42 results about "Density based" patented technology

Disclosed in the present invention is a three-dimensional circle detection method for a freeform surface, comprising: acquiring freeform surface point cloud data, and using a normal vector-guided rolling ball method to extract a freeform surface circular-hole point cloud boundary contour from the point cloud data; performing Euclidean clustering-based boundary segmentation on the point cloud boundary contour to obtain a clustering result of all boundary point clouds, the clustering result consisting of a plurality of circular-hole contours; performing a density-based weighted iterative algorithm on each circular-hole contour to obtain a freeform surface circular-hole normal vector; and projecting a freeform surface circular hole along the freeform surface circular-hole normal vector onto a plane, and then performing circular-hole iterative fitting based on solving an overdetermined equation on the projected circular-hole point cloud to obtain final positioning information. The present invention is applicable to circular-hole positioning on freeform surfaces of different curvatures, has strong robustness, and effectively improves the accuracy of circular-hole positioning on the freeform surfaces.

The invention provides a three-dimensional steel structure full-coverage path planning inspection method based on topology reconstruction, and relates to the technical field of industrial robots, and the method comprises the steps: obtaining a model file of a to-be-inspected three-dimensional steel structure; constructing an original vertex set and an original edge set according to the model file; performing adaptive clustering on each original vertex in the original vertex set through a density-based spatial clustering algorithm to obtain a cluster; taking the geometric center of the original vertex in each cluster as a topological node, and establishing a mapping relation between the original vertex and the topological node; carrying out topology reconstruction on the original edge set, and constructing an undirected weighted graph; stitching non-connected sub-graphs in the undirected weighted graph through a K-dimensional tree and a minimum spanning tree algorithm to obtain a fully connected graph; generating a full-coverage continuous path sequence through a Chinese postman algorithm; the full-coverage continuous path sequence is converted into a three-dimensional space coordinate sequence, and the three-dimensional steel structure to be inspected is inspected according to the three-dimensional space coordinate sequence.

The invention provides a micro-motion H / V spectrum ratio data processing method and device based on machine learning and a medium, and the method can comprise the steps: obtaining micro-motion H / V spectrum ratio data containing a plurality of curves, recognizing and removing the curves containing abnormal morphological characteristics through a preset curve removing model, and obtaining a candidate data set; classifying peak values of the curves in the candidate data set according to a preset peak value classification model to obtain an effective peak value set; clustering the effective peak value set based on a density clustering algorithm to obtain effective peak value clusters in different frequency intervals; and determining the effective peak cluster with the lowest frequency as a main peak cluster, and rejecting curves of peak values with abnormal frequencies and amplitudes in the main peak cluster to obtain processed micro-motion H / V spectrum ratio data. The method has higher stability and accuracy, the spectrum distribution of the processed curve is more concentrated, the standard deviation curve is more convergent, and the peak value is clearer and more stable.

A transformer partial discharge positioning detection method based on ultrahigh frequency signals is characterized by comprising the following steps: S1, estimating time delay of signals obtained by an ultrahigh frequency (UHF) sensor array based on a generalized cross-correlation method; and S2, arranging and combining signals of the UHF sensor array, and solving coordinates of a positioning point based on an improved multi-moth optimization (MFO) algorithm according to the time delay obtained in the step S1. And S3, clustering the coordinates of the plurality of positioning points obtained in the step S2 based on a density clustering algorithm (DBSCAN), and selecting the geometric center position of the category with the maximum sample number as the final local discharge source coordinate.

Methods for detecting power system events in an electrical power system. An example method comprises determining a signal envelope for each of at least first and second power system signals and performing density-based spatial clustering of a series of points formed by combining respective values of the signal envelopes for at least the first and second power system signals. The example method further comprises detecting one or more power system events by identifying outlier points or groups of points in the spatial clustering. Some methods may further comprise automatically classifying power system events by collecting a data set comprising, for each detected power system event, power system signal features corresponding to the detected power system event, and classifying each of the detected power system events using the data set and a machine-learning-based classification algorithm, where said classifying comprises determining a classification label from among two or more predetermined classification labels.

