131 results about "Statistical algorithm" patented technology

The invention relates to a blueberry sugar degree hyperspectral inversion method based on improved Laplacian mapping, and belongs to the technical field of blueberry hyperspectral acquisition and analysis. The method comprises the following steps: firstly, collecting blueberry samples of different varieties and different maturity degrees in a complex scene, measuring hyperspectral data of the blueberry samples and sugar content of corresponding blueberries, then dividing the blueberry sample data into a training set and a test set according to a proportion by using a statistical algorithm, and performing data preprocessing by using an MSC + FOD combination to obtain a training set and a test set; extracting characteristic wave bands from the preprocessed spectral data by using ILE provided by the invention, establishing a blueberry sugar degree prediction model by using CNN, training the model by using a training set, and finally comprehensively evaluating the model by using a test set in combination with regression indexes R2, RMSE and RPD. The method can quickly and accurately predict the sugar degrees of blueberries of different varieties and different maturity degrees in a complex scene, and provides powerful technical support for prediction of the sugar degrees of the blueberries.

The invention discloses an application sequence prediction method and device, electronic equipment and a storage medium. The method comprises the steps of obtaining a historical use behavior sequence corresponding to a target application program; establishing a first-order state transition matrix based on the historical use behavior sequence; determining a reference application program from the historical use behavior sequence, and obtaining an application program set corresponding to the reference application program from the first-order state transition matrix; determining a reference application program sequence based on the historical use behavior sequence; and splicing the application program set with the reference application program sequence to obtain a target application program set, and determining a second number of application programs from the target application program set as an application program sequence prediction result. According to the method, the application program sequence to be used by the user is predicted by directly combining the matrix transfer algorithm and the segmentation statistical algorithm, a neural network model does not need to be introduced for prediction, and the problem of deploying the neural network model on marginalized equipment with limited computing power resources is solved.

The invention provides a construction method of a compact sandstone core natural fracture characteristic parameter characterization model. The construction method specifically comprises the following steps: step 100, self-making a compact sandstone core natural fracture image data set; step 200, establishing an efficient self-adaptive Frac-YOLOv8 rock core natural fracture segmentation network; step 300, training the network by using the data set to obtain a rock core natural fracture segmentation model; step 400, inputting a core image to be segmented into the model, and segmenting cracks; step 500, generating a binary crack data set; step 600, applying a crack skeletonization extraction algorithm to quantify the crack length; step 700, using a pixel statistical algorithm to quantify the actual area of the crack and calculating the average width of the crack; and finally, calculating the maximum width pixel value of the crack by using a crack variable circle algorithm, and quantifying the maximum width through the diameter of an inscribed circle. The method provides an effective basis for evaluation and analysis of natural rock core cracks of tight sandstone.

Apparatuses, systems, program products, and method are disclosed for detecting suitability of machine learning models for datasets. An apparatus includes a training evaluation module configured to calculate a first statistical data signature for a training data set of a machine learning system using one or more predefined statistical algorithms. An apparatus includes an inference evaluation module configured to calculate a second statistical data signature for an inference data set of a machine learning system using one or more predefined statistical algorithms. An apparatus includes a score module configured to calculate a suitability score describing the suitability of a training data set to an inference data set as a function of a first and a second statistical data signature. An apparatus includes an action module configured to perform an action related to a machine learning system in response to a suitability score satisfying an unsuitability threshold.

The invention discloses a multi-device collaborative passenger flow statistical method and system, and the method comprises the following steps: presetting a unique identity label and a physical position index for devices, reading the unique identity label and the physical position index, and initializing the attribute information of the devices; a user datagram protocol broadcasting mechanism is started, and heartbeat information including the unique identity label, the physical position index and the online state is sent according to a preset period; monitoring the user datagram protocol broadcast message in the local area network, constructing and maintaining an online equipment list, and updating the online state of the equipment according to the heartbeat information receiving analysis condition; judging adjacent equipment based on a physical location index, and deciding whether to start a first boundary or a second boundary according to the online state of the adjacent equipment; and the decision result is transmitted to a passenger flow statistical algorithm to generate a shop-crossing detection line. According to the invention, multi-device collaborative passenger flow statistics dynamic boundary configuration is realized, the shop-crossing detection line is accurately generated, and the passenger flow statistics problems of fixed boundary configuration, easy missed counting and poor multi-device collaboration are solved.

