Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
1110results about How to "Improve forecasting efficiency" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Attack-oriented network security situation prediction method, device and system
ActiveCN108494810ARealize dynamic associationIn line with the actual environmentData switching networksSecuring communicationCountermeasureAttack graph
The invention belongs to the technical field of network security and particularly relates to an attack-oriented network security situation prediction method, device and system. The method comprises the following steps: detecting and collecting alarm data and network environment operation and maintenance information in a network countermeasure environment, obtaining an element set required by network security situation prediction, wherein the element set comprises three types of information of an attacker, a defense party and a network environment; evaluating the attacker capability and the level of the defense party, establishing a dynamic Bayesian attack graph, and calculating an attack phase number and an attack state occurrence probability vector; and combining a vulnerability scoring standard and network asset information, and performing time-space dimension quantification on the network security situation value. According to the method, dynamic association of the situation elements of the defense party, the attacker, the environment information and the like is achieved, the actual environment of the network is better conformed to, the future situation and the attack occurrencetime can be accurately predicted, higher prediction efficiency is achieved, and storage scale and timeliness of network security situation awareness are optimized, so as to provide more effective guidance for network protection.
Owner:PLA STRATEGIC SUPPORT FORCE INFORMATION ENG UNIV PLA SSF IEU
Automotive exhaust emission data fusion system
ActiveCN106650825ADo not interfere with drivingAvoid harmCharacter and pattern recognitionNeural architecturesDiagnostic systemAir pollutant concentrations
The invention discloses an automotive exhaust emission data fusion system. The automotive exhaust emission data fusion system comprises a roadside air pollutant concentration estimation module, a roadside air pollutant concentration prediction module, a city global atmospheric environment prediction module, an automotive exhaust emission factor estimation module and an automotive exhaust emission feather analysis module, wherein the five modules are used for respectively realizing different data analysis functions, and the different functions can be realized by virtue of the different modules; the modules can be independently used, or two or more modules can be combined for use, so as to realize the storage, analysis and fusion of automotive exhaust telemetering data, automotive attributes, driving working stations, detection time and meteorological condition data; and by combining with a vehicle-mounted diagnosis system database, a portable emission test system database, a vehicle inspection station offline database, a traffic information database and a geographic information database, automotive exhaust telemetering data is analyzed, and the highest discriminatory key indexes and statistical data are acquired, so that effective supports are provided for the formulation of relevant decisions of government departments.
Owner:UNIV OF SCI & TECH OF CHINA
LSTM-RNN model-based air pollutant concentration forecast method
ActiveCN106599520AImprove perceptionTake advantage ofForecastingDesign optimisation/simulationTest sampleModel parameters
The invention relates to an LSTM (Long Short-Term Memory)-RNN model-based air pollutant concentration forecast method. The method comprises the steps of monitoring and collecting air pollutant concentration data in a relatively long time; preprocessing historical data to construct training, verification and test sample data of a to-be-trained LSTM-RNN model; obtaining a pre-trained LSTM-RNN model through the training sample data, then performing fine adjustment and training through the constructed verification and test sample data to obtain LSTM-RNN model parameters, improving model precision by further correcting model parameters, and taking a corrected LSTM-RNN model as an air pollutant concentration forecast model; and finally taking the preprocessed air pollutant concentration data of a target city in the relatively long time as input data of the LSTM-RNN model, and performing model output to obtain a forecast result of air pollutant concentration at a current moment or at a moment in the future.
Owner:UNIV OF SCI & TECH OF CHINA
Traffic state prediction method for urban road network based on key road sections
InactiveCN109285346AConvenient inductionQuality improvementDetection of traffic movementForecastingTime correlationState prediction
The invention discloses a traffic state prediction method for the urban road network based on key road sections, which is characterized by comprising the steps of first, carrying out data preprocessing; second, establishing a spatial weight matrix of the road network; third, establishing a time correlation matrix; fourth, recognizing key road sections by using a time-space correlation matrix; andfifth, establishing a deep convolution neural network, predicting the state of the road network in the future, and carrying out evaluation on a prediction model. The traffic state prediction method predicts the urban traffic flow state from a level of the wide-range road network, thereby being conducive to guiding the traffic flow from a macroscopic perspective, and fully exploring time-space correlation characteristics of the traffic flow. The key road sections in the road network are recognized, so that the training time of the model can be greatly reduced compared with a method of taking historical states of all road sections as input data, and the prediction efficiency is improved; and the convolution neural network is adopted to serve as the prediction model, and the prediction resultis also more accurate.