According to an aspect, there is provided a computer-implemented method comprising the following. Initially, information on a plurality of anomaly events relating to operation of a target system is obtained. The information comprises one or more time series of anomaly score data. Segments satisfying one or more pre-defined criteria for anomalous operation are detected from the one or more time series. The one or more pre-defined criteria are defined to exclude fully non-anomalous anomaly score data. Anomaly durations and standardized anomaly scores are determined for the segments. Partition or density based clustering is performed in a two-dimensional space formed by the standardized anomaly scores and the anomaly durations to form n clusters, and m smallest clusters of the n clusters are identified. At least one of the following is performed: outputting information on the m smallest clusters or causing adjusting of operation of the target system based on the m smallest clusters.

Techniques are described for providing a ML data analytics application including guided ML workflows that facilitate the end-to-end training and use of various types of ML models, where such guided workflows may also be referred to as ML “experiments.” For example, the ML data analytics application may enable users to create experiments related to prediction of numeric fields (for example, using linear regression techniques), predicting categorical fields (for example, using logistic regression), detecting numerical outliers (for example, using various distribution statistics), detecting categorical outliers (for example, using probabilistic statistics), forecasting time series data, and clustering numeric events (for example, using k-means, density-based spatial clustering of applications with noise (DBSCAN), spectral clustering, or other techniques), among other possible uses of various types of ML models to analyze data.

The application discloses a data clustering method and device based on density peaks, a medium, and direct subordination is used to describe the relative density of each data point, wherein the data point is a picture or a word feature in a data set, a mixed density value combining the relative density and the absolute density is designed to identify a clustering center, and the effective subordination is defined through similarity reachability, main distribution of non-center points is performed, and the label of a remaining point is determined in combination with the k-layer upper distribution of different clusters, so that the data points of the same category in the data set can be effectively gathered in one category, and the classification of the data set is efficiently and accurately completed.

The invention discloses a three-dimensional object collision body optimization method based on a density clustering algorithm, and the method comprises the steps: S1, extracting a position representation feature containing position information of each primitive on the surface of a three-dimensional object, and extracting N types of additional geometric features of each primitive on the surface of the three-dimensional object, jointly constructing feature description of the surface of the three-dimensional object through the extracted position characterization features and the N additional geometric features; s2, a density clustering algorithm is adopted, distance measurement and similarity measurement between the primitives are evaluated based on the feature description constructed in the step S1, and the primitives with the distance measurement smaller than a first preset threshold value theta1 and the similarity measurement smaller than a second preset threshold value theta2 are divided into the same cluster. According to the method, the hierarchical bounding box structure with the local collision body as the leaf node can be constructed, the local geometric features of the three-dimensional object can be reserved, and the fitting precision of the three-dimensional object can be improved, so that misjudgment collision can be avoided when the hierarchical bounding box structure is used for collision detection.

The invention provides a dynamic anchor position detection method based on density clustering algorithm optimization. The method comprises the following steps: data cleaning: decoding, abnormal value filtering and standardization processing are carried out on ship AIS data; dBSCAN track point clustering: identifying a ship anchoring and gathering area based on a density clustering algorithm; post-processing a clustering result: filtering noise points, and selecting a cluster containing the most data points as an anchor area; and anchor location point positioning: calculating a coordinate mean value of all points in the anchor location area, and outputting a real anchor location point through anti-standardization. Intelligent transition from a fuzzy'anchoring area 'to an accurate'physical anchoring position point' is realized, the anchoring position can be positioned more accurately, environmental change can be adapted more dynamically, data noise can be resisted effectively, and a real and reliable technical basis is provided for intelligent anchoring monitoring, collision risk early warning and fine management of an anchoring ground.

This invention belongs to the field of robotic arm motion planning and control technology, and discloses a control method for a harvesting robotic arm based on density clustering and agent integration. First, the DBSCAN algorithm is used to simplify the harvesting scenario, determining the objective function, constraints, input state space, action space, reward function, and termination condition of the agent in the harvesting scenario model. Based on the clustering results of the DBSCAN algorithm, the agent is prepared for training. Then, the selected agent algorithm is trained. Finally, an error reciprocal weighted combination method based on agent reward is used to integrate the motion control decisions of each trained agent algorithm for the same robotic arm and accumulate the total reward value after integration processing. This invention is applicable to the control of harvesting robotic arms, realizes multi-angle decision-making, effectively compensates for the shortcomings of single algorithms, improves the accuracy of robotic arm motion, and thus provides reliable support for modern agricultural automation technology.