The invention discloses a pouring planning method and device of a material distributing machine, electronic equipment and a storage medium, and the method comprises the steps: obtaining a BIM model of a pouring site, a material distributing machine model and obstacle information of the pouring site, and obtaining a feasible region of the material distributing machine corresponding to the material distributing machine model in the pouring site according to the BIM model, the material distributing machine model and the obstacle information; according to the pouring attributes of the components contained in the BIM model, the components contained in the pouring site are divided into pouring components and poured components, communication processing is conducted according to the adjacency of the pouring components, and the area where all the pouring components are located is determined as a pouring area; according to the BIM model of the pouring area and the feasible region, based on concrete flow collapse and component connectivity, a collapse statistical algorithm is used for calculation, and a pouring planning result of the material distributing machine is generated; and according to the pouring planning result, a material distributing machine is controlled to move in the pouring site so as to conduct pouring treatment on all the areas in the pouring area. And the pouring safety and the pouring efficiency are improved.

The invention relates to the technical field of organic light-emitting device production process data processing, and provides an organic light-emitting device production process optimization method, which comprises the following steps of: monitoring key parameters in an evaporation cavity in real time, analyzing data in a cleaning treatment process by utilizing a preset statistical algorithm, and optimizing the production process of an organic light-emitting device. And extracting feature data influencing the surface cleanliness and flatness of the substrate. And then, establishing a mathematical model in the vacuum evaporation process, and solving by applying an optimization algorithm to obtain a parameter combination which enables the performance of the device to be optimal. Furthermore, electrical and optical performance and life stability data of the device are collected, and optimization parameters are simulated, calculated and optimized through a data processing model. In the production process, equipment operation data are collected in real time, optimization parameters and real-time data are compared, and the parameters are optimized in real time through a stochastic gradient descent method and stored in a knowledge base. The device performance and the production efficiency are effectively improved, and the production cost is reduced.

The invention provides a liver and gall disease prediction model construction method, system and device combined with multi-modal data and a medium, and belongs to the technical field of data prediction model construction. Medical data of a patient is collected; extracting the medical data in the medical data set, and evaluating the feature weight of each piece of medical data by using a regression analysis statistical algorithm; a comprehensive feature vector set is generated through fusion, and a preliminary liver and gall disease prediction model is constructed; and deploying the liver and gall disease prediction model to a medical terminal, and performing periodic updating through a cloud. A regression analysis statistical algorithm is utilized to evaluate a feature weight, features, such as key features such as glutamic-pyruvic transaminase and liver ultrasound image texture features, which have important influences on liver and gall disease prediction can be screened out, the data dimension is reduced, the model complexity is reduced, the key feature effect is highlighted, and the interpretability and prediction accuracy of the model are improved.

Data compression with quantum-resistant intrusion detection, that measures in real-time the probability distribution of an encoded data stream and analyzes entropy characteristics across multiple bit-scale windows to detect both classical and quantum-generated intrusions. The system compares the probability distribution to a reference probability distribution and uses statistical algorithms to determine divergence between distributions while simultaneously analyzing entropy cascade patterns characteristic of quantum computing sources. When divergence exceeds configured thresholds or quantum-generated characteristics are detected, the system generates intrusion alerts identifying the threat type. The system comprises encoding and decoding machines, an intrusion detection engine that performs multi-scale entropy analysis, a codebook training engine that creates quantum-resistant codebooks using entropy-stratified training algorithms, and databases including a quantum signature database storing compression patterns of known quantum algorithms. The codebook training engine adaptively retrains encoding algorithms upon detecting new quantum patterns, maintaining system effectiveness against evolving quantum threats.

