prediction model: constructing a hybrid prediction model fusing long-short term memory (LSTM) and extreme gradient boost (XGBoost), inputting a high-frequency component into the LSTM model, inputting a low-frequency component into the XGBoost model, and finally performing superposition and integration on prediction results of the models; and (4) multi-component prediction result integration and performance verification. According to the method, adaptive optimization of VMD parameters is realized through SSA, the feature extraction and time sequence modeling capability is improved by combining the advantages of LSTM and XGBoost, and the prediction precision and stability of the water quality time sequence are effectively improved.

The invention discloses an airport flight quantity and throughput prediction method and system, and relates to the technical field of intelligent airport management. The method comprises the following steps: firstly, determining a future target time period to be predicted, and obtaining related multi-source data according to the future target time period; preprocessing the data and extracting time sequence and non-time sequence features; processing time sequence features by using the trained long-short-term memory neural network model, processing non-time sequence features by using the extreme gradient boosting tree model, and respectively obtaining prediction results; and integrating the outputs of the two types of models through a weighted fusion strategy to obtain an accurate prediction value of the flight sortie and the single-machine passenger capacity, and further calculating to obtain a passenger throughput prediction result. According to the method and the system provided by the invention, through the architecture of multi-source data fusion and hybrid intelligent model cooperation, the prediction precision and reliability are effectively improved, and scientific decision support is provided for airport operation management.

The invention discloses a risk indicator construction method and system for new energy output prediction, and belongs to the technical field of data processing and power system management, and the method comprises the steps: obtaining the preprocessing data of a plurality of new energy stations, carrying out the spatial-temporal feature analysis, and generating a spatial-temporal feature set; obtaining meteorological prediction data, and performing medium and long term output prediction through an extreme gradient boosting tree based on the space-time feature set; comparing the output prediction result with historical real output data to obtain a prediction error, and performing probability coupling modeling and quantile regression prediction in combination with a meteorological element evolution sequence to generate a dynamic quantile value; and determining a dynamic risk interval, and constructing a graded early warning index. According to the method, probabilistic coupling modeling and quantile regression prediction are adopted, prediction errors are deeply associated with dynamic evolution of meteorological elements, predicted uncertain risks can be quantized and graded, and decision support is provided for optimal scheduling and risk management of a power grid.

The invention provides a loan risk assessment method which can be applied to the technical field of artificial intelligence. The method comprises the steps that under the condition of user authorization, structured data and time series data of a user are acquired, the structured data are identity attributes, financial qualification and loan application information of the user, and the time series data are historical credit behavior data of the user; inputting the structured data into a preset random forest model, and outputting a first predicted value; inputting the structured data into a preset limit gradient lifting model, and outputting a second predicted value; inputting the time sequence data into a preset long-short-term memory network model, and outputting a third predicted value; performing weighted fusion on the first predicted value, the second predicted value and the third predicted value to obtain a combined predicted value; and outputting a final loan risk assessment result according to the joint prediction value. The invention further provides a loan risk assessment device and equipment, a storage medium and a program product.

The present application relates to a kind of carbon emission space refinement simulation and driving mechanism analysis method based on multi-source data and machine learning, including obtaining night light remote sensing, population density data, multi-source data such as interest point density, nonlinear spatial fitting model is constructed and trained by using information entropy weight method to carry out multi-source data fusion and construct economic energy comprehensive index, use city land use classification data as industry space restriction, combined with the total carbon emission of each industry calculated to build carbon emission space simulation base map, based on extreme gradient boosting tree, introduce SHAP framework for post-analysis, from global, local and spatial three scales, the nonlinear driving mechanism of carbon emission of multi-source city form element is analyzed, overcome the over-saturation defect of single night light data in city core area, realize the leap from pure space fitting to mechanism explanation, provide scientific basis and method support for high-density city accurate locking emission hotspot and making low-carbon policy.

The invention discloses a short message classification method and system, and relates to the technical field of artificial intelligence, and the method comprises the steps: carrying out the feature extraction of a short message text, and obtaining a multi-dimensional feature; and inputting the multi-dimensional features into a pre-trained extreme gradient boosting tree model to obtain a probability that the to-be-predicted short message belongs to a specified type, if the importance probability is greater than a preset threshold value, determining that the to-be-predicted short message is an important short message, and if the importance probability is less than the preset threshold value, determining that the to-be-predicted short message is a non-important short message. The problem that the importance of the short messages cannot be efficiently, accurately and automatically classified in the prior art is solved.