Owner:BEIHANG UNIV
Motion vector prediction method and devices
ActiveCN109089119AEnrich the list of predictorsImprove forecasting efficiencyDigital video signal modificationMotion vectorInter frame
The embodiments of the invention disclose a motor vector prediction method and devices, which are used for determining a motion vector predicted value of a current block and improving prediction efficiency of a motion vector. The method of the embodiments of the invention includes the following steps: obtaining a reference frame corresponding to the motion vector of the current block; determininga motion vector type of the motion vector of the current block according to a reference frame type of the reference frame; obtaining a motion vector type of a first motion vector of at least one spatial adjacent prediction block when the at least one spatial adjacent prediction block of the current block is an inter-frame prediction block; and determining a second motion vector of adjacent pixel blocks according to decoding information of the spatial adjacent pixel blocks of the current block when the obtained motion vector type of the first motion vector is different form the motion vector type of the motion vector of the current block, and taking the second motion vector or a scaling value of the second motion vector as a candidate motion vector prediction value of the current block.
Owner:HUAWEI TECH CO LTD
Improved random forest algorithm based system and method for software fault prediction
ActiveCN103257921AComprehensive measurementImprove performanceSoftware testing/debuggingData setSoftware fault
The invention discloses improved random forest algorithm based system and method for software fault prediction. The system comprises a data processing layer, a prediction model building layer and a fault predication layer. The method includes calculating a software project attribute set used for acquiring a training model to acquire a training data set of a software prediction model, and performing equalization to the training data set; building a prediction model according to an improved random forest algorithm; screening the model according to performance limiting of accuracy rate and recall ratio; and predicting a software project according to attribute set information of the to-be-predicted software project and a trained prediction model and displaying prediction results and the prediction model. The improved random forest algorithm based system and method for software fault prediction have the advantages of high prediction accuracy rate, performance stability and high execution efficiency, can evaluate whether a final software product reaches specified quality or meets expectation of a user or not, and can guide developers to formulate distribution strategies of software testing and formal verification resources.
Owner:XIDIAN UNIV
Prediction device and prediction method for state of emergency topic
ActiveCN104216954AAvoid complex calculationsAvoid high-order operations and fit issuesSpecial data processing applicationsUnexpected eventsState prediction
The invention relates to a prediction device and a prediction method for the state of an emergency topic. The prediction device and the prediction method are provided based on the research of a microblog topic production mechanism and the influence of opinion leaders of emergency on the state of the emergency topic. The prediction device is provided with four components of a text acquisition unit, a topic clustering unit, a topic state recognition unit and a topic state prediction unit, and the topic state is predicted through the participation state of the opinion leaders, so that the prediction method of the topic state is simplified, the prediction accuracy is higher, and a basis can be provided for monitoring the tendency of the emergency topic. Through the calculation method of topic attention provided by the invention, the computation complexity of a traditional topic attention method is reduced. Moreover, the numerical value prediction of the topic attention is replaced by adopting the prediction of the state of the topic, so that the prediction content is more reasonable, and the prediction accuracy is higher. Furthermore, a prediction method of a hidden Markov model is provided, the set of the opinion leaders and the model of topic prediction are constructed through incremental iteration, so that the prediction operation can be obviously simplified, and the prediction efficiency is improved.