The invention relates to the technical field of grid-connected monitoring data accurate checking, in particular to a grid-connected monitoring data accurate checking method, system and device based on intelligent sensor fusion and a medium. The method comprises the following steps: collecting power grid monitoring data in real time, and preprocessing the collected power grid monitoring data; fusing the power grid monitoring data to obtain fused power grid data, and filtering systematic deviation; constructing a power grid monitoring data model, and detecting data exception and positioning an exception source in combination with a statistical algorithm; checking and correcting the data subjected to anomaly detection, performing data optimization, and adjusting sensor parameters through a feedback mechanism according to the checked data; and storing the checked data in a database, and sending the data to a power grid dispatching center. Real-time detection and source positioning of abnormal data are realized, problems are found quickly, and measures are taken.

The invention discloses a fast beam forming method based on a sparse fast Fourier transform algorithm, and belongs to the field of array signal processing. The method comprises the steps of sparse fast Fourier transform, multi-channel large-value frequency point statistics, narrowband beam forming algorithm and the like. Firstly, a sparse fast Fourier transform algorithm is used for calculating the large-value frequency and the corresponding amplitude of a signal, and the frequency domain calculation speed is increased; secondly, the most suitable large-value frequency point and the corresponding amplitude are obtained through a multi-channel large-value frequency point statistical algorithm, and the influence of noise interference is reduced; and finally, based on the large-value frequency points and the corresponding amplitudes, obtaining energy of each angle by using a narrowband beam forming algorithm, and outputting the energy as a beam forming result. The method has the characteristics of high calculation speed and high stability.

The invention provides a multi-algorithm integrated quasi-real-time environment air quality abnormal data identification method, and relates to the technical field of environment data analysis. The method comprises the following steps: acquiring air index data acquired by a plurality of ambient air quality monitoring stations, and marking abnormal data; marking the air index data of which the numerical value is within the first preset range as invalid or corrected; screening single-point abnormal values; screening air index data with abnormal space consistency; screening a trend abnormal value in the air index data; screening an abnormal peak value in the air index data according to the obtained trend value; and determining normal data in the air index data. According to the method, the abnormal values of the air index data can be screened out according to the abnormal data distribution characteristics of the air index data, an integrated statistical algorithm, a time sequence analysis model and a rule algorithm, the advantages of multiple methods are fused, and the error recognition rate of local high-value bubbling is reduced through multi-index collaboration and correlation check, so that the accuracy of local high-value bubbling is improved. And the overall precision of data quality control is improved.

A method for testing device software of a device using a fuzzing algorithm. The method includes: initializing the fuzzing algorithm to detect an initial behavior of the device software of the device under test; executing a fuzzing test loop including: generating a fuzzed message from predefined message types; sending the generated, fuzzed message to the device under test to test the device software on the basis of the fuzzed message; detecting side-channel information during testing of the device software on the basis of the fuzzed message; recognizing anomalies in the side-channel information using at least one machine learning model and / or statistical algorithm; and if an anomaly is recognized, adjusting a parameter including adjusting fuzzability weights, of the initialized fuzzing algorithm and performing a next loop iteration of the fuzzing test loop; and if no anomaly is recognized, performing the next loop iteration of the fuzzing test loop.

Techniques for modifying application-generating code are disclosed. A system determines if a change to an application-generating code module results in a statistically significant change in the performance of applications generated by the module. The system makes the determination by comparing performance metrics of multiple applications generated by an un-changed application-generating code module to performance metrics of multiple applications generated by a changed application-generating code module. The system compares the performance metrics by generating distributions representing the respective performance metrics. The system generates the distributions by fitting the performance metrics to a statistical algorithm including an inter-application influence factor. The influence factor modifies the statistical model by converting a change in the shape of the distribution from (a) around a center of the performance metric distribution to (b) a shift of the center of the performance metric distribution toward a clustering of measured performance metric values.

