228results about How to "Efficient forecasting" patented technology

The invention discloses a secure clustering routing management method for a wireless sensor network. The method is characterized by comprising the following steps: 1) intrusion detection with an energy prediction capability; 2) cluster head selection based on trust; and 3) safe communication guarantee and hostile attack resistance through a secure clustering mechanism based on trust management. By using the method, hostile nodes in a network can be efficiently and correctly detected; in addition, the secure clustering mechanism is established based on trust; on one hand, reliable cluster head selection can be ensured; on the other hand, hostile attack behavior is resisted; therefore, the problems of reduction of communication throughtput rate caused by hostile attack and the like can be solved.

The invention relates to an electromechanical device nonlinear failure prediction method, comprising the following steps: 1, obtain data which can represent the running state of a device and select a section continuous vibration signal which has a long course and is sensitive to the failure to analyze; 2, respectively carry out exceptional value elimination and missing data filling to the vibration data by a 3 sigma method and an interpolation method; 3, carry out noise reduction to the vibration signal by a lifting wavelet method; 4, decompose the vibration signal after the noise reduction to corresponding characteristic bandwidths; 5, obtain a low dimension manifold character by utilizing a typical predicted characteristic bandwidth and adopting a nonlinear manifold learning method through decoupling of topological mapping and non-failure energy information; 6, carry out intelligent failure prediction with long course trend in a time domain by utilizing a recurrent neural network which has the dynamic self-adaptive characteristic and a first dimension of the low dimension manifold character as a neural network input. The lifting wavelet method is adopted in the invention, the algorithm is simple, the arithmetic speed is high, and the used memory is less, thereby being suitable for the characteristic bandwidth abstraction of failure character. The electromechanical device nonlinear failure prediction method can be widely applied to the failure prediction of all kinds of electromechanical devices.

The invention provides a PSO-ELM based hot rolled plate tissue-performance prediction method. The method comprises the steps of step1, obtaining parameters affecting hot rolled plate tissue-performance; step2, obtaining the plate cooling rate Rc; step3, performing mechanical property test on the plate according to the data obtained in the step1 and the cooling rate obtained in the step2 to obtain plate yield strength, tensile strength and ductility test values; step4, building an extreme learning machine (ELM) based hot rolled plate tissue-performance prediction model; step5, training the model build in the step4 through a particle swarm algorithm; step6, predicting the hot rolled plate tissue-performance through the prediction model obtained in the step5. By the aid of the method, online real-time accurate prediction of the hot rolled plate tissue-performance is achieved, and the problem that prior mechanical performances are detected by only relying on machines is solved.

The embodiment of the invention provides an aquaculture dissolved oxygen prediction method and device. The method includes the steps that water quality parameters and environment meteorological parameters of an aquaculture pond are acquired to serve as to-be-analyzed data, wherein the water quality parameters comprise the dissolved oxygen content; a principal component analysis method is adopted for carrying out dimension reduction and analysis on the to-be-analyzed data, principal components influencing the water quality dissolved oxygen change are acquired, and key influence factor data of the water quality dissolved oxygen is determined according to the principal components; the key influence factor data is input in a trained LSTM network model, and predicted data of the dissolved oxygen content of the aquaculture pond is obtained according to the output result of the LSTM network model. The problems that a traditional prediction model is low in prediction precision, poor in stability and the like are solved, the effect of efficiently predicting the water quality dissolved oxygen content is achieved, and a decision basis can be provided for regulation and control management of the aquaculture water quality dissolved oxygen.

A method for detecting loss of SF6 gas from electrical utility apparatus determines a molar ratio of gas in a container at an initial time and of gas in the container at a subsequent time. Measurement of temperature is determined by averaging ambient temperature and temperature of the surface of the container. The initial values of pressure and temperature define the initial value of n as follows:

The value at a subsequent time is

The molar ratio can be defined as

n_n/n_o or as n_o/n_n

The invention discloses an emotion recognition method of multi-channel electroencephalogram (EEG) data and an electronic device. The method includes the steps: sending frequency domain features of channels of extracted EEG data into a sequence feature extractor so as to obtain hidden-layer feature vectors of the channels of the EEG data, capturing association between the EEG channels and emotion categories, and sending the association and the hidden-layer feature vectors to an automatic encoder so as to obtain probability value vectors of the emotion category corresponding to the EEG data. Long-term and short-term memory networks are utilized to learn the non-linear relationship between the EEG channels on the EEG channel sequence, the high-dimensional EEG features related to the emotion categories are extracted, the key information in the multi-channel EEG signals are selected automatically, and EEG feature field differences which are caused by instability of the EEG data and environmental change are reduced.