Owner:BEIJING UNIV OF POSTS & TELECOMM
Method for compensating positioning errors of robot based on deep neural network
ActiveCN110385720AImprove absolute positioning accuracyAccurate predictionProgramme-controlled manipulatorPattern recognitionAbsolute positioning
The invention discloses a method for compensating positioning errors of a robot based on a deep neural network. The method comprises the following steps: taking theoretical coordinate data of each sampling point and corresponding actual positioning errors as one group of sample data; constructing a robot positioning error prediction model, and training and testing the robot positioning error prediction model by adopting the sample data, wherein the robot positioning error prediction model is used for predicting positioning errors of an inputted target point to obtain a positioning error prediction value; and inputting theoretical pose data to the robot positioning error prediction model to obtain prediction errors and compensating and correcting target point coordinates. According to the method disclosed by the invention, the influence of the position and the pose of a positioning point on the positioning errors is comprehensively considered; and a complex mapping relation between theoretical pose and actual positioning errors of a robot is expressed by using the deep neural network to predict the positioning errors of the target point and compensate the errors. By use of the method disclosed by the invention, absolute positioning precision of the robot can be remarkably improved.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Storage battery residual capacity and health state rapid detection method and device
ActiveCN105807230AImprove forecasting efficiencyThe test result is accurateElectrical testingSecondary cellsDirect-current dischargeInternal resistance
The invention provides a storage battery residual capacity and health state rapid detection method and device. The method comprises the following steps of: enabling a storage battery to carry out instant larger current discharging through a controllable discharge circuit, monitoring the discharging current in the discharging circuit in the process by a current sampling circuit, synchronously monitoring the end voltage of the storage battery through a voltage sampling circuit, and utilizing a direct current discharge method to measure the internal resistance of the storage battery, wherein the discharge circuit and the voltage sampling circuit are connected in parallel with two wiring columns of the storage battery, so that the internal resistance of the storage battery is measured according to a Kelvin four-wire system measuring method, and the maximum discharge current, the load voltage and the internal resistance data of the storage battery are obtained; and according to an associated relation model, calculating SOC and SOH of the storage battery. By adopting the method provided by the invention, the residual capacity and the health state of the storage battery can be accurately detected on line.
Owner:郑贵林
A short-term power load prediction method based on a GRU neural network and transfer learning
ActiveCN109711620AImprove forecasting efficiencyReduce training timeForecastingNeural architecturesNerve networkLoad forecasting
The invention discloses a short-term power load prediction method based on a GRU neural network and transfer learning, and belongs to the field of power load prediction. A short-term power load prediction problem is solved. The invention provides a short-term power load prediction method based on a GRU neural network and transfer learning. A GRU-based recurrent neural network is utilized to solvethe problem that a traditional neural network cannot extract time characteristics, auxiliary information input influencing load change is expanded, including influence factors such as date, temperature and weather, a Dropout layer and a normalization layer are added to avoid the overfitting problem, and the accuracy of load prediction is improved; Historical knowledge is migrated through migrationlearning, a network which is normally put into use is adjusted, retraining and fine tuning are carried out through target prediction data, the value of the historical data is brought into play, and the precision and efficiency of load prediction are further improved.
Owner:ZHEJIANG UNIV
Driving energy consumption prediction system and method, storage medium and equipment
The invention discloses a driving energy consumption prediction system and method, a storage medium and equipment. The prediction method comprises the steps of obtaining historical working condition data of a planned driving route; constructing a training sample data set based on the historical working condition data; performing data training on the training sample data set, and establishing a vehicle speed feature BP neural network model and a driving energy consumption BP neural network model; acquiring real-time working condition information on the planned driving route; and inputting the real-time working condition information into a vehicle speed characteristic BP neural network model for prediction to obtain vehicle speed characteristic data of future driving, and then inputting thevehicle speed characteristic data into a driving energy consumption BP neural network model for prediction to obtain future driving energy consumption data so as to realize online prediction of driving energy consumption. According to the invention, online effective prediction of the driving energy consumption under the driving working conditions of different road environments and traffic states can be realized, and the efficiency of intelligent energy management of the vehicle is improved.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Load prediction method based on dynamic time warping and long-short time memory
ActiveCN109754113AImprove forecasting efficiencyIncreased clustering accuracyForecastingCharacter and pattern recognitionUtilization behaviorMachine learning
The invention discloses a load prediction method based on dynamic time warping and long-short time memory, and the method comprises the following steps: S1, obtaining the basic data required for short-term load prediction of a user from a power system; S2, carrying out the clustering of users with similar power utilization behaviors through employing a dynamic time warping method according to thehistorical load data of the user; S3, performing pooling processing on the user data of the same category; S4, selecting training data, preprocessing the training data and using the preprocessed training data as input; and S5, constructing a short-term load prediction method based on the deep long-term and short-term memory recurrent neural network, and verifying the effectiveness. According to the method, the users with similar electricity consumption behaviors are clustered according to the characteristic of large cardinal number of the to-be-predicted users, so that the prediction efficiency is improved. Meanwhile, through pooling processing on the data in the same category, the diversity of the training data is increased, the short-term load prediction precision is improved, and certain engineering application significance is achieved.