The invention discloses an ecological product value evaluation method, and relates to the technical field of urban traffic, and the method comprises the steps: 1, converting remote sensing image land classification data into vector space point data, and recording the vector space point data as a data set A; step 2, spatial clustering processing is performed on the data set A based on a DBSCAN density clustering algorithm to obtain a DBSCAN density clustering result, convex hull and concave hull processing is performed on the DBSCAN density clustering result to obtain a minimum convex hull and a minimum concave hull of each category, all the minimum convex hulls form a first clustering result s, and all the minimum concave hulls form a second clustering result S1; 3, performing index calculation on the first clustering result S in combination with the second clustering result S1; step 4, performing clustering processing on the index calculation result I of the S to obtain a result C; and step 5, carrying out classification spatial distribution visualization processing on S according to C. According to the method, the value of the ecological product can be evaluated by constructing the spatial form and the population analysis index of the ecological product.

A method for determining the association and continuity combination of top-side-rock structural surfaces based on unsupervised learning is proposed. This method involves investigating the structural surfaces of the roof and side-rock masses in underground engineering projects to obtain geometric and statistical information. A unified encoding is performed to construct a joint feature set of roof-side-rock structural surfaces. An unsupervised density-based clustering algorithm is used for initial cluster analysis of the joint feature set. A swarm intelligence-based Lüperfox optimization algorithm is introduced to optimize key parameters of the DBSCAN clustering algorithm. A Latin hypercube sampling method is used to improve the population initialization process of the Lüperfox optimization algorithm, resulting in better DBSCAN hyperparameters and optimized structural surface clustering results. The method determines the structural surface system affiliation of structural surfaces in different locations, quantitatively calculates the spatial continuity and combination relationship of structural surfaces, and outputs the spatial association determination results and continuity levels of the roof-side-rock structural surfaces. This method enables intelligent identification and quantitative analysis of the spatial relationship between roof and side-rock rock structural surfaces.

The present application relates to wine grape thinning technical field, specifically, it is a kind of wine grape thinning device and method based on machine vision, method includes the following steps: step S1: multimodal image acquisition and adaptive enhancement preprocessing;Step S2: accurate segmentation of cluster and peduncle based on improved loss function;Step S3: dynamic decision of peduncle clamping point based on mechanical optimal model;Step S4: thinning intensity decision based on density clustering and random forest regression;Step S5: trajectory planning of mechanical arm and mechanical claw collaborative pruning;Step S6: thinning effect verification and closed-loop correction.The present application can preferably carry out wine grape thinning.

The invention discloses a three-dimensional point cloud-based adaptive plane stacked object segmentation method and system, and the method comprises the following steps: obtaining three-dimensional point cloud data of a to-be-processed scene, and carrying out the preprocessing of the three-dimensional point cloud data; performing space cutting on the preprocessed three-dimensional point cloud data, and executing adaptive voxel downsampling according to point cloud space distribution characteristics to form a point cloud data set with balanced density; performing plane fitting on the point cloud data set based on a random consistency sampling algorithm, identifying and separating point clouds meeting ground judgment conditions as ground point clouds, and obtaining non-ground point clouds at the same time; constructing a spatial index structure for the non-ground point cloud, and performing main clustering processing based on a density constraint clustering algorithm to obtain a plurality of initial clusters; and calculating the height distribution characteristic of each initial cluster, and executing secondary clustering processing on the corresponding initial cluster when the height difference meets a preset trigger condition. According to the invention, through height feature analysis and a secondary clustering mechanism, automatic and accurate segmentation of stacked objects is realized.