The invention provides a method and a device for predicting the effluent concentration of pollutants in a constructed wetland based on machine learning, and the technical key points are as follows: constructing a multi-feature data set by collecting data including environment operation conditions, water quality parameters and wetland conditions of the constructed wetland; an initial constructed wetland water quality prediction model is constructed, and the processed multi-feature data set is trained through four single-output machine learning models of a random forest, gradient lifting, limit gradient lifting and a gradient lifting decision tree; a plurality of indexes are adopted to evaluate the prediction performance of the four single-output machine learning models on the test set, and an optimal single-output model with the optimal comprehensive performance of the indexes is obtained; establishing a multi-target joint prediction model of multi-output regression by using the optimal single-output model, and predicting the water quality index of the effluent of the constructed wetland; and sorting the importance of different target variables which are explained by the multi-target joint prediction model and are influenced by the multi-target joint prediction model through an SHAP method.

The invention relates to the technical field of data processing and engineering project process management, in particular to a full-process intelligent management method and system for bridge and tunnel maintenance engineering. The method comprises the following steps: extracting a disease geometric contour based on bridge and tunnel inner wall three-dimensional point cloud data, and calculating a centroid coordinate, a volume and a surface contour area; constructing a space retrieval sphere by using a target disease centroid, screening an adjacent disease set, and calculating a local aggregation density by combining the volume and the centroid distance; calculating the average depth of the target disease, and deducing the overlapping sharing rate of the working plane; constructing a group topology consumption equivalent through linear analysis; and inputting the extreme gradient lifting model to output an optimal repair material dosage table and a material distribution operation instruction book. According to the method, the disease space distribution and aggregation degree can be accurately evaluated, the construction loss surface overlapping probability and the material sharing potential are scientifically evaluated, the material preparation accuracy is improved, waste and cost are reduced, and the whole-process intelligent management of bridge and tunnel maintenance engineering is realized.

The invention discloses a distribution network line fault trip prediction method and device, a medium and a product, and relates to the field of power distribution network operation and maintenance, and the method comprises the steps: obtaining fault data of a distribution network line; constructing a fault data set; according to the fault data set, constructing a trip prediction model based on an akaike information criterion; an exogenous variable corresponding to the tripping prediction model is determined; constructing a limit gradient lifting model based on a grid search method according to the exogenous variables and the historical fault trip times; constructing a fusion model according to the trip prediction model and the limit gradient lifting model; respectively determining prediction errors of the tripping prediction model and the fusion model, and determining a final prediction model according to the prediction errors; determining the number of fault tripping times of the month to be predicted by using the final prediction model; and regularly obtaining fault data of the distribution network line to regularly update the final prediction model. The monthly fault trip times of the distribution network line can be efficiently predicted, and the operation and maintenance reliability of the distribution network is improved.

The invention discloses a hydropower station peak capability evaluation method under an extreme scene. The method comprises the following steps: automatically classifying hydrological scenes of the hydropower station based on a ten-day runoff drought threshold value and a ten-day runoff flood threshold value of the hydropower station in a kurtosis period; based on the hydrological scene classification result of the hydropower station, simulating the operation process of the hydropower station by using a hydropower guarantee supply absorption operation model, and obtaining the peak duration of the hydropower station so as to construct a training set; and constructing a hydropower station peak capability evaluation model based on an extreme gradient lifting method, training the hydropower station peak capability evaluation model by using the training set to obtain a trained hydropower station peak capability evaluation model, and further obtaining a peak capability evaluation result and a corresponding visual analysis result of the hydropower station in a peak summering period. According to the method, the problem that the peak capacity of the hydropower station in extreme weather cannot be quantitatively evaluated by a traditional method is solved, the conversion from passive response to active pre-judgment is realized, and the scientificity and foresight of a power grid supply guarantee decision are improved.