Owner:NANJING UNIV OF POSTS & TELECOMM
Simulating and predicting method of urban storm flood
ActiveCN101694680AImprove computing efficiencyImprove forecasting efficiencySpecial data processing applicationsICT adaptationInformatizationFlow management
The invention provides a simulating and predicting method of urban storm flood, which comprises the following steps: A. modifying and enabling a storm radial flow management model to accord with a data model of a geographic information system; B. embedding a counting kernel of the storm radial flow management model into the geographic information system by the geographic information system; C. dividing a sub drainage area of an investigating area; D. utilizing the geographic information system to obtain parameters required by each model; E. carrying out analog computation in the geographic information system by the storm radial flow management model; and F. realizing three-dimensional visualization according to a result of the analog computation. The simulating and predicting method of urban storm flood can effectively improve the predicting efficiency of the urban storm flood, realize informatization and numeralization of the urban flood prediction, and provide rapid, accurate and intuitive effective prediction for the location, the depth, the time and the duration of the seeper of the urban storm flood so as to provide decision supports for the disaster prevention and mitigation.
Owner:SHENZHEN INST OF ADVANCED TECH
Audio-video-coding-standard (AVS)-based intra-frame prediction method
InactiveCN102186086AAdd forecast modeImprove forecasting efficiencyTelevision systemsDigital video signal modificationAlgorithmIntra-frame
The invention discloses a novel audio-video-coding-standard (AVS)-based two-way intra-frame prediction method. In the novel two-way intra-frame prediction method, the weighted sum of pixel values calculated by any two intra-frame prediction modes in an AVS is calculated to obtain final two-way intra-frame predicted pixel values. The method comprises the following steps of: first adding a reverse scanning sequence on the basis of AVS raster scanning; then adding the intra-frame prediction modes corresponding to reverse scanning, and calculating the weighted sum of any two of the newly added intra-frame prediction modes corresponding to the reverse scanning to obtain the two-way intra-frame predicted pixel values corresponding to the reverse scanning; and finally selecting an optimal intra-frame prediction mode from all intra-frame prediction and two-way intra-frame prediction modes corresponding to the raster scanning and the reverse scanning by utilizing a sum of absolute errors (SAE)standard. By the novel two-way intra-frame prediction method provided by the invention, coding performance is further improved, and the shortcomings of relatively fewer intra-frame prediction modes and relatively lower prediction efficiency in the AVS are overcome.
Owner:WUHAN UNIV
Expressway traffic flow forecasting method based on time series
InactiveCN104269055AMeeting forecast needsMeet engineering needsDetection of traffic movementForecastingTraffic flowBusiness forecasting
The invention discloses an expressway traffic flow forecasting method based on time series. The expressway traffic flow forecasting method includes the steps of selecting one time scale, and carrying out statistics to build the traffic flow time series Q=(x); setting the value range of the number p of autoregression items and the number q of moving average items according to the selected time scale; solving the number p of the autoregression items and the number q of the moving average items; fitting the optimal number p of the autoregression items and the optimal number q of the moving average items through the maximum likelihood estimation in cooperation with the traffic flow time series Q to obtain an optimal ARMA model, and obtaining weight parameters of historical measured values and weight parameters of historical error values; solving the traffic flow forecasting series (please see the specifications) under the different time scales. By means of the expressway traffic flow forecasting method, an obtained time series model can better meet the requirement for forecasting various kinds of flow of an expressway, and the forecasting universality is improved; operation is simple, the forecasting efficiency is improved, the forecasting speed is increased, and the engineering requirement of traffic forecasting of the expressway is met.