The invention belongs to the technical field of industrial control, and discloses an industrial control virtual equipment resource pool construction method, system, equipment and medium, and the method comprises the steps: optimizing parameters of a transition probability and an observation probability in a time sequence data statistical algorithm according to time sequence characteristics of an industrial control scene, and extracting resource characteristics; generating a virtual resource model, and constructing a bidirectional mapping table of physical resources and virtual resources; optimizing a clustering algorithm by using a time weight factor, dynamically aggregating the time sequence metadata in combination with a streaming computing framework, and performing anomaly detection on a resource state in combination with the aggregated time sequence metadata based on an anomaly detection technology; based on a layered decoupling flattening architecture, a resource pool is divided into a resource layer, a data layer, a link layer, a technical support layer and an interface layer. According to the method, logic-physical layered decoupling of the industrial control resource pool is realized, seamless access and dynamic optimal distribution of multi-protocol equipment are supported, and high-reliability and low-delay bottom support is provided for users.

Methods, apparatus, and processor-readable storage media for enhancing web page loading using machine learning techniques are provided herein. An example computer-implemented method includes obtaining activity-related data associated with at least one user device and at least one web application during a web browsing session; generating one or more predictions of one or more web pages, associated with the at least one web application, to be sought in connection with the web browsing session by processing at least a portion of the activity-related data using one or more statistical algorithms and one or more machine learning techniques; and automatically preloading, in connection with the at least one web application, at least one of the one or more web pages for use in the web browsing session by the at least one user device.

The application provides a diversity biological collection and identification system, a high-definition camera and a microphone are mounted on a UAV platform, a plurality of groups of biological species and living habits are included in a database, the biological species and the living habits are in one-to-one correspondence, the living habits include sound characteristics, living traces, habitats and the like; a habit analysis module is used for obtaining animal traces in an image to be analyzed in an image analysis technology, a habit influence value is obtained by calculating the living trace reliability of all marked animal traces; a sound recognition module is used for obtaining animal calls or activity sounds in sound data as audio segments to be analyzed, a sound influence value is obtained by calculating the sound similarity of the marked audio to be analyzed; a comprehensive evaluation module is used for obtaining the number of biological samples to be analyzed, the habit influence value and the sound influence value, and obtaining the expected number of biological samples in a specified area by using a statistical algorithm.

The present invention relates to a gridded intelligent fusion method and system for sea surface wind fields based on multi-source satellite payloads. The method comprises: constructing a deep neural network model and combining the advantages of the D-Matrix statistical algorithm for medium and low wind speed inversion to obtain MWRI sea surface wind speed products for the entire wind speed range; performing spatiotemporal matching processing between multi-source satellite data and an EC background field to obtain the data source for the fusion analysis period; combining the EC background field with the wind speed, divergence, vorticity, and second-order derivative terms of wind speed at each point in the fused wind field to obtain a cost function; obtaining the gradient terms of each cost function within the cost function based on the cost function and summing them to obtain the function gradient; and obtaining the final fused wind field based on the cost function and the function gradient. The present invention achieves efficient fusion of sea surface wind field data from multi-source satellite payloads, and can improve the accuracy and spatiotemporal resolution of sea surface wind field data.

An iterative statistical algorithm based on a discrete-to-discrete data model with iterative coordinate descent optimization for image reconstruction from radiation measurements obtained in emission tomography, i.e. in a Positron Emission Tomography scanner, is described in this invention. The method presented here allows for the presence of the regularization as an additive term. Furthermore, this method makes it possible to control the convergence of the algorithm using a specific parameter. These improvements are due to the signals obtained regarding the given statistics of this imaging technique.

The disclosed system provides real-time detection and remediation of metric anomalies in a replenishment network. A computer system can receive, from data sources, event data, retrieve historic metric data associated with a metric of a retail environment, aggregate the event data and historic metric data into aggregated data for the metric, store the aggregated data in a cache data store, determine, based on applying a statistical algorithms model to the cached aggregated data, (i) a predicted metric value and (ii) upper and lower tolerance bounds for the metric, iteratively receive the event data, aggregate the data, and determine (i) and (ii) until (a) determining a condition is triggered to evaluate the metric or (b) expiration of a time period to which the predicted value and the upper and lower tolerances apply, and return, based on determining the condition is triggered to evaluate the metric, information about metric anomalies.