The application provides a single crystal silicon edge break prediction method based on improved SSA and extreme gradient boosting, and relates to the technical field of data processing. The method comprises the following steps: calculating the difference between the current constant diameter growth stage data of the single crystal silicon to be predicted and the standard constant diameter growth stage data determined according to the weight coefficients formed by clustering the historical constant diameter growth stage data of a plurality of sample single crystal silicon, to obtain current difference constant diameter growth stage data; performing statistical feature extraction on the current difference constant diameter growth stage data to obtain current difference features; inputting the current difference features into a prediction model to obtain the edge break prediction result of the single crystal silicon to be predicted; and the prediction model is obtained by optimizing an extreme gradient boosting model based on the historical difference features and edge break labels of each sample single crystal silicon and an improved sparrow optimization algorithm (SSA). The application realizes efficient and accurate single crystal silicon edge break prediction by reducing the dependence on a mechanism model.

The application discloses a new energy vehicle modeling design method and system, electronic equipment and a storage medium, and belongs to the technical field of vehicle industrial design. The method comprises the following steps: based on an interval 2-type trapezoidal fuzzy Kano model, the weight of the user emotional vocabulary obtained through the evaluation construction diagram is calculated and sorted to identify key emotional needs; based on a limit gradient boosting model optimized by a hippo optimization algorithm, a nonlinear mapping relationship between the key emotional vocabulary and the new energy vehicle form design features is established; the mapping relationship is used to predict and generate an optimal form feature combination with the highest emotional evaluation value; the generated design scheme is comprehensively evaluated subjectively and objectively by combining eye tracking technology and a discrete information data fluctuation weighting method, and a final design scheme is screened out. The method can accurately quantify and sort the subjective and fuzzy emotional needs of users, establish a nonlinear mapping relationship between the emotional needs of users and specific product design features, and improve the efficiency of new energy vehicle modeling design.

Systems and methods for predicting esophageal adenocarcinoma (EAC) and gastric cardia adenocarcinoma (GCA) using machine learning are provided. An example system may obtain an electronic health record (EHR) dataset, identify missing values in the EHR dataset, and generate imputed values for the missing values using simple random sampling imputation. The system may train a model using an extreme gradient boosting algorithm and a training dataset including the EHR dataset to generate a trained model including multiple decision trees. Training the model includes tuning the model to achieve a greatest value of an area under a receiver operating characteristic curve associated with the model. The system may obtain a patient EHR dataset, generate a prediction associated with a risk of EAC and / or GCA by applying the trained model to the patient EHR dataset, and provide the prediction to a computing device to determine a patient treatment protocol.

The invention discloses a tunnel structure earthquake vulnerability evaluation method and device based on multi-model integration and interpretability analysis. The method comprises the following steps: acquiring tunnel parameters, geological conditions and seismic oscillation parameters, and constructing a training database; training is carried out based on various machine learning models such as extreme gradient lifting, random forest, a support vector machine and a neural network, and multiple model outputs are fused by adopting an integrated learning strategy; inputting seismic oscillation characteristics of a tunnel to be evaluated and a target, and outputting damage levels, damage probabilities or seismic vulnerability curves of the tunnel under different seismic intensities; and identifying key influence factors by utilizing feature importance analysis, Shapley additive interpretation or sensitivity analysis, and generating an analysis report containing a prediction result and interpretation information. The method has the advantages of high prediction efficiency, high result interpretability, high robustness and wide application range, and can be widely applied to aseismic design and safety evaluation of tunnels and other underground structures.

The application discloses a kind of dabigatran bleeding risk prediction methods based on machine learning, it is related to computer-aided drug risk management technical field, the method is by obtaining patient baseline and follow-up data, multiple imputation method is handled missing value;With HAS-BLED score as the basis, candidate variables are screened from potential risk factors using LassoCV algorithm, and anemia, insulin use and antifungal agent use are determined as new prediction variables through clinical correlation analysis to construct a set of prediction variables;Finally, a random forest or gradient boosting algorithm is used to train the model to output the bleeding risk assessment results of the individual to be tested.The application combines machine learning algorithm, improves the prediction accuracy of dabigatran bleeding risk in Chinese non-valvular atrial fibrillation patients, solves the problem of insufficient prediction accuracy of traditional HAS-BLED score, and provides a more reliable basis for clinical individualized anticoagulant therapy decision.