Owner:四川省交通科学研究所
Database based complex-contour aircraft distributed heat environment parameter prediction method
ActiveCN106202804AAccurate predictionImprove design accuracyGeometric CADSustainable transportationEnvironmental designOrthogonal basis
The invention discloses a database based complex-contour aircraft distributed heat environment parameter prediction method and belongs to the field of aircraft heat environment design. The method comprises the steps that an aircraft surface heat flow database is established, order reducing processing is conducted on the database by utilizing a POD method to obtain orthogonal basis vectors of the database, and aircraft surface heat environment parameters can be predicted along a ballistic trajectory by combining with a corresponding basic coefficient interpolation method. The method can really reflect the space distribution characteristics and interference characteristics of the aerodynamic heat environment for all points on the surface of a complex-contour aircraft. Value result comparison shows that the method can remarkably improve the computational efficiency, and prediction precision is not lost. A surface distributed heat flow is provided for calculation of a heat proof temperature field through the points along the ballistic trajectory, more exquisite temperature distribution can be obtained, and accordingly the design level of a whole heat preventing and insulation system is improved.
Owner:BEIJING LINJIN SPACE AIRCRAFT SYST ENG INST +1
Method for forecasting travel time between bus stops
ActiveCN102610088AConvenient travelImprove forecast accuracyRoad vehicles traffic controlUltrasound attenuationPredictive methods
The invention discloses a method for forecasting travel time between bus stops on the basis of self-adaptive attenuation Kalman filtering, including steps of acquiring data of the history travel time of a bus between bus stops by the aid of a vehicle-mounted GPS (global position system) device, and then forecasting the future travel time of the bus between bus stops by a self-adaptive attenuation filtering forecasting model. Affection of history data to filtering is suppressed by introducing forgetting factors so as to ensure the vantage ground of new information during the forecasting process, and accordingly the defects of filtering divergence and computing divergence of a conventional forecasting model are overcome. Besides, an exponential declined noise model is used as a filtering start value, the forecasting precision and efficiency of the model is improved effectively. In addition, the method overcomes the defect of poor robustness of the conventional Kalman filtering, and has the advantages of high forecast precision, convenience in computing and high practicability.
Owner:SOUTHEAST UNIV
Intention recognition method and device
PendingCN109522556AImprove efficiencyImprove service qualityFinanceSemantic analysisText entryIntent recognition
Owner:北京九狐时代智能科技有限公司
Medium and long term hydrologic forecasting method based on empirical mode decomposition
InactiveCN104091074AThe method steps are simpleReasonable designSpecial data processing applicationsKernel principal component analysisSupport vector machine
The invention discloses a medium and long term hydrologic forecasting method based on empirical mode decomposition. The medium and long term hydrologic forecasting method based on empirical mode decomposition comprises the steps that firstly, a hydrologic forecasting model is built according to the following procedures of (101) empirical mode decomposition, wherein empirical mode decomposition is carried out on a hydrologic time sequence s(t) of a forecast drainage basin, (102) kernel principle component analysis, wherein kernel principle component analysis is carried out on n intrinsic mode function components Fj obtained through empirical mode decomposition and a trend item rn, and p main components F'k are extracted, (103) building of a training sample set, wherein the training sample set is built according to the extracted p main components F'k, (104) building of a support vector machine model, and (105) training of the support vector machine model; secondly, annual runoff data of the years needing forecasting are forecast through the built hydrologic forecasting model. The medium and long term hydrologic forecasting method based on empirical mode decomposition is simple in step, convenient to realize, easy and convenient to operate, good in use effect and capable of effectively resolving the problem of low forecasting accuracy of an existing hydrologic forecasting method.
