25 results about "Euclidean distance matrix" patented technology

The present application provides a kind of for shallow thick oil reservoir vapor channeling passage discrimination method and system, this method includes: step 1, establish observation data matrix, standardization is carried out to observation data matrix;Step 2, establish vapor channeling passage classification grade, to evaluation matrix normalization processing;Step 3, initial evaluation matrix is calculated with observation data matrix, and classification center is determined;Step 4, the Euclidean distance matrix of each observation well distance classification center is calculated, and evaluation matrix is revised using distance matrix;Step 5, using distance matrix and evaluation matrix to calculate objective function;Step 6, according to maximum evaluation coefficient, the grade of the well vapor channeling passage is determined, and the classification evaluation result of each observation well vapor channeling passage is given.The method and system for shallow thick oil reservoir vapor channeling passage discrimination provide important theoretical basis for improving vapor drive development efficiency, preventing steam from prematurely vapor channeling, and developing reasonable steam drive development scheme, and have important application value in heavy oil thermal recovery development field.

The application discloses a kind of multidimensional timbre perception space model modeling method based on electroencephalogram characteristics, which comprises the following steps: collecting a variety of musical instrument single timbre samples and pretreating;To timbre sample, extract acoustic time-frequency domain feature, and extract psychological perception feature by behavior psychology experiment;Multiple musical instrument timbre samples are used as auditory stimulus to carry out electroencephalogram experiment, and corresponding event-related potential ERP signal is extracted as electroencephalogram feature;The dissimilarity of different timbre characteristics is represented by the Euclidean distance of different timbre points;The distance between different timbre points is calculated;According to the Euclidean distance matrix between sample timbre points, a low-dimensional space with mutually orthogonal dimensions is fitted, the dissimilarity of timbre feature vector is transformed into low-dimensional space, the timbre feature vector is directly mapped into low-dimensional space, a point set is formed, and the similarity and dissimilarity of each musical instrument timbre are directly displayed.The application represents the mapping relationship between acoustic characteristics, psychological perception characteristics and electroencephalogram characteristics.

The application discloses a kind of underwater wireless sensor network node positioning method based on matrix completion, steps are as follows: S1: the Euclidean distance between two different sensor nodes is obtained by TOA ranging method, so as to obtain the Euclidean distance matrix of underwater sensor network node;S2: the Euclidean distance matrix is recovered and completed using the matrix completion algorithm based on non-convex rank approximation, and the distance measurement between all nodes in the network is obtained;S3: the relative coordinates of all nodes underwater are calculated using MDS-MAP algorithm, the relative coordinates of conventional nodes are converted into absolute coordinates by the position of a part of anchor nodes, and the coordinates of conventional nodes are output.The application can not only accurately recover and complete the missing distance matrix, but also effectively handle the influence of Gaussian noise and outlier noise, with good robustness and accuracy.Using the position information of a small number of anchor nodes, the relative position is converted into absolute position, with high node positioning accuracy.

The application discloses a multi-constellation multi-fault detection and elimination method and device and electronic equipment, and belongs to the technical field of satellite navigation and positioning. The method comprises the following steps: acquiring GNSS observation data and a fisheye image, performing semantic segmentation on the image to identify a sky area, and judging satellite visibility; constructing an Euclidean distance matrix, a geometric angle matrix and an inter-satellite pseudo-range difference matrix for each constellation; based on a triangular geometric relationship and a cosine theorem, a geometric distance from a reference star to a terminal is obtained by using median robust estimation, and a residual error matrix is constructed; a fault voting matrix is generated through K-means clustering, a fault satellite set is output, and positioning calculation is performed by using non-fault satellites. The application fuses visual semantic information and inter-satellite geometric constraints, does not need iterative search and a large amount of training data, realizes one-time multi-fault real-time detection and elimination in a complex urban environment, and has good generalization ability and robustness.

The invention discloses a real-time assembly error recognition and early warning method based on multi-dimensional dynamic threshold adjustment. The method comprises the following steps: extracting a multi-modal assembly state descriptor and a field assembly information sequence; field assembly information fragments are intercepted for similarity calculation; constructing a time sequence prediction module, and taking the field assembly information sequence as input to predict the assembly state of the next frame; constructing a weighted Euclidean distance matrix of the field fragment and the template fragment, and calculating a minimum cumulative distance to quantify the difference between the two sequences; a dynamic threshold model is established based on statistical process control, and whether errors exist in the assembly process or not is judged according to the model; based on an incremental dynamic time planning algorithm and a real-time data acquisition module, a real-time identification system is constructed to realize early warning and standard step pushing, and a real-time adaptive quality control closed loop is formed. According to the method, a real-time and self-adaptive quality control closed-loop system is formed through integration with multi-mode sensing and AR guide technologies, and an effective solution is provided for a complex industrial assembly scene.