The present disclosure relates to an application of gene markers in multi-cancer early detection, a method for constructing an early detection model, and a detection device. In the present disclosure, low-coverage whole-genome sequencing is conducted on cell-free DNAs (cfDNAs) from a plasma sample, and according to high-throughput sequencing results, six differential features of the cfDNA fragments are analyzed for each cancer. Then the training and modeling are conducted with a convolutional neural network to allow the early detection of a plurality of cancers at a low sequencing depth. Then the training and modeling are conducted with a generalized linear model (GLM), a gradient boosting machine, a random forest model, a deep learning model, and an extreme gradient boosting model, and staking is conducted with a GLM to construct a multi-feature algorithm, to allow the tissue-of-origin-based detection of cancers.

The invention belongs to the technical field of environmental engineering, and particularly relates to a rapid prediction method of trichloromethane generation potential in a water disinfection process, and the rapid prediction method of trichloromethane generation potential in the water disinfection process comprises the following steps: obtaining a plurality of organic compounds and trichloromethane generation potential values corresponding to the organic compounds respectively; key molecular characteristic parameters corresponding to each organic compound are obtained; an extreme gradient lifting machine learning algorithm is adopted to construct a trichloromethane generation potential prediction model, and model precision verification is carried out; optimizing by adopting a Bayesian optimization algorithm to obtain a trichloromethane generation potential optimal prediction model; and inputting key molecular characteristic parameters of a target compound into the optimal prediction model to obtain a trichloromethane generation potential value of the target compound. The rapid prediction method provided by the invention realizes rapid and accurate prediction of the TCMFP value of the organic compound, and has the advantages of convenience, rapidness, low cost, convenience in use, high stability and the like.

The invention discloses a rockburst disaster prediction method based on an optimized extreme gradient lifting classification model, and relates to the technical field of environment monitoring, and the method comprises the steps: obtaining multi-shift monitoring data of a coal mine working face, carrying out the preprocessing, dividing the data into a training set and a test set, and taking an initial hyper-parameter extreme gradient lifting classifier as a basic model, and using at least one meta-heuristic optimization algorithm to optimize the hyper-parameters, training and constructing a hybrid prediction model, inputting real-time monitoring data into the hybrid prediction model to carry out rockburst disaster prediction, and outputting a coal mine rock burst disaster risk prediction result. According to the method, the technical problems of low disaster prediction accuracy and dangerous state recall rate and high missing report risk caused by insufficient sensitivity of an existing coal mine rock burst disaster prediction model to unbalanced monitoring data are solved, and the purposes of optimizing an extreme gradient lifting classifier through a meta-heuristic algorithm and improving the prediction accuracy of the coal mine rock burst disaster prediction model are achieved. The disaster prediction accuracy and the dangerous state recall rate are improved, and the missing report risk is reduced.

The invention discloses a mining area vegetation change driving factor and contribution rate fine calculation method, and the method comprises the steps: widely selecting driving factors closely related to vegetation change according to the environment and ecological characteristics of a mining area, and constructing a mining area vegetation change driving factor data set; calculating a Pearson correlation coefficient between each driving factor and the mining area vegetation NDVI through a correlation analysis module, and screening out an optimal driving factor combination which has a remarkable influence on the change of the vegetation NDVI; performing parameter optimization on the limit gradient boosting algorithm XGBoost by adopting a sparrow search algorithm SSA, constructing an SSA-XGBoost model, and training and verifying the SSA-XGBoost model by utilizing an optimal driving factor combination; and performing attribution analysis on the trained SSA-XGBoost model by using an SHAP interpretability analysis module, and quantifying the contribution rate of each driving factor to the vegetation NDVI change. According to the method, the prediction accuracy and the interpretation capability of the model are improved, and the defects of incomplete consideration of driving factor indexes, insufficient nonlinear analysis and weak interpretation capability in an existing research method are overcome.

The application relates to the technical field of power equipment state monitoring and signaling devices, and particularly discloses a cable temperature real-time monitoring and early warning method based on an Internet of Things, which comprises the following steps: deploying temperature sensing nodes with edge computing capabilities at key positions of cables; constructing a dynamic early warning model driven by a mixed frog leap algorithm and coordinated by a resource scheduling engine and an extreme gradient boosting classifier; dynamically adjusting data collection frequency, transmission power and inference depth to balance power consumption and accuracy; uploading early warning information to a cloud platform through a low-power wide-area network; generating a global risk situation map and triggering a three-level early warning mechanism. Through the above technical scheme, the application realizes adaptive, low-power and highly reliable cable temperature monitoring and early thermal fault warning, and improves the intelligent level and emergency response efficiency of power system operation and maintenance.