Owner:CHANGAN UNIV +2
Network pharmacology method used for finding active ingredients of traditional Chinese medicine and effect targets thereof
ActiveCN103150490ARapid modeling methodFast prediction methodSpecial data processing applicationsNODALAdditive ingredient
The invention discloses a network pharmacology method used for finding active ingredients of traditional Chinese medicine and effect targets thereof. The network pharmacology method comprises the steps as follows: chemical compounds and proteins that can build training sets are collected, and characteristic descriptors are calculated according to molecular structures of the chemical compounds and amino acid sequences of the proteins; the training sets are built based on the characteristic descriptors of the chemical compounds and the proteins, predictive models relative to the interaction of the chemical compounds and the proteins are built according to a machine learning method; the known chemical compound ingredients of the traditional Chinese medicine needing to be forecasted, the characteristic descriptors are calculated, and forecast sets are built; the built predictive models are utilized to forecast the forecast sets, and the chemical compounds and the proteins with the forecasted interaction results greater than a given threshold are used for building a network; and the chemical compounds and the proteins with larger network node connection number are the potential active ingredients and the potential effect targets. The network pharmacology method can improve the finding accuracy rate and finding efficiency of the active ingredients of the traditional Chinese medicine and the effect targets.
Owner:ZHEJIANG UNIV
Support vector machine (SVM) based prediction method for the degradation tendency of super-capacitor capacitance value
InactiveCN106446940AImprove selection efficiencyImprove forecast accuracyCharacter and pattern recognitionMachine learningCapacitancePredictive function
The invention discloses a support vector machine (SVM) based prediction method for the degradation tendency of super-capacitor capacitance value. The prediction method utilizes the regression function of the support vector machine to predict the degradation tendency of the super capacitor capacitance value and comprises: 1) pre-processing the input value and the output value; 2) carrying out trainings to the training set data for a regression estimation function; 3) using the particle swarm optimization algorithm to automatically optimize the relevant parameters of the support vector machine; 4) according to the optimization result, configuring the corresponding parameter values of the support vector machine; substituting the training set data into a correlation vector machine model to obtain a regression prediction model for the degradation tendency of the capacitance value; and 5) substituting the training set data into the regression prediction model to obtain the degradation tendency of the capacitance value. According to the invention, it is possible to conduct online prediction to the degradation tendency of the capacitance value. Through the introduction of a particle swarm optimization algorithm to modify the parameter optimization method, the prediction efficiency and accuracy of the algorithm are increased so that it can be applied in a larger scope.
Owner:DALIAN UNIV OF TECH
Milling stability domain prediction method under multi-modal coupling
ActiveCN103559550AImprove forecasting efficiencyImprove efficiencyForecastingProcess systemsModal testing
The invention discloses a milling stability domain prediction method under multi-modal coupling to solve a technical problem that the efficiency of an existing milling stability domain prediction method is low. The technical scheme is that firstly the transmission function of a process system is determined through a modal test experiment, then modal parameters are extracted from the transmission function and two orthogonal direction modal parameters are paired and combined, a milling test is carried out to calibrate a milling force coefficient, based on the milling force coefficient and each scale of modal parameters, an improved semi discrete method is employed to obtain a stability lobe diagram under each scale of modals, and finally lobe diagrams under obtained from each scale of modals are drawn in a same coordinate system to obtain a stable domain under multi modal coupling. Through a test, when a cutting cycle is divided into 40 sections, 80 sections and 120 sections, compared with a background technology method, the method can save time for 4949.6 seconds, 74200.4 seconds and 344699.5 seconds, and the efficiency is increased by 85.9%, 92% and 88.5%.