The invention discloses a packaging process parameter data processing and consistency evaluation method and system, and relates to the technical field of data processing and quality consistency evaluation. According to the method, multi-source data fusion is carried out on the side wall morphology features after wafer scribing and the infrared thermal image dynamic features in the parallel seam welding process, and refined space-time two-dimensional fragmentation processing is carried out on the seam welding process, so that the problem that the packaging process state cannot be comprehensively reflected by a traditional single index is effectively solved; according to the method, multi-dimensional characteristic parameters are mapped to a unified coding interval and principal component dimensionality reduction is carried out to generate a fingerprint code capable of representing the comprehensive process state of a device, and then statistical analysis and heat map visualization of an Euclidean distance matrix are utilized to realize objective quantification of process consistency in batches and visual positioning of systematic deviation.

The invention belongs to the technical field of water supply network monitoring, and particularly relates to a water supply network leakage detection method based on a Kriging interpolation method and a CatBoost model, and the method comprises the steps: firstly constructing a network hydraulic model, and calculating an inter-node Euclidean distance matrix; a hydraulic model is used for simulating multiple times of leakage, and pressure data of pressure value monitoring points and corresponding leakage labels are collected to form training samples; based on a Kriging interpolation method, fusing the pressure data and the distance matrix, estimating a pressure value of a non-monitoring point, and constructing a pressure feature set covering nodes of the whole network; performing importance sorting and screening on the features to obtain an optimal feature subset; combining the data with leakage labels to form a training sample matrix, and inputting the training sample matrix into a CatBoost model for training; and utilizing the trained model to realize the identification of the leakage area and grade according to the real-time pressure data. According to the invention, based on the pressure data of a small number of monitoring points, the independent metering partition where leakage occurs can be positioned more accurately, and the severity of the leakage can be judged.

The invention provides a wafer defect detection method and system based on YOLO-Label comparison, and the method comprises the steps: obtaining a to-be-detected wafer image, carrying out the adaptive acceleration non-local mean filtering denoising and adaptive multi-scale gradient enhancement Canny edge detection of the to-be-detected wafer image, and obtaining a binary edge image; inputting the image into a pre-trained target detection model to obtain target positioning information in a YOLO-Label format, wherein the model is obtained by training a YOLOv8n network which is subjected to Ghost convolution lightweight and single-channel adaptive transformation by adopting a wafer binary image sample set; and comparing the target positioning information of the to-be-detected image with the standard positioning information of the defect-free image, extracting bounding box feature points, calculating an Euclidean distance matrix, and judging missing defects or redundant defects based on threshold matching. According to the invention, high-precision, high-efficiency and high-robustness wafer defect automatic detection can be realized with less labeled data under a complex imaging condition, and the detection speed and integrity are significantly improved.

The application discloses a node time synchronization and ranging method and system of a wireless sensor network, and is used for solving the technical problem that the existing node time synchronization and ranging technology of the wireless sensor network causes poor time synchronization and ranging precision. The method comprises the following steps: when a passive node in the wireless sensor network receives a first synchronization signal sent by an active node in the wireless sensor network, the passive node determines first observation data according to the first synchronization signal, and sends the first observation data to the active node based on a preset communication condition; the active node screens the first observation data and second observation data, determines target observation data, and combines a predicted filter state vector, a predicted state covariance matrix and a preset initial observation noise covariance matrix to output a target filter state vector used for realizing time synchronization between the active node and the passive node, and then constructs a node Euclidean distance matrix according to the target filter state vector.

Ultra-wideband (UWB) tags can be used as part of a high-resolution motion capture system that may not require a cost or a complexity that is typically associated with visually based motion capture systems. The UWB based motion capture uses a bundle of UWB tags, which in a possible implementation, can be affixed to body parts of a user to sense motion of the body parts. The absolute positions of each UWB tag can then be determined by reconstructing a skeletal topology from a Euclidean distance matrix based on inter-tag ranging measurements using handshake signals of a UWB protocol.