Groups of patrons may be discovered by measuring website and mobile site patron clickstream data in a mathematical and unsupervised way over a predetermined time and by graphically clustering the patron clickstream data using non-linear dimensionality reduction in the form of a Uniform Manifold Approximation and Projection algorithm (UMAP). The data from the UMAP may then be feed into a Density Based Spatial Clustering of Applications with Noise algorithm (DBSCAN) in order to identify a center of each cluster. Next, using the data from the UMAP and the center of each cluster from the DBSCAN, a K-Nearest Neighbor algorithm (KNN) may be applied to identify data points closest to the center of each cluster and to shade each of the data points to graphically identify each cluster of the plurality of clusters. Next, illustrate a graph on the display representative of the data points shaded following application of the KNN.

The application discloses an intelligent division method for police case high-occurrence areas based on density clustering and k-means clustering, and the method comprises the following steps: obtaining police case data of a city; preprocessing original police case data to obtain data after unification and standardization; clustering the data after preprocessing by using a density algorithm to obtain all categories and corresponding data of each category; clustering the police case data of all categories by using a k-means algorithm; then clustering all police cases of each police case data by using the density algorithm to obtain all categories and corresponding data of each category; extracting boundary points of each category data to obtain corresponding boundary contours, that is, to obtain police case high-occurrence areas. The application can accurately identify police case high-occurrence areas, and can effectively balance the uneven distribution of police case high-occurrence areas in urban areas and suburban areas, thereby providing effective data support for subsequent police deployment, unified dispatching and command.

This invention discloses an automatic identification method and system for rock mass discontinuities based on density peak clustering. The method includes: acquiring three-dimensional point cloud data of the rock mass; acquiring a normal vector field based on the three-dimensional point cloud data; automatically determining the number of clusters of dominant groups of discontinuities using a density peak clustering algorithm based on the normal vector field to obtain cluster centers; performing spatial-directional ensemble clustering on the three-dimensional point cloud data according to the cluster centers and the normal vector field to obtain an initial clustering result; optimizing the boundaries of the initial clustering result using a region growing algorithm to obtain an optimized clustering result; and performing multi-scale decomposition on the optimized clustering result to obtain the attitude parameters of the rock mass discontinuities.

The application provides a ground point bottom model establishment method based on a point cloud minimum elevation clustering algorithm, which is divided into the following steps: open pit point cloud data collection, open pit point cloud data preprocessing, open pit point cloud data gridding, open pit point cloud bottom model establishment based on a DBSCAN density clustering algorithm, missing point cloud interpolation, and open pit final ground point bottom model point cloud data establishment. Specifically, first, open pit full point cloud data is collected, and the point cloud data is subjected to thinning processing; second, the point cloud data is gridded, all grid point cloud data is traversed, and the DBSCAN density clustering number of the lowest point in the grid is calculated in the order of elevation from low to high, and when the clustering number reaches N, the point is considered to be the minimum ground point; finally, missing point cloud is filled in through a nearest neighbor interpolation method, and then the final open pit ground bottom model point cloud data is obtained. The method aims to calculate the DBSCAN density clustering number of the lowest point in the grid, so that the open pit ground bottom model point cloud data can be quickly and accurately collected, which provides important guidance value for the establishment of an open pit DEM model by using an auxiliary progressive morphological filter and the intelligent acceptance of open pit blasting.

The application relates to a road obstacle detection method and system based on a three-dimensional point cloud, which is characterized in that: three-dimensional point cloud data of a road acquired by a four-camera is subjected to density-based spatial clustering to obtain a plurality of clusters; for each cluster, the width of an obstacle is obtained by calculating the difference between the maximum x-coordinate value and the minimum x-coordinate value of the point cloud in the three-dimensional coordinate axis; the height of the obstacle is obtained by calculating the difference between the maximum y-coordinate value and the minimum y-coordinate value of the point cloud; and the distance between the obstacle and the body is obtained by calculating the average value of the z-coordinate values of the point cloud. The method directly uses three-dimensional point cloud data generated by a four-camera, so that the perception module of an unmanned driving system obtains depth information, which can be one-to-one corresponding to the coordinates of a real object in a three-dimensional space. When the method is applied to the perception of road obstacles in an unmanned driving system, not only the existence of the obstacles can be detected, but also the size of the obstacles and the distance between the obstacles and the unmanned vehicle can be detected.