Owner:NORTHWESTERN POLYTECHNICAL UNIV
Early warning method and device applied to information system
ActiveCN106909487AIncrease flexibilityImprove adaptabilityHardware monitoringWeight coefficientOriginal data
The invention discloses an early warning method and device applied to an information system. The method comprises the steps that original monitoring data of a monitored node within a preset period of time is collected, original data description is constructed according to preset characteristic indexes; according to the original data description, comprehensive indexes are determined, wherein the comprehensive indexes include weight coefficients corresponding to index components; according to the original data description and the comprehensive indexes, training data is determined, according to the training data, a prediction model is trained, the prediction model is determined, and target prediction data of a target node is determined according to the prediction model; actually obtained data of the target node is determined and converted according to the comprehensive indexes, and the conversion result is compared with the target prediction data; when the comparison result conforms to preset characteristics, corresponding information system early warning information is sent out. According to the method, flexibility and adaptability of information system risk early warning and the early warning result accuracy can be improved.
Owner:北京盛世全景科技股份有限公司
Human movement mode speculation model based on variation track context perception, training method and speculation method
ActiveCN110147892ASolve forecasting problemsImprove forecasting efficiencyCharacter and pattern recognitionMachine learningSemantic vectorLower limit
The invention discloses a human movement mode speculation model, a training method and a speculation method based on variation track context perception. The method comprises the following steps: firstly, respectively obtaining a track semantic vector and a variation hidden variable through a circular track encoder and a variation track encoder; and obtaining an attention vector of the track basedon a variational attention mechanism, cascading the attention vector with the variational hidden variable so as to reconstruct input data of a decoder, and finally restoring a previous track and generating a prediction track according to an output semantic vector of the decoder. According to the invention, the frame of the encoder-decoder solves the problem of track context learning. Two sub-tasks, namely track recovery and track prediction, speculated by a human movement mode are completed; not only can the probability density be estimated and the lower limit of the data possibility be optimized, but also the sequence and time characteristics of human mobility can be captured, the problem of track speculation according to track context perception is effectively solved, and the effect is improved for speculation of a human movement mode.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA
Soil moisture content prediction method based on LSTM deep learning model
ActiveCN110084367ASave manpower and material resourcesFully reflect the timing characteristicsWatering devicesForecastingTest sampleMaterial resources
The invention discloses a soil moisture content prediction method based on an LSTM deep learning model. The soil moisture content prediction method comprises the following steps: firstly, collecting soil physicochemical and meteorological data of a target farmland within a period of time; preprocessing the collected data, and dividing the preprocessed data into a training sample set and a test sample set; constructing an LSTM deep learning model; training the LSTM deep learning model through the training sample set to obtain a parameter-adjusted LSTM deep learning model, verifying the parameter-adjusted LSTM deep learning model through the test sample set, and finally taking the verified LSTM deep learning model as a soil moisture content prediction model; inputting the collected data intoa soil moisture content prediction model, and finally outputting a soil moisture content prediction result at a future moment through the soil moisture content prediction model. According to the method, the soil moisture content is forecasted by using a deep learning method, manpower and material resources are saved, the influence of early-stage data on a later-stage result can be truly reflected, and time sequence characteristics are fully embodied.
Owner:ANHUI AGRICULTURAL UNIVERSITY
LSSVM annual electricity consumption prediction method based on ant lion optimization
InactiveCN107274038AImprove forecast accuracyRelatively small errorForecastingArtificial lifeElectricityLeast squares support vector machine
The present invention relates to a kind of LSSVM annual power consumption prediction method based on antlion optimization, the annual power consumption prediction method comprises the following steps: determine the input variable of least square support vector machine (Least Square Support Vector Machines, LSSVM) prediction model; Initialize the antlion optimization algorithm; calculate the fitness value of the initial antlion to obtain the initial elite antlion; update the position of the ant, calculate the fitness value of the current antlion, and compare it with the fitness value of the corresponding antlion to determine whether to update the antlion Lion position; compare the fitness value of the antlion after the updated position with the fitness value of the previous elite antlion one by one, keep the antlion corresponding to the smaller fitness value, and obtain the elite antlion of this iteration; judge whether The maximum number of iterations is reached, if yes, then output the location of the elite antlion and the corresponding predicted value of annual electricity consumption, if no, continue to iterate. Compared with the prior art, the present invention has the advantages of higher prediction accuracy and higher prediction efficiency.