The application provides a self-adaptive radar signal sorting method and system based on an RFSoC heterogeneous platform. The method works in cooperation with a PS end and a PL end. First, a normalization constant is calculated based on input PDW data, and parallel normalization is performed. Subsequently, a three-part search is used to determine the most dominant energy field radiation factor online, false alarm pulses are removed, and an index mapping is established. The effective pulses are re-normalized, the pulse pair Euclidean distance matrix is calculated, and the nearest neighbor sorting is performed, and then the local density neighborhood scale is determined. The PS end calculates the local density and the relative distance, generates the decision graph basic data, and automatically selects the clustering center through a second-order polynomial regression. Based on the clustering center, pulse assignment and cluster merging are performed, and finally the sorting result of the original batch is output through the index mapping. The application has the characteristics of heterogeneous architecture cooperative design and algorithm hardware friendliness, realizes self-adaptive sorting, and maintains the operation precision.

The invention discloses a net load scene classification method and system, and relates to the field of net load scene classification, and the method comprises the following steps: carrying out the potential feature extraction of net load data and meteorological data through a conditional variation auto-encoder (CVAE), carrying out the preliminary training of a model through reconstruction loss and KL divergence loss in a pre-training stage, and carrying out the classification of net load scenes. The method comprises the following steps of: firstly, selecting a net load curve with the highest representativeness in each scene based on an Euclidean distance matrix by using an iterative clustering enhancement training strategy, dynamically updating a clustering center by using the iterative clustering enhancement strategy in combination with a K-means algorithm, introducing clustering consistency loss in each mini-batch training process, and selecting the net load curve with the highest representativeness in each scene based on the Euclidean distance matrix by using a Medoid method. And obtaining a typical scene in the multi-class scene set. According to the method, the cohesiveness and discrimination of clustering can be remarkably improved, and accurate classification and efficient representation of the net load scene are realized.

The invention relates to a few-sample point cloud classification method based on multi-modal pulse fusion neurons, and the method comprises the steps: carrying out the queue type sampling time sequence coding of three-dimensional point cloud data, and constructing a point cloud time sequence; performing perspective projection on the point cloud time sequence to generate a multi-view depth map to form an image mode; constructing a multi-layer pulse perceptron and a pulse residual block; based on a multi-layer pulse perceptron, in combination with a sampling grouping module and mixed pooling, point cloud modal features are obtained; based on the multi-layer pulse perceptron and the pulse residual block, obtaining an image modal feature; multi-modal fusion features are obtained based on the multi-modal pulse fusion neurons; enhanced support set features and enhanced query set features are obtained based on cosine similarity, a support prototype vector is calculated, and a few-sample point cloud classification result is obtained according to an Euclidean distance matrix between the support prototype vector and the enhanced query set features. Compared with an existing few-sample point cloud classification method, the point cloud classification accuracy is effectively improved, and the calculation energy consumption of the network is reduced.

Techniques and devices for determining a central node for reporting sensor data are described for an electronic device that inserts ranges between nodes in the wireless network into a Euclidean distance matrix (EDM) and decodes the EDM to generate a global topology for the nodes in the wireless network. The electronic device sums, for each node in the wireless network, events detected by each node during a predetermined time period and performs a kernel density filtering of the sums of the detected events over a two-dimensional space of the global topology. The electronic device calculates a product of Gaussian distributions calculated during the kernel density filtering and selects the node that is spatially closest to a peak of the product of Gaussian distributions as the central node for event reporting.

The application discloses a positioning method, a positioning system, an electronic device and a computer readable storage medium. The method comprises: determining the measured distances between a plurality of labels on a target object and their visible anchor points respectively; determining a second Euclidean distance matrix according to the measured distances, the positions of the labels on the target object and the positions of the anchor points in the target scene; wherein the second Euclidean distance matrix takes the squares of the plurality of measured distances, the squares of the estimated distances between the labels and their invisible anchor points, the squares of each first predetermined distance and the squares of each second predetermined distance as elements; and determining the accurate position of a reference point of the target object and the accurate attitude angle of the target object according to the second Euclidean distance matrix, the positions of the labels on the target object and the positions of the anchor points in the target scene. The application has the characteristics of high precision, high availability, high robustness and low complexity, and is suitable for the situation that the radio communication between some labels and anchor points is blocked.

The application provides a mobile network cooperative positioning method based on tensor completion, acquires relative distances between unknown nodes in a wireless sensor network, constructs incomplete and noisy Euclidean distance matrices at different times, obtains Euclidean distance tensors according to the incomplete and noisy Euclidean distance matrices at different times and complete Euclidean distance matrices at different times, completes and denoises the Euclidean distance tensors, obtains denoised and completed Euclidean distance matrices according to the denoised and completed Euclidean distance tensors, obtains relative coordinates of the unknown nodes through multi-dimensional scaling of the denoised and completed Euclidean distance matrices, and obtains global positions of the unknown nodes through coordinate registration of the relative coordinates of the unknown nodes by means of Procrustes analysis, so that the Euclidean distance matrices are accurately recovered, and the positioning accuracy of the unknown nodes is improved.