The invention provides a hydraulic power plant power generation flow data prediction method, and relates to the technical field of hydraulic power plant power generation flow prediction, and the method comprises the steps: collecting meteorological data, landform data, soil characteristic data and hydraulic power plant operation data of a watershed where a hydraulic power plant is located through a multi-source sensor; data missing values are filled by adopting a long and short term memory network interpolation model, abnormal values in the data are detected by adopting a density-based spatial clustering method in combination with an isolated forest method, and the abnormal values are corrected by using a conversion-based smoothing algorithm; a deep belief network DBN and a convolutional neural network CNN are combined to construct a prediction model, data are input into the prediction model, feature extraction is performed on topographic and geomorphic data and soil characteristic data through the CNN, deep feature learning is performed on the extracted features, meteorological data and hydraulic power plant operation data through the DBN, and the power generation flow of the hydraulic power plant is predicted. By adopting the scheme, accurate and efficient prediction of the power generation flow of the hydraulic power plant is realized.

The invention discloses a target satellite group intention recognition method based on unsupervised learning, and belongs to the technical field of space safety and maintenance, and the method comprises the following steps: constructing a target satellite group task intention set; building a convolutional neural network based on a TS2Vec self-supervised learning framework, and training the neural network to learn three-dimensional lattice sequence features of target star group configuration; based on a DBSCAN density clustering algorithm, grouping target star groups to configure a three-dimensional lattice sequence; and applying the trained algorithm to target satellite group intention recognition. According to the method, the intention recognition problems that an existing algorithm is difficult to process, label sample data is scarce, data noise is strong, the nature of the configuration is difficult to analyze, and unknown intentions emerge continuously and are difficult to extend are solved.

The invention discloses a transaction process-oriented risk sample adaptive selection and labeling method, particularly relates to the technical field of industrial risk control data processing, and is used for solving the problems of business exception redundancy pushing and checking overload. The method comprises the steps that firstly, a transaction flow and a physical flow log are fused to construct a multi-modal space-time transaction feature matrix, a high-frequency deviation sample is extracted in combination with a graph structure relative entropy and a hysteresis damping coefficient, and false positive interference is eliminated; then, analyzing an isomorphic risk cluster based on density clustering, stripping homogenized redundancy by using information entropy and centrality in the cluster, extracting representative samples to generate a high-entropy refined subset, and reducing auditing redundancy; and finally, the concurrent throughput and the cognitive load threshold are monitored to establish a dynamic quota game mechanism, the optimal sample slices are intercepted to be subjected to terminal identification labeling, a closed-loop system from feature fusion to adaptive pushing is constructed, and scientific support is provided for industrial transaction risk control.

The invention discloses a method, a device, equipment and a medium for detecting and sorting frequency hopping signals of an unmanned aerial vehicle, and relates to the technical field of signal detection. And different clustering centers divide data objects in a certain radius range into different classes by taking the distance as a reference. Compared with a traditional K-means algorithm, when unmanned aerial vehicle frequency hopping signal detection data is processed, an initial k supervision value does not need to be set, self-adaptive classification is directly carried out through elements in a data set, and the influence on a data sorting result by setting an initial manually determined k classification value is avoided; and secondly, the clustering radius weight is adopted to balance the value, so that the clustering result is more reasonable, and non-spherical clusters can be processed.

This invention discloses a machine vision-based method for counting blocks of the same color, comprising the following steps: image acquisition and preprocessing; color space transformation and focusing to generate a color feature saliency map; generation of a two-dimensional spatial-color distribution vector set; seed point localization based on density peak search; object region division and final counting based on adaptive region growing; and output of the counting results. This invention completely eliminates the reliance on prior information about object shape and complete contours, utilizing color as a stable feature as the core clue. It effectively solves the problems of contact and occlusion between objects, accurately separating and counting even tightly clustered objects. It avoids complex and time-consuming model training processes, achieving a lightweight and highly robust solution based on traditional image processing and intelligent algorithms. It improves the overall robustness and adaptability of the system, enabling stable operation even under slight changes in lighting and relatively complex backgrounds, and is easily deployed on low-cost hardware platforms.