The embodiment of the invention discloses a learning disorder recognition method and device and electronic equipment, and the method comprises the steps: outputting an interaction interface, and obtaining the learning difficulty degree of a to-be-recognized child in daily life damage, score damage and learning disorder subtype in the interaction interface, and the identity information of the to-be-recognized child; after calculating scores of all the dimensions, inputting the scores and the identity information into a pre-trained target recognition model to obtain an initial judgment result about whether learning obstacles exist or not; when the initial judgment is positive, target user information is judged through subtype truncation values, and classification results of all subtypes are obtained; the target recognition model can be a logistic regression model, a random forest model, a support vector machine or an extreme gradient lifting model. By implementing the application, multi-dimensional information can be automatically collected through the electronic scale, obstacles can be quickly and accurately screened through the machine learning model, subtypes are refined, the evaluation efficiency and objectivity are improved, and the method is suitable for large-scale early intervention of schools and medical institutions.

The invention discloses a rail transit traction power supply system locomotive combination condition identification method and system, and the method comprises the steps: carrying out the dimension reduction processing of first power quality monitoring data of a power supply arm through employing a principal component analysis algorithm, and enabling the features after dimension reduction to retain the main energy and change trend in original data; noise and redundancy characteristics can be effectively suppressed, and a Gaussian mixture model clustering algorithm introducing a time sequence continuity constraint is used for clustering the dimension-reduced first electric energy quality monitoring data, so that the problem of insufficient self-adaptability caused by dependence on fixed power or current threshold division in a traditional method is solved; performing feature extraction on second power quality monitoring data of the power supply side of the traction transformer by using a feature extraction method based on a sliding time window to ensure a better model training effect, and training an extreme gradient boosting tree classification model by using a combined working condition label and a feature vector; therefore, the working condition of the locomotive of the rail transit traction power supply system can be accurately identified in a non-intrusive manner.

The invention discloses an interventional operation risk prediction method based on double-view cross-semantic interaction, and belongs to the crossing field of artificial intelligence and intelligent diagnosis and treatment of cardiovascular diseases. Aiming at the problems of feature redundancy, incomplete single-view modeling, semantic isolation and the like existing in complication prediction in the existing percutaneous coronary intervention treatment process, the method comprises the following specific implementation processes: firstly, screening key clinical features by adopting a two-stage recursive feature elimination-extreme gradient lifting mechanism; secondly, constructing a patient-index double-view module to describe patient similarity and index association; and then, an asymmetric cross-semantic interaction module is provided, the semantic consistency is ensured by designing collaborative reasoning alignment loss, and finally, dynamic information aggregation between nodes is realized. Accurate prediction and traceable attribution of complications in the percutaneous coronary intervention treatment process are achieved, and decision support is provided for early recognition of high-risk patients.

The invention relates to the technical field of wireless communication network optimization, and discloses a wireless signal thermodynamic prediction method and system. According to the method, concentric circular ring sampling points are generated through a recursive growth coefficient based on a path loss logarithmic relationship, and the density of each circular ring sampling point is dynamically adjusted according to a distance attenuation weight function, so that near-field sampling points are dense and far-field sampling points are sparse; building information model data and environment parameter data are obtained, and feature vectors are calculated; training a signal strength prediction model based on a limit gradient boosting tree model; and generating a signal thermodynamic diagram by adopting an inverse distance weighted interpolation algorithm. According to the method, the technical problems of unreasonable sampling point distribution, insufficient model precision and poor scene adaptability of a traditional method are solved.

This invention discloses a method and system for sensory classification and flavor critical threshold extraction of raw tea, belonging to the field of artificial intelligence and machine learning technology. By collecting macroscopic sensory data and microscopic targeted omics data from raw tea samples, the method utilizes a random forest algorithm to assess the feature importance of high-dimensional physicochemical components, selecting a subset of core features and constructing standard radar fingerprint maps for different sensory categories. A multi-classification model is built based on a limit gradient boosting tree, and a SHAP tree interpreter is used to calculate the local marginal contribution value of each core feature to the prediction results. For the target sensory category, a dependency mapping between the concentration of core features and their SHAP contribution values ​​is constructed. By searching for zero-value crossover points, the physical concentration critical threshold triggering specific sensory judgments is extracted in reverse. This invention inversely transforms artificial intelligence prediction results into quantitative flavor component standards that can guide industrial production, providing a scientific basis for the procurement, blending, and flavor standardization management of raw tea for new tea beverages.