The invention relates to a thundercloud coverage area identification method based on space-time dynamic clustering, and belongs to the technical field of meteorological monitoring and thunder and lightning early warning. The method comprises the following steps: introducing time as a third dimension to construct a weighted Euclidean distance matrix; based on the weighted Euclidean distance matrix, adopting an adaptive DBSCAN algorithm to identify a thunderstorm cloud cluster core area; and dynamically identifying the thundercloud coverage boundary of the thunderstorm cloud cluster core area in combination with an improved grid division method to obtain a prediction result of the thundercloud coverage range in the future period. The objective of the invention is to solve the technical problems that a thunderstorm cloud cluster boundary has irregularity and a traditional clustering method neglects time dimension.

This application proposes an analytical device and equipment for mental illness. The device divides the whole brain of the subject into Regions of Interest (ROIs) and obtains the centroid coordinates and BOLD time series of each ROI. It processes fMRI data using a sliding window method, calculates the correlation between ROIs within the time window to obtain a time-resolved functional connectivity (FC) matrix, processes DTI data using a probabilistic tracking method to obtain a structural functional connectivity (SC) matrix, obtains a Euclidean distance matrix based on the ROI centroid coordinates, and obtains several structural index matrices based on the SC matrix. It constructs an edge-pair feature matrix based on these matrices, where each element corresponds to a pair of ROIs. It performs PCA on the edge-pair feature matrix and maps the PCA results back to ROI pairs to obtain a secondary edge-pair feature matrix. Based on multiple linear regression, it estimates the predictive power from the secondary edge-pair feature matrix to the FC matrix, obtaining a dynamic structural-functional coupling time series matrix for each subject. Based on this matrix, mental illness analysis can be performed, fully considering the dynamic changes in functional connectivity over time, which is beneficial for comprehensively assessing brain network abnormalities related to mental illness.

The invention provides a mental disease analysis device and equipment. ROI is divided for a tested whole brain, ROI centroid coordinates and a BOLD time sequence are obtained, fMRI data are processed through a sliding window method, correlation between ROIs in a time window is calculated, a time-resolved FC matrix is obtained, DTI data are processed through a probability tracking method, an SC matrix is obtained, and the SC matrix is used for analyzing mental diseases. An Euclidean distance matrix is obtained based on ROI centroid coordinates, a plurality of structure index matrixes are obtained based on an SC matrix, an edge pair feature matrix is constructed based on the matrixes, each element corresponds to a pair of ROIs, PCA is executed on the edge pair feature matrix, a PCA result is mapped back to the ROI pairs, a secondary edge pair feature matrix is obtained, and the secondary edge pair feature matrix is obtained based on multiple linear regression. According to the method, the predictive capacity from the secondary side to the feature matrix to the FC matrix is estimated, a dynamic structure function coupling time sequence matrix of each tested object is obtained, mental disease analysis can be performed based on the matrix, the dynamic change characteristic of function connection along with time is fully considered, and brain network abnormity related to mental diseases can be comprehensively evaluated.

The application provides an adaptive DBSCAN abnormal battery identification method based on a Euclidean distance without prior weight, belongs to the technical field of battery anomaly detection of energy storage power stations under data driving, and comprises the following steps: preprocessing original data; taking the preprocessed data as input, obtaining the no-prior weight w of each attribute of the original input data of the battery of the energy storage power station; obtaining the multivariate time series Euclidean distance matrix dist with the no-prior weight w; based on dist, respectively performing MDS low-dimensional embedding and adaptive selection of DBSCAN clustering algorithm parameters; performing DBSCAN clustering abnormal battery identification; and finally outputting a sequence composed of the clustering labels of each battery, wherein the label value of-1 indicates that the battery corresponding to the serial number is an abnormal battery. The application can effectively mine the potential information of the distribution of original battery data, better measure the differences between the input attributes of the multivariate time series, solve the problem of unsatisfactory clustering outlier identification caused by small differences between input parameters, and improve the accuracy of abnormal battery identification of the energy storage power station.