The invention provides an improved density peak value clustering method based on potential energy entropy and a structural plane grouping identification system, and relates to the technical field of engineering geology and rock mass structure analys.The method comprises the steps that structural plane occurrence data are obtained, abnormal values of the structural plane occurrence data are removed, a potential energy density field is constructed, potential energy distribution is defined, and the potential energy entropy is calculated based on the potential energy density field; and performing weighted correction on the local density based on the potential energy entropy to obtain a correction density, identifying a structural plane occurrence clustering center based on the correction density and the minimum distance according to a density peak clustering principle, distributing other data points to a cluster to which the nearest high-density center belongs, judging a cluster boundary, and outputting a clustering result. According to the method, the adaptive capacity of the local density is enhanced by introducing the potential energy entropy, noise interference is effectively restrained, the structural plane grouping precision and stability are improved, and the method is particularly suitable for structural plane rapid grouping identification under the conditions of high noise and complex distribution and has wide application prospects in slope stability analysis, underground engineering and mining engineering.

The application discloses a risk sample adaptive selection and labeling method for transaction process, and particularly relates to the technical field of industrial risk control data processing, and is used for solving the problems of business exception redundancy push and audit overload. First, a multi-modal space-time transaction feature matrix is constructed by fusing transaction flow and physical flow log, high-frequency deviation samples are extracted by combining graph structure relative entropy and lag damping coefficient, and false positive interference is excluded; then, isomorphic risk clusters are analyzed based on density clustering, homogenization redundancy is stripped by using cluster information entropy and centrality, representative samples are extracted to generate a high-entropy refined subset, and audit redundancy is reduced; finally, a dynamic quota game mechanism is established by monitoring the concurrent throughput and cognitive load threshold, the optimal sample slice is intercepted to the terminal discrimination labeling, and a closed-loop system from feature fusion to adaptive push is constructed, which provides scientific support for industrial transaction risk control.

The invention relates to a point cloud clustering method, electronic equipment and a storage medium. The method comprises the steps of obtaining a to-be-clustered target point cloud; determining the spatial orientation of each spatial point in the target point cloud, wherein the spatial orientation is used for representing the spatial orientation of a target to which the spatial point belongs; a first feature constraint condition is determined, the first feature constraint condition comprises a first neighborhood range of the spatial points, and the first neighborhood range has a long axis; performing density-based spatial clustering on the target point cloud based on the spatial orientation of each spatial point in the target point cloud and a first feature constraint condition, wherein the direction of the long axis of the first neighborhood range changes along with the spatial orientation of the spatial point; and obtaining a clustering result of the target point cloud. According to the technical scheme, the neighborhood range with the long axis is used, the long axis direction of the neighborhood range is adjusted based on the spatial orientation of the spatial point for clustering, and the accuracy of the clustering result is improved by combining distance and direction constraints.

The application discloses a mobile robot motion tracking control method based on a CLUBS algorithm, which comprises the following steps: S1, acquiring robot gait information, and dividing the whole data space into two types of blocks: one type is that each block contains only one cluster, and the other type is that each block contains only noise; S2, after each division, the Alinski-Harabasz value is recalculated, if the CH value increases, S2 is repeated, if the CH value decreases to below 70%, step S3 is entered; S3, all blocks are incrementally sorted based on density; the blocks containing clusters are separated from all blocks; the separated blocks containing clusters generate an elliptical cluster, S4, if a pair of clusters are merged, a condition that a relatively small increase in the minimum intra-cluster sum of squares is caused; S5, the elliptical cluster is reconstructed, the clustering quality is improved, and the final abnormal point is determined. The application also discloses a mobile robot motion tracking control system based on the CLUBS algorithm, and the method and the system have the functions of robot automatic navigation transportation, human-computer interaction enhancement, and emergency response.

The application discloses a multi-density data classification method and system based on density stratified clustering, and belongs to the technical field of multi-dimensional data classification. The method separates data in different density layers by using a Gaussian mixture model to perform density stratification on data of each category, and then uses a DBSCAN algorithm to identify a plurality of data regions in each density layer to form sub-categories. Finally, the sub-categories are identified and summarized by using a Bayesian model, so that the classification of multi-density data is realized. The method can more accurately depict the internal structure of data, and enables the Bayesian classifier to more accurately adapt to the characteristics of different density regions.