The invention relates to an intelligent statistical algorithm for mobile on-duty management based on security non-fixed places, which solves the technical problems of unscientificity, low efficiency, low real-time performance and repeated on-duty of security in a period of time, and comprises the following steps of: 1, carrying out multi-source data acquisition and preprocessing; 2, dynamic task planning modeling is completed; step 3, security equilibrium configuration calculation is carried out; 4, behavior analysis and early warning are completed; 5, dynamically adjusting the threshold value; according to the technical scheme, the problem is well solved, and the method can be used for intelligent statistics of security guard on-duty management.

This invention discloses a discrete element method, system, medium, and equipment for simulating equivalent crystalline materials, relating to the field of numerical simulation of rock mechanics. The method includes: converting granite images into binary images using a binarization method to identify various minerals within the binary images; determining the size data of various minerals in the binary images based on a particle size statistical algorithm; extracting micromechanical parameters using nanoindentation experiments combined with a trial-and-error method, and constructing multiple sets of equivalent crystalline models based on the mineral size data; dividing each set of equivalent crystalline models into multiple regions using a Brazilian splitting experiment; determining the optimal magnification for each region of each set of equivalent crystalline models by magnifying from non-critical regions to critical regions using a magnification algorithm, obtaining differentiated equivalent crystalline models; and performing Brazilian splitting numerical simulation using these differentiated equivalent crystalline models to obtain simulation results.

A system and method for filesystem data compression using codebooks, that measures in real-time the probability distribution of an encoded data stream, compares the probability distribution to a reference probability distribution, and uses one or more statistical algorithms to determine the divergence between the two sets of probability distributions to determine if an unusual distribution is the result of a data intrusion. The system comprises both encoding and decoding machines, an intrusion detection module, a codebook training module, and various databases which perform various analyses on encoded data streams. Further, the system comprises a system for integrating the compression into a filesystem for both system-wide compression on a per-file or filegroup basis, and intrusion or alteration detection of files.

The present invention relates to the fields of bridge engineering and signal processing technology, and in particular to a method and application for fully automatic cable frequency extraction, order determination, and cable force identification. The present invention first uses a sensor to obtain time-course signals such as acceleration and displacement of cable vibration, and uses Fourier transform and other methods to obtain the spectrum of the vibration signal; then uses a memory-type sieve peak algorithm to search for peaks in the spectrum, that is, the modal frequency of the cable; hash voting is performed on all acquired frequency peaks to obtain the nominal fundamental frequency, and then the order corresponding to all picked frequencies is determined; after obtaining all frequencies and orders, the cable-beam vibration theory can be used to obtain parameters such as cable force. The present invention combines the memory-type sieve peak algorithm and the hash voting statistical algorithm to achieve a fully automatic and intervention-free cable force identification process, and has strong engineering applicability.

Embodiments of the present application relate to the field of image processing technology and disclose a temperature coefficient calibration method, system, electronic device, and storage medium. The method includes: selecting several sample cameras from a current batch of cameras, and determining a corresponding shooting temperature for each of the sample cameras based on an operating temperature range of the current batch of cameras; obtaining a first speckle pattern captured by each sample camera on a preset plane at a first temperature, and a second speckle pattern captured on the preset plane at a second temperature; traversing each sample camera, and determining a temperature coefficient of the current sample camera based on a preset temperature compensation model, the first speckle pattern and the second speckle pattern corresponding to the current sample camera; determining a unified temperature coefficient based on a preset statistical algorithm and the temperature coefficients of each sample camera, and calibrating the temperature coefficients of all cameras in the current batch to the unified temperature coefficient. This method can improve the efficiency and quality of camera temperature coefficient calibration and reduce the cost of temperature coefficient calibration for the entire production line.