This invention discloses a method for topology identification of low-voltage distribution network areas based on a dual-modal liquid graph neural network, comprising the following steps: macroscopic topology localization of user nodes in the low-voltage distribution network area; construction of a dynamic nearest neighbor spatial topology adjacency matrix; construction of a discrete liquid graph neural network to calculate the Euclidean distance matrix of depth spatial features; calculation of the explicit waveform trend distance matrix; execution of dual-modal weighted fusion to generate the final fused distance matrix; application of an agglomerative hierarchical clustering algorithm, combined with intelligent search for optimal cluster numbers using contour coefficients, to output the final topology structure of micrometer boxes. This invention, through a discrete truncation mechanism and a dual-modal weighted fusion model, can effectively improve the accuracy of micro-topology identification of low-voltage distribution network areas while avoiding complex continuous differential solutions; combined with embedded space optimization training and intelligent optimization of contour coefficients, it can obtain better meter box clustering results within the candidate cluster number search interval, improving the accuracy and stability of topology identification.

The application provides a wafer defect detection method and system based on YOLO-Label comparison, comprising: obtaining a wafer image to be detected, performing adaptive accelerated non-local mean filtering denoising and adaptive multi-scale gradient enhancement Canny edge detection on the wafer image to be detected, and obtaining a binary edge image; inputting the binary edge image into a pre-trained target detection model to obtain target positioning information in the YOLO-Label format, wherein the model is obtained by training a YOLOv8n network that is lightened by Ghost convolution and is adapted to a single channel, using a wafer binary image sample set; comparing the target positioning information of the image to be detected with standard positioning information of a defect-free image, extracting feature points of a bounding box, calculating an Euclidean distance matrix, and based on threshold matching, determining missing defects or redundant defects. The application can realize high-precision, high-efficiency and high-robustness wafer defect automatic detection with less labeled data under complex imaging conditions, and significantly improves the detection speed and integrity.

The application discloses a relative positioning method based on SMACOF and progressive Helmert transformation, and comprises the following steps: calculating the weighted Euclidean distance between nodes to obtain a weighted Euclidean distance matrix; wherein the nodes comprise unknown nodes and anchor nodes; calculating the relative coordinates of all nodes by an MDS positioning algorithm based on the weighted Euclidean distance matrix to obtain a relative coordinate matrix; obtaining an optimal relative coordinate matrix by solving the optimal solution of the relative coordinate matrix through an SMACOF algorithm; mapping the optimal relative coordinate matrix to global coordinates through Helmert transformation to obtain an absolute coordinate matrix; optimizing the absolute coordinate matrix through a progressive correction mechanism to obtain optimal transformation parameters; and obtaining an optimal absolute coordinate matrix by performing Helmert transformation on the optimal relative coordinate matrix again through the optimal transformation parameters, so as to obtain the accurate positions of all nodes.

The invention discloses a millimeter wave radar point cloud filtering method, system and device and a medium, and relates to the technical field of radar signal processing and railway safety monitoring, and the method comprises the steps: carrying out the DBSCAN coarse clustering of a first frame target point cloud imaging data set of a continuous multi-frame railway foreign matter invasion target point cloud imaging data set, obtaining a first frame coarse clustering result, constructing an Euclidean distance matrix, obtaining a category center point, determining a mutation index, and carrying out abnormal point removal on the first frame coarse clustering result; and screening the maximum value of each type of minimum neighborhood radius and the minimum value of each type of minimum neighborhood density in the first frame of coarse clustering result as the neighborhood radius and the neighborhood density of the DBSCAN coarse clustering of the next frame of point cloud data, obtaining the next frame of coarse clustering result based on the DBSCAN coarse clustering algorithm, and carrying out abnormal point removal until the abnormal point removal is carried out on each frame. According to the method, point cloud miscellaneous points can be effectively removed, and sparse point cloud targets are accurately classified.

The invention relates to the technical field of Internet of Things node positioning, and discloses an Internet of Things positioning data completion method, which comprises the following steps: acquiring a distance matrix of partial observation between nodes; extracting observation distances from each node to all other nodes to form a one-dimensional distance sequence, and converting the one-dimensional distance sequence into a Hankel matrix through a sliding window; constructing a three-dimensional Euclidean distance observation tensor, namely, an observation EDT tensor; establishing a joint optimization model based on structured prior and deep low-rank prior to obtain a complete EDT tensor; solving the joint optimization model by adopting an alternating direction multiplier method framework based on Plug-and-Play, and iteratively updating and outputting a complete EDT tensor; the complete Euclidean distance matrix is inversely converted into the complete Euclidean distance matrix for node positioning of the Internet of Things, and the method aims at improving the data recovery precision and robustness under the condition that the distance measurement information is seriously lost.