Owner:SHANGHAI UNIVERSITY OF ELECTRIC POWER
Photovoltaic fault detection method based on improved particle swarm optimization Elman network
InactiveCN108665112AOvercome the defects of local optimal solutionEasy maintenanceForecastingNeural learning methodsLocal optimumNeural network topology
The invention relates to a photovoltaic failure detection method based on an improved particle swarm optimization Elman network, which is characterized by comprising the following steps: (1) initializing particle swarm algorithm; (2) constructing an Elman neural network topology structure; (3) determining the particle evaluation function and calculating the particle fitness value; (4) updating theparticles and introducing the mutation operator to obtain new population particles: re-determining the individual extreme value and the global extreme value, and obtaining the optimal particle when reaching the set precision or the maximum number of iterations; (5) obtaining the optimal weight values according to the optimal particles obtained in the step (4) to carry out network training and result prediction. The method obtains the optimal weight value of the neural network through the improved particle swarm algorithm, overcoming the defect of the Elman neural network trapped in local optimal solution, greatly improving the prediction efficiency and speed, and facilitating the maintenance and management of the photovoltaic power generation system.
Owner:DONGHUA UNIV
Predicting device and method of voltage stability of wind power parallel network system
ActiveCN102082433AAvoid errorsSimple extraction of input volumeSingle network parallel feeding arrangementsWind energy generationData acquisitionModel parameters
The invention relates to a predicting device and method of the voltage stability of a wind power system, belonging to the technical field of wind power generation. The device comprises a sensor, a data acquisition chip, a central processing unit, an industrial personal computer and a wireless communication module. The predicting method comprises the following steps of: 1, acquiring the parallel network point data of a wind power station; 2, arraying acquired power network data into a time sequence according to acquisition time, and carrying out phase space reconstruction on the time sequence;3, carrying out a deterministic test on chaotic characteristics; 4, acquiring model parameter c and epsilon values and a kernel function parameter gamma value; and 5, analyzing a prediction result of the voltage stability of a power network. The invention prevents the errors caused when a model is established or parameters are selected in the traditional method and has the advantages of easy input quantity extraction, high precision, good accuracy and high prediction efficiency.
Owner:DANDONG ELECTRIC POWER SUPPLY COMPANY OF STATE GRID LIAONING ELECTRIC POWER SUPPLY
Method and apparatus for predicting re-purchasing probability of user, method and apparatus for determining quality of user, and electronic equipment
ActiveCN107220845AImprove forecast accuracyImprove forecasting efficiencyMarket predictionsMachine learningFeature DatasetFeature data
The embodiment of the invention, which relates to the field of the internet technology, provides a method and apparatus for predicting a re-purchasing probability of a user and electronic equipment. The method for predicting a re-purchasing probability of a user comprises: carrying out learning on a training sample set to obtain a prediction model for a re-purchasing probability of a user; obtaining a feature data set of a to-be-predicted user; and using the feature data set of the to-be-predicted user as an input of the prediction mode and carrying out processing to obtain a re-purchasing probability prediction value of the to-be-predicted user by the prediction model. Therefore, on the basis of multi-feature-dimension data of a user, the re-purchasing probability prediction value of the to-be-predicted user can be obtained automatically by the prediction model, so that the prediction accuracy is improved and the prediction efficiency is enhanced.
Owner:BEIJING XIAODU INFORMATION TECH CO LTD
Method for bedrock crack prediction based on multi-attribute fusion
ActiveCN108931814AImprove forecasting efficiencyAccurately determineSeismic signal processingBasementLithology
Owner:CHINA PETROLEUM & CHEM CORP +1
Features
- R&D
- Intellectual Property
- Life Sciences
- Materials
- Tech Scout
Why Patsnap Eureka
- Unparalleled Data Quality
- Higher Quality Content
- 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com