The application is a power prediction method based on empirical Fourier decomposition and sample entropy aggregation, belonging to the technical field of power system prediction. The method firstly performs empirical Fourier decomposition on the power time series to obtain multiple oscillation components and residual components; then calculates the sample entropy of each component and aggregates them into a small number of aggregated components according to the entropy value similarity; then trains three types of base models of support vector regression, extreme gradient boosting and long short-term memory network for each aggregated component and residual component in parallel; further, the outputs of each base model are used as stacked features to train a ridge regression meta-model for fusion; finally, the rolling prediction mode is adopted to predict each component, and the final power prediction value is obtained by adding the prediction results of the aggregated components and the residual components. The application is suitable for power system dispatching and transaction decision support.

The invention discloses an unconventional reservoir compressibility evaluation method based on a limit gradient boosting tree model. The method comprises the following steps: step 1, extracting target rock sample data, and taking the target rock sample data and conventional logging data as sample data of a training model in a one-to-one correspondence manner based on depth values; 2, performing data preprocessing on the sample data in the step 1; step 3, training a plurality of rock mineral component prediction models based on sample data by using a limit gradient algorithm, and optimizing and storing the models through evaluation indexes; and 4, predicting newly added production logging data according to the optimized model in the step 3, calculating a brittleness index, and evaluating the stratum compressibility based on the brittleness index. According to the method, the sample data is processed by designing specific data preprocessing processes such as data cleaning, feature enhancement, normalization and dimension reduction processing, and then the prediction model is established based on the processed sample data, so that the accuracy of the prediction model is effectively improved.

The application is suitable for the field of advanced manufacturing and intelligent detection technology, and provides an aluminum alloy resistance spot welding nugget diameter prediction method, which comprises the following steps: collecting multi-source dynamic signals in the aluminum alloy resistance spot welding process and preprocessing to obtain a pure main welding waveform; constructing a physical benchmark model based on a heat transfer equation with an electrode degradation penalty term correction, and outputting a physical benchmark diameter; constructing a residual compensation network based on an extreme gradient boosting algorithm, taking the process features extracted from the pure main welding waveform as input, and predicting the residual between the physical benchmark diameter and the actual nugget diameter; adding the physical benchmark diameter and the residual to obtain the final predicted diameter. Through additive fusion of physical guidance and residual learning, the defects of pure physical model being difficult to adapt to dynamic working conditions and pure data-driven model being prone to overfitting and lacking of interpretability are overcome, and high-precision, strong-generalization and physically interpretable aluminum alloy resistance spot welding nugget diameter online prediction is realized.

The invention discloses a method, a system and equipment for evaluating active corrosion defects of a pipeline and a storage medium. The method comprises the following steps: acquiring multi-dimensional pipeline characteristic data of a pipeline detected by an inner detector; determining a defect type and an activity degree index corresponding to the pipeline based on the multi-dimensional pipeline features and a pre-constructed two-stage series machine learning model; wherein the two-stage series machine learning model comprises a first-stage convolutional neural network model trained based on a sample defect image and a second-stage extreme gradient boosting model trained based on sample multi-dimensional data; and determining a predicted development rate and a predicted residual life corresponding to the pipeline based on the defect type and the activity degree index, and generating an evaluation result of the active corrosion defect of the pipeline based on the predicted development rate and the predicted residual life. And the evaluation accuracy of the pipeline corrosion defect is improved.

The invention provides a vehicle classification system and method based on XGBoost and a multi-target genetic algorithm, and the system comprises a data preprocessing module, a software module and a hardware module. The software module is integrated with a vehicle classification model which takes an extreme gradient boosting XGBoost module as a core classifier and adopts a multi-target genetic algorithm MobGA to carry out parameter optimization and feature subset selection. According to the method, a multi-target genetic algorithm (MobGA) is adopted to carry out joint automatic optimization on hyper-parameters and feature subsets of the XGBoost module. And over-fitting can be effectively avoided, so that the generalization ability and the overall classification accuracy of the model on unknown data are remarkably improved.