The invention discloses a public bicycle renting forecasting method based on multi-source data fusion. According to the method, historical data about public bicycle renting/returning records, weather, temperature, holidays, festivals and the like are cleaned and preprocessed, and training datasets are acquired; the datasets are classified with a clustering algorithm, and different renting modes of public bicycles are divided; the classified datasets are used to establish a Bayesian classifier used for forecasting the renting modes according to conditions of holidays, festivals, weather and air temperature of one day in the future; a self-adaptive particle swarm neural network model corresponding to each mode is trained for different modes of datasets respectively; finally, the renting mode of one day is forecasted by the aid of the Bayesian classifier, a corresponding particle swarm neural network model is selected to forecast the renting law of public bicycles. The forecasting accuracy is high, the operation speed is high, reference basis is provided for bicycle renting and returning by a user, the duration time of the unbalanced state of a public bicycle station is shortened, and the users' satisfaction is improved.

The invention belongs to the technical field of traffic management, and relates to a road traffic flow prediction method based on cell phone data. The method comprises the following steps of: dividing the time when the traffic flow is needed to be predicted and monitored during the day into different periods of time; in an observation phase, for each observed day, obtaining the cell phone data ofeach period of time through monitoring cell phone switching quantity among different base stations arranged at the same road section, and monitoring and counting road traffic flow data of each periodof time; calculating a related coefficient between the cell phone data and the road traffic flow data; in a prediction phase, monitoring the cell phone data of each period of time in real time; and predicting the traffic flow data in the current period of time according to the cell phone data monitored in real time and the related coefficient. The road traffic flow prediction method based on the cell phone data can reduce cost and labor power invested in road detection devices, and provides an effective way for implementing intelligent urban traffic and solving problems of traffic jams.

The embodiment of the invention provides a method, a device and a system for intelligently diagnosing a factory. The method comprises steps: according to real-time state data of each factory device acquired by a data acquisition device, a server diagnoses the abnormal state of each factory device, and corresponding warning information or early warning information is generated, wherein the warning information or the early warning information at least comprises a corresponding abnormal reason, a warning priority, a warning type and a warning description; each abnormal reason is further analyzed, and a reason judgment basis for the abnormal reason is obtained; and the warning information and/or the early warning information and the reason judgment basis for each abnormal reason are transmitted to a user terminal for being displayed. The warning fault diagnosis reliability is greatly improved, hidden device or process faults can be efficiently judged or predicted, an operator in the factory is reminded to timely handle the fault, happening of safety accidents is reduced, and the economic benefits of the factory are improved.

The invention discloses a gene panel for detecting tumor targeted drug related gene mutation, an application, a method and a kit. The gene panel provided by the invention comprises 15, 027 targeting DNA probes used for capturing targeting DNA. The targeting DNA comprises 357 gene exon regions on a human genome and 511 probes used for capturing gene fusion. The gene panel disclosed by the inventioncan be used for detecting DNA mutation and variation of a plurality of sites at one time, therefore, the optimal individualized treatment medicine and scheme can be selected according to the genome characteristics of a patient in the cancer immunotherapy process. The gene panel can be used for measuring various types of biomarkers such as SNV, Indel, CNV, gene fusion, MSI, TMB and HLA.

The invention provides a charging pile fault prediction method and device based on a Markov chain, and the method comprises: obtaining a state vector of a target charging pile in an initial time period, and enabling the state vector to serve as the initial state probability distribution of a preset charging pile Markov chain prediction model; wherein the Markov chain prediction model of the charging pile is used for representing a discrete event random process in which a non-fault state and at least one fault state of the charging pile are mutually converted and different fault states of the charging pile are mutually converted; and according to the initial state probability distribution and the Markov chain prediction model, determining the probability that the target charging pile has atleast one fault in a prediction time period. Automatic fault prediction of the charging pile can be achieved, the prediction process is efficient, the prediction result is accurate, and then timely and targeted maintenance can be conducted on the fault of the charging pile.

The invention relates to the fields of biotechnology, DNA mutation detection technology and bioinformatics, in particular to a gene panel for predicting a new antigen load and detecting genome mutation. Specifically, the invention relates to the gene panel which combines 839 genes and integrates 511 gene fusion events. The gene panel provided by the invention can rapidly, efficiently and accurately predict a new antigen load, and can also detect DNA mutation of multiple sites at one time, so that an optimal individualized treatment drug and scheme can be selected according to genomic characteristics of a patient in a cancer immunotherapy process. In addition, the gene panel provided by the invention can also be used for measuring various types of biomarkers such as SNV, Indel, CNV, gene fusion, MSI, TMB and HLA.

The present invention relates to a system for predicting the probability of poor ovarian response of a subject under an antagonist regimen, and a system for guiding the selection of a gonadotropin starting medication dose. The system for predicting the probability of poor ovarian response includes: a data acquisition module for acquiring the age, the anti-Mullerian hormone (AMH) level, the follicle stimulating hormone (FSH) level, the antralfollicle count (AFC) data of the subject; and a module for calculating the probability of poor ovarian response, which is used for calculating the information obtained in the data acquisition module to calculate the probability of poor ovarian response of the subject, and giving a starting dose recommendation for exogenous gonadotropin (Gn) based on thepredicted probability of poor ovarian response.