A method for determining a convolution kernel for an iterative statistical algorithm based on a continuous-to-continuous data model. The method is used for image reconstruction from radiation measurements obtained in emission tomography, specifically in a Time-of-Flight Positron Emission Tomography (TOF PET) scanner. The presented method is a non-list-mode solution that reduces the computational complexity of the reconstruction problem, improves the resolution of reconstructed images, reduces the radiation dose absorbed by patients during TOF PET examinations, and / or shortens the measurement acquisition time without significantly compromising the quality of the diagnostic images. Notably, the quality of the functional images remains at the same level. These improvements are achieved by designing the convolution kernel to account for the statistical properties of the measurement signals registered during the TOF PET scanner's acquisition process.

The invention relates to the technical field of constructional engineering informatization, and discloses a steel bar optimized blanking method and system based on construction specification constraint and dynamic planning, and the method comprises the steps: collecting multi-dimensional feature data, and organizing the multi-dimensional feature data into a graph structure; performing dimension reduction and hidden variable learning on the high-dimensional joint feature data by using a variational auto-encoder, and constructing a joint performance evolution probability generation model in a submerged space; capturing a complex dependency relationship through a time sequence attention module and a graph convolution module; constructing a life distribution function by applying a Monte Carlo statistical algorithm; a particle swarm algorithm is combined with a chaos disturbance exploration cutting scheme, and an optimal cutting strategy is solved through a dynamic programming algorithm; according to the method, multi-dimensional feature fusion representation, long-term performance prediction precision improvement, full-life-cycle optimization decision and engineering specification conformity guarantee are realized, and scientific and reliable decision support is provided for large-scale infrastructure engineering reinforcement construction.

The invention discloses an LLM-based open source webpage information analysis method and device, a medium and a product, and relates to the field of open source information analysis. According to the method, the semantic comprehension capability and the instruction following capability of LLM are fully utilized, an xpath expression extraction technology, a statistical algorithm extraction technology and an LLM-based retrieval enhancement generation (RAG) technology which are common in the webpage information crawling field are integrated, effective open source webpage information mining analysis is achieved, a corresponding open source information analysis application process framework is designed, and the method has the advantages of being high in practicability and easy to popularize. The method can intelligently query and generate a brief report and a research and judgment report of a hot event, provides factual reference information related to the report, displays analysis results and insight of related events, themes or individuals to a user, and helps the user to better understand conditions, so that a more scientific and reasonable decision scheme is formulated, and the method has better engineering application benefits.

The application relates to a multi-modal data governance method, device and equipment based on multi-agent cooperation. The method comprises the following steps: identifying the variable mode of a variable in to-be-governed data; converting mixed-mode variables into text or numerical-mode variables by using a mixed data agent; performing standardization evaluation, standard term rewriting and material type division on the text-type variable by using a text agent; dividing the numerical-type variable into a continuous type, an unordered discrete type or an ordered discrete type based on variable semantics and value characteristics by using a numerical agent; and performing corresponding statistical algorithm governance operations according to the divided material types. By using the method, semantic-level recognition and conversion of multi-modal data can be realized through multi-agent cooperation, governance strategies can be accurately matched based on fine statistical attribute classification, and the accuracy and automation efficiency of data governance can be significantly improved.

This invention relates to a field weed infestation early warning method based on weed density detection: First, the operating coordinates of a rice transplanter are obtained, and the transplanter's operating trajectory is constructed. Then, the mechanical characteristics of the transplanter's implements are used to locate the theoretical seedling coordinates. Next, the spacing of the actual seedling geographical coordinates is used to construct a theoretical seedling circle region with the theoretical seedling geographical coordinates as the origin and a preset distance as the radius. Then, images of the farmland after transplanting are collected using a drone, and a deep learning target detection model is constructed. A computational mapping model is constructed to map the theoretical seedling circle region onto the farmland image. A plant quantity statistics algorithm model is constructed to perform quantity statistics calculations on the plants detected by the target detection algorithm in the farmland image. Target detection processing and plant quantity statistics are performed on the farmland images outside the theoretical seedling circle region. A weed infestation early warning threshold is set; exceeding this threshold indicates severe weed infestation, requiring an early warning.