3 results about "Affinity propagation clustering" patented technology

The application discloses a visual detection method for early warning of icing environment, and relates to the technical field of aviation icing detection, comprising the following steps: constructing a two-dimensional joint feature residual space based on real-time contour vectors and real-time gray field vectors, generating a candidate region set, constructing a three-dimensional feature vector for maximum points in the candidate region set, clustering by using an affinity propagation clustering algorithm, and obtaining structured ice phase units; combining the affinity propagation clustering algorithm with an effective rank quantization method based on singular value entropy of a trajectory matrix to construct an ice layer analysis mechanism with multiple singular structure decoupling capabilities and continuous morphological phase state quantization capabilities; and constructing a spatial distribution sequence of internal deformation variables of each ice phase unit into a trajectory matrix, introducing singular value decomposition and Shannon entropy calculation to obtain an effective rank continuous scalar, and improving the perception granularity of the icing visual detection system on the spatial non-uniformity of the ice layer.

The application discloses a kind of comprehensive energy load aggregate short-term probability prediction model establishing method and device.The method includes: the historical data of comprehensive energy load aggregate collected is preprocessed and dimensionality reduction;Grouping is carried out to the data after dimensionality reduction using affinity propagation clustering algorithm based on comprehensive similarity, and the centroid feature of each group is extracted as representative load feature input prediction model;The short-term probability prediction model of comprehensive energy load aggregate that fusion Copula self-adapting correlation analysis, cross feature-time graph neural network and mixed density network is constructed.The precision of short-term probability prediction of comprehensive energy load aggregate is effectively improved by dynamic coupling relationship mining and spatiotemporal feature joint learning mechanism.

The invention provides a method for judging a cell time delay problem based on an XGBoost decision tree. The method comprises the following steps: acquiring a detailed call record of a user plane XDR and network management KPI index data; analyzing and screening characteristic indexes strongly correlated with the downlink time delay of the base station through a Pearson correlation coefficient; carrying out dynamic clustering on the key characteristic indexes by using an affinity propagation clustering method; an XGBoost regression model is constructed, and model training is carried out; hyper-parameter tuning is carried out on the XGBoost model; according to the trained model, identifying a key root cause influencing the time delay; outputting a delimiting conclusion and an optimization suggestion of the cell delay problem in combination with the clustering result and the feature importance; according to the method, a large-scale data set formed by massive user plane XDR call tickets and network side KPI indexes can be efficiently processed, and the characteristic engineering and the strong computing power of the XGBoost model are learned through a machine.