The invention discloses a dynamic STKNN model-based short-time traffic prediction method. The method comprises the steps of: a, feature representation: averaging traffic conditions of each road segment in history days, and carrying out feature representation on each road segment by utilizing an average speed vector; b, automatic traffic mode recognition: automatically recognizing similar traffic modes of road networks through an AP cluster algorithm; c, automatic time interval division: aiming at the automatically recognized traffic modes, automatically dividing time intervals through a K-Means algorithm; and d, self-adaptive STKNN model construction: aiming at each time interval of each traffic mode obtained in the step 2 and 3, respectively constructing an STKNN model. The method is capable of directly helping the traffic management department to generate reasonable and efficient strategies to ease traffic congestion, thereby realizing redistribution of road network traffic flows andhelping the public to realize correct path planning.

The invention relates to the technical field of power load prediction, and provides a transformer area power load prediction method and prediction device, and the method comprises the steps: collecting transformer area power load data at a first preset moment, and obtaining a first data vector; inputting the first data vector into a trained prediction neural network, so that the prediction neuralnetwork outputs transformer area power load data at a second preset moment, wherein the prediction neural network comprises an encoder and a decoder connected with the encoder, the encoder and the decoder are realized based on a time convolution network, the encoder is used for performing feature extraction on the first data vector to obtain a first feature vector, and the decoder is used for calculating a second data vector according to the first feature vector and taking the second data vector as transformer area power load data at a second preset moment. According to the technical scheme provided by the invention, the power load of the transformer area can be accurately and efficiently predicted.

The invention discloses an all-weather surface temperature inversion method and system, and the method comprises the steps: obtaining surface temperature-related data which comprises thermal infraredsurface temperature data, passive microwave data, surface temperature reanalysis data, a normalized vegetation index, and digital elevation model data; if the passive microwave data has a value, predicting the surface temperature based on a random forest model; and if the passive microwave data is missing, predicting the surface temperature based on the temperature annual cycle model. According tothe technical scheme, the problem of inaccurate surface temperature inversion data caused by passive microwave data loss of the surface temperature is solved, and the all-weather surface temperaturecan be efficiently and accurately predicted.

The invention provides a shale gas reservoir logging porosity rapid prediction method comprising the following steps: obtaining shale gas reservoir logging data, predicting according to a predetermined proportion of logging curve data in the shale gas reservoir logging data to obtain a pore value corresponding to shale, and generating a pore prediction threshold according to the pore value; establishing a random forest porosity prediction model through a random forest regression algorithm according to the data of the remaining proportion of the shale gas reservoir logging data; substituting the logging curve data into the random forest porosity prediction model to obtain a pore prediction value; comparing the pore prediction value with the pore prediction threshold, and generating a porosity prediction model according to a comparison result and the random forest porosity prediction model; and obtaining a porosity prediction result according to the porosity prediction model and the logging data of the shale gas reservoir to be measured.

The invention discloses a rice yield prediction method. According to the rice yield prediction method, a test district is selected; rice leaf normalization vegetation indexes of the test district are acquired, a sum value of all the rice leaf normalization vegetation indexes is solved to acquire an NDVI sum value; rice leaf photochemical vegetation indexes of the test district are acquired, a sum value of all the rice leaf photochemical vegetation indexes is solved to acquire a PRI sum value; rice yield of the test district is acquired; a multiple regression analysis method of SPSS software is utilized, linear relationships among the rich yield, the NDVI sum value and the PRI sum value are analyzed, and a rich yield prediction model is acquired; the rich yield is predicted according to the rice yield prediction model. Through the method, the relationships between japonica rice leaf NDVI and PRI values at different growth periods and japonica rice yield change can be timely monitored, japonica rice yield estimation business operation can be realized, high efficiency, rapid and precise rice yield estimation is realized, and precise prediction of the japonica rice yield can be realized, and a japonica rice growth state can be effectively tracked.

Disclosed is a method for testing phase and frequency change before and after switching primary and secondary clocks of a navigation satellite. Phases of output signals of satellite clocks are measured by a phase measuring device, phase measuring data are acquired at equal time intervals, phase measuring data before and after output of on-off switching action of the satellite clocks are recorded for a long time, on-off switching time is recorded, phase testing data before and after switching are respectively subjected to curve-fitting by the least square method, and change quantities of the phases and frequency are calculated according to fitted values corresponding to the switching time before and after switching. By the method, the influence of frequency drift of the satellite clocks and measuring instruments on testing results can be reduced, and measuring